WO2021027267A1 - 语音交互方法、装置、终端及存储介质 - Google Patents

语音交互方法、装置、终端及存储介质 Download PDF

Info

Publication number
WO2021027267A1
WO2021027267A1 PCT/CN2020/074988 CN2020074988W WO2021027267A1 WO 2021027267 A1 WO2021027267 A1 WO 2021027267A1 CN 2020074988 W CN2020074988 W CN 2020074988W WO 2021027267 A1 WO2021027267 A1 WO 2021027267A1
Authority
WO
WIPO (PCT)
Prior art keywords
service type
target
service
mapping relationship
type set
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Ceased
Application number
PCT/CN2020/074988
Other languages
English (en)
French (fr)
Inventor
石子娟
聂为然
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huawei Technologies Co Ltd
Original Assignee
Huawei Technologies Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Huawei Technologies Co Ltd filed Critical Huawei Technologies Co Ltd
Priority to JP2021569122A priority Critical patent/JP7324313B2/ja
Priority to EP20803428.0A priority patent/EP3933830B1/en
Priority to EP25184716.6A priority patent/EP4664269A3/en
Publication of WO2021027267A1 publication Critical patent/WO2021027267A1/zh
Priority to US17/179,764 priority patent/US11922935B2/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G—PHYSICS
    • G06—COMPUTING OR CALCULATING; COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/16—Sound input; Sound output
    • G06F3/167—Audio in a user interface, e.g. using voice commands for navigating, audio feedback
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/08—Speech classification or search
    • G10L15/18—Speech classification or search using natural language modelling
    • G10L15/1815—Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L13/00—Speech synthesis; Text to speech systems
    • G10L13/02—Methods for producing synthetic speech; Speech synthesisers
    • G10L13/04—Details of speech synthesis systems, e.g. synthesiser structure or memory management
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/223—Execution procedure of a spoken command
    • G—PHYSICS
    • G10—MUSICAL INSTRUMENTS; ACOUSTICS
    • G10L—SPEECH ANALYSIS TECHNIQUES OR SPEECH SYNTHESIS; SPEECH RECOGNITION; SPEECH OR VOICE PROCESSING TECHNIQUES; SPEECH OR AUDIO CODING OR DECODING
    • G10L15/00—Speech recognition
    • G10L15/22—Procedures used during a speech recognition process, e.g. man-machine dialogue
    • G10L2015/225—Feedback of the input speech
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2201/00—Electronic components, circuits, software, systems or apparatus used in telephone systems
    • H04M2201/40—Electronic components, circuits, software, systems or apparatus used in telephone systems using speech recognition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M2250/00—Details of telephonic subscriber devices
    • H04M2250/74—Details of telephonic subscriber devices with voice recognition means

Definitions

  • This application relates to the field of terminal technology, and in particular to a voice interaction method, device, terminal, and storage medium.
  • terminals With the development of terminal technology, more and more terminals support the function of voice interaction. Users can interact with the terminal through man-machine interaction by emitting voice, thereby freeing both hands and improving the efficiency of man-machine interaction.
  • the voice interaction process usually includes: when the user wants to interact with the terminal, first, the user speaks the wake-up word, and the terminal will collect the voice command to determine whether the voice command contains a wake-up word. If the voice command contains a wake-up word, the terminal It will switch from the standby state to the working state, that is, the terminal is awakened; after that, the user speaks the service that needs to be processed by the terminal, and the terminal collects voice commands again, and according to the voice commands, determines the service to be processed and processes the service.
  • the wake-up word of a vehicle-mounted terminal is "Hello, Xiaohua”
  • the user turns on the radio while driving, and wants to play a song on the vehicle-mounted terminal
  • the terminal is awakened, and the user says “Help play the songs of "Eastern Music Radio”
  • the vehicle-mounted terminal will automatically adjust the radio station to "Eastern Music Radio” and play the songs of "Eastern Music Radio”.
  • the user When using the above-mentioned method for voice interaction, the user needs to speak the wake-up word before waking up the terminal to process services, which results in cumbersome operations and low efficiency.
  • the embodiments of the present application provide a voice interaction method, device, terminal, and storage medium, which can solve the technical problems of cumbersome operations and low efficiency of voice interaction in related technologies.
  • the technical solution is as follows:
  • a voice interaction method includes: determining that a target event is detected to occur, and the target event is an event that can trigger a voice interaction; according to the target event, querying a mapping relationship to obtain a service type set ,
  • the service type set includes one or more target service types; collecting voice instructions; obtaining the first service corresponding to the semantic information according to the semantic information corresponding to the voice command; if the service type of the first service is For any target service type in the service type set, the first service is executed according to the voice instruction.
  • This embodiment provides a method for triggering voice interaction without wake-up words.
  • the set of service types for which the user has voice interaction intention is predicted. If the service type of the first service expressed by the voice command is service
  • the first service is executed.
  • the determining that the target event is detected to occur includes: determining that the first operation of the user is detected;
  • the querying the mapping relationship according to the target event to obtain the service type set includes: according to the first operation, querying the mapping relationship to obtain the service type set, and the target service type included in the service type set is A service type corresponding to one or more target second operations, where the one or more target second operations are continuous operations associated with the first operation.
  • the next operation will be executed continuously, so the intention of voice interaction for the business corresponding to the next operation will be generated.
  • This optional method makes full use of the operation
  • the law of continuity will map the user's current operation to the business type corresponding to the next operation to be executed under a certain probability, so that when the user performs the operation, the user can accurately predict which business type the user wants to target Perform voice interaction, thus ensuring the accuracy of the target service type.
  • the determining that the target event is detected to occur includes: receiving a notification message from an operating system or an application;
  • the querying the mapping relationship according to the target event to obtain the service type set includes:
  • the mapping relationship is queried to obtain the service type set, and the target service type included in the service type set is message viewing or message processing corresponding to the notification message.
  • the terminal receives a notification message
  • the user will have the need to view the notification message or process the notification message, so the voice interaction intention for message viewing or message processing will be generated.
  • This optional method fully considers the user
  • the need to view notification messages or process notification messages will map the event of receiving notification messages to the service type of message viewing or message processing, so that when the notification message is received, the user’s desire can be accurately predicted Which service type should be used for voice interaction, thus ensuring the accuracy of the target service type.
  • the notification message includes at least one of an incoming call notification, a short message, an instant messaging message, and an alarm message
  • the querying the mapping relationship according to the notification message to obtain the service type set includes the following At least one:
  • the mapping relationship According to the incoming call notification, query the mapping relationship to obtain the service type set, and the target service type included in the service type set is answering the call;
  • query the mapping relationship to obtain the service type set, and the target service type included in the service type set is message viewing or message reply;
  • the mapping relationship is queried to obtain the service type set, and the target service type included in the service type set is fault processing or information query.
  • the determining that the target event is detected includes: determining that the current environmental parameter satisfies the first condition
  • the querying the mapping relationship according to the target event to obtain the service type set includes: querying the mapping relationship according to the environmental parameter to obtain the service type set, and the target service type included in the service type set is adjustment Environmental parameters.
  • the environment will affect the user's perception, and the user will have the need to cope with the environment. For example, if a certain environmental parameter changes, the user will have the need to adjust this environmental parameter, so a voice for adjusting the environmental parameter will be generated Interactive intention, and through this optional method, the user’s need to respond to the environment is fully considered, and the event that the environmental parameter meets the first condition is mapped to the business type of adjusting the environmental parameter, so that the environmental parameter meets the first condition. Under certain conditions, it accurately predicts which service type the user wants to perform voice interaction with, thus ensuring the accuracy of the target service type.
  • the determining that the target event has been detected includes: determining that the progress of the current business meets the second condition;
  • the querying the mapping relationship according to the target event to obtain the service type set includes: querying the mapping relationship according to the current service to obtain the service type set, and the target service type included in the service type set is all State the business type of the current business.
  • the progress of the current business will affect the user’s perception, and the user will have the need to cope with the current business. For example, if the current business is about to end, the user usually wants to re-execute the current business, stop executing the current business, or respond to the current business. The business is adjusted, and through this optional method, the user’s needs for responding to business changes are fully considered, and the event that the current business progress meets the second condition is mapped to the business type of the current business, so that the current business When the progress meets the second condition, it accurately predicts which service type the user wants to perform voice interaction for, thus ensuring the accuracy of the target service type.
  • the target event can cover multiple modalities, and the target event of any modal can trigger the voice interaction function of the corresponding service type, so that in a variety of application scenarios, it can support wake-up without wake-up words Function, expand the scope of application.
  • the process of establishing the mapping relationship includes:
  • the historical record obtain the historical business executed in association with the historical target event, and write the business type of the historical business and the historical target event into the mapping relationship;
  • the user due to the regularity of the personal behavior pattern of the same user, under normal circumstances, the user’s voice interaction intention after the current target event will be more likely to be compared with the historical time after the historical target event. If the generated voice interaction intentions are the same or similar, then the business that will be executed after the current target event will be the same or similar to the business that will be executed by the historical target event with a high probability. Therefore, it is predicted by combining historical records The target service type targeted by the current voice interaction intention can improve the accuracy of the target service type.
  • the process of establishing the mapping relationship includes: invoking a machine learning model, inputting sample target events into the machine learning model, outputting business types, and writing the output business types and the sample target events into the mapping relationship ,
  • the machine learning model is used to predict the type of business according to the event.
  • the method further includes: if the service type of the first service is in the service type set Each target service type of is different, and the service type of the first service is written into the mapping relationship.
  • the service type set obtained will include the service type of the first service. Then, when the user expresses the service type of the first service through voice commands, Will respond to voice commands to perform the first service.
  • the terminal detects event X in the historical operation process, the user expresses the intention of voice interaction with service type Y through voice, and the event X and service type Y can be added to the mapping relationship. Then, On the one hand, with the execution of the voice interaction process, the correlation between events and business types can be mined, and the business types corresponding to events and semantic information can be supplemented and improved.
  • the terminal can add new events and new service types to the mapping relationship to improve the scalability and timeliness of the mapping relationship.
  • the querying the mapping relationship according to the target event to obtain the service type set includes: querying the mapping relationship according to the target event to obtain the service type set and each of the service type sets The probability corresponding to the target service type.
  • the probability indicates the probability that the service corresponding to the target service type will be executed; if the service type of the first service is any target service type in the service type set, according to the Before the voice command executes the first service, the method further includes: filtering out target service types whose probability does not meet the probability threshold from the service type set.
  • the method further includes: updating the mapping relationship according to the semantic information corresponding to the voice instruction The probability.
  • the probability can be dynamically adjusted according to the semantic information expressed by the user this time, so as to evaluate the correctness of the predicted business type in a self-learning manner. Iteratively corrects the probability, so that the probability of each business type in the mapping relationship can be continuously optimized with the occurrence of the target event and the semantics expressed by the user, gradually getting closer to the user's personal behavior habits, and ensuring the mapping relationship is more accurate.
  • the updating the probability in the mapping relationship according to the semantic information corresponding to the voice instruction includes:
  • the service type of the first service is any target service type in the service type set, increase the probability corresponding to the service type of the first service in the mapping relationship;
  • the target event X corresponds to the target service type Y
  • the user always requests to execute the service of the target service type Y through voice, indicating that the target service type Y happens to happen
  • the probability of the target service type Y will continue to increase, so when the target event is detected again subsequently, the probability of the target service type Y will be The probability threshold is met, so that the target service type Y will be screened out. If the voice command expresses the semantic information of the target service type Y, the terminal will process the service in response to the voice command.
  • the updating the probability in the mapping relationship according to the semantic information corresponding to the voice instruction includes:
  • the target event X corresponds to the target service type Y
  • the user does not request to execute the service of the target service type Y through voice, indicating that the target service type Y does not occur
  • the probability of the target service type Y will continue to decrease, so when the target event X is detected again subsequently, the probability of the target service type Y If the probability threshold is not met, the target service type Y will be filtered out, and the terminal will not process the service of the target service type Y, thereby avoiding false wakeup.
  • the updating the probability in the mapping relationship according to the semantic information corresponding to the voice instruction includes: if the semantic information includes a wake-up word, adding the service type of the first service in the mapping relationship The corresponding probability.
  • the target event X corresponds to the target business type Y
  • the user will speak a wake-up word, indicating that the target business type Y happens to be after the target event X occurs, and the user has The service type of the voice interaction intention
  • the probability of the target service type Y will continue to increase. Therefore, when the target event is subsequently detected again, the probability of the target service type Y will meet the probability threshold, making the target service type Y will be screened out. If the voice command expresses the semantic information of the target service type Y, the terminal will process the service in response to the voice command.
  • the method further includes: if the service type of the first service is in the service type set Each target service type is different, and the voice command is discarded.
  • the terminal may not respond to voice commands, but discard voice commands, so as to avoid false wake-ups caused by service processing based on voice commands, and save the buffer space occupied by voice commands.
  • a voice interaction device in a second aspect, has the function of implementing voice interaction in the first aspect or any one of the optional methods of the first aspect.
  • the device includes at least one module, and the at least one module is configured to implement the voice interaction method provided in the first aspect or any one of the optional modes of the first aspect.
  • a terminal in a third aspect, includes one or more processors and one or more memories, and at least one instruction is stored in the one or more memories.
  • the processor loads and executes to implement the voice interaction method provided in the first aspect or any one of the optional modes of the first aspect.
  • a computer-readable storage medium is provided, and at least one instruction is stored in the storage medium, and the instruction is loaded and executed by a processor to implement the foregoing first aspect or any one of the optional methods of the first aspect.
  • Voice interaction method provided.
  • a computer program product includes: computer program code, when the computer program code is run by a terminal, the terminal can execute the first aspect or any one of the first aspects. Select the voice interaction method provided by the method.
  • a chip including a processor, configured to call and execute instructions stored in the memory from a memory, so that a terminal installed with the chip can execute the first aspect or any one of the first aspects. Select the voice interaction method provided by the method.
  • another chip including: an input interface, an output interface, a processor, and a memory, the input interface, output interface, the processor, and the memory are connected by an internal connection path, and the processing
  • the processor is configured to execute the code in the memory, and when the code is executed, the processor is configured to execute the voice interaction method provided in the first aspect or any one of the optional modes of the first aspect.
  • FIG. 1 is a schematic diagram of an implementation environment of a voice interaction method provided by an embodiment of the present application
  • FIG. 2 is a schematic structural diagram of a terminal 100 provided by an embodiment of the present application.
  • FIG. 3 is a functional architecture diagram of a terminal 100 provided by an embodiment of the present application.
  • FIG. 4 is a flowchart of a voice interaction method provided by an embodiment of the present application.
  • Figure 5 is a software architecture diagram of a voice interaction system provided by an embodiment of the present application.
  • FIG. 6 is a schematic structural diagram of a vehicle-mounted terminal provided by an embodiment of the present application.
  • Fig. 7 is a schematic structural diagram of a voice interaction device provided by an embodiment of the present application.
  • Business type a general term for a type of business, and a business type can also be called a business field.
  • business types can include message viewing, message processing, adjustment of environmental parameters, navigation, schedule consultation, air conditioning, radio, music, car control, mileage inquiry, question and answer consultation, games, system settings, vehicle control, charging, maintenance, communication
  • the message viewing may include viewing short messages, viewing instant messaging messages of instant messaging applications, and viewing push messages of resource recommendation applications.
  • the message processing may include answering calls, message responses, troubleshooting, information query, etc.
  • adjusting environmental parameters may include Adjust dust concentration, adjust humidity, adjust light, adjust noise intensity, adjust temperature, etc.
  • the service type of message checking can be: checking the conversation message X sent by user A, checking the latest group announcement Y in the group chat, checking the preferential news released by the shopping application today, etc., and adjusting the environmental parameters.
  • the type of business can be: adjust the temperature to 25° through air-conditioning
  • the business of the music business type can be: play the latest song Z of singer B
  • the business of the navigation business type can be: navigate to C city D district E In the district of Road F
  • the business type of answering incoming calls can be: answering the call of the caller ZZ
  • the business type of replying to the message can be: replying to the contact G with a short message "I am driving, I will reply later”
  • the service type of radio station can be: Open "Oriental Music Radio".
  • Fig. 1 is a schematic diagram of an implementation environment of a voice interaction method provided by an embodiment of the present application.
  • the implementation environment includes: a terminal 100 and a voice interaction platform 200.
  • the terminal 100 is connected to the voice interaction platform 200 through a wireless network or a wired network.
  • the terminal 100 can be a smart phone, a smart speaker, a robot, a smart car, a car terminal, a home device, a game console, a desktop computer, a tablet computer, an e-book reader, a smart TV, MP3 (moving picture experts, group audio layer III, dynamic video) Expert compression standard audio layer 3) player or MP4 (moving picture experts group audio layer IV, moving picture expert compression standard audio layer 4) player and laptop portable computer at least one.
  • the terminal 100 installs and runs an application program supporting voice interaction.
  • the application can be a voice assistant, an intelligent question answering application, etc.
  • the terminal 100 is a terminal used by a user, and a user account is logged in an application program running in the terminal 100.
  • the voice interaction platform 200 includes at least one of a server, multiple servers, a cloud computing platform, and a virtualization center.
  • the voice interaction platform 200 is used to provide background services for applications that support voice interaction.
  • the voice interaction platform may construct the mapping relationship provided in the following method embodiments, and send the mapping relationship to the terminal 100 so that the terminal 100 can perform voice interaction based on the mapping relationship.
  • the voice interaction platform 200 includes: a voice interaction server 201 and a database 202.
  • the voice interaction server 201 is used to provide background services related to voice interaction.
  • the voice interaction server 201 may be one or more.
  • there are multiple voice interaction servers 201 there are at least two voice interaction servers 201 for providing different services, and/or there are at least two voice interaction servers 201 for providing the same service, for example, in a load balancing manner.
  • the same service is not limited in this embodiment of the application.
  • the database 202 can be used to store the mapping relationship.
  • the database 202 may store sample events and sample service types, so that the voice interaction server 201 reads the sample events and sample service types from the database 202, and trains a machine learning model based on the sample events and sample service types. Through the machine learning model Establish a mapping relationship.
  • the terminal 100 may generally refer to one of multiple terminals, and this embodiment only uses the terminal 100 as an example for illustration. Those skilled in the art may know that the number of the aforementioned terminals 100 may be more or less. For example, there may be only one terminal 100, or there may be dozens or hundreds of terminals 100, or more. In this case, the voice interaction system may also include other terminals. The embodiment of the present application does not limit the number of terminals 100 and the device type.
  • FIG. 2 is a schematic structural diagram of a terminal 100 provided by an embodiment of the present application.
  • the terminal 100 may include a processor 110, an external memory interface 120, an internal memory 121, a universal serial bus (USB) interface 130, a charging management module 140, a power management module 141, a battery 142, an antenna 1, an antenna 2, Mobile communication module 150, wireless communication module 160, audio module 170, speaker 170A, receiver 170B, microphone 170C, earphone interface 170D, sensor module 180, buttons 190, motor 191, indicator 192, camera 193, display screen 194, and user An identification module (subscriber identification module, SIM) card interface 195, etc.
  • SIM subscriber identification module
  • the sensor module 180 may include pressure sensor 180A, gyroscope sensor 180B, air pressure sensor 180C, magnetic sensor 180D, acceleration sensor 180E, distance sensor 180F, proximity light sensor 180G, fingerprint sensor 180H, temperature sensor 180J, touch sensor 180K, ambient light Sensor 180L, bone conduction sensor 180M, etc.
  • the structure illustrated in the embodiment of the present application does not constitute a specific limitation on the terminal 100.
  • the terminal 100 may include more or fewer components than shown, or combine certain components, or split certain components, or arrange different components.
  • the illustrated components can be implemented in hardware, software, or a combination of software and hardware.
  • the processor 110 may include one or more processing units.
  • the processor 110 may include an application processor (AP), a modem processor, a graphics processing unit (GPU), and an image signal processor. (image signal processor, ISP), controller, video codec, digital signal processor (digital signal processor, DSP), baseband processor, and/or neural-network processing unit (NPU), etc.
  • AP application processor
  • modem processor modem processor
  • GPU graphics processing unit
  • image signal processor image signal processor
  • ISP image signal processor
  • controller video codec
  • digital signal processor digital signal processor
  • DSP digital signal processor
  • NPU neural-network processing unit
  • the different processing units may be independent devices or integrated in one or more processors.
  • the controller can generate operation control signals according to the instruction operation code and timing signals to complete the control of fetching and executing instructions.
  • a memory may also be provided in the processor 110 to store instructions and data.
  • the memory in the processor 110 is a cache memory.
  • the memory can store instructions or data that have just been used or recycled by the processor 110. If the processor 110 needs to use the instruction or data again, it can be directly called from the memory. Repeated accesses are avoided, the waiting time of the processor 110 is reduced, and the efficiency of the system is improved.
  • the processor 110 may include one or more interfaces.
  • the interface may include an integrated circuit (inter-integrated circuit, I2C) interface, an integrated circuit built-in audio (inter-integrated circuit sound, I2S) interface, a pulse code modulation (pulse code modulation, PCM) interface, and a universal asynchronous transmitter (universal asynchronous transmitter) interface.
  • I2C integrated circuit
  • I2S integrated circuit built-in audio
  • PCM pulse code modulation
  • PCM pulse code modulation
  • UART universal asynchronous transmitter
  • MIPI mobile industry processor interface
  • GPIO general-purpose input/output
  • SIM subscriber identity module
  • USB Universal Serial Bus
  • the I2C interface is a two-way synchronous serial bus, including a serial data line (SDA) and a serial clock line (SCL).
  • the processor 110 may include multiple sets of I2C buses.
  • the processor 110 may be coupled to the touch sensor 180K, charger, flash, camera 193, etc. through different I2C bus interfaces.
  • the processor 110 may couple the touch sensor 180K through an I2C interface, so that the processor 110 and the touch sensor 180K communicate through the I2C bus interface to implement the touch function of the terminal 100.
  • the I2S interface can be used for audio communication.
  • the processor 110 may include multiple sets of I2S buses.
  • the processor 110 may be coupled with the audio module 170 through an I2S bus to realize communication between the processor 110 and the audio module 170.
  • the audio module 170 may transmit audio signals to the wireless communication module 160 through an I2S interface, so as to realize the function of answering calls through a Bluetooth headset.
  • the PCM interface can also be used for audio communication to sample, quantize and encode analog signals.
  • the audio module 170 and the wireless communication module 160 may be coupled through a PCM bus interface.
  • the audio module 170 may also transmit audio signals to the wireless communication module 160 through the PCM interface, so as to realize the function of answering calls through the Bluetooth headset. Both the I2S interface and the PCM interface can be used for audio communication.
  • the UART interface is a universal serial data bus used for asynchronous communication.
  • the bus can be a two-way communication bus. It converts the data to be transmitted between serial communication and parallel communication.
  • the UART interface is generally used to connect the processor 110 and the wireless communication module 160.
  • the processor 110 communicates with the Bluetooth module in the wireless communication module 160 through the UART interface to implement the Bluetooth function.
  • the audio module 170 may transmit audio signals to the wireless communication module 160 through a UART interface, so as to realize the function of playing music through a Bluetooth headset.
  • the MIPI interface can be used to connect the processor 110 with the display screen 194, the camera 193 and other peripheral devices.
  • the MIPI interface includes camera serial interface (camera serial interface, CSI), display serial interface (display serial interface, DSI), etc.
  • the processor 110 and the camera 193 communicate through a CSI interface to implement the shooting function of the terminal 100.
  • the processor 110 and the display screen 194 communicate through a DSI interface to realize the display function of the terminal 100.
  • the GPIO interface can be configured through software.
  • the GPIO interface can be configured as a control signal or as a data signal.
  • the GPIO interface can be used to connect the processor 110 with the camera 193, the display screen 194, the wireless communication module 160, the audio module 170, the sensor module 180, and so on.
  • GPIO interface can also be configured as I2C interface, I2S interface, UART interface, MIPI interface, etc.
  • the USB interface 130 is an interface that complies with the USB standard specification, and specifically may be a Mini USB interface, a Micro USB interface, a USB Type C interface, and so on.
  • the USB interface 130 can be used to connect a charger to charge the terminal 100, and can also be used to transfer data between the terminal 100 and peripheral devices. It can also be used to connect headphones and play audio through the headphones. This interface can also be used to connect to other terminals, such as AR devices.
  • the interface connection relationship between the modules illustrated in the embodiment of the present application is merely a schematic description, and does not constitute a structural limitation of the terminal 100.
  • the terminal 100 may also adopt different interface connection modes in the foregoing embodiments, or a combination of multiple interface connection modes.
  • the charging management module 140 is used to receive charging input from the charger.
  • the charger can be a wireless charger or a wired charger.
  • the charging management module 140 may receive the charging input of the wired charger through the USB interface 130.
  • the charging management module 140 may receive the wireless charging input through the wireless charging coil of the terminal 100. While the charging management module 140 charges the battery 142, it can also supply power to the terminal through the power management module 141.
  • the power management module 141 is used to connect the battery 142, the charging management module 140 and the processor 110.
  • the power management module 141 receives input from the battery 142 and/or the charging management module 140, and supplies power to the processor 110, the internal memory 121, the display screen 194, the camera 193, and the wireless communication module 160.
  • the power management module 141 can also be used to monitor parameters such as battery capacity, battery cycle times, and battery health status (leakage, impedance).
  • the power management module 141 may also be provided in the processor 110.
  • the power management module 141 and the charging management module 140 may also be provided in the same device.
  • the wireless communication function of the terminal 100 can be implemented by the antenna 1, the antenna 2, the mobile communication module 150, the wireless communication module 160, the modem processor, and the baseband processor.
  • the antenna 1 and the antenna 2 are used to transmit and receive electromagnetic wave signals.
  • Each antenna in the terminal 100 can be used to cover a single or multiple communication frequency bands. Different antennas can also be reused to improve antenna utilization.
  • antenna 1 can be multiplexed as a diversity antenna of a wireless local area network.
  • the antenna can be used in combination with a tuning switch.
  • the mobile communication module 150 can provide a wireless communication solution including 2G/3G/4G/5G and the like applied to the terminal 100.
  • the mobile communication module 150 may include at least one filter, switch, power amplifier, low noise amplifier (LNA), etc.
  • the mobile communication module 150 can receive electromagnetic waves by the antenna 1, and perform processing such as filtering and amplifying the received electromagnetic waves, and then transmitting them to the modem processor for demodulation.
  • the mobile communication module 150 can also amplify the signal modulated by the modem processor, and convert it into electromagnetic waves for radiation via the antenna 1.
  • at least part of the functional modules of the mobile communication module 150 may be provided in the processor 110.
  • at least part of the functional modules of the mobile communication module 150 and at least part of the modules of the processor 110 may be provided in the same device.
  • the modem processor may include a modulator and a demodulator.
  • the modulator is used to modulate the low frequency baseband signal to be sent into a medium and high frequency signal.
  • the demodulator is used to demodulate the received electromagnetic wave signal into a low-frequency baseband signal. Then the demodulator transmits the demodulated low-frequency baseband signal to the baseband processor for processing.
  • the low-frequency baseband signal is processed by the baseband processor and then passed to the application processor.
  • the application processor outputs a sound signal through an audio device (not limited to the speaker 170A, the receiver 170B, etc.), or displays an image or video through the display screen 194.
  • the modem processor may be an independent device.
  • the modem processor may be independent of the processor 110 and be provided in the same device as the mobile communication module 150 or other functional modules.
  • the wireless communication module 160 can provide applications on the terminal 100, including wireless local area networks (WLAN) (such as wireless fidelity (Wi-Fi) networks), Bluetooth (BT), and global navigation satellite systems. (global navigation satellite system, GNSS), frequency modulation (frequency modulation, FM), near field communication technology (near field communication, NFC), infrared technology (infrared, IR) and other wireless communication solutions.
  • WLAN wireless local area networks
  • BT Bluetooth
  • GNSS global navigation satellite system
  • frequency modulation frequency modulation, FM
  • NFC near field communication technology
  • infrared technology infrared, IR
  • the wireless communication module 160 may be one or more devices integrating at least one communication processing module.
  • the wireless communication module 160 receives electromagnetic waves via the antenna 2, frequency modulates and filters the electromagnetic wave signals, and sends the processed signals to the processor 110.
  • the wireless communication module 160 can also receive the signal to be sent from the processor 110, perform frequency modulation, amplify it, and convert it into electromagnetic wave radiation via the antenna 2.
  • the antenna 1 of the terminal 100 is coupled with the mobile communication module 150, and the antenna 2 is coupled with the wireless communication module 160, so that the terminal 100 can communicate with the network and other devices through wireless communication technology.
  • the wireless communication technology may include the global system for mobile communications (GSM), general packet radio service (GPRS), code division multiple access (CDMA), broadband code Division multiple access (wideband code division multiple access, WCDMA), time-division code division multiple access (TD-SCDMA), long term evolution (LTE), BT, GNSS, WLAN, NFC, FM, and/or IR technology, etc.
  • the GNSS may include the global positioning system (GPS), the global navigation satellite system (GLONASS), the Beidou navigation satellite system (BDS), and the quasi-zenith satellite system (quasi- Zenith satellite system, QZSS) and/or satellite-based augmentation systems (SBAS).
  • GPS global positioning system
  • GLONASS global navigation satellite system
  • BDS Beidou navigation satellite system
  • QZSS quasi-zenith satellite system
  • QZSS quasi-zenith satellite system
  • SBAS satellite-based augmentation systems
  • the terminal 100 implements a display function through a GPU, a display screen 194, and an application processor.
  • the GPU is a microprocessor for image processing, connected to the display 194 and the application processor.
  • the GPU is used to perform mathematical and geometric calculations for graphics rendering.
  • the processor 110 may include one or more GPUs, which execute program instructions to generate or change display information.
  • the display screen 194 is used to display images, videos, etc.
  • the display screen 194 includes a display panel.
  • the display panel can adopt liquid crystal display (LCD), organic light-emitting diode (OLED), active-matrix organic light-emitting diode or active-matrix organic light-emitting diode (active-matrix organic light-emitting diode).
  • LCD liquid crystal display
  • OLED organic light-emitting diode
  • active-matrix organic light-emitting diode active-matrix organic light-emitting diode
  • AMOLED flexible light-emitting diode (FLED), Miniled, MicroLed, Micro-oLed, quantum dot light-emitting diode (QLED), etc.
  • the terminal 100 may include one or N display screens 194, and N is a positive integer greater than one.
  • the terminal 100 can realize a shooting function through an ISP, a camera 193, a video codec, a GPU, a display screen 194, and an application processor.
  • the ISP is used to process the data fed back from the camera 193. For example, when taking a picture, the shutter is opened, the light is transmitted to the photosensitive element of the camera through the lens, the light signal is converted into an electrical signal, and the photosensitive element of the camera transmits the electrical signal to the ISP for processing and transforms it into an image visible to the naked eye.
  • ISP can also optimize the image noise, brightness, and skin color. ISP can also optimize the exposure, color temperature and other parameters of the shooting scene.
  • the ISP may be provided in the camera 193.
  • the camera 193 is used to capture still images or videos.
  • the object generates an optical image through the lens and projects it to the photosensitive element.
  • the photosensitive element may be a charge coupled device (CCD) or a complementary metal-oxide-semiconductor (CMOS) phototransistor.
  • CMOS complementary metal-oxide-semiconductor
  • the photosensitive element converts the optical signal into an electrical signal, and then transmits the electrical signal to the ISP to convert it into a digital image signal.
  • ISP outputs digital image signals to DSP for processing.
  • DSP converts digital image signals into standard RGB, YUV and other formats.
  • the terminal 100 may include 1 or N cameras 193, and N is a positive integer greater than 1.
  • Digital signal processors are used to process digital signals. In addition to digital image signals, they can also process other digital signals. For example, when the terminal 100 selects a frequency point, the digital signal processor is used to perform Fourier transform on the energy of the frequency point.
  • Video codecs are used to compress or decompress digital video.
  • the terminal 100 may support one or more video codecs.
  • the terminal 100 can play or record videos in multiple encoding formats, for example: moving picture experts group (MPEG) 1, MPEG2, MPEG3, MPEG4, and so on.
  • MPEG moving picture experts group
  • NPU is a neural-network (NN) computing processor.
  • NN neural-network
  • applications such as intelligent cognition of the terminal 100 can be implemented, such as image recognition, face recognition, voice recognition, text understanding, etc.
  • the external memory interface 120 may be used to connect an external memory card, such as a Micro SD card, to expand the storage capacity of the terminal 100.
  • the external memory card communicates with the processor 110 through the external memory interface 120 to realize the data storage function. For example, save music, video and other files in an external memory card.
  • the internal memory 121 may be used to store computer executable program code, where the executable program code includes instructions.
  • the internal memory 121 may include a storage program area and a storage data area.
  • the storage program area can store an operating system, at least one application program (such as a sound playback function, an image playback function, etc.) required by at least one function.
  • the data storage area can store data (such as audio data, phone book, etc.) created during the use of the terminal 100.
  • the internal memory 121 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, a universal flash storage (UFS), etc.
  • the processor 110 executes various functional applications and data processing of the terminal 100 by running instructions stored in the internal memory 121 and/or instructions stored in a memory provided in the processor.
  • the terminal 100 can implement audio functions through the audio module 170, the speaker 170A, the receiver 170B, the microphone 170C, the earphone interface 170D, and the application processor. For example, music playback, recording, etc.
  • the audio module 170 is used for converting digital audio information into an analog audio signal for output, and also for converting an analog audio input into a digital audio signal.
  • the audio module 170 can also be used to encode and decode audio signals.
  • the audio module 170 may be provided in the processor 110, or part of the functional modules of the audio module 170 may be provided in the processor 110.
  • the speaker 170A also called a “speaker” is used to convert audio electrical signals into sound signals.
  • the terminal 100 can listen to music through the speaker 170A, or listen to a hands-free call.
  • the receiver 170B also called “earpiece” is used to convert audio electrical signals into sound signals.
  • the terminal 100 answers a call or voice message, it can receive the voice by bringing the receiver 170B close to the human ear.
  • the microphone 170C also called “microphone”, “microphone”, is used to convert sound signals into electrical signals.
  • the user can approach the microphone 170C through the mouth to make a sound, and input the sound signal to the microphone 170C.
  • the terminal 100 may be provided with at least one microphone 170C. In other embodiments, the terminal 100 may be provided with two microphones 170C, which can implement noise reduction functions in addition to collecting sound signals. In other embodiments, the terminal 100 may also be provided with three, four or more microphones 170C to collect sound signals, reduce noise, identify sound sources, and realize directional recording functions.
  • the earphone interface 170D is used to connect wired earphones.
  • the earphone interface 170D may be a USB interface 130, or may be a 3.5mm open mobile terminal platform (open mobile terminal platform, OMTP) standard interface, and a cellular telecommunications industry association (cellular telecommunications industry association of the USA, CTIA) standard interface.
  • open mobile terminal platform OMTP
  • cellular telecommunications industry association cellular telecommunications industry association of the USA, CTIA
  • the pressure sensor 180A is used to sense the pressure signal and can convert the pressure signal into an electrical signal.
  • the pressure sensor 180A may be provided on the display screen 194.
  • the capacitive pressure sensor may include at least two parallel plates with conductive material. When a force is applied to the pressure sensor 180A, the capacitance between the electrodes changes.
  • the terminal 100 determines the strength of the pressure according to the change in capacitance.
  • the terminal 100 detects the intensity of the touch operation according to the pressure sensor 180A.
  • the terminal 100 may also calculate the touched position according to the detection signal of the pressure sensor 180A.
  • touch operations that act on the same touch position but have different touch operation strengths may correspond to different operation instructions. For example: when a touch operation whose intensity is less than the first pressure threshold is applied to the short message application icon, an instruction to view the short message is executed. When a touch operation with a touch operation intensity greater than or equal to the first pressure threshold acts on the short message application icon, an instruction to create a new short message is executed.
  • the gyro sensor 180B may be used to determine the movement posture of the terminal 100.
  • the angular velocity of the terminal 100 around three axes ie, x, y, and z axes
  • the gyro sensor 180B can be used for image stabilization.
  • the gyro sensor 180B detects the shake angle of the terminal 100, calculates the distance that the lens module needs to compensate according to the angle, and allows the lens to counteract the shake of the terminal 100 through a reverse movement to achieve anti-shake.
  • the gyro sensor 180B can also be used for navigation and somatosensory game scenes.
  • the air pressure sensor 180C is used to measure air pressure.
  • the terminal 100 calculates the altitude based on the air pressure value measured by the air pressure sensor 180C to assist positioning and navigation.
  • the magnetic sensor 180D includes a Hall sensor.
  • the terminal 100 may use the magnetic sensor 180D to detect the opening and closing of the flip holster.
  • the terminal 100 can detect the opening and closing of the flip according to the magnetic sensor 180D.
  • features such as automatic unlocking of the flip cover are set.
  • the acceleration sensor 180E can detect the magnitude of the acceleration of the terminal 100 in various directions (generally three axes). When the terminal 100 is stationary, the magnitude and direction of gravity can be detected. It can also be used to identify the terminal's posture, apply to horizontal and vertical screen switching, pedometer and other applications.
  • the terminal 100 can measure the distance by infrared or laser. In some embodiments, when shooting a scene, the terminal 100 may use the distance sensor 180F to measure the distance to achieve fast focusing.
  • the proximity light sensor 180G may include, for example, a light emitting diode (LED) and a light detector such as a photodiode.
  • the light emitting diode may be an infrared light emitting diode.
  • the terminal 100 emits infrared light to the outside through the light emitting diode.
  • the terminal 100 uses a photodiode to detect infrared reflected light from nearby objects. When sufficient reflected light is detected, it can be determined that there is an object near the terminal 100. When insufficient reflected light is detected, the terminal 100 may determine that there is no object near the terminal 100.
  • the terminal 100 can use the proximity light sensor 180G to detect that the user holds the terminal 100 close to the ear to talk, so as to automatically turn off the screen to save power.
  • the proximity light sensor 180G can also be used in leather case mode, and the pocket mode will automatically unlock and lock the screen.
  • the ambient light sensor 180L is used to sense the brightness of the ambient light.
  • the terminal 100 can adaptively adjust the brightness of the display screen 194 according to the perceived brightness of the ambient light.
  • the ambient light sensor 180L can also be used to automatically adjust the white balance when taking pictures.
  • the ambient light sensor 180L can also cooperate with the proximity light sensor 180G to detect whether the terminal 100 is in a pocket to prevent accidental touch.
  • the fingerprint sensor 180H is used to collect fingerprints.
  • the terminal 100 can use the collected fingerprint characteristics to realize fingerprint unlocking, access application locks, fingerprint photographs, fingerprint answering calls, and so on.
  • the temperature sensor 180J is used to detect temperature.
  • the terminal 100 uses the temperature detected by the temperature sensor 180J to execute a temperature processing strategy. For example, when the temperature reported by the temperature sensor 180J exceeds a threshold value, the terminal 100 executes to reduce the performance of the processor located near the temperature sensor 180J, so as to reduce power consumption and implement thermal protection.
  • the terminal 100 when the temperature is lower than another threshold, the terminal 100 heats the battery 142 to avoid abnormal shutdown of the terminal 100 due to low temperature.
  • the terminal 100 boosts the output voltage of the battery 142 to avoid abnormal shutdown caused by low temperature.
  • Touch sensor 180K also called “touch device”.
  • the touch sensor 180K may be disposed on the display screen 194, and the touch screen is composed of the touch sensor 180K and the display screen 194, which is also called a “touch screen”.
  • the touch sensor 180K is used to detect touch operations acting on or near it.
  • the touch sensor can pass the detected touch operation to the application processor to determine the type of touch event.
  • the visual output related to the touch operation can be provided through the display screen 194.
  • the touch sensor 180K may also be disposed on the surface of the terminal 100, which is different from the position of the display screen 194.
  • the bone conduction sensor 180M can acquire vibration signals.
  • the bone conduction sensor 180M can obtain the vibration signal of the vibrating bone mass of the human voice.
  • the bone conduction sensor 180M can also contact the human pulse and receive the blood pressure pulse signal.
  • the bone conduction sensor 180M may also be provided in the earphone, combined with the bone conduction earphone.
  • the audio module 170 can parse out the voice command based on the vibration signal of the vibrating bone block of the voice obtained by the bone conduction sensor 180M to realize the voice function.
  • the application processor can analyze the heart rate information based on the blood pressure beating signal obtained by the bone conduction sensor 180M, and realize the heart rate detection function.
  • the button 190 includes a power button, a volume button, and so on.
  • the button 190 may be a mechanical button. It can also be a touch button.
  • the terminal 100 may receive key input, and generate key signal input related to user settings and function control of the terminal 100.
  • the motor 191 can generate vibration prompts.
  • the motor 191 can be used for incoming call vibration notification, and can also be used for touch vibration feedback.
  • touch operations applied to different applications can correspond to different vibration feedback effects.
  • Acting on touch operations in different areas of the display screen 194, the motor 191 can also correspond to different vibration feedback effects.
  • Different application scenarios for example: time reminding, receiving information, alarm clock, games, etc.
  • the touch vibration feedback effect can also support customization.
  • the indicator 192 may be an indicator light, which may be used to indicate the charging status, power change, or to indicate messages, missed calls, notifications, and so on.
  • the SIM card interface 195 is used to connect to the SIM card.
  • the SIM card can be inserted into the SIM card interface 195 or pulled out from the SIM card interface 195 to achieve contact and separation with the terminal 100.
  • the terminal 100 may support 1 or N SIM card interfaces, and N is a positive integer greater than 1.
  • the SIM card interface 195 can support Nano SIM cards, Micro SIM cards, SIM cards, etc.
  • the same SIM card interface 195 can insert multiple cards at the same time. The types of the multiple cards can be the same or different.
  • the SIM card interface 195 can also be compatible with different types of SIM cards.
  • the SIM card interface 195 may also be compatible with external memory cards.
  • the terminal 100 interacts with the network through the SIM card to implement functions such as call and data communication.
  • the terminal 100 adopts an eSIM, that is, an embedded SIM card.
  • the eSIM card can be embedded in the terminal 100 and cannot be separated from the terminal 100.
  • the software system of the terminal 100 may adopt a layered architecture, an event-driven architecture, a microkernel architecture, a microservice architecture, or a cloud architecture.
  • the software structure of the terminal 100 is exemplified.
  • FIG. 3 is a functional architecture diagram of a terminal 100 provided by an embodiment of the present application.
  • the layered architecture divides the software into several layers, and each layer has a clear role and division of labor. Communication between layers through software interface.
  • the Android system is divided into four layers, from top to bottom, the application layer, the application framework layer, the Android runtime and system library, and the kernel layer.
  • the application layer can include a series of application packages.
  • the application package can include applications such as camera, gallery, calendar, call, map, navigation, WLAN, Bluetooth, music, video, short message, etc.
  • the application framework layer provides application programming interfaces (application programming interface, API) and programming frameworks for applications in the application layer.
  • the application framework layer includes some predefined functions.
  • the application framework layer can include a window manager, a content provider, a view system, a phone manager, a resource manager, and a notification manager.
  • the window manager is used to manage window programs.
  • the window manager can obtain the size of the display, determine whether there is a status bar, lock the screen, take a screenshot, etc.
  • the content provider is used to store and retrieve data and make these data accessible to applications.
  • This data can include videos, images, audios, calls made and received, browsing history and bookmarks, phone book, etc.
  • the view system includes visual controls, such as controls that display text and controls that display pictures.
  • the view system can be used to build applications.
  • the display interface can be composed of one or more views.
  • a display interface that includes a short message notification icon may include a view that displays text and a view that displays pictures.
  • the phone manager is used to provide the communication function of the terminal 100. For example, the management of the call status (including connecting, hanging up, etc.).
  • the resource manager provides various resources for the application, such as localized strings, icons, pictures, layout files, video files, etc.
  • the notification manager enables the application to display notification information in the status bar, which can be used to convey notification-type messages, and it can disappear automatically after a short stay without user interaction.
  • the notification manager is used to notify the download completion, message reminder, etc.
  • the notification manager can also be a notification that appears in the status bar at the top of the system in the form of a chart or scroll bar text, such as a notification of an application running in the background, or a notification that appears on the screen in the form of a dialog window.
  • prompt text information in the status bar sound a prompt tone, terminal vibration, flashing indicator light, etc.
  • Android Runtime includes core libraries and virtual machines. Android runtime is responsible for the scheduling and management of the Android system.
  • the core library consists of two parts: one part is the function functions that the java language needs to call, and the other part is the core library of Android.
  • the application layer and the application framework layer run in a virtual machine.
  • the virtual machine executes the java files of the application layer and the application framework layer as binary files.
  • the virtual machine is used to perform functions such as object life cycle management, stack management, thread management, security and exception management, and garbage collection.
  • the system library can include multiple functional modules. For example: surface manager (surface manager), media library (Media Libraries), three-dimensional graphics processing library (for example: OpenGL ES), 2D graphics engine (for example: SGL), etc.
  • the surface manager is used to manage the display subsystem and provides a combination of 2D and 3D layers for multiple applications.
  • the media library supports playback and recording of a variety of commonly used audio and video formats, as well as still image files.
  • the media library can support multiple audio and video encoding formats, such as: MPEG4, H.264, MP3, AAC, AMR, JPG, PNG, etc.
  • the 3D graphics processing library is used to realize 3D graphics drawing, image rendering, synthesis, and layer processing.
  • the 2D graphics engine is a drawing engine for 2D drawing.
  • the kernel layer is the layer between hardware and software.
  • the kernel layer contains at least display driver, camera driver, audio driver, and sensor driver.
  • the process of detecting the trigger operation may include: when the touch sensor 180K receives the touch operation, a corresponding hardware interrupt is sent to the kernel layer.
  • the kernel layer processes touch operations into original input events (including touch coordinates, time stamps of touch operations, etc.).
  • the original input events are stored in the kernel layer.
  • the application framework layer obtains the original input event from the kernel layer, identifies the control corresponding to the input event, and detects that the touch operation occurs.
  • the touch operation as a click operation
  • the control corresponding to the click operation is an icon of a music application as an example
  • the music application calls the interface of the application framework layer to start the music application, and then displays the interface of the music application through the display screen 194.
  • the embodiments of the present application can be applied to a scenario where a terminal is awakened for voice interaction.
  • a terminal is awakened for voice interaction.
  • the function of avoiding wake-up word can be realized.
  • the terminal's wake-up word "Hello, Xiaohua" as an example, the following is a comparative description in combination with scenario one to scenario eight:
  • Scenario 1 During driving, the user wants to play a song on the vehicle terminal.
  • this scenario includes the following steps 1 to 7:
  • Step 1 The user says "Hello, Xiaohua”.
  • Step 2 The vehicle terminal collects the voice command and determines that the voice command contains "Hello, Xiaohua", the vehicle terminal is awakened, and the voice "Is there" is played, thereby responding to the user's voice command; after that, the vehicle terminal is preset If the voice command is not collected for the duration, the vehicle-mounted terminal sleeps again.
  • Step 3 The user turns on the radio switch.
  • Step 4 The user says "Hello, Xiaohua”.
  • Step 5 The vehicle-mounted terminal collects the voice command and determines that the voice command contains "Hello, Xiaohua", and the vehicle-mounted terminal is re-awakened and plays the voice "Are you there", thereby responding to the user's voice command.
  • Step 6 The user says “Help play the song of "Eastern Music Radio”.
  • Step 7 The vehicle-mounted terminal collects the voice command and determines that the voice command contains "Hello, Xiaohua", then the vehicle-mounted terminal will adjust the radio station to "Eastern Music Radio” and play songs from "Eastern Music Radio".
  • this scenario may include the following steps 1 to 4:
  • Step 1 The user turns on the radio switch.
  • Step 2 The radio switch sends a signal to the vehicle-mounted terminal, and the vehicle-mounted terminal determines that the opening operation of the radio switch is detected. According to the opening operation of the radio switch, the mapping relationship is inquired, and the target service type obtained is music, thereby predicting that the user has a target The intention of the business of music business type to conduct voice interaction.
  • Step 3 The user says “Help play the songs of "Eastern Music Radio”.
  • Step 4 The vehicle-mounted terminal collects the voice command, obtains that the service type corresponding to "Help to play the song of "Oriental Music Radio” is music, and determines that the predicted target service type is the same as the service type expressed by the user through voice, and then plays the "Oriental Music” Radio” songs. In addition, if the content said by the user in step 3 has nothing to do with music, the vehicle-mounted terminal may not respond to the content said by the user.
  • the user can activate the voice interaction function of the vehicle-mounted terminal for the business type of music, which is free of wake-up words, thereby eliminating the step of frequently speaking the wake-up words by the user.
  • Scenario 2 During driving, the user wants to view instant messaging messages.
  • this scenario includes the following steps 1 to 7:
  • Step 1 Application A running on the mobile phone receives an instant messaging message.
  • Step 2 The user says "Hello, Xiaohua”.
  • Step 3 The terminal collects the voice command and confirms that the voice command contains "Hello, Xiaohua", then the phone is woken up and plays the voice "Are you there", so as to respond to the user's voice command; after that, the phone does not collect the voice command for a preset time When the voice command is reached, the phone sleeps again.
  • Step 4 The user says "Hello, Xiaohua”.
  • Step 5 The mobile phone collects the voice command and confirms that the voice command contains "Hello, Xiaohua", then the mobile phone is re-awakened and the voice "Are there" is played, thereby responding to the user's voice command.
  • Step 6 The user says “Look at what application A is saying”.
  • Step 7 The mobile phone collects the voice command and confirms that the voice command contains "Look at what application A is saying", then the mobile phone obtains the instant messaging message "Go eat hot pot at 7pm" received by application A, and then plays the voice "7pm at night” Order to eat hot pot”.
  • this scenario may include the following steps 1 to 4:
  • Step 1 Application A running on the mobile phone receives an instant messaging message.
  • Step 2 The mobile phone queries the mapping relationship according to the received instant messaging message, and the target service type obtained is application A, thereby predicting that the user has the intention of voice interaction for the service of the application A type.
  • Step 3 The user says “Look at what application A is saying”.
  • Step 4 The mobile phone collects voice commands and obtains the service type corresponding to "Look at what application A is saying" as application A.
  • the mobile phone determines that the predicted target service type is the same as the service type expressed by the user through voice, then the mobile phone obtains the application
  • the instant messaging message "Go to eat hot pot at seven in the evening" received by Program A plays the voice "Go eat hot pot at seven in the evening".
  • the mobile phone may not respond to the content said by the user, thereby avoiding false wakeup.
  • the wake-up-free voice interaction function of the mobile phone for instant messaging application services can be activated, thereby eliminating the need for users to frequently speak wake-up words.
  • Scenario 3 When a song is about to end, the user wants to continue playing another song.
  • this scenario includes the following steps 1 to 5:
  • Step 1 The song A currently playing on the smart speaker will end.
  • Step 2 The user says "Hello, Xiaohua”.
  • Step 3 The smart speaker collects the voice command and determines that the voice command contains "Hello, Xiaohua", then the smart speaker is awakened and plays the voice "Are you there", thereby responding to the user's voice command.
  • Step 4. The user says “put down song B”.
  • Step 5 The smart speaker collects the voice command and determines that the voice command contains "put down song B", and the smart speaker plays song B.
  • this scenario may include the following steps one to three:
  • Step 1 The song A currently played by the smart speaker is about to end, the smart speaker determines that the current business progress meets the conditions, and the smart speaker queries the mapping relationship according to the current business music, and the target business type obtained is music, thereby predicting that the user has music-oriented The intention of this type of service for voice interaction.
  • Step 2 The user says “put down song B”.
  • Step 3 The smart speaker collects the voice command and obtains that the service type corresponding to "Put Down Song B" is music. Then it is determined that the predicted target service type is the same as the service type expressed by the user through voice, and the smart speaker plays song B. In addition, if the content said by the user in step 2 has nothing to do with music, the smart speaker may not respond to the content said by the user.
  • this scenario includes the following steps 1 to 4:
  • Step 1 The user says "Hello, Xiaohua”.
  • Step 2 The vehicle-mounted terminal collects voice commands and determines that the voice command contains "Hello, Xiaohua", and the vehicle-mounted terminal is awakened and plays the voice "Are you there", thereby responding to the user's voice command.
  • Step 3 The user says “Turn on the wipers”.
  • Step 4 The vehicle-mounted terminal collects the voice command and determines that the voice command includes "open the wiper", then the vehicle-mounted terminal sends a signal to the car's controller, and the controller controls the wiper drive circuit to drive the wiper to rotate.
  • this scenario may include the following steps one to three:
  • Step 1 The vehicle-mounted terminal determines that it detects rain through the raindrop sensor, and then queries the mapping relationship according to the rain, and the target service type is wiper, thus predicting that the user has the intention of voice interaction for the service type of wiper .
  • Step 2 The user says “Turn on the wiper.”
  • Step 3 The vehicle-mounted terminal collects the voice command and obtains that the service type corresponding to "Turn on the wiper" is the wiper. Then it is determined that the predicted target service type is the same as the service type expressed by the user through voice, and the vehicle-mounted terminal sends a signal to the car controller. The controller instructs the drive circuit of the wiper to drive the wiper to rotate. In addition, if the content said by the user in step 2 has nothing to do with the wiper, the vehicle-mounted terminal may not respond to the content said by the user.
  • the mobile phone can activate the wake-up word-free voice interaction function of the service type of wiper, thereby eliminating the need for users to frequently speak wake-up words.
  • Scenario 5 During driving, the car's fuel is insufficient.
  • this scenario includes the following steps 1 to 4:
  • Step 1 The user says "Hello, Xiaohua”.
  • Step 2 The vehicle-mounted terminal collects the voice command and determines that the voice command contains "Hello, Xiaohua", then the mobile phone is awakened and the voice "Are there" is played, thereby responding to the user's voice command.
  • Step 3 The user says "where is the nearest gas station”.
  • Step 4 The on-board terminal collects the voice command and determines that the voice command contains "Where is the nearest gas station", then the on-board terminal calls the interface with the navigation application to query the gas station address, and the voice "gas station address is in X area Y road” .
  • this scenario may include the following steps one to three:
  • Step 1 The vehicle-mounted terminal detects the fuel quantity of the car and determines that the fuel quantity is lower than the threshold. Then the mapping relationship is queried according to the fuel quantity, and the service type set obtained includes gas station and navigation, thereby predicting that the user has two types of gas station or navigation The intent of the business type of business for voice interaction.
  • Step 2 The user says "where is the nearest gas station”.
  • Step 3 The vehicle-mounted terminal collects voice instructions and obtains that the service type corresponding to "Where is the nearest gas station" is navigation. Then it is determined that the predicted target service type is the same as the service type expressed by the user through voice, and the vehicle-mounted terminal calls and navigation applications To query the address of the gas station, the voice "gas station address is in X area Y road" is played. In addition, if the content said by the user in step 2 has nothing to do with navigation, the vehicle-mounted terminal may not respond to the content said by the user.
  • the on-board terminal can activate the wake-up-free voice interaction function for the two types of services, gas station or navigation, thereby eliminating the need for users to frequently speak wake-up words.
  • this scenario includes the following steps 1 to 5:
  • Step 1 When the mobile phone receives the call request from the calling party, the operating system of the mobile phone pushes the incoming call notification.
  • Step 2 The user says "Hello, Xiaohua”.
  • Step 3 The terminal collects the voice command and determines that the voice command contains "Hello, Xiaohua", then the mobile phone is awakened and the voice "Are there" is played.
  • Step 4. The user says “Help me answer the call”.
  • Step 5 The mobile phone collects the voice command and confirms that the voice command contains "Help me answer the call", then the mobile phone answers the call.
  • this scenario may include the following steps one to three:
  • Step 1 When the mobile phone receives the call request from the calling party, the operating system of the mobile phone pushes the notification of the incoming call, and the mobile phone detects the notification of the incoming call. According to the notification of the incoming call, the mapping relationship is queried, and the target service type obtained is communication, thus predicting that the user has The intention of voice interaction for the business type of communication.
  • Step 2 The user says “Help me answer the call”.
  • Step 3 The mobile phone collects the voice command, and obtains the semantic information "answer the call” corresponding to the semantic information "answer the call” according to the semantic information "answer the call” as the communication type, and determine the predicted target business type and the user's pass If the voice service type is the same, the mobile phone will answer the call. In addition, if the content said by the user in step 3 has nothing to do with the communication, the vehicle-mounted terminal may not respond to the content said by the user.
  • the mobile phone if it receives an incoming call, it can activate the mobile phone's voice interaction function without wake-up words for the service type of communication, thereby eliminating the need for users to frequently speak wake-up words.
  • Scene 7 The car drives to an area with poor air quality.
  • this scenario includes the following steps 1 to 4:
  • Step 1 The user says "Hello, Xiaohua”.
  • Step 2 The terminal collects the voice command and determines that the voice command contains "Hello, Xiaohua", then the mobile phone is awakened and the voice "Are there" is played, thereby responding to the user's voice command.
  • Step 3 The user says “Turn on the air purifier”.
  • Step 4 The vehicle-mounted terminal collects the voice command and determines that the voice command includes "turn on the air purifier", then the vehicle-mounted terminal sends a signal to the car's controller, and the controller controls the air purifier to turn on.
  • this scenario may include the following steps one to three:
  • Step 1 The sensor of the air purifier detects the dust concentration and sends the detected dust concentration to the vehicle terminal.
  • the vehicle terminal determines that the dust concentration exceeds the threshold, and then queries the mapping relationship according to the dust concentration, and the target service type is air purifier , Thus predicting that the user has the intention of voice interaction for the air purifier type of business.
  • Step 2 The user says “Turn on the air purifier”.
  • Step 3 The vehicle-mounted terminal collects the voice command, obtains that the service type corresponding to "turn on the air purifier" is the air purifier, and determines that the predicted target service type is the same as the service type expressed by the user through voice, and the vehicle-mounted terminal reports to the car controller Send a signal and the controller controls the air purifier to turn on.
  • the vehicle-mounted terminal may not respond to the content said by the user.
  • the on-board terminal can activate the wake-up-free voice interaction function for the service type of air purifier, thereby eliminating the need for users to frequently speak wake-up words.
  • this scenario includes the following steps 1 to 4:
  • Step 1 The user says "Hello, Xiaohua”.
  • Step 2 The vehicle-mounted terminal collects voice commands and determines that the voice command contains "Hello, Xiaohua", and the vehicle-mounted terminal is awakened and plays the voice "Are you there", thereby responding to the user's voice command.
  • Step 3 The user says “Stop putting down the sun shade.”
  • Step 4 The vehicle-mounted terminal collects the voice command and determines that the voice command contains "Put down the sun shade".
  • the vehicle-mounted terminal sends a stop signal to the car's controller.
  • the stop signal is used to instruct to stop opening the sun shade.
  • the drive circuit that controls the sun shade stops and continues to open the sun shade.
  • this scenario may include the following steps one to three:
  • Step 1 The sun shade sends the current status to the vehicle-mounted terminal.
  • the vehicle-mounted terminal determines that the opening degree of the sun shade satisfies the condition according to the state of the sun shade, and then queries the mapping relationship according to the sun shade to obtain the target service type "sun shade". Therefore, it is predicted that the user has the intention of voice interaction for the "sun shade" type of business.
  • Step 2 The user says “Stop putting down the sun shade.”
  • Step 3 The vehicle-mounted terminal collects the voice command, and according to the semantic information "Stop putting down the sun shade” corresponding to the voice instruction, the semantic information "Stop putting down the sun shade” is obtained.
  • the service type corresponding to the sun shade then the vehicle terminal sends a stop to the car controller Signal, stop signal is used to instruct to stop opening the sun shade.
  • stop signal is used to instruct to stop opening the sun shade.
  • the controller receives the stop signal, the drive circuit that controls the sun shade stops and continues to open the sun shade.
  • the vehicle-mounted terminal may not respond to the content said by the user.
  • the on-board terminal can activate the wake-up word-free voice interaction function for the business type of sun shade, thereby eliminating the need for users to frequently speak wake-up words step.
  • Fig. 4 is a flowchart of a voice interaction method provided by an embodiment of the present application. This embodiment is described by taking the execution subject as a terminal as an example. Referring to Fig. 4, the method includes:
  • the terminal determines that a target event has been detected.
  • the target event is an event that can trigger voice interaction. If the target event occurs, the user will have a certain probability of generating the intention of voice interaction, and has the need to wake up the terminal for voice interaction. In view of this, the terminal will detect the target event, so that when it is determined that the target event is detected, the target event and the voice command are combined to determine whether to activate the voice interaction function.
  • the target event may have one or more modalities, and the modalities refer to the form or dimension of the target event.
  • the modality of the target event can be the user's operation
  • the modality of the target event can also be a notification message
  • the modality of the target event can also be that the environmental parameters meet the first condition
  • the modality of the target event can also be the current business The progress of the target event satisfies the second condition.
  • the modal of the target event can also be replaced with other modalities according to business requirements. This embodiment does not limit the modal of the target event.
  • the user's operation may not be limited to one or more of the operation of the physical button, the operation of the interface, the voice command, and the browsing behavior.
  • the physical button may be a button on the terminal body, or a button on another device that has established a communication connection with the terminal.
  • the terminal is a vehicle-mounted terminal
  • the physical button can be a button on any device mounted on the car.
  • the physical button can be an air-conditioning switch, a radio switch, and so on. If the user operates the physical button, the physical button can send a signal to the terminal, and the terminal determines that the operation on the physical button is detected.
  • the interface can be the system interface of the terminal or the interface of an application program.
  • the terminal determines that the operation on the interface is detected.
  • Voice commands can be collected through a microphone.
  • the browsing behavior may be the behavior of the user browsing the interface of the terminal. If the user performs the browsing behavior, the terminal may capture the user's line of sight through a camera, thereby determining that the browsing behavior is detected.
  • the operation may be a pressing operation, a clicking operation or a sliding operation, etc. The specific type of operation is not limited in this embodiment.
  • the notification message may be a message pushed by the operating system or an application program.
  • the notification message may be one or more of incoming call notification, short message, instant messaging message, alarm message, and resource recommendation message.
  • the alarm message may indicate that the terminal has malfunctioned, for example, it may indicate that the power is lower than 10% of the total power, insufficient memory, or the network is attacked; the alert message may also indicate that other devices that have established a communication connection with the terminal have failed.
  • an alarm message from a vehicle-mounted terminal can indicate that the motor of the car is malfunctioning;
  • a resource recommendation message can indicate a resource recommended to the user, for example, it can be news recommended by news applications, goods or services recommended by e-commerce applications, or game applications recommended Virtual items, etc.
  • Environmental parameters can be but not limited to one or more of noise, temperature, humidity, brightness, dust concentration, and oil volume.
  • the first condition may not be limited to that the environmental parameter exceeds the parameter threshold or the change amount of the environmental parameter exceeds the change threshold.
  • the sensor may collect the environmental parameter in real time or periodically, and send the collected environmental parameter to the terminal.
  • a temperature sensor can collect temperature and send temperature to the terminal;
  • a humidity sensor can collect humidity and send humidity to a terminal;
  • a dust sensor can collect dust concentration and send it to the terminal;
  • a brightness sensor can collect brightness and send brightness to a terminal;
  • a microphone can Collect the noise intensity and send the noise intensity to the terminal.
  • the fuel level sensor can collect the current remaining fuel level of the vehicle and send the fuel level to the terminal.
  • the terminal may receive the environmental parameter from the sensor; the terminal may determine whether the environmental parameter exceeds the parameter threshold, and if the environmental parameter exceeds the parameter threshold, it is determined that the detected environmental parameter satisfies the first condition.
  • the terminal can obtain the change amount of the environmental parameter according to the currently obtained environmental parameter and the historically obtained environmental parameter, and determine whether the change amount of the environmental parameter exceeds the change amount threshold. If the change amount of the environmental parameter exceeds the change amount threshold, it indicates the environment If a change occurs, it is determined that the detected environmental parameter meets the first condition.
  • the current service may be the service currently performed by the terminal or the service currently performed by other devices that have established a communication connection with the terminal.
  • the terminal is a vehicle-mounted terminal
  • the vehicle-mounted terminal can establish a communication connection with the air conditioner, sunshade, and wiper on the vehicle through the vehicle controller
  • the current service can be the navigation service or music service currently performed by the vehicle-mounted terminal, or it can be Air conditioner temperature adjustment business, windshield wiper rotation business, sun shade lowering business.
  • the second condition may not be limited to a change in the progress of the business.
  • the progress of the business may exceed the threshold or the amount of change in the progress of the business exceeds the threshold of change.
  • the second condition may be that the business is about to end and the business is executed. Half wait.
  • the current business progress meeting the second condition can be that the air conditioner starts to perform temperature adjustment services, such as the air conditioner starts to set the temperature, the air conditioner starts to increase the air volume, etc.; the current business progress meets the second condition, it can also be the air conditioner
  • the progress of the temperature adjustment service performed changes, for example, the temperature sensor of an air conditioner detects a temperature change.
  • the terminal can obtain the progress of the current business and determine whether the progress of the current business exceeds the threshold, and if the progress of the current business exceeds the threshold, determine that the progress of the current business meets the second condition; Alternatively, the terminal can obtain the change amount of the current business progress according to the current progress of the current business and the historical progress of the current business, and judge whether the change amount exceeds the change amount threshold. If the change amount of the current business progress exceeds the change amount threshold, it indicates the current If the business changes, it is determined that the current business progress meets the second condition.
  • the amount of change and the threshold value of the amount of change may be expressed by the percentage of change, or may be expressed by the time of change, of course, it may also be expressed by data of other dimensions, which is not limited in this embodiment.
  • the target event is not limited to this. It should be understood that the modality of the target event can be expanded according to the actual service of the terminal, but any event that can trigger a voice interaction can be provided as a target event, and this embodiment does not limit the target event.
  • the terminal queries the mapping relationship according to the target event to obtain a service type set.
  • the service type set includes one or more target service types, and each target service type is a service type corresponding to the voice interaction intention.
  • the terminal can predict the user's voice interaction intention based on the target event, and obtain a set of service types.
  • the target service type can be the type of service performed by the terminal, or the type of service performed by other devices that have established a communication connection with the terminal.
  • the target service type can be the air conditioner on the vehicle.
  • Type of business performed by equipment such as, lights, etc.
  • the target service type may be one or more of navigation, schedule consultation, air conditioning, radio, music, car control, mileage inquiry, question and answer consultation, games, system settings, vehicle control, charging, maintenance, and communication.
  • the mapping relationship may include one or more events and one or more business types.
  • the mapping relationship may indicate the corresponding relationship between the event and the business type.
  • Each event in the mapping relationship may correspond to one or more business types.
  • the event in the mapping relationship can be the first entry
  • the service type corresponding to the event can be the second entry
  • the positions of the first entry and the second entry correspond to each other.
  • the first entry and the second entry can be Located in the same row.
  • the mapping relationship can be shown in Table 1 below.
  • the terminal can use the target event as an index, and in the mapping relationship, the service type set can be obtained by querying. For example, if the detected target event is the operation of the master switch, look up Table 1, and the service type set obtained is (navigation, music, schedule consultation).
  • the mapping relationship may specifically include the first mapping relationship between the user's operation and the service type corresponding to the operation, the second mapping relationship between the notification message and message viewing or message processing, and the relationship between the environmental parameter and the adjustment environmental parameter.
  • the first mapping relationship may include one or more operations and service types corresponding to the one or more operations, and any operation may correspond to one or more service types.
  • the first mapping relationship may be as shown in Table 2 below.
  • the first mapping relationship may be constructed based on operation continuity rules.
  • the operation continuity rule refers to: if operation A and operation B are continuous operations, then if the user performs operation A, it can be predicted that the user has the intention to perform operation B. Continuous operation means that after the user performs operation A, operation B is performed immediately.
  • operation A (the user's current operation) is called the first operation
  • operation B (the continuous operation associated with the first operation) is called the target second operation
  • the target second operation is the execution of the first operation.
  • the target second operation is the predicted operation
  • the target second operation may or may not be performed
  • the target second operation may be the first operation after the first operation.
  • the first mapping relationship may include a mapping relationship between the first operation and one or more business types, each business type in the first mapping relationship is a business type corresponding to the target second operation, and one or more target second operations
  • the operation is a continuous operation associated with the first operation. For example, referring to Table 2, turning on the master switch (first operation) and navigating to the destination (target second operation) are continuous operations, and turning on the master switch (first operation) and clicking the song play button (target second operation) ) Is also a continuous operation, and turning on the master switch (first operation) and viewing today’s schedule (target second operation) are also continuous operations.
  • the business type of navigating to the destination is navigation, click on the song to play
  • the business type corresponding to the button operation is music
  • the business type of viewing today’s schedule is schedule consultation. Therefore, when constructing the first mapping relationship, the operation of the master switch can be the first operation to navigate, music, and As the business type corresponding to the target second operation, the schedule consultation will write the operation, navigation, music and schedule consultation of the master switch into the first mapping relationship.
  • opening the navigation interface (first operation) and entering the navigation destination on the navigation interface (target second operation) are continuous operations, and the operation corresponding to the operation of entering the navigation destination is navigation.
  • the operation of the master switch can be used as the first operation, and navigation is the target.
  • the second operation corresponds to the business type. Then the mapping relationship between the navigation interface and the navigation will be opened and stored in the first mapping relationship.
  • the terminal can predict the navigation as the target service type.
  • the second mapping relationship includes one or more notification messages and message viewing or message processing.
  • Message viewing can include viewing short messages, viewing instant messaging messages of instant messaging applications, and viewing push messages of resource recommendation applications.
  • Message processing can include answering calls and messages. Reply, trouble shooting and information inquiry.
  • Table 3 the second mapping relationship may be as shown in Table 3 below.
  • the second mapping relationship may be constructed based on the user's requirements for viewing notification messages or processing notification messages. Specifically, if a notification message is received, it can be predicted that the user has the intention of viewing or processing the notification message. Therefore, the second mapping relationship may be a mapping relationship between notification messages and message viewing, or the second mapping relationship may be The mapping relationship between notification messages and message processing. For example, referring to Table 3 above, if an instant messaging application pushes an instant messaging message, it can be predicted that the user has the intention of viewing instant messaging messages, and the service type corresponding to viewing instant messaging messages can be instant messaging applications, so you can build a second In the mapping relationship, the instant messaging message and the identifier of the instant messaging application can be written into the second mapping relationship.
  • the third mapping relationship includes one or more environmental parameters and adjustment environmental parameters.
  • the third mapping relationship may be as shown in Table 4 below.
  • the third mapping relationship may be constructed based on the user's needs to respond to environmental changes. Specifically, considering that the environmental parameters will affect the user’s perception when the conditions are met, it can be predicted that the user has the intention to adjust the environmental parameters. Therefore, the third mapping relationship may include the relationship between the environmental parameters and the business types corresponding to the adjusted environmental parameters. The mapping relationship. For example, referring to Table 4 above, if the temperature change meets the threshold, it can be predicted that the user has the need to adjust the temperature, and the service type corresponding to the temperature adjustment is air conditioning. Therefore, when the third mapping relationship is constructed, the temperature change can be satisfied The mapping relationship between the threshold and the air conditioner is stored in the third mapping relationship.
  • the fourth mapping relationship may include one or more current services and service types of the current services. Schematically, the fourth mapping relationship may be as shown in Table 5 below.
  • the fourth mapping relationship may be constructed based on the user's response requirements. Specifically, considering that the current business progress will affect the user’s perception when the conditions are met, it can be predicted that the user will restart the current business, stop the current business, or adjust the current business. Therefore, the fourth mapping relationship can be the current business Mapping relationship with the business type of the current business.
  • the mapping relationship between the music about to end and the music can be stored in the fourth mapping relationship.
  • the process of establishing the mapping relationship may include the following implementation manner 1 to implementation manner 2:
  • Implementation mode 1 The terminal obtains the historical business executed in association with the historical target event according to the historical record, and writes the business type of the historical business and the historical target event into the mapping relationship.
  • the mapping relationship can be constructed according to the historical voice interaction process. Specifically, if the terminal detects a historical target event at a historical point in time, the user interacts with the terminal by voice so that the terminal executes a certain historical service in response to the user’s voice command, the terminal can establish the historical target event and the The mapping relationship between the service types of historical services, then after the subsequent terminal detects the target event, it can be awakened, and when the service type corresponding to the voice command is the same as the service type of the historical service, it can execute in response to the voice command business.
  • the historical record includes historical target events and historical services executed in association with the historical target events.
  • the historical services executed in association with the historical target events are the services executed after the historical target event is detected. It can be the first time after the historical target event is detected. Services performed by voice interaction. For example, if an operation triggered on the main switch is detected yesterday, and the service performed by the first voice interaction is to navigate to cell A, the history record can include the operation triggered on the main switch and the navigation to cell A. The operation triggered by the master switch and the navigation to cell A write the mapping relationship. Then, if the terminal currently detects an operation triggered on the master switch, it can query the mapping relationship according to the operation of the master switch, and the target service type in the service type set will include navigation.
  • the terminal may write the service type of the recently executed historical service into the mapping relationship.
  • the terminal can obtain the historical time period according to the current time point and the preset time period, and obtain the historical service executed in association with the historical target event in the historical time period according to the historical record, and the service type of the historical service and the historical target event, Write the mapping relationship.
  • the historical time period may be the last day, the last week, or the last month.
  • the end point of the historical time period may be the current time point, and the preset duration may be one day, one week, and so on. In this way, the timeliness of the mapping relationship can be guaranteed, and the mapping relationship can better reflect the user's recent behavior habits.
  • the terminal may write historical services executed at a high frequency into the mapping relationship.
  • the terminal can obtain the number of executions of each historical service executed in association with the target event according to the historical record; the terminal can select the historical service with the most execution times from a plurality of historical services, and the service type of the historical service with the most execution times and Historical target events are written into the mapping relationship.
  • the terminal may select historical services whose execution times exceed the threshold, and write the service types and historical target events corresponding to the historical services whose execution times exceed the threshold into the mapping relationship.
  • the user's voice interaction intention after the current target event will be highly likely to interact with the voice interaction generated after the historical target event in the past. If the intent is the same or similar, then the business that will be executed after the current target event occurs will have a high probability of being the same or similar to the business executed after the historical target event occurs. Therefore, the current voice can be predicted by combining historical records The target business type targeted by the interaction intention can improve the accuracy of the target business type.
  • Implementation mode 2 The terminal calls the machine learning model, inputs the sample target event into the machine learning model, outputs the business type, and writes the output business type and the sample target event into the mapping relationship.
  • the machine learning model is used to predict the type of business based on the event. For example, it can predict the type of business executed in association with the event based on the current event.
  • multiple sample events and multiple sample business types can be used for model training to obtain the machine learning model.
  • the sample event can be an event executed by the sample user’s terminal or the history of the terminal. Events recorded in the log.
  • the sample business type is the business type of the business executed in association with the sample event.
  • the machine learning model can be, but is not limited to, a neural network model.
  • the machine learning model can learn the mapping relationship between events and business types through a large number of samples in advance. Then, the machine learning model can accurately predict the target business targeted by the voice interaction intention based on the current target event. Type, thereby improving the accuracy of the target business type.
  • mapping relationship can be constructed by the terminal or other devices other than the terminal, and the other device sends the constructed mapping relationship to the terminal, and the terminal can receive the mapping relationship to obtain the mapping relationship.
  • other devices may not be limited to the voice interaction platform 200 shown in FIG. 1.
  • the terminal can also obtain the mapping relationship in other ways.
  • the mapping relationship can be published through a certain link address, and the terminal can access the link address and download the mapping relationship from the Internet. This embodiment does not show how the terminal obtains the mapping relationship. Make specific restrictions.
  • step 402 may not be limited to one or more of the following cases (1) to (4):
  • the terminal queries the mapping relationship according to the first operation to obtain the service type set.
  • the target service type included in the service type set is the service type corresponding to one or more target second operations, and the one or The multiple target second operations are continuous operations associated with the first operation.
  • the terminal may use the service type corresponding to the target second operation as the target service type.
  • one first operation may correspond to one or more target second operations. For example, if the user triggers a confirmation operation on the air conditioner button, generally speaking, the user will adjust the temperature immediately after the confirmation operation on the air conditioner button, then the confirmation operation on the air conditioner button is the first operation, and adjusting the temperature is the target second operation.
  • the service type corresponding to the temperature adjustment is air conditioner, so the terminal can obtain the air conditioner as the target service type; another example, if the user clicks on the music search option, generally speaking, the user clicks on the music search option and then fills in the song name. Clicking on the music search option is the first operation, and filling in the song name is the target second operation, and the service type corresponding to the song name is music, so the terminal can obtain music as the target service type; for another example, if the user clicks the fault display Options. Generally speaking, after the user clicks on the fault display option, the user will search for the fault solution or solve the fault according to the fault information viewed. Clicking on the fault display option is the first operation, and searching for the fault solution or solving the fault is the goal. Second operation, and the service type corresponding to the search for the solution to the fault or the solution to the fault is the fault, vehicle control or search, so the terminal can acquire the fault, vehicle control or search as the target service type.
  • the next operation will be executed continuously, so the intention of voice interaction for the business corresponding to the next operation will be generated.
  • the rule of maps the operation currently performed by the user to the service type corresponding to the next operation to be performed with a certain probability, so that when the user performs the operation, it can accurately predict which service type the user wants to voice Interaction, thus ensuring the accuracy of the target business type.
  • the terminal may query the first mapping relationship according to the first operation to obtain the service type set.
  • Case (2) The terminal queries the mapping relationship to obtain the service type set, and the target service type included in the service type set is the message viewing or message processing corresponding to the notification message.
  • the message view may be to view the notification message through an application that pushes the notification message.
  • the notification message is an instant messaging message
  • the message view may be through an instant messaging application to view the instant messaging message.
  • the notification message is For news recommendations, the news can be viewed through the news application to view the news; or, the news can be viewed by playing the notification message, displaying the notification message on the screen, or projecting the notification message, etc.; the message processing can be performed for the notification message Search, reply to notification messages, and handle failures corresponding to notification messages.
  • the terminal receives a notification message
  • the user will have the need to view the message or process the message, so the voice interaction intention to view or process the message will be generated.
  • the user s view or processing of the message is fully considered
  • the message demand will map the target event of receiving a notification message to two target service types: message viewing or message processing, so that when the notification message is received, the user can accurately predict which service the user wants to target Type for voice interaction, thus ensuring the accuracy of the target service type.
  • case (2) may include one or more of the following cases (2.1) to (2.3).
  • message viewing can be to convert short messages or instant messaging messages from text to voice, and to play voice short messages or instant messaging messages.
  • the message reply can be based on the short message or instant messaging message, obtaining the reply information corresponding to the short message or instant messaging message, and sending the reply information to the sender of the short message or instant messaging message; or, receiving the reply information entered by the user and sending the reply information Send to the sender of the SMS or IM message.
  • Fault handling can be output fault handling plan, repair and maintenance, etc. For example, if the warning message is a low battery message, the fault handling can be mileage inquiry or charging station. If the alarm message is a motor fault message, the fault handling can be Q&A consultation, motor maintenance, etc. Information query can be to query the solution of the fault, query the source of the fault, etc.
  • the corresponding target service type is predicted for each notification message, so that it can support various application scenarios in which the notification message is received, and expand the application range.
  • the terminal may query the second mapping relationship according to the notification message to obtain one or more target service types.
  • Adjusting environmental parameters can include reducing dust concentration through air purifiers, increasing humidity through humidifiers, adjusting temperature through air conditioners or car windows, adjusting light intensity through sunshades or car windows, and adjusting rainfall through wipers.
  • the environment will affect the user's perception, and the user will have the need to cope with the environment. For example, if a certain environmental parameter changes, the user will have the need to adjust this environmental parameter, so a voice for adjusting the environmental parameter will be generated In this way, the user’s need to respond to the environment is fully considered, and the target event that the environmental parameter meets the first condition is mapped to the target business type of adjusting the environmental parameter, so that the environmental parameter meets the first condition. Under certain conditions, it accurately predicts which service type the user wants to perform voice interaction with, thus ensuring the accuracy of the target service type.
  • the terminal can query the third mapping relationship according to the environmental parameters to obtain one or more target service types.
  • the service type of the current service can be, but not limited to, re-execute the current service, stop performing the current service, or adjust the current service. For example, if the current service is playing music, the current service type can be playing other music or re-playing. Music, stop playing music, etc.
  • the progress of the current business will affect the user’s perception, and the user will have the need to cope with the current business. For example, if the current business is about to end, the user usually wants to re-execute the current business, stop executing the current business, or respond to the current business. The business is adjusted. In this way, the user’s needs for responding to business changes are fully considered, and the target event that the current business progress meets the second condition is mapped to the business type of the current business, so that the current business progress When the second condition is met, it can accurately predict which service type the user wants to perform voice interaction for, thus ensuring the accuracy of the target service type.
  • step 402 may be replaced with: the terminal obtains the historical service executed in association with the historical target event according to the historical record, and obtains the service type corresponding to the historical service as the target service type.
  • the target business type can be obtained by querying historical records without establishing a mapping relationship based on historical records.
  • step 402 can be replaced with: the terminal invokes a machine learning model, inputs the target event into the machine learning model, and outputs the one or more target service types, and the machine learning model is used to predict the target service type according to the target event. That is, the target business type can be obtained through the machine learning model, without the need to establish a mapping relationship based on the machine learning model.
  • the mapping relationship may also include the probability of each target service type.
  • Step 402 may be replaced with: the terminal queries the mapping relationship according to the target event to obtain the service type set and each target service type in the service type set The corresponding probability.
  • the probability indicates the probability that the business corresponding to the target business type will be executed.
  • the greater the probability the greater the possibility that the service corresponding to the target service type will be executed after the corresponding event is detected. For example, if there is a mapping relationship between the target event i, the target business type j, and the target business type j corresponding to the probability 1, the target business type k, and the target business type k corresponding to the probability 2 there is a mapping relationship, then the mapping relationship can indicate that if it is determined to detect When the target event i occurs, it is predicted that the service of the target service type j or the target service type k will be executed, the probability of the service of the target service type j being executed is probability 1, and the probability of the service of the target service type k being executed is probability 2.
  • i is the identifier of the target event
  • j and k are the identifiers of the target business type.
  • mapping relationship may be as shown in Table 6 below, where "/" in Table 6 means none.
  • the set of service types can be obtained as (navigation, music, schedule query), where the probability corresponding to navigation is 0.6, the probability corresponding to music is 0.7, and the probability corresponding to schedule query is 0.4.
  • mapping relationship shown in Table 6 can be provided as a multi-modal wake-up model.
  • the input parameters of the multi-modal wake-up model include target events, and the output parameters of the multi-modal wake-up model include service type set and probability
  • the multi-modal wake-up model can be used to predict the service type set according to the detected target event.
  • the user can run the multi-modal wake-up model on the terminal or sell the multi-modal wake-up model to a third party.
  • the terminal filters out target service types whose probability does not meet the probability threshold from the service type set.
  • the terminal can compare the probability corresponding to the target service type with the probability threshold. If the probability corresponding to the target service type meets the probability threshold, the terminal will screen out the target service type, then If the service type of the first service corresponding to the subsequently collected voice command is the target service type, the first service will be executed; if the probability corresponding to the target service type does not meet the probability threshold, the terminal will filter out the target service type, then The business of the target business type will not be executed in the future.
  • the same probability threshold can be preset for each target service type, and the probability threshold is pre-stored in the terminal, and the terminal can compare each target service type with the same probability threshold.
  • a corresponding probability threshold can be set for each target business type, and the probability threshold corresponding to each target business type can be written into the mapping relationship, and the terminal can query the mapping relationship to obtain each target business The probability threshold corresponding to the type is compared with the corresponding probability threshold for each target service type.
  • the probability thresholds corresponding to different service types may be the same or different, which is not limited in this embodiment.
  • the mapping relationship may include Table 7 below. If the service type set is (navigation, music, schedule consultation), according to Table 6 above, the probability corresponding to navigation is 0.6, the probability corresponding to music is 0.7, and the corresponding probability to schedule consultation is The probability is 0.4. According to Table 7, the probability threshold corresponding to navigation is 0.5, the probability threshold corresponding to music is 0.5, and the probability threshold corresponding to schedule consultation is 0.5. For navigation, the probability 0.6 is greater than the probability threshold 0.5. For music, the probability 0.7 is greater than the probability threshold 0.5. For schedule consultation, the probability 0.4 is less than the probability threshold 0.5. Therefore, navigation and music are filtered out. Drop the schedule consultation.
  • Target business type Probability threshold navigation 0.5 music 0.5 Radio station 0.5 communication 0.7 SMS 0.7 WeChat 0.7 Schedule consultation 0.5 news 0.4 Q&A 0.4 air conditioning 0.4 Car control 0.8 system 0.7 Maintenance 0.5
  • the probability of the target service type does not meet the probability threshold, it indicates that the target service type is less likely to be the service type targeted by the user’s voice interaction intention. If the target service type is subsequently processed, the probability of false wake-up will be higher. If you wake up by mistake, it will cause interference to the user and cause excessive load on the terminal. Therefore, by filtering out the target service type, the subsequent voice commands of the service whose semantic information is the target service type will not be responded to. Reduce the probability of false wakeup, thereby avoiding the interference to the user and the load on the terminal due to false wakeup.
  • step 403 is an optional step, not a mandatory step.
  • the following steps are executed according to all the obtained target service types.
  • the terminal collects voice instructions.
  • the terminal may start monitoring when it is determined that the target event has been detected, and end monitoring when the monitoring time has elapsed.
  • the terminal can collect the voice command through the microphone.
  • the time period from the start of monitoring to the end of monitoring can be referred to as the receiving window, and the monitoring time can be set according to experiment, experience, or demand, and can be stored in the terminal in advance.
  • the same monitoring duration can be set for each service type, or different monitoring durations can be set for different service types, and the mapping relationship between the service type and the monitoring duration is stored in the terminal, which is not limited in this embodiment.
  • the terminal obtains the first service corresponding to the semantic information according to the semantic information corresponding to the voice command.
  • the terminal may perform automatic speech recognition (ASR) on the voice command to obtain text information; perform semantic recognition on the text information to obtain semantic information; and obtain the first service by querying according to the semantic information. For example, if the semantic information is "Xiaohua, help plan the route to Building YY in XX Community", the first service is “Navigate to Building YY in XX Community”, and if the semantic information is "Xiaohua, help to put first ZZ" "Songs", the first business is "Play ZZ songs”.
  • ASR automatic speech recognition
  • the terminal executes the first service according to the voice instruction.
  • the terminal can compare the service type of the first service with each target service type in the service type set. If the service type of the first service is the same as any target service type, it indicates that the service type expressed by the user’s voice is within the predicted service type. Within the scope, if the terminal predicts the service type correctly, and the user does have the intention of voice interaction, the wake-up is successful, the terminal will activate the voice interaction function, and in response to the voice command, execute the first service according to the voice command, that is, perform voice The business expressed by the instruction.
  • the service type set is (navigation, music) and the first service is "Navigate to Building YY in XX Community"
  • the service type of the first service is navigation, and the service type of the first service is in the service type set If the target service type navigation is the same, the terminal will navigate to Building YY in XX community.
  • the terminal discards the voice command.
  • the service type set does not include the service type of the first service, it indicates that the service type expressed by the user's voice is outside the range of the predicted service type, the terminal's prediction of the service type is incorrect, and the user has no intention of voice interaction, and the terminal may not In response to voice commands, the voice commands are discarded, so as to avoid false wakeups caused by service processing based on the voice commands, and save the buffer space occupied by the voice commands.
  • the service type set is (navigation, music), and the first service is "Turn on the air conditioner"
  • the service type of the first service is air conditioning, and the service type of the first service is related to each target service type in the service type set If they are different, the terminal will not respond to voice commands, that is, the air conditioner will not be turned on.
  • the terminal can start timing when it detects the occurrence of the target event. If the recorded duration reaches the preset duration and the terminal does not receive a voice command, the terminal will exit the monitoring.
  • step 407 is an optional step, not a mandatory step.
  • the terminal updates the probability in the mapping relationship according to the semantic information corresponding to the voice command.
  • the probability can be dynamically adjusted according to the semantic information expressed by the user this time, so as to evaluate the predicted target business in a self-learning manner.
  • the correctness of the type through iteration to continuously correct the probability, so that the mapping relationship can be continuously optimized with the occurrence of the target event and the semantics expressed by the user, and gradually approach the user's personal behavior habits, ensuring that the mapping relationship is more accurate.
  • the update method may include one or more of the following methods (1) to (3).
  • the terminal will increase the probability of navigation.
  • the user If each time a target event X is detected, the user always requests to perform services of the target service type Y through voice, indicating that the target service type Y happens to be the service type for which the user has voice interaction intentions after the target event X occurs, then through this Optionally, the probability of the target service type Y will continue to increase. Therefore, when the target event is detected again later, the probability of the target service type Y will meet the probability threshold, so that the target service type Y will be screened out. Then if the voice command corresponds to The first service corresponding to the semantic information of is the service of the target service type Y, and the terminal will respond to the voice command to execute the service of the target service type Y.
  • the terminal can write the service type of the first service into the mapping relationship. Specifically, if the target event is not included in the mapping relationship, or the business type of the first business is not included in the mapping relationship, or the target event in the mapping relationship does not correspond to the business type of the first business, then the three In either case, the terminal may write the service type of the target event and the first service into the mapping relationship, so that the service type of the target event and the first service is added to the mapping relationship.
  • the mapping relationship can be queried to obtain the service type of the first service, and the service type of the first service can be obtained as the target service type.
  • the terminal detects event X during the historical operation process, the user expresses the intention of voice interaction with service type Y through voice, and by writing event X and service type Y into the mapping relationship, the mapping relationship will be new Increasing event X and service type Y, then, on the one hand, with the execution of the voice interaction process, the correlation between the event and the service type can be mined to supplement and improve the mapping relationship.
  • the terminal can add new events and new service types to the mapping relationship to improve the scalability and timeliness of the mapping relationship.
  • the probability corresponding to the service type of the first service may be generated, and the generated probability may be written into the mapping relationship.
  • it is also possible to use the default probability as the probability corresponding to the service type of the first service write the service type and default probability of the first service to the mapping relationship, and subsequently adjust the default probability by performing the process shown in step 408.
  • the terminal will reduce the probability of navigation and music correspondence.
  • the target event X corresponds to the target service type Y
  • the user does not request to execute the service of the target service type Y through voice, indicating that the target service type Y is not the target event X
  • the user has The service type of the voice interaction intention
  • the probability of the target service type Y will continue to decrease. Therefore, when the target event X is subsequently detected again, the probability of the target service type Y will not meet the probability threshold, so The target service type Y will be filtered out, and the terminal will not process the service of the target service type Y, thereby avoiding false wake-up.
  • the terminal will increase the probability of navigation.
  • the target event X corresponds to the target service type Y
  • the user speaks a wake-up word, indicating that the target service type Y happens to be the service type for which the user has voice interaction intentions after the target event X occurs.
  • the probability of the target business type Y will continue to increase. Therefore, when the target event is detected again later, the probability of the target business type Y will meet the probability threshold, so that the target business type Y will be screened out, then If the voice command expresses the semantic information of the target service type Y, the terminal will process the service in response to the voice command.
  • step 408 is an optional step, not a mandatory step.
  • This embodiment provides a method for triggering voice interaction without wake-up words.
  • the target event that can trigger voice interaction predict the set of service types for which the user has voice interaction intentions. If the service type of the first service expressed by the voice command is predicted If the target business type is listed, the first business will be executed.
  • the target event covers multiple modalities, and any target event of any modal can trigger the voice interaction function of the corresponding service type, so that in a variety of application scenarios, it can support the wake-up function without wake-up words, which expands the scope of application .
  • FIG. 5 is a software architecture diagram of a voice interaction system provided by an embodiment of the present application.
  • the system includes the following functional modules, and each module may be a software module.
  • Voice activity detection (VAD) module or front-end speech (front-end speech) module used to collect audio signals, perform noise reduction and enhancement processing on the collected audio signals, and detect whether the audio signals are voice commands It is also a non-voice command. If the audio signal is a voice command, the voice command is input to the ASR module, where the non-voice command can be a noise signal, a music signal, etc.
  • ASR Automatic speech recognition module: used to receive voice commands from the VAD module or front-end voice module, convert the voice commands into text information, and input the text information into the dialogue understanding module or dialogue management module.
  • Multi-modal detection module used to detect the target event, if the target event is detected, the target event is input into the user intention prediction module.
  • the multi-modal detection module can receive notification messages pushed by the operating system or application programs, such as short messages, incoming calls, application recommendation messages, and alarm messages; or, it can detect one or more modal operations: Operation of physical buttons or interface, voice commands; or, used to detect environmental changes or business changes, such as: temperature drop, excessive air pollution, music is about to end, etc.
  • User intention prediction module used to receive target events from the multi-modal detection module, consider the user's operation continuity rules, user requirements for viewing, processing or response, the impact of environment or business on user perception, predict the user's voice interaction intention, and output The set of business types and the probability corresponding to each target business type in the set of business types.
  • SLU Spoken language understanding
  • DM dialogue management
  • Historical data learning Based on the user's historical operation data, iteratively update the data in the user intention prediction module.
  • RG Response generator
  • TTS text to speech
  • the vehicle-mounted terminal can be implemented by a combination of hardware and software.
  • the structure of the vehicle-mounted terminal can be as shown in Figure 6, including:
  • CPU Used to access each functional module on the memory or other storage, run each functional module, and can also access the storage and audio manager through the data bus (D-BUS).
  • D-BUS data bus
  • the processor can access various cloud services and cloud service management modules through a network interface.
  • the processor can also access the controller area network (English: Controller Area Network, abbreviated as: CAN) bus through the gateway, read data of the vehicle and various devices carried by the vehicle, and control the vehicle and various devices carried by the vehicle.
  • controller area network Terms: Controller Area Network, abbreviated as: CAN
  • the storage includes memory and disk storage, and the stored content includes the functional modules shown in Figure 5.
  • the audio manager is used to manage car speakers, microphone arrays or other audio devices.
  • the voice interaction method of the embodiment of the present application is introduced above, and the voice interaction device provided by the embodiment of the present application is introduced below. It should be understood that the voice interaction device has any function of the terminal in the voice interaction method described above.
  • FIG. 7 is a schematic structural diagram of a voice interaction device provided by an embodiment of the present application. As shown in FIG. 7, the device includes:
  • the determining module 701 is used to perform step 401; the query module 702 is used to perform step 402; the acquisition module 703 is used to perform step 404; the acquisition module 704 is used to perform step 405; the processing module 705 is used to perform step 406 .
  • the determining module 701 is configured to determine that the first operation of the user is detected; the query module 702 is configured to execute the case (1) in step 402.
  • the determining module 701 is configured to receive notification messages from the operating system or an application program; the query module 702 is configured to execute the case (2) in step 402.
  • the determining module 701 is configured to determine that the current environmental parameter satisfies the first condition; the query module 702 is configured to execute the case (3) in step 402.
  • the determining module 701 is configured to determine that the progress of the current service meets the second condition; the query module 702 is configured to perform the case (4) in step 402.
  • the device further includes: a writing module, configured to write the first service into the mapping relationship if the service type of the first service is different from each target service type in the service type set Business type.
  • a writing module configured to write the first service into the mapping relationship if the service type of the first service is different from each target service type in the service type set Business type.
  • the query module 702 is further configured to query the mapping relationship according to the target event to obtain the service type set and the probability corresponding to each target service type in the service type set;
  • the device also includes: a filtering module for performing step 408.
  • the device further includes: an update module for performing step 408.
  • the update module is specifically configured to execute one or more of the methods (1) to (3) in step 408.
  • the device further includes: a discarding module for performing step 407.
  • the voice interaction device provided in the above embodiment only uses the division of the above functional modules for example during voice interaction.
  • the above functions can be allocated by different functional modules according to needs, namely The internal structure of the terminal is divided into different functional modules to complete all or part of the functions described above.
  • the voice interaction device provided in the foregoing embodiment and the voice interaction method embodiment belong to the same concept, and the specific implementation process is detailed in the method embodiment, which will not be repeated here.
  • a computer-readable storage medium such as a memory including instructions, which may be executed by a processor of a terminal to complete the voice interaction method in each of the foregoing embodiments.
  • the computer-readable storage medium may be non-transitory.
  • the computer-readable storage medium may be Read-Only Memory (Read-Only Memory, ROM for short), Random Access Memory (Random Access Memory, RAM for short), or Compact Disc Read-Only Memory, ROM for short. : CD-ROM), magnetic tapes, floppy disks and optical data storage devices.
  • a computer program product includes: computer program code, when the computer program code is run by a terminal, the terminal causes the terminal to execute the voice interaction method in each of the foregoing embodiments.
  • a chip including a processor, configured to call and execute instructions stored in the memory from a memory, so that a device installed with the chip executes the voice interaction method in each of the foregoing embodiments.
  • another chip including: an input interface, an output interface, a processor, and a memory.
  • the input interface, output interface, the processor and the memory are connected by an internal connection path, and the processor uses To execute the code in the memory, when the code is executed, the processor is used to execute the voice interaction method in each of the foregoing embodiments.
  • the computer program product includes one or more computer program instructions.
  • the computer may be a general-purpose computer, a dedicated computer, a computer network, or other programmable devices.
  • the computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium.
  • the computer program instructions can be passed from a website, computer, server, or data center.
  • the computer-readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server or data center integrated with one or more available media.
  • the usable medium may be a magnetic medium (for example, a floppy disk, a hard disk, and a magnetic tape), an optical medium (for example, a digital video disc (DVD), or a semiconductor medium (for example, a solid state hard disk).
  • multiple in this application means two or more than two, for example, multiple data packets refer to two or more data packets.
  • the program can be stored in a computer-readable storage medium.
  • the storage medium can be read-only memory, magnetic disk or optical disk, etc.

Landscapes

  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Computational Linguistics (AREA)
  • Acoustics & Sound (AREA)
  • Theoretical Computer Science (AREA)
  • Artificial Intelligence (AREA)
  • General Physics & Mathematics (AREA)
  • General Engineering & Computer Science (AREA)
  • General Health & Medical Sciences (AREA)
  • Telephone Function (AREA)
  • User Interface Of Digital Computer (AREA)
  • Telephonic Communication Services (AREA)

Abstract

一种语音交互方法、装置、终端及存储介质，属于终端技术领域。一种免唤醒词触发语音交互的方法，根据能够触发语音交互的目标事件，来预测用户具有语音交互意图的业务类型集合，如果语音指令表达的第一业务的业务类型为业务类型集合中的目标业务类型，则执行第一业务。通过免去了语音交互过程中用户需要频繁说出唤醒词的繁琐操作，从而解决了频繁说出唤醒词造成语音交互效率过低的问题，让操作更加便捷，并且让语音交互的流程更加自然和拟人化，从而提高了语音交互的用户体验。

Description

语音交互方法、装置、终端及存储介质
本申请要求于2019年08月15日提交的申请号为201910755150.6、发明名称为“语音交互方法、装置、终端及存储介质”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本申请涉及终端技术领域，特别涉及一种语音交互方法、装置、终端及存储介质。
背景技术
随着终端技术的发展，越来越多的终端支持语音交互的功能，用户通过发出语音，即可与终端进行人机交互，从而解放了双手，提高了人机交互的效率。
目前，语音交互的流程通常包括：当用户想要与终端进行语音交互时，首先，用户说出唤醒词，终端会采集语音指令，判断语音指令是否包含唤醒词，如果语音指令包含唤醒词，终端会从待机状态切换为工作状态，也即是，终端被唤醒；之后，用户说出需要终端处理的业务，终端再次采集语音指令，根据语音指令，确定需要处理的业务，处理该业务。在一个示例性场景中，假设某车载终端的唤醒词为“你好，小华”，用户在开车的过程中，打开了电台，想要车载终端放首歌曲，则需要说出“你好，小华”，则终端被唤醒，用户说“帮忙放《东方音乐电台》的歌曲”，则车载终端会自动将电台调整至《东方音乐电台》，播放《东方音乐电台》的歌曲。
采用上述方法进行语音交互时，用户需要先说出唤醒词，才能唤醒终端处理业务，导致操作较为繁琐，效率低下。
发明内容
本申请实施例提供了一种语音交互方法、装置、终端及存储介质，能够解决相关技术中语音交互的操作繁琐、效率低下的技术问题。所述技术方案如下：
第一方面，提供了一种语音交互方法，所述方法包括：确定检测到目标事件发生，所述目标事件为能够触发语音交互的事件；根据所述目标事件，查询映射关系，得到业务类型集合，所述业务类型集合包括一个或多个目标业务类型；采集语音指令；根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务；如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，根据所述语音指令执行所述第一业务。
本实施例提供了一种免唤醒词触发语音交互的方法，根据能够触发语音交互的目标事件，来预测用户具有语音交互意图的业务类型集合，如果语音指令表达的第一业务的业务类型为业务类型集合中的目标业务类型，则执行第一业务。通过免去了语音交互过程中用户需要频繁说出唤醒词的繁琐操作，从而解决了频繁说出唤醒词造成语音交互效率过低的问题，让操作更加便捷，并且让语音交互的流程更加自然和拟人化，从而提高了语音交互的用户体验。
可选地，所述确定检测到目标事件发生，包括：确定检测到用户的第一操作；
所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述第一操作，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为与一个或多个目标第二操作相对应的业务类型，所述一个或多个目标第二操作为所述第一操作相关联的连续性操作。
通常来讲，如果用户执行了任一操作，会连续性地执行下一个操作，因此会产生针对下一个操作对应的业务进行语音交互的意图，而通过这种可选方式，充分利用了操作具有连续性的规律，会将用户当前执行的操作，映射为一定概率下将要执行的下一个操作对应的业务类型，从而可以在用户执行操作的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此保证了目标业务类型的准确性。
可选地，所述确定检测到目标事件发生，包括：从操作系统或应用程序接收通知消息；
所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：
根据所述通知消息，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为与所述通知消息对应的消息查看或消息处理。
通常来讲，如果终端接收到了通知消息，用户会具有查看通知消息或处理通知消息的需求，因此会产生对消息查看或消息处理的语音交互意图，而通过这种可选方式，充分考虑了用户的查看通知消息或处理通知消息的需求，会将接收到通知消息这一事件，映射为消息查看或消息处理这种业务类型，从而可以在接收到通知消息的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此保证了目标业务类型的准确性。
可选地，所述通知消息包括来电通知、短信、即时通信消息以及告警消息中的至少一项，所述根据所述通知消息，查询所述映射关系，得到所述业务类型集合，包括下述至少一项：
根据来电通知，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为接听来电；
根据短信或即时通信消息，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为消息查看或消息回复；
根据告警消息，查询映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为故障处理或信息查询。
可选地，所所述确定检测到目标事件发生，包括：确定当前的环境参数满足第一条件；
所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述环境参数，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为调节环境参数。
通常来讲，环境会影响到用户的感知，用户会具有应对环境的需求，比如说，如果某种环境参数发生变化，用户会具有调节这种环境参数的需求，因此会产生调节环境参数的语音交互意图，而通过这种可选方式，充分考虑了用户应对环境的需求，会将环境参数满足第一条件这一事件，映射为调节环境参数这种业务类型，从而可以在环境参数满足第一条件的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此保证了目标业务类型的准确性。
可选地，所述确定检测到目标事件发生，包括：确定当前业务的进度满足第二条件；
所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述当前业务，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为所述 当前业务的业务类型。
通常来讲，当前业务的进度会影响到用户的感知，用户会具有应对当前业务的需求，比如说如果当前业务将要结束时，用户通常会想要重新执行当前业务、停止执行当前业务或者对当前业务进行调整，而通过这种可选方式，充分考虑了用户应对业务变化的需求，会将当前业务的进度满足第二条件这一事件，映射为当前业务的业务类型，从而可以在当前业务的进度满足第二条件的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此保证了目标业务类型的准确性。
结合上述多种可选方式，目标事件能够涵盖多个模态，任意模态的目标事件均能够触发对应业务类型的语音交互功能，从而在多种应用场景下，均可以支持免唤醒词的唤醒功能，扩展了应用范围。
可选地，所述映射关系的建立过程包括：
根据历史记录，得到与历史目标事件关联执行的历史业务，将所述历史业务的业务类型以及所述历史目标事件，写入所述映射关系；
通过这种可选方式，由于同一用户的个人行为模式具有规律性，通常情况下，用户在当前发生目标事件后产生的语音交互意图，会在很大概率上与历史时间上发生历史目标事件后产生的语音交互意图相同或相近，那么，当前发生目标事件后将要执行的业务，也就会在很大概率上与历史发生目标事件将要执行的业务相同或相近，因此通过结合历史记录，来预测当前的语音交互意图针对的目标业务类型，可以提高目标业务类型的精确性。
可选地，所述映射关系的建立过程包括：调用机器学习模型，将样本目标事件输入所述机器学习模型，输出业务类型，将输出的业务类型以及所述样本目标事件写入所述映射关系，所述机器学习模型用于根据事件预测业务类型。
通过这种可选方式，能够预先通过大量的样本进行训练，得到机器学习模型，让机器学习模型学习出事件到业务类型之间的映射关系，因此可以通过机器学习模型，构建出较为准确的映射关系。
可选地，所述根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务之后，所述方法还包括：如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，向所述映射关系中，写入所述第一业务的业务类型。
通过这种可选方式，下一次检测到目标事件发生时，查询映射关系后，得到的业务类型集合会包括第一业务的业务类型，那么当用户通过语音指令表达第一业务的业务类型后，会响应语音指令来执行第一业务。如此，如果终端在历史运行过程中，每当检测到事件X，用户通过语音表达出对业务类型Y进行语音交互的意图，即可向映射关系中补入事件X与业务类型Y，那么，一方面，可以随着语音交互过程的执行，挖掘出事件和业务类型之间的关联性，补充和完善事件与语义信息对应的业务类型。另一方面，终端可以随着业务的扩展，向映射关系补入新增的事件和新增的业务类型，提高映射关系的可扩展性和时效性。
可选地，所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述目标事件，查询所述映射关系，得到所述业务类型集合以及所述业务类型集合中每个目标业务类型对应的概率，概率表示将要执行对应目标业务类型的业务的可能性大小；所述如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，根据所述语音指令执行所述第一业务之前，所述方法还包括：从所述业务类型集合中，过滤掉概率不满足概率阈值 的目标业务类型。
可选地，所述根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务之后，所述方法还包括：根据所述语音指令对应的语义信息，更新所述映射关系中的概率。
通过这种可选方式，每当目标事件发生时，可以根据用户本次表达的语义信息，对概率进行动态地调整，从而以自学习的方式，通过评估已预测的业务类型的正确性，通过迭代来不断修正概率，令映射关系中每个业务类型的概率可以随着目标事件的发生以及用户表达的语义，得到不断优化，逐渐更趋近于用户个人的行为习惯，保证映射关系更加精确。
可选地，所述根据所述语音指令对应的语义信息，更新所述映射关系中的概率，包括：
如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，增加所述映射关系中所述第一业务的业务类型对应的概率；
通过这种可选方式，如果目标事件X与目标业务类型Y对应，而每次检测到目标事件X时，用户总是通过语音要求执行目标业务类型Y的业务，表明目标业务类型Y恰好是发生目标事件X后，用户具有语音交互意图的业务类型，那么通过这种可选方式，目标业务类型Y的概率会不断增长，因此后续再次检测到该目标事件发生时，目标业务类型Y的概率会满足概率阈值，使得目标业务类型Y会被筛选出来，那么如果语音指令表达出目标业务类型Y的语义信息，终端会响应于语音指令处理业务。
可选地，所述根据所述语音指令对应的语义信息，更新所述映射关系中的概率，包括：
如果所述语义信息对应的业务类型与所述一个或多个目标业务类型中的每个目标业务类型不同，减少所述映射关系中与所述目标事件以及所述一个或多个目标业务类型对应的概率；
通过这种可选方式，如果目标事件X与目标业务类型Y对应，而每次检测到目标事件X时，用户都没有通过语音要求执行目标业务类型Y的业务，表明目标业务类型Y并不是发生目标事件X后，用户具有语音交互意图的业务类型，那么通过这种可选方式，则目标业务类型Y的概率会不断减少，因此后续再次检测到该目标事件X时，目标业务类型Y的概率会不满足概率阈值，使得目标业务类型Y会被过滤掉，则终端不会处理目标业务类型Y的业务，从而避免误唤醒。
可选地，所述根据所述语音指令对应的语义信息，更新所述映射关系中的概率，包括：如果所述语义信息包含唤醒词，增加所述映射关系中所述第一业务的业务类型对应的概率。
通过这种可选方式，如果目标事件X与目标业务类型Y对应，而每次检测到目标事件X时，用户都说出唤醒词，表明目标业务类型Y恰好是发生目标事件X后，用户具有语音交互意图的业务类型，那么通过这种可选方式，目标业务类型Y的概率会不断增长，因此后续再次检测到该目标事件时，目标业务类型Y的概率会满足概率阈值，使得目标业务类型Y会被筛选出来，那么如果语音指令表达出目标业务类型Y的语义信息，终端会响应于语音指令处理业务。
可选地，所述根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务之后，所述方法还包括：如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，丢弃所述语音指令。
通过这种可选方式，如果业务类型集合中不包括第一业务的业务类型，表明用户语音表达的业务类型处于预测的业务类型的范围之外，终端对业务类型预测不正确，用户并没有语音交互的意图，终端可以不响应语音指令，而是丢弃语音指令，从而避免根据语音指令进行 业务处理会造成的误唤醒，并且节省语音指令占据的缓存空间。
第二方面，提供了一种语音交互装置，所述语音交互装置具有实现上述第一方面或第一方面任一种可选方式中语音交互的功能。所述装置包括至少一个模块，所述至少一个模块用于实现上述第一方面或第一方面任一种可选方式所提供的语音交互方法。
第三方面，提供一种终端，所述终端包括一个或多个处理器和一个或多个存储器，所述一个或多个存储器中存储有至少一条指令，所述指令由所述一个或多个处理器加载并执行以实现上述第一方面或第一方面任一种可选方式所提供的语音交互方法。
第四方面，提供一种计算机可读存储介质，所述存储介质中存储有至少一条指令，所述指令由处理器加载并执行以实现上述第一方面或第一方面任一种可选方式所提供的语音交互方法。
第五方面，提供一种计算机程序产品，所述计算机程序产品包括：计算机程序代码，当所述计算机程序代码被终端运行时，使得所述终端执行上述第一方面或第一方面任一种可选方式所提供的语音交互方法。
第六方面，提供一种芯片，包括处理器，用于从存储器中调用并运行所述存储器中存储的指令，使得安装有所述芯片的终端执行上述第一方面或第一方面任一种可选方式所提供的语音交互方法。
第七方面，提供另一种芯片，包括：输入接口、输出接口、处理器和存储器，所述输入接口、输出接口、所述处理器以及所述存储器之间通过内部连接通路相连，所述处理器用于执行所述存储器中的代码，当所述代码被执行时，所述处理器用于执行上述第一方面或第一方面任一种可选方式所提供的语音交互方法。
附图说明
图1是本申请实施例提供的一种语音交互方法的实施环境的示意图；
图2是本申请实施例提供的一种终端100的结构示意图；
图3是本申请实施例提供的一种终端100的功能架构图；
图4是本申请实施例提供的一种语音交互方法的流程图；
图5是本申请实施例提供的一种语音交互系统的软件架构图；
图6是本申请实施例提供的一种车载终端的结构示意图；
图7是本申请实施例提供的一种语音交互装置的结构示意图。
具体实施方式
为使本申请的目的、技术方案和优点更加清楚，下面将结合附图对本申请实施方式作进一步地详细描述。
以下，对本申请的术语进行解释。
业务类型：为一类业务的统称，业务类型也可以称为业务领域。例如，业务类型可以包括消息查看、消息处理、调节环境参数、导航、日程咨询、空调、电台、音乐、车控、里程查询、问答咨询、游戏、系统设置、车辆控制、充电、维修保养、通讯等，该消息查看可以包括查看短信、查看即时通信应用的即时通信消息、查看资源推荐应用的推送消息，该消息处理可以包括接听来电、消息回复、故障处理、信息查询等，调节环境参数可以包括调节粉尘浓度、调节湿度、调节光照、调节噪声强度、调节温度等。
业务：为待执行的具体事务。例如，消息查看这一业务类型的业务可以是：查看用户A发来的会话消息X、查看群聊中最新发布的群公告Y、查看购物应用今天发布的优惠消息等，调节环境参数这一业务类型的业务可以是：通过空调将温度调节至25°，音乐这一业务类型的业务可以是：播放歌手B的最新歌曲Z，导航这一业务类型的业务可以是：导航至C市D区E路F小区，接听来电这一业务类型的业务可以是：接听主叫方ZZ的电话，消息回复这一业务类型的业务可以是：向联系人G回复短信“我在开车，稍后回复”，电台这一业务类型的业务可以是：打开“东方音乐电台”。
以下，对实施环境进行示例性描述。
图1是本申请实施例提供的一种语音交互方法的实施环境的示意图。该实施环境包括：终端100和语音交互平台200。
终端100通过无线网络或有线网络与语音交互平台200相连。终端100可以是智能手机、智能音箱、机器人、智能汽车、车载终端、家居设备、游戏主机、台式计算机、平板电脑、电子书阅读器、智能电视、MP3(moving picture experts group audio layer III，动态影像专家压缩标准音频层面3)播放器或MP4(moving picture experts group audio layer IV，动态影像专家压缩标准音频层面4)播放器和膝上型便携计算机中的至少一种。终端100安装和运行有支持语音交互的应用程序。该应用程序可以是语音助手、智能问答应用等。示例性的，终端100是用户使用的终端，终端100中运行的应用程序内登录有用户账号。
语音交互平台200包括一台服务器、多台服务器、云计算平台和虚拟化中心中的至少一种。语音交互平台200用于为支持语音交互的应用程序提供后台服务。例如，语音交互平台可以构建下述方法实施例提供的映射关系，将该映射关系发送给终端100，以便终端100基于映射关系进行语音交互。
可选地，语音交互平台200包括：语音交互服务器201和数据库202。语音交互服务器201用于提供语音交互有关的后台服务。语音交互服务器201可以是一台或多台。当语音交互服务器201是多台时，存在至少两台语音交互服务器201用于提供不同的服务，和/或，存在至少两台语音交互服务器201用于提供相同的服务，比如以负载均衡方式提供同一种服务，本申请实施例对此不加以限定。数据库202中可以用于存储映射关系。另外，数据库202可以存储有样本事件以及样本业务类型，以便语音交互服务器201从数据库202读取样本事件以及样本业务类型，根据样本事件以及样本业务类型，训练得到机器学习模型，通过该机器学习模型建立映射关系。
终端100可以泛指多个终端中的一个，本实施例仅以终端100来举例说明。本领域技术人员可以知晓，上述终端100的数量可以更多或更少。比如上述终端100可以仅为一个，或者上述终端100为几十个或几百个，或者更多数量，此时上述语音交互系统还包括其他终端。 本申请实施例对终端100的数量和设备类型不加以限定。
以下，对终端的硬件结构进行示例性描述。
图2是本申请实施例提供的一种终端100的结构示意图。
终端100可以包括处理器110，外部存储器接口120，内部存储器121，通用串行总线(universal serial bus，USB)接口130，充电管理模块140，电源管理模块141，电池142，天线1，天线2，移动通信模块150，无线通信模块160，音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，传感器模块180，按键190，马达191，指示器192，摄像头193，显示屏194，以及用户标识模块(subscriber identification module，SIM)卡接口195等。其中传感器模块180可以包括压力传感器180A，陀螺仪传感器180B，气压传感器180C，磁传感器180D，加速度传感器180E，距离传感器180F，接近光传感器180G，指纹传感器180H，温度传感器180J，触摸传感器180K，环境光传感器180L，骨传导传感器180M等。
可以理解的是，本申请实施例示意的结构并不构成对终端100的具体限定。在本申请另一些实施例中，终端100可以包括比图示更多或更少的部件，或者组合某些部件，或者拆分某些部件，或者不同的部件布置。图示的部件可以以硬件，软件或软件和硬件的组合实现。
处理器110可以包括一个或多个处理单元，例如：处理器110可以包括应用处理器(application processor，AP)，调制解调处理器，图形处理器(graphics processing unit，GPU)，图像信号处理器(image signal processor，ISP)，控制器，视频编解码器，数字信号处理器(digital signal processor，DSP)，基带处理器，和/或神经网络处理器(neural-network processing unit，NPU)等。其中，不同的处理单元可以是独立的器件，也可以集成在一个或多个处理器中。
控制器可以根据指令操作码和时序信号，产生操作控制信号，完成取指令和执行指令的控制。
处理器110中还可以设置存储器，用于存储指令和数据。在一些实施例中，处理器110中的存储器为高速缓冲存储器。该存储器可以保存处理器110刚用过或循环使用的指令或数据。如果处理器110需要再次使用该指令或数据，可从该存储器中直接调用。避免了重复存取，减少了处理器110的等待时间，因而提高了系统的效率。
在一些实施例中，处理器110可以包括一个或多个接口。接口可以包括集成电路(inter-integrated circuit，I2C)接口，集成电路内置音频(inter-integrated circuit sound，I2S)接口，脉冲编码调制(pulse code modulation，PCM)接口，通用异步收发传输器(universal asynchronous receiver/transmitter，UART)接口，移动产业处理器接口(mobile industry processor interface，MIPI)，通用输入输出(general-purpose input/output，GPIO)接口，用户标识模块(subscriber identity module，SIM)接口，和/或通用串行总线(universal serial bus，USB)接口等。
I2C接口是一种双向同步串行总线，包括一根串行数据线(serial data line，SDA)和一根串行时钟线(derail clock line，SCL)。在一些实施例中，处理器110可以包含多组I2C总线。处理器110可以通过不同的I2C总线接口分别耦合触摸传感器180K，充电器，闪光灯，摄像头193等。例如：处理器110可以通过I2C接口耦合触摸传感器180K，使处理器110与触摸传感器180K通过I2C总线接口通信，实现终端100的触摸功能。
I2S接口可以用于音频通信。在一些实施例中，处理器110可以包含多组I2S总线。处理器110可以通过I2S总线与音频模块170耦合，实现处理器110与音频模块170之间的通信。 在一些实施例中，音频模块170可以通过I2S接口向无线通信模块160传递音频信号，实现通过蓝牙耳机接听电话的功能。
PCM接口也可以用于音频通信，将模拟信号抽样，量化和编码。在一些实施例中，音频模块170与无线通信模块160可以通过PCM总线接口耦合。在一些实施例中，音频模块170也可以通过PCM接口向无线通信模块160传递音频信号，实现通过蓝牙耳机接听电话的功能。该I2S接口和该PCM接口都可以用于音频通信。
UART接口是一种通用串行数据总线，用于异步通信。该总线可以为双向通信总线。它将要传输的数据在串行通信与并行通信之间转换。在一些实施例中，UART接口通常被用于连接处理器110与无线通信模块160。例如：处理器110通过UART接口与无线通信模块160中的蓝牙模块通信，实现蓝牙功能。在一些实施例中，音频模块170可以通过UART接口向无线通信模块160传递音频信号，实现通过蓝牙耳机播放音乐的功能。
MIPI接口可以被用于连接处理器110与显示屏194，摄像头193等外围器件。MIPI接口包括摄像头串行接口(camera serial interface，CSI)，显示屏串行接口(display serial interface，DSI)等。在一些实施例中，处理器110和摄像头193通过CSI接口通信，实现终端100的拍摄功能。处理器110和显示屏194通过DSI接口通信，实现终端100的显示功能。
GPIO接口可以通过软件配置。GPIO接口可以被配置为控制信号，也可被配置为数据信号。在一些实施例中，GPIO接口可以用于连接处理器110与摄像头193，显示屏194，无线通信模块160，音频模块170，传感器模块180等。GPIO接口还可以被配置为I2C接口，I2S接口，UART接口，MIPI接口等。
USB接口130是符合USB标准规范的接口，具体可以是Mini USB接口，Micro USB接口，USB Type C接口等。USB接口130可以用于连接充电器为终端100充电，也可以用于终端100与外围设备之间传输数据。也可以用于连接耳机，通过耳机播放音频。该接口还可以用于连接其他终端，例如AR设备等。
可以理解的是，本申请实施例示意的各模块间的接口连接关系，只是示意性说明，并不构成对终端100的结构限定。在本申请另一些实施例中，终端100也可以采用上述实施例中不同的接口连接方式，或多种接口连接方式的组合。
充电管理模块140用于从充电器接收充电输入。其中，充电器可以是无线充电器，也可以是有线充电器。在一些有线充电的实施例中，充电管理模块140可以通过USB接口130接收有线充电器的充电输入。在一些无线充电的实施例中，充电管理模块140可以通过终端100的无线充电线圈接收无线充电输入。充电管理模块140为电池142充电的同时，还可以通过电源管理模块141为终端供电。
电源管理模块141用于连接电池142，充电管理模块140与处理器110。电源管理模块141接收电池142和/或充电管理模块140的输入，为处理器110，内部存储器121，显示屏194，摄像头193，和无线通信模块160等供电。电源管理模块141还可以用于监测电池容量，电池循环次数，电池健康状态(漏电，阻抗)等参数。在其他一些实施例中，电源管理模块141也可以设置于处理器110中。在另一些实施例中，电源管理模块141和充电管理模块140也可以设置于同一个器件中。
终端100的无线通信功能可以通过天线1，天线2，移动通信模块150，无线通信模块160，调制解调处理器以及基带处理器等实现。
天线1和天线2用于发射和接收电磁波信号。终端100中的每个天线可用于覆盖单个或多个通信频带。不同的天线还可以复用，以提高天线的利用率。例如：可以将天线1复用为无线局域网的分集天线。在另外一些实施例中，天线可以和调谐开关结合使用。
移动通信模块150可以提供应用在终端100上的包括2G/3G/4G/5G等无线通信的解决方案。移动通信模块150可以包括至少一个滤波器，开关，功率放大器，低噪声放大器(low noise amplifier，LNA)等。移动通信模块150可以由天线1接收电磁波，并对接收的电磁波进行滤波，放大等处理，传送至调制解调处理器进行解调。移动通信模块150还可以对经调制解调处理器调制后的信号放大，经天线1转为电磁波辐射出去。在一些实施例中，移动通信模块150的至少部分功能模块可以被设置于处理器110中。在一些实施例中，移动通信模块150的至少部分功能模块可以与处理器110的至少部分模块被设置在同一个器件中。
调制解调处理器可以包括调制器和解调器。其中，调制器用于将待发送的低频基带信号调制成中高频信号。解调器用于将接收的电磁波信号解调为低频基带信号。随后解调器将解调得到的低频基带信号传送至基带处理器处理。低频基带信号经基带处理器处理后，被传递给应用处理器。应用处理器通过音频设备(不限于扬声器170A，受话器170B等)输出声音信号，或通过显示屏194显示图像或视频。在一些实施例中，调制解调处理器可以是独立的器件。在另一些实施例中，调制解调处理器可以独立于处理器110，与移动通信模块150或其他功能模块设置在同一个器件中。
无线通信模块160可以提供应用在终端100上的包括无线局域网(wireless local area networks，WLAN)(如无线保真(wireless fidelity，Wi-Fi)网络)，蓝牙(bluetooth，BT)，全球导航卫星系统(global navigation satellite system，GNSS)，调频(frequency modulation，FM)，近距离无线通信技术(near field communication，NFC)，红外技术(infrared，IR)等无线通信的解决方案。无线通信模块160可以是集成至少一个通信处理模块的一个或多个器件。无线通信模块160经由天线2接收电磁波，将电磁波信号调频以及滤波处理，将处理后的信号发送到处理器110。无线通信模块160还可以从处理器110接收待发送的信号，对其进行调频，放大，经天线2转为电磁波辐射出去。
在一些实施例中，终端100的天线1和移动通信模块150耦合，天线2和无线通信模块160耦合，使得终端100可以通过无线通信技术与网络以及其他设备通信。该无线通信技术可以包括全球移动通讯系统(global system for mobile communications，GSM)，通用分组无线服务(general packet radio service，GPRS)，码分多址接入(code division multiple access，CDMA)，宽带码分多址(wideband code division multiple access，WCDMA)，时分码分多址(time-division code division multiple access，TD-SCDMA)，长期演进(long term evolution，LTE)，BT，GNSS，WLAN，NFC，FM，和/或IR技术等。该GNSS可以包括全球卫星定位系统(global positioning system，GPS)，全球导航卫星系统(global navigation satellite system，GLONASS)，北斗卫星导航系统(beidou navigation satellite system，BDS)，准天顶卫星系统(quasi-zenith satellite system，QZSS)和/或星基增强系统(satellite based augmentation systems，SBAS)。
终端100通过GPU，显示屏194，以及应用处理器等实现显示功能。GPU为图像处理的微处理器，连接显示屏194和应用处理器。GPU用于执行数学和几何计算，用于图形渲染。处理器110可包括一个或多个GPU，其执行程序指令以生成或改变显示信息。
显示屏194用于显示图像，视频等。显示屏194包括显示面板。显示面板可以采用液晶 显示屏(liquid crystal display，LCD)，有机发光二极管(organic light-emitting diode，OLED)，有源矩阵有机发光二极体或主动矩阵有机发光二极体(active-matrix organic light emitting diode的，AMOLED)，柔性发光二极管(flex light-emitting diode，FLED)，Miniled，MicroLed，Micro-oLed，量子点发光二极管(quantum dot light emitting diodes，QLED)等。在一些实施例中，终端100可以包括1个或N个显示屏194，N为大于1的正整数。
终端100可以通过ISP，摄像头193，视频编解码器，GPU，显示屏194以及应用处理器等实现拍摄功能。
ISP用于处理摄像头193反馈的数据。例如，拍照时，打开快门，光线通过镜头被传递到摄像头感光元件上，光信号转换为电信号，摄像头感光元件将该电信号传递给ISP处理，转化为肉眼可见的图像。ISP还可以对图像的噪点，亮度，肤色进行算法优化。ISP还可以对拍摄场景的曝光，色温等参数优化。在一些实施例中，ISP可以设置在摄像头193中。
摄像头193用于捕获静态图像或视频。物体通过镜头生成光学图像投射到感光元件。感光元件可以是电荷耦合器件(charge coupled device，CCD)或互补金属氧化物半导体(complementary metal-oxide-semiconductor，CMOS)光电晶体管。感光元件把光信号转换成电信号，之后将电信号传递给ISP转换成数字图像信号。ISP将数字图像信号输出到DSP加工处理。DSP将数字图像信号转换成标准的RGB，YUV等格式的图像信号。在一些实施例中，终端100可以包括1个或N个摄像头193，N为大于1的正整数。
数字信号处理器用于处理数字信号，除了可以处理数字图像信号，还可以处理其他数字信号。例如，当终端100在频点选择时，数字信号处理器用于对频点能量进行傅里叶变换等。
视频编解码器用于对数字视频压缩或解压缩。终端100可以支持一种或多种视频编解码器。这样，终端100可以播放或录制多种编码格式的视频，例如：动态图像专家组(moving picture experts group，MPEG)1，MPEG2，MPEG3，MPEG4等。
NPU为神经网络(neural-network，NN)计算处理器，通过借鉴生物神经网络结构，例如借鉴人脑神经元之间传递模式，对输入信息快速处理，还可以不断的自学习。通过NPU可以实现终端100的智能认知等应用，例如：图像识别，人脸识别，语音识别，文本理解等。
外部存储器接口120可以用于连接外部存储卡，例如Micro SD卡，实现扩展终端100的存储能力。外部存储卡通过外部存储器接口120与处理器110通信，实现数据存储功能。例如将音乐，视频等文件保存在外部存储卡中。
内部存储器121可以用于存储计算机可执行程序代码，该可执行程序代码包括指令。内部存储器121可以包括存储程序区和存储数据区。其中，存储程序区可存储操作系统，至少一个功能所需的应用程序(比如声音播放功能，图像播放功能等)等。存储数据区可存储终端100使用过程中所创建的数据(比如音频数据，电话本等)等。此外，内部存储器121可以包括高速随机存取存储器，还可以包括非易失性存储器，例如至少一个磁盘存储器件，闪存器件，通用闪存存储器(universal flash storage，UFS)等。处理器110通过运行存储在内部存储器121的指令，和/或存储在设置于处理器中的存储器的指令，执行终端100的各种功能应用以及数据处理。
终端100可以通过音频模块170，扬声器170A，受话器170B，麦克风170C，耳机接口170D，以及应用处理器等实现音频功能。例如音乐播放，录音等。
音频模块170用于将数字音频信息转换成模拟音频信号输出，也用于将模拟音频输入转 换为数字音频信号。音频模块170还可以用于对音频信号编码和解码。在一些实施例中，音频模块170可以设置于处理器110中，或将音频模块170的部分功能模块设置于处理器110中。
扬声器170A，也称“喇叭”，用于将音频电信号转换为声音信号。终端100可以通过扬声器170A收听音乐，或收听免提通话。
受话器170B，也称“听筒”，用于将音频电信号转换成声音信号。当终端100接听电话或语音信息时，可以通过将受话器170B靠近人耳接听语音。
麦克风170C，也称“话筒”，“传声器”，用于将声音信号转换为电信号。当拨打电话或发送语音信息时，用户可以通过人嘴靠近麦克风170C发声，将声音信号输入到麦克风170C。终端100可以设置至少一个麦克风170C。在另一些实施例中，终端100可以设置两个麦克风170C，除了采集声音信号，还可以实现降噪功能。在另一些实施例中，终端100还可以设置三个，四个或更多麦克风170C，实现采集声音信号，降噪，还可以识别声音来源，实现定向录音功能等。
耳机接口170D用于连接有线耳机。耳机接口170D可以是USB接口130，也可以是3.5mm的开放移动终端平台(open mobile terminal platform，OMTP)标准接口，美国蜂窝电信工业协会(cellular telecommunications industry association of the USA，CTIA)标准接口。
压力传感器180A用于感受压力信号，可以将压力信号转换成电信号。在一些实施例中，压力传感器180A可以设置于显示屏194。压力传感器180A的种类很多，如电阻式压力传感器，电感式压力传感器，电容式压力传感器等。电容式压力传感器可以是包括至少两个具有导电材料的平行板。当有力作用于压力传感器180A，电极之间的电容改变。终端100根据电容的变化确定压力的强度。当有触摸操作作用于显示屏194，终端100根据压力传感器180A检测该触摸操作强度。终端100也可以根据压力传感器180A的检测信号计算触摸的位置。在一些实施例中，作用于相同触摸位置，但不同触摸操作强度的触摸操作，可以对应不同的操作指令。例如：当有触摸操作强度小于第一压力阈值的触摸操作作用于短消息应用图标时，执行查看短消息的指令。当有触摸操作强度大于或等于第一压力阈值的触摸操作作用于短消息应用图标时，执行新建短消息的指令。
陀螺仪传感器180B可以用于确定终端100的运动姿态。在一些实施例中，可以通过陀螺仪传感器180B确定终端100围绕三个轴(即，x，y和z轴)的角速度。陀螺仪传感器180B可以用于拍摄防抖。示例性的，当按下快门，陀螺仪传感器180B检测终端100抖动的角度，根据角度计算出镜头模组需要补偿的距离，让镜头通过反向运动抵消终端100的抖动，实现防抖。陀螺仪传感器180B还可以用于导航，体感游戏场景。
气压传感器180C用于测量气压。在一些实施例中，终端100通过气压传感器180C测得的气压值计算海拔高度，辅助定位和导航。
磁传感器180D包括霍尔传感器。终端100可以利用磁传感器180D检测翻盖皮套的开合。在一些实施例中，当终端100是翻盖机时，终端100可以根据磁传感器180D检测翻盖的开合。进而根据检测到的皮套的开合状态或翻盖的开合状态，设置翻盖自动解锁等特性。
加速度传感器180E可检测终端100在各个方向上(一般为三轴)加速度的大小。当终端100静止时可检测出重力的大小及方向。还可以用于识别终端姿态，应用于横竖屏切换，计步器等应用。
距离传感器180F，用于测量距离。终端100可以通过红外或激光测量距离。在一些实施例中，拍摄场景，终端100可以利用距离传感器180F测距以实现快速对焦。
接近光传感器180G可以包括例如发光二极管(LED)和光检测器，例如光电二极管。发光二极管可以是红外发光二极管。终端100通过发光二极管向外发射红外光。终端100使用光电二极管检测来自附近物体的红外反射光。当检测到充分的反射光时，可以确定终端100附近有物体。当检测到不充分的反射光时，终端100可以确定终端100附近没有物体。终端100可以利用接近光传感器180G检测用户手持终端100贴近耳朵通话，以便自动熄灭屏幕达到省电的目的。接近光传感器180G也可用于皮套模式，口袋模式自动解锁与锁屏。
环境光传感器180L用于感知环境光亮度。终端100可以根据感知的环境光亮度自适应调节显示屏194亮度。环境光传感器180L也可用于拍照时自动调节白平衡。环境光传感器180L还可以与接近光传感器180G配合，检测终端100是否在口袋里，以防误触。
指纹传感器180H用于采集指纹。终端100可以利用采集的指纹特性实现指纹解锁，访问应用锁，指纹拍照，指纹接听来电等。
温度传感器180J用于检测温度。在一些实施例中，终端100利用温度传感器180J检测的温度，执行温度处理策略。例如，当温度传感器180J上报的温度超过阈值，终端100执行降低位于温度传感器180J附近的处理器的性能，以便降低功耗实施热保护。在另一些实施例中，当温度低于另一阈值时，终端100对电池142加热，以避免低温导致终端100异常关机。在其他一些实施例中，当温度低于又一阈值时，终端100对电池142的输出电压执行升压，以避免低温导致的异常关机。
触摸传感器180K，也称“触控器件”。触摸传感器180K可以设置于显示屏194，由触摸传感器180K与显示屏194组成触摸屏，也称“触控屏”。触摸传感器180K用于检测作用于其上或附近的触摸操作。触摸传感器可以将检测到的触摸操作传递给应用处理器，以确定触摸事件类型。可以通过显示屏194提供与触摸操作相关的视觉输出。在另一些实施例中，触摸传感器180K也可以设置于终端100的表面，与显示屏194所处的位置不同。
骨传导传感器180M可以获取振动信号。在一些实施例中，骨传导传感器180M可以获取人体声部振动骨块的振动信号。骨传导传感器180M也可以接触人体脉搏，接收血压跳动信号。在一些实施例中，骨传导传感器180M也可以设置于耳机中，结合成骨传导耳机。音频模块170可以基于该骨传导传感器180M获取的声部振动骨块的振动信号，解析出语音指令，实现语音功能。应用处理器可以基于该骨传导传感器180M获取的血压跳动信号解析心率信息，实现心率检测功能。
按键190包括开机键，音量键等。按键190可以是机械按键。也可以是触摸式按键。终端100可以接收按键输入，产生与终端100的用户设置以及功能控制有关的键信号输入。
马达191可以产生振动提示。马达191可以用于来电振动提示，也可以用于触摸振动反馈。例如，作用于不同应用(例如拍照，音频播放等)的触摸操作，可以对应不同的振动反馈效果。作用于显示屏194不同区域的触摸操作，马达191也可对应不同的振动反馈效果。不同的应用场景(例如：时间提醒，接收信息，闹钟，游戏等)也可以对应不同的振动反馈效果。触摸振动反馈效果还可以支持自定义。
指示器192可以是指示灯，可以用于指示充电状态，电量变化，也可以用于指示消息，未接来电，通知等。
SIM卡接口195用于连接SIM卡。SIM卡可以通过插入SIM卡接口195，或从SIM卡接口195拔出，实现和终端100的接触和分离。终端100可以支持1个或N个SIM卡接口，N为大于1的正整数。SIM卡接口195可以支持Nano SIM卡，Micro SIM卡，SIM卡等。同一个SIM卡接口195可以同时插入多张卡。该多张卡的类型可以相同，也可以不同。SIM卡接口195也可以兼容不同类型的SIM卡。SIM卡接口195也可以兼容外部存储卡。终端100通过SIM卡和网络交互，实现通话以及数据通信等功能。在一些实施例中，终端100采用eSIM，即：嵌入式SIM卡。eSIM卡可以嵌在终端100中，不能和终端100分离。终端100的软件系统可以采用分层架构，事件驱动架构，微核架构，微服务架构，或云架构。
以分层架构的Android(安卓)系统为例，示例性说明终端100的软件结构。
图3是本申请实施例提供的一种终端100的功能架构图。
分层架构将软件分成若干个层，每一层都有清晰的角色和分工。层与层之间通过软件接口通信。在一些实施例中，将Android系统分为四层，从上至下分别为应用程序层，应用程序框架层，安卓运行时(Android runtime)和系统库，以及内核层。
应用程序层可以包括一系列应用程序包。
如图3所示，应用程序包可以包括相机，图库，日历，通话，地图，导航，WLAN，蓝牙，音乐，视频，短信息等应用程序。
应用程序框架层为应用程序层的应用程序提供应用编程接口(application programming interface，API)和编程框架。应用程序框架层包括一些预先定义的函数。
如图3所示，应用程序框架层可以包括窗口管理器，内容提供器，视图系统，电话管理器，资源管理器，通知管理器等。
窗口管理器用于管理窗口程序。窗口管理器可以获取显示屏大小，判断是否有状态栏，锁定屏幕，截取屏幕等。
内容提供器用来存放和获取数据，并使这些数据可以被应用程序访问。该数据可以包括视频，图像，音频，拨打和接听的电话，浏览历史和书签，电话簿等。
视图系统包括可视控件，例如显示文字的控件，显示图片的控件等。视图系统可用于构建应用程序。显示界面可以由一个或多个视图组成的。例如，包括短信通知图标的显示界面，可以包括显示文字的视图以及显示图片的视图。
电话管理器用于提供终端100的通信功能。例如通话状态的管理(包括接通，挂断等)。
资源管理器为应用程序提供各种资源，比如本地化字符串，图标，图片，布局文件，视频文件等等。
通知管理器使应用程序可以在状态栏中显示通知信息，可以用于传达告知类型的消息，可以短暂停留后自动消失，无需用户交互。比如通知管理器被用于告知下载完成，消息提醒等。通知管理器还可以是以图表或者滚动条文本形式出现在系统顶部状态栏的通知，例如后台运行的应用程序的通知，还可以是以对话窗口形式出现在屏幕上的通知。例如在状态栏提示文本信息，发出提示音，终端振动，指示灯闪烁等。
Android Runtime包括核心库和虚拟机。Android runtime负责安卓系统的调度和管理。
核心库包含两部分：一部分是java语言需要调用的功能函数，另一部分是安卓的核心库。
应用程序层和应用程序框架层运行在虚拟机中。虚拟机将应用程序层和应用程序框架层的java文件执行为二进制文件。虚拟机用于执行对象生命周期的管理，堆栈管理，线程管理，安全和异常的管理，以及垃圾回收等功能。
系统库可以包括多个功能模块。例如：表面管理器(surface manager)，媒体库(Media Libraries)，三维图形处理库(例如：OpenGL ES)，2D图形引擎(例如：SGL)等。
表面管理器用于对显示子系统进行管理，并且为多个应用程序提供了2D和3D图层的融合。
媒体库支持多种常用的音频，视频格式回放和录制，以及静态图像文件等。媒体库可以支持多种音视频编码格式，例如:MPEG4，H.264，MP3，AAC，AMR，JPG，PNG等。
三维图形处理库用于实现三维图形绘图，图像渲染，合成，和图层处理等。
2D图形引擎是2D绘图的绘图引擎。
内核层是硬件和软件之间的层。内核层至少包含显示驱动，摄像头驱动，音频驱动，传感器驱动。
下面结合事件检测场景，示例性说明终端100软件以及硬件的工作流程。
以目标事件为对界面进行了触摸操作为例，检测触发操作的流程可以包括：当触摸传感器180K接收到触摸操作，相应的硬件中断被发给内核层。内核层将触摸操作加工成原始输入事件(包括触摸坐标，触摸操作的时间戳等信息)。原始输入事件被存储在内核层。应用程序框架层从内核层获取原始输入事件，识别该输入事件所对应的控件，从而检测到该触摸操作发生。以该触摸操作是单击操作，该单击操作所对应的控件为音乐应用的图标为例，音乐应用调用应用框架层的接口，启动音乐应用，进而通过显示屏194显示音乐应用的界面。
以下，示例性描述本申请实施例的应用场景。
本申请实施例可以应用于唤醒终端进行语音交互的场景。相关技术中，每当用户想要终端执行某个业务时，都需要说一遍终端的唤醒词，而通过应用下述方法实施例提供的方法，可以实现免唤醒词唤醒的功能。以终端的唤醒词为“你好，小华”为例，下面结合场景一至场景八进行对比描述：
场景一、在驾驶过程中，用户想要车载终端放首歌曲。
相关技术中，该场景包括下述步骤一至步骤七：
步骤一、用户说“你好，小华”。
步骤二、车载终端采集语音指令，确定语音指令包含“你好，小华”，则车载终端被唤醒，播放语音“在呢”，从而对用户的语音指令进行响应；之后，车载终端经过预设时长未采集到语音指令，则车载终端重新休眠。
步骤三、用户打开电台开关。
步骤四、用户说“你好，小华”。
步骤五、车载终端采集语音指令，确定语音指令包含“你好，小华”，则车载终端被重新唤醒，播放语音“在呢”，从而对用户的语音指令进行响应。
步骤六、用户说“帮忙放《东方音乐电台》的歌曲”。
步骤七、车载终端采集语音指令，确定语音指令包含“你好，小华”，则车载终端会将电台调整至《东方音乐电台》，播放《东方音乐电台》的歌曲。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤四：
步骤一、用户打开电台开关。
步骤二、电台开关向车载终端发送信号，则车载终端确定检测到对电台开关的打开操作，根据对电台开关的打开操作，查询映射关系，得到的目标业务类型为音乐，从而预测出用户具有针对音乐这一业务类型的业务进行语音交互的意图。
步骤三、用户说“帮忙放《东方音乐电台》的歌曲”。
步骤四、车载终端采集语音指令，获取“帮忙放《东方音乐电台》的歌曲”对应的业务类型为音乐，判定预测出的目标业务类型与用户通过语音表达的业务类型相同，则播放《东方音乐电台》的歌曲。另外，如果步骤三中用户所说的内容和音乐无关，车载终端可以不响应用户所说的内容。
通过上述描述可以看出，用户通过打开电台开关，即可激活车载终端对音乐这一业务类型的业务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
场景二、在驾驶过程中，用户想查看即时通信消息。
相关技术中，该场景包括下述步骤一至步骤七：
步骤一、手机上运行的应用程序A接收到一条即时通信消息。
步骤二、用户说“你好，小华”。
步骤三、终端采集语音指令，确定语音指令包含“你好，小华”，则手机被唤醒，播放语音“在呢”，从而对用户的语音指令进行响应；之后，手机经过预设时长未采集到语音指令，则手机重新休眠。
步骤四、用户说“你好，小华”。
步骤五、手机采集语音指令，确定语音指令包含“你好，小华”，则手机被重新唤醒，播放语音“在呢”，从而对用户的语音指令进行响应。
步骤六、用户说“看下应用程序A在说什么”。
步骤七、手机采集语音指令，确定语音指令包含“看下应用程序A在说什么”，则手机获取应用程序A接收到的即时通信消息“晚上七点去吃火锅”，则播放语音“晚上七点去吃火锅”。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤四：
步骤一、手机上运行的应用程序A接收到一条即时通信消息。
步骤二、手机根据接收到的即时通信消息，查询映射关系，得到的目标业务类型为应用程序A，从而预测出用户具有针对应用程序A类型的业务进行语音交互的意图。
步骤三、用户说“看下应用程序A在说什么”。
步骤四、手机采集语音指令，获取“看下应用程序A在说什么”对应的业务类型为应用程序A，手机判定预测出的目标业务类型与用户通过语音表达的业务类型相同，则手机获取应用程序A接收到的即时通信消息“晚上七点去吃火锅”，播放语音“晚上七点去吃火锅”。另外，如果步骤三中用户所说的内容和应用程序A无关，手机可以不响应用户所说的内容，从而避免误唤醒。
通过上述描述可以看出，如果接收到即时通信消息，即可激活手机对即时通信应用的业务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
场景三、当一首歌曲快播放结束时，用户想继续播放另一首歌曲。
相关技术中，该场景包括下述步骤一至步骤五：
步骤一、智能音箱当前播放的歌曲A将要结束。
步骤二、用户说“你好，小华”。
步骤三、智能音箱采集语音指令，确定语音指令包含“你好，小华”，则智能音箱被唤醒，播放语音“在呢”，从而对用户的语音指令进行响应。
步骤四、用户说“放下歌曲B”。
步骤五、智能音箱采集语音指令，确定语音指令包含“放下歌曲B”，则智能音箱播放歌曲B。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤三：
步骤一、智能音箱当前播放的歌曲A将要结束，则智能音箱确定当前业务的进度满足条件，智能音箱根据当前业务音乐，查询映射关系，得到的目标业务类型为音乐，从而预测出用户具有针对音乐这一业务类型的业务进行语音交互的意图。
步骤二、用户说“放下歌曲B”。
步骤三、智能音箱采集语音指令，获取“放下歌曲B”对应的业务类型为音乐，则判定预测出的目标业务类型与用户通过语音表达的业务类型相同，则智能音箱播放歌曲B。另外，如果步骤二中用户所说的内容和音乐无关，智能音箱可以不响应用户所说的内容。
通过上述描述可以看出，如果当前播放的歌曲将要结束，即可激活手机对音乐这一业务类型的业务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
场景四、驾驶过程中突然下雨。
相关技术中，该场景包括下述步骤一至步骤四：
步骤一、用户说“你好，小华”。
步骤二、车载终端采集语音指令，确定语音指令包含“你好，小华”，则车载终端被唤醒，播放语音“在呢”，从而对用户的语音指令进行响应。
步骤三、用户说“打开雨刷”。
步骤四、车载终端采集语音指令，确定语音指令包含“打开雨刷”，则车载终端向汽车的控制器发送信号，控制器控制雨刷的驱动电路驱动雨刷转动。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤三：
步骤一、车载终端通过雨滴传感器，确定检测到下雨，则根据下雨，查询映射关系，得到的目标业务类型为雨刷，从而预测出用户具有针对雨刷这一业务类型的业务进行语音交互的意图。
步骤二、用户说“打开雨刷”。
步骤三、车载终端采集语音指令，获取“打开雨刷”对应的业务类型为雨刷，则判定预测出的目标业务类型与用户通过语音表达的业务类型相同，则车载终端向汽车的控制器发送信号，控制器指示雨刷的驱动电路驱动雨刷转动。另外，如果步骤二中用户所说的内容和雨刷无关，车载终端可以不响应用户所说的内容。
通过上述描述可以看出，如果下雨，即可激活手机对雨刷这一业务类型的业务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
场景五、在驾驶过程中，汽车的燃油不足。
相关技术中，该场景包括下述步骤一至步骤四：
步骤一、用户说“你好，小华”。
步骤二、车载终端采集语音指令，确定语音指令包含“你好，小华”，则手机被唤醒，播放语音“在呢”，从而对用户的语音指令进行响应。
步骤三、用户说“最近的加油站在哪里”。
步骤四、车载终端采集语音指令，确定语音指令包含“最近的加油站在哪里”，则车载终端调用与导航应用的接口，查询加油站地址，则播放语音“加油站地址在X区Y路”。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤三：
步骤一、车载终端检测汽车的燃油量，确定燃油量低于阈值，则根据燃油量查询映射关系，得到的业务类型集合包括加油站以及导航，从而预测出用户具有针对加油站或导航这两种业务类型的业务进行语音交互的意图。
步骤二、用户说“最近的加油站在哪里”。
步骤三、车载终端采集语音指令，得到“最近的加油站在哪里”对应的业务类型为导航，则判定预测出的目标业务类型与用户通过语音表达的业务类型相同，则车载终端调用与导航应用的接口，查询加油站地址，则播放语音“加油站地址在X区Y路”。另外，如果步骤二中用户所说的内容和导航无关，车载终端可以不响应用户所说的内容。
通过上述描述可以看出，如果汽车燃油不足，即可激活车载终端对加油站或导航这两种业务类型的业务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
场景六、接听来电。
相关技术中，该场景包括下述步骤一至步骤五：
步骤一、手机接收到主叫方的呼叫请求，则手机的操作系统推送来电通知。
步骤二、用户说“你好，小华”。
步骤三、终端采集语音指令，确定语音指令包含“你好，小华”，则手机被唤醒，播放语音“在呢”。
步骤四、用户说“帮我接下电话”。
步骤五、手机采集语音指令，确定语音指令包含“帮我接下电话”，则手机接听来电。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤三：
步骤一、手机接收到主叫方的呼叫请求，则手机的操作系统推送来电通知，则手机检测到来电通知，根据来电通知，查询映射关系，得到的目标业务类型为通信，从而预测出用户具有针对通信这一业务类型的业务进行语音交互的意图。
步骤二、用户说“帮我接下电话”。
步骤三、手机采集语音指令，根据“帮我接下电话”对应的语义信息“接听电话”，得到语义信息“接听电话”对应的业务类型为通信类型，判定预测出的目标业务类型与用户通过语音表达的业务类型相同，则手机接听来电。另外，如果步骤三中用户所说的内容和通信无关，车载终端可以不响应用户所说的内容。
通过上述描述可以看出，如果手机接收到来电，即可激活手机对通信这一业务类型的业 务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
场景七、汽车驾驶到空气质量差的区域。
相关技术中，该场景包括下述步骤一至步骤四：
步骤一、用户说“你好，小华”。
步骤二、终端采集语音指令，确定语音指令包含“你好，小华”，则手机被唤醒，播放语音“在呢”，从而对用户的语音指令进行响应。
步骤三、用户说“打开空气净化器”。
步骤四、车载终端采集语音指令，确定语音指令包含“打开空气净化器”，则车载终端向汽车的控制器发送信号，控制器控制空气净化器开启。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤三：
步骤一、空气净化器的传感器对粉尘浓度进行检测，向车载终端发送检测到的粉尘浓度，车载终端确定粉尘浓度超过阈值，则根据粉尘浓度，查询映射关系，得到的目标业务类型为空气净化器，从而预测出用户具有针对空气净化器这一类型的业务进行语音交互的意图。
步骤二、用户说“打开空气净化器”。
步骤三、车载终端采集语音指令，获取“打开空气净化器”对应的业务类型为空气净化器，判定预测出的目标业务类型与用户通过语音表达的业务类型相同，则车载终端向汽车的控制器发送信号，控制器控制空气净化器开启。另外，如果步骤二中用户所说的内容和空气净化器无关，车载终端可以不响应用户所说的内容。
通过上述描述可以看出，如果粉尘浓度超过阈值，即可激活车载终端对空气净化器这一业务类型的业务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
场景八、在驾驶过程中，汽车的遮阳帘打开到一半，用户希望遮阳帘别继续打开了。
相关技术中，该场景包括下述步骤一至步骤四：
步骤一、用户说“你好，小华”。
步骤二、车载终端采集语音指令，确定语音指令包含“你好，小华”，则车载终端被唤醒，播放语音“在呢”，从而对用户的语音指令进行响应。
步骤三、用户说“停止放下遮阳帘”。
步骤四、车载终端采集语音指令，确定语音指令包含“放下遮阳帘”，则车载终端向汽车的控制器发送停止信号，停止信号用于指示停止继续打开遮阳帘，控制器接收到停止信号后，控制遮阳帘的驱动电路停止继续打开遮阳帘。
而通过应用本实施例提供的方法，该场景下可以包括下述步骤一至步骤三：
步骤一、遮阳帘向车载终端发送当前的状态，车载终端根据遮阳帘的状态，确定遮阳帘的打开程度满足条件，则根据据遮阳帘，查询映射关系，得到的目标业务类型“遮阳帘”，从而预测出用户具有针对“遮阳帘”类型的业务进行语音交互的意图。
步骤二、用户说“停止放下遮阳帘”。
步骤三、车载终端采集语音指令，根据语音指令对应的语义信息“停止放下遮阳帘”，得到语义信息“停止放下遮阳帘”对应的业务类型为遮阳帘，则车载终端向汽车的控制器发送停止信号，停止信号用于指示停止继续打开遮阳帘，控制器接收到停止信号后，控制遮阳帘的 驱动电路停止继续打开遮阳帘。另外，如果步骤二中用户所说的内容和遮阳帘无关，车载终端可以不响应用户所说的内容。
通过上述描述可以看出，如果遮阳帘的打开程度满足条件，即可激活车载终端机对遮阳帘这一业务类型的业务的免唤醒词语音交互功能，从而免去了用户频繁说出唤醒词的步骤。
以下，示例性介绍本申请的方法流程。
图4是本申请实施例提供的一种语音交互方法的流程图，该实施例以执行主体为终端为例进行说明，参见图4，该方法包括：
401、终端确定检测到目标事件发生。
目标事件为能够触发语音交互的事件。如果目标事件发生，用户会有一定的概率产生语音交互的意图，具有唤醒终端进行语音交互的需求。有鉴于此，终端会对目标事件进行检测，以便在确定检测到目标事件发生时，结合目标事件以及语音指令，判定是否激活语音交互的功能。
可选地，目标事件可以具有一个或多个模态，模态是指目标事件的形式或者维度。作为示意，目标事件的模态可以是用户的操作，目标事件的模态也可以是通知消息，目标事件的模态也可以是环境参数满足第一条件，目标事件的模态也可以是当前业务的进度满足第二条件，当然，目标事件的模态还可以根据业务需求替换为其他模态，本实施例对目标事件的模态不做限定。
用户的操作可以而不限于是对物理按键的操作、对界面的操作、语音指令、浏览行为中的一项或多项。其中，物理按键可以是终端本体上的按键，也可以是与终端建立了通信连接的其他设备上的按键。例如，如果终端为车载终端，物理按键可以是汽车上搭载的任意设备上的按键，比如说，物理按键可以是汽车的空调开关、电台开关等。如果用户对物理按键进行了操作，物理按键可以向终端发送信号，则终端确定检测到对物理按键的操作。界面可以是终端的系统界面或应用程序的界面。如果用户对界面进行了操作，界面的显示屏幕可以向终端发送信号，则终端确定检测到对界面的操作。语音指令可以通过麦克风采集到。浏览行为可以是用户浏览终端的界面的行为，如果用户进行了浏览行为，终端可以通过摄像头，捕获到用户的视线，从而确定检测到浏览行为。操作可以按压操作、点击操作或者滑动操作等，本实施例对操作的具体类型不做限定。
通知消息可以为操作系统或应用程序推送的消息。例如，通知消息可以是来电通知、短信、即时通信消息、告警消息、资源推荐消息中的一项或多项。其中，告警消息可以表示终端发生了故障，比如说可以表示电量低于总电量的10％、内存不足、受到网络攻击等；告警消息也可以表示与终端建立了通信连接的其他设备发生了故障。比如说，车载终端的告警消息可以表示汽车的电机发生故障；资源推荐消息可以表示向用户推荐的资源，比如说可以是新闻应用推荐的新闻、电商应用推荐的商品或服务、游戏应用推荐的虚拟物品等。
环境参数可以而不限于是噪声、温度、湿度、亮度、粉尘浓度、油量中的一项或多项。第一条件可以而不限于是环境参数超过参数阈值或者环境参数的变化量超过变化量阈值。
关于检测环境参数满足第一条件的具体过程，传感器可以实时或周期性地采集环境参数，向终端发送采集到的环境参数。例如，温度传感器可以采集温度，向终端发送温度；湿度传感器可以采集湿度，向终端发送湿度；粉尘传感器可以采集粉尘浓度，向终端发送粉尘浓度； 亮度传感器可以采集亮度，向终端发送亮度；麦克风可以采集噪声强度，向终端发送噪声强度，油量传感器可以采集车辆当前的剩余油量，向终端发送油量。终端可以从传感器接收环境参数；终端可以判断环境参数是否超过参数阈值，如果环境参数超过参数阈值，确定检测到环境参数满足第一条件。或者，终端可以根据当前获取的环境参数与历史获取到的环境参数，获取环境参数的变化量，判断环境参数的变化量是否超过变化量阈值，如果环境参数的变化量超过变化量阈值，表明环境发生了变化，则确定检测到环境参数满足第一条件。
当前业务可以是终端当前执行的业务，也可以是与终端建立了通信连接的其他设备当前执行的业务。例如，如果终端为车载终端，车载终端可以通过车辆的控制器，与车辆搭载的空调、遮阳帘、雨刷建立通信连接，则当前业务可以是车载终端当前执行的导航业务或音乐业务，也可以是空调执行的温度调节业务、雨刷执行的转动业务、遮阳帘执行的放下业务。
第二条件可以而不限于是业务的进度发生变化，比如可以是业务的进度超过阈值或者业务的进度的变化量超过变化量阈值，示意性地，第二条件可以是业务将要结束、业务执行了一半等。例如，对于空调而言，当前业务的进度满足第二条件可以是空调开始执行温度调节业务，比如空调开始设定温度、空调开始调大风量等；当前业务的进度满足第二条件也可以是空调执行的温度调节业务的进度发生变化，比如空调的温度传感器检测到温度发生了变化。
关于检测当前业务的进度满足第二条件的具体过程，终端可以获取当前业务的进度，判断当前业务的进度是否超过阈值，如果当前业务的进度是否超过阈值，确定当前业务的进度满足第二条件；或者，终端可以根据当前业务的当前进度与当前业务的历史进度，获取当前业务的进度的变化量，判断变化量是否超过变化量阈值，如果当前业务的进度的变化量超过变化量阈值，表明当前业务发生了变化，则确定当前业务的进度满足第二条件。其中，变化量以及变化量阈值可以通过变化的百分比表示，也可以通过变化的时间表示，当然还可以通过其他维度的数据表示，本实施例对此不做限定。
需要说明的一点是，用户的操作、通知消息、环境参数满足第一条件、当前业务的进度满足第二条件仅是对目标事件的举例，而不限定目标事件仅限于此。应理解，目标事件的模态可以根据终端的实际业务进行相应扩展，但凡能够触发语音交互的事件均可以提供为目标事件，本实施例对目标事件不做限定。
402、终端根据该目标事件，查询映射关系，得到业务类型集合。
业务类型集合包括一个或多个目标业务类型，每个目标业务类型为语音交互意图对应的业务类型。终端可以根据目标事件，对用户的语音交互意图进行预测，得到业务类型集合。其中，目标业务类型可以是终端执行的业务的类型，也可以是与终端建立了通信连接的其他设备执行的业务的类型，比如如果终端是车辆的控制器，目标业务类型可以是车辆搭载的空调、灯等设备执行的业务类型。例如，目标业务类型可以是导航、日程咨询、空调、电台、音乐、车控、里程查询、问答咨询、游戏、系统设置、车辆控制、充电、维修保养、通讯中的一项或多项。
映射关系可以包括一个或多个事件以及一个或多个业务类型，映射关系可以指示事件与业务类型之间的对应关系，映射关系中的每个事件可以对应于一个或多个业务类型。其中，映射关系中的事件可以为第一表项，事件对应的业务类型可以为第二表项，第一表项和第二表项的位置对应，例如第一表项和第二表项可以位于同一行中。作为示例，映射关系可以如下表1所示。
表1
Figure PCTCN2020074988-appb-000001
终端可以以目标事件为索引，在该映射关系中，查询得到业务类型集合。例如，如果检测到的目标事件为对总开关的操作，查询表1，得到的业务类型集合为(导航、音乐、日程咨询)。可选地，映射关系具体可以包括用户的操作与操作相对应的业务类型之间的第一映射关系、通知消息与消息查看或消息处理之间的第二映射关系、环境参数与调节环境参数之间的第三映射关系以及当前业务与当前业务的业务类型之间的第四映射关系中的一项或多项。第一映射关系可以包括一个或多个操作以及一个或多个操作相对应的业务类型，任一操作可以对应一个或多个业务类型。示意性的，第一映射关系可以如下表2所示。
表2
Figure PCTCN2020074988-appb-000002
在一些可能的实施例中，第一映射关系可以基于操作连续性规则构建。操作连续性规则是指：如果操作A与操作B为连续性操作，那么如果用户执行了操作A，可以预测用户具有执行操作B的意图。连续性操作是指：用户执行操作A之后，紧接着执行操作B。为了便于表述，在此将操作A(用户当前的操作)称为第一操作，操作B(与第一操作相关联的连续性操作)称为目标第二操作，目标第二操作为执行第一操作之后，具有一定概率将要执行的操作，目标第二操作为预测出的操作，目标第二操作可能执行也可能不执行，目标第二操作可以是第一操作之后的第一个操作。第一映射关系可以包括第一操作与一个或多个业务类型之间的映射关系，第一映射关系中的每个业务类型为目标第二操作相对应的业务类型，一个或多个目标第二操作为该第一操作相关联的连续性操作。例如，参见表2，打开总开关(第一操作)与导航到目的地(目标第二操作)为连续性操作，并且，打开总开关(第一操作)与点击歌曲播放按钮(目标第二操作)也为连续性操作，并且，打开总开关(第一操作)与查看今天日程(目标第二操作)也为连续性操作，而导航到目的地这种操作的业务类型为导航，点击歌曲播放按钮这种操作对应的业务类型为音乐，查看今天日程这种操作的业务类型为日程咨询，因此在构建第一映射关系时，可以以对总开关的操作为第一操作，以导航、音乐以及日程咨询作为目标第二操作对应的业务类型，则将对总开关的操作、导航、音乐以及日程咨询，写入第一映射关系。又如，打开导航界面(第一操作)与在导航界面上输入导航目的地(目标第二操作)为连续性操作，而输入导航目的地这种操作对应的业务类型为导航，因此在构建第一映射关系时，可以以对总开关的操作为第一操作，以导航作为目标第二操作对应的业务类型，则将打开导航界面与导航之间的映射关系，存入第一映射关系，那么，当用户打开导航界面时，终端可以将导航预测为目标业务类型。
第二映射关系包括一个或多个通知消息以及消息查看或消息处理，消息查看可以为查看短信、查看即时通信应用的即时通信消息、查看资源推荐应用的推送消息，消息处理可以包括接听来电、消息回复、故障处理以及信息查询。示意性的，第二映射关系可以如下表3所示。
表3
Figure PCTCN2020074988-appb-000003
在一些可能的实施例中，第二映射关系可以基于用户的查看通知消息的需求或处理通知消息的需求构建。具体地，如果接收到通知消息，可以预测用户具有查看通知消息或处理通知消息的意图，因此，第二映射关系可以为通知消息与消息查看之间的映射关系，或者，第二映射关系可以为通知消息与消息处理之间的映射关系。例如，参见上表3，如果即时通信应用推送了一条即时通信消息，可以预测用户具有查看即时通信消息的意图，而查看即时通信消息对应的业务类型可以是即时通信应用，因此可以在构建第二映射关系时，可以将即时 通信消息与即时通信应用的标识写入第二映射关系。
第三映射关系包括一个或多个环境参数以及调节环境参数。示意性的，第三映射关系可以如下表4所示。
表4
Figure PCTCN2020074988-appb-000004
在一些可能的实施例中，第三映射关系可以基于用户应对环境变化的需求构建。具体来讲，考虑到环境参数满足条件时，会影响到用户的感知，因此可以预测用户具有调节环境参数的意图，因此，第三映射关系可以包括环境参数与调节环境参数对应的业务类型之间的映射关系。例如，参见上表4，如果温度的变化量满足阈值，可以预测用户具有调节温度的需求，而调节温度对应的业务类型为空调，因此在构建第三映射关系时，可以将温度的变化量满足阈值与空调之间的映射关系存入第三映射关系。
第四映射关系可以包括一个或多个当前业务以及当前业务的业务类型。示意性的，第四映射关系可以如下表5所示。
表5
Figure PCTCN2020074988-appb-000005
在一些可能的实施例中，第四映射关系可以基于用户的应对需求构建。具体来讲，考虑到当前业务的进度满足条件时，会影响到用户的感知，因此可以预测用户具有重启当前业务、停止当前业务或调整当前业务的意图，因此，第四映射关系可以为当前业务与当前业务的业务类型之间的映射关系。例如，参见上表5，如果当前播放的音乐将要结束，可以预测用户具有播放下一首歌曲、停止播放歌曲或重新播放歌曲的需求，而播放下一首歌曲、停止播放歌曲或重新播放歌曲对应的业务类型均为音乐，因此在构建第四映射关系时，可以将音乐将要结束与音乐之间的映射关系，存入第四映射关系。
在一些可能的实施例中，映射关系的建立过程可以包括下述实现方式一至实现方式二：
实现方式一、终端根据历史记录，得到与历史目标事件关联执行的历史业务，将该历史业务的业务类型以及该历史目标事件，写入该映射关系。
本实现方式中，映射关系可以根据历史语音交互过程构建。具体来讲，如果终端在历史时间点检测到历史目标事件后，用户与终端进行了语音交互，使得终端响应于用户的语音指 令，执行了某一历史业务，则终端可以建立历史目标事件与该历史业务的业务类型之间的映射关系，那么，后续终端检测到目标事件后，能够被唤醒，在语音指令对应的业务类型与历史业务的业务类型相同的情况下，响应于语音指令，来执行业务。
历史记录包括历史目标事件以及与历史目标事件关联执行的历史业务，该与历史目标事件关联执行的历史业务为检测到历史目标事件后之后执行的业务，可以为检测到历史目标事件之后第一次语音交互所执行的业务。例如，如果昨天检测到了对总开关触发的操作，之后第一次语音交互所执行的业务为导航到小区A，则历史记录可以包括对总开关触发的操作以及导航到小区A，则可以将对总开关触发的操作以及导航到小区A写入映射关系。那么，如果终端当前检测到了对总开关触发的操作，可以根据总开关的操作，查询映射关系，得到业务类型集合中的目标业务类型会包括导航。
可选地，终端可以将近期执行的历史业务的业务类型写入映射关系。具体地，终端可以根据当前时间点以及预设时长，获取历史时间段，根据历史记录，得到历史时间段内与历史目标事件关联执行的历史业务，将该历史业务的业务类型以及历史目标事件，写入该映射关系。其中，历史时间段可以为最近一天、最近一周、最近一月，具体地，历史时间段的结束点可以是当前时间点，预设时长可以是一天、一周等。通过这种方式，可以保证映射关系的时效性，让映射关系更能反映用户近期的行为习惯。
可选地，终端可以将高频执行的历史业务写入映射关系。具体地，终端可以根据历史记录，获取目标事件关联执行的每个历史业务的执行次数；终端可以从多个历史业务中选择执行次数最多的历史业务，将执行次数最多的历史业务的业务类型以及历史目标事件，写入映射关系。或者，终端可以选择执行次数超过次数阈值的历史业务，将执行次数超过次数阈值的历史业务对应的业务类型以及历史目标事件，写入映射关系。
通过实现方式一，由于同一用户的个人行为模式具有规律性，通常情况下，用户在当前发生目标事件后产生的语音交互意图，会在很大概率上与过去发生历史目标事件后产生的语音交互意图相同或相近，那么，当前发生目标事件后将要执行的业务，也就会在很大概率上与发生历史目标事件后关联执行的业务相同或相近，因此通过结合历史记录，来预测当前的语音交互意图针对的目标业务类型，可以提高目标业务类型的精确性。
实现方式二、终端调用机器学习模型，将样本目标事件输入该机器学习模型，输出业务类型，将输出的业务类型以及该样本目标事件写入该映射关系。
机器学习模型用于根据事件预测业务类型，例如，可以根据当前发生的事件，预测与事件关联执行的业务的业务类型。在一种可能的实现中，可以采用多个样本事件以及多个样本业务类型进行模型训练，得到该机器学习模型，其中，样本事件可以是样本用户的终端执行的事件，也可以是终端的历史记录中记录的事件。样本业务类型为与该样本事件关联执行的业务的业务类型。该机器学习模型可以而不限于是神经网络模型。
通过实现方式二，机器学习模型能够预先通过大量样本，学习出从事件到业务类型之间的映射关系，那么通过机器学习模型，可以根据当前的目标事件，准确预测出语音交互意图针对的目标业务类型，从而提高目标业务类型的精确性。
需要说明的一点是，映射关系可以由终端构建，也可以由终端之外的其他设备构建，再由其他设备将构建好的映射关系发送至终端，终端可以接收映射关系，从而得到映射关系。其中，其他设备可以而不限于图1所示的语音交互平台200。当然，终端也可以通过其他方 式得到映射关系，比如说，映射关系可以通过某一链接地址发布，终端可以访问该链接地址，从互联网下载映射关系，本实施例对终端如何得到映射关系的方式不做具体限定。
结合事件的具体模态，步骤402可以而不限于下述情况(1)至情况(4)中的一项或多项：
情况(1)终端根据该第一操作，查询该映射关系，得到该业务类型集合，该业务类型集合包括的目标业务类型为与一个或多个目标第二操作相对应的业务类型，该一个或多个目标第二操作为该第一操作相关联的连续性操作。
如果用户执行了第一操作，可以预测用户的语音交互意图为执行目标第二操作。因此，终端可以将目标第二操作相对应的业务类型作为目标业务类型。其中，一个第一操作可以对应于一个或多个目标第二操作。例如，如果用户对空调按钮触发了确认操作，通常来讲，用户对空调按钮触发确认操作之后紧接着会调节温度，则对空调按钮的确认操作为第一操作，调节温度为目标第二操作，调节温度对应的业务类型是空调，因此终端可以将空调获取为目标业务类型；又如，如果用户点击了音乐搜索选项，通常来讲，用户点击音乐搜索选项之后紧接着会填入歌曲名称，则点击音乐搜索选项为第一操作，填入歌曲名称为目标第二操作，填入歌曲名称对应的业务类型是音乐，因此终端可以将音乐获取为目标业务类型；又如，如果用户点击了故障显示选项，通常来讲，用户点击故障显示选项之后，紧接着会根据查看的故障信息，搜索故障解决方法或解决故障，则点击故障显示选项为第一操作，搜索故障解决方法或解决故障为目标第二操作，而搜索故障解决方法或解决故障对应的业务类型是故障、车辆控制或搜索，因此终端可以将故障、车辆控制或搜索获取为目标业务类型。
通常来讲，如果用户执行了任一操作，会连续性地执行下一个操作，因此会产生针对下一个操作对应的业务进行语音交互的意图，而通过这种方式，充分利用了操作具有连续性的规律，会将用户当前执行的操作，映射为具有一定概率将要执行的下一个操作对应的业务类型，从而可以在用户执行操作的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此保证了目标业务类型的准确性。
关于情况(1)下获取目标业务类型的具体过程，在一种可能的实现中，终端可以根据第一操作，查询第一映射关系，得到该业务类型集合。
情况(2)终端查询该映射关系，得到该业务类型集合，该业务类型集合包括的目标业务类型为与该通知消息对应的消息查看或消息处理。
示例性地，消息查看可以是通过推送该通知消息的应用程序，查看通知消息，比如说，如果通知消息为即时通信消息，则消息查看可以是通过即时通信应用，查看即时通信消息，如果通知消息为新闻推荐消息，则消息查看可以是通过新闻应用，查看新闻消息；或者，消息查看可以是播放通知消息、在屏幕中显示通知消息或投影出通知消息等；消息处理可以是为该通知消息进行搜索、对通知消息进行回复、对通知消息对应的故障进行处理。
通常来讲，如果终端接收到了通知消息，用户会具有查看消息或处理消息的需求，因此会产生查看消息或处理消息的语音交互意图，而通过这种方式，充分考虑了用户的查看消息或处理消息的需求，会将接收到通知消息这一目标事件，映射为消息查看或消息处理这两种目标业务类型，从而可以在接收到通知消息的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此保证了目标业务类型的准确性。
具体地，情况(2)可以包括下述情况(2.1)至情况(2.3)中的一项或多项。
情况(2.1)根据来电通知，查询该映射关系，得到该业务类型集合，该业务类型集合包括的目标业务类型为接听来电。
情况(2.2)根据短信或即时通信消息，查询该映射关系，得到该业务类型集合，该业务类型集合包括的目标业务类型为消息查看或消息回复。
例如，消息查看可以是将短信或即时通信消息从文字转换为语音，播放语音形式的短信或即时通信消息。例如，消息回复可以是根据短信或即时通信消息，获取短信或即时通信消息对应的答复信息，将答复信息发送至短信或即时通信消息的发送用户；或者，接收用户输入的答复信息，将答复信息发送至短信或即时通信消息的发送用户。
情况(2.3)根据告警消息，查询映射关系，得到该业务类型集合，该业务类型集合包括的目标业务类型为故障处理或信息查询。
故障处理可以是输出故障的处理方案、维修保养等。例如，如果告警消息为电量低的消息，则故障处理可以是里程查询、充电站。如果告警消息为电机故障消息，则故障处理可以是问答咨询、维修电机等。信息查询可以是查询故障的处理方案、查询故障源等。
通过上述情况(2.1)至情况(2.3)，为每种通知消息分别预测出了对应的目标业务类型，从而能够支持各种接收到通知消息的应用场景，扩展了应用范围。
关于情况(2)下获取目标业务类型的具体过程，在一种可能的实现中，终端可以根据通知消息，查询第二映射关系，得到一个或多个目标业务类型。
情况(3)根据该环境参数，查询该映射关系，得到该业务类型集合，该业务类型集合包括的目标业务类型为调节环境参数。
调节环境参数可以是通过空气净化器来降低粉尘浓度、通过加湿器来提高湿度、通过空调或车窗来调节温度、通过遮阳帘或车窗来调节光线强度、通过雨刷来调节雨量等。
通常来讲，环境会影响到用户的感知，用户会具有应对环境的需求，比如说，如果某种环境参数发生变化，用户会具有调节这种环境参数的需求，因此会产生调节环境参数的语音交互意图，而通过这种方式，充分考虑了用户应对环境的需求，会将环境参数满足第一条件这一目标事件，映射为调节环境参数这种目标业务类型，从而可以在环境参数满足第一条件的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此保证了目标业务类型的准确性。
关于情况(3)下获取目标业务类型的具体过程，在一种可能的实现中，终端可以根据环境参数，查询第三映射关系，得到一个或多个目标业务类型。
情况(4)根据该当前业务，查询该映射关系，得到该业务类型集合，该业务类型集合包括的目标业务类型为该当前业务的业务类型。
当前业务的业务类型可以而不限于是重新执行当前业务、停止执行当前业务或者对当前业务进行调整等，比如说，如果当前业务为播放音乐，当前业务的业务类型可以是播放其他音乐、重新播放音乐、停止播放音乐等。
通常来讲，当前业务的进度会影响到用户的感知，用户会具有应对当前业务的需求，比如说如果当前业务将要结束时，用户通常会想要重新执行当前业务、停止执行当前业务或者对当前业务进行调整，而通过这种方式，充分考虑了用户应对业务变化的需求，会将当前业务的进度满足第二条件这一目标事件，映射为当前业务的业务类型，从而可以在当前业务的进度满足第二条件的情况下，准确地预测出用户想要针对哪个业务类型进行语音交互，因此 保证了目标业务类型的准确性。
可选地，步骤402可以替换为：终端根据历史记录，得到与历史目标事件关联执行的历史业务，将该历史业务对应的业务类型，获取为目标业务类型。也即是，可以通过查询历史记录来得到目标业务类型，而无需根据历史记录来建立映射关系。
可选地，步骤402可以替换为：终端调用机器学习模型，将该目标事件输入该机器学习模型，输出该一个或多个目标业务类型，该机器学习模型用于根据目标事件预测目标业务类型。也即是，可以通过机器学习模型来得到目标业务类型，而无需根据机器学习模型来建立映射关系。
可选地，映射关系还可以包括每个目标业务类型的概率，步骤402可以替换为：终端根据该目标事件，查询该映射关系，得到该业务类型集合以及该业务类型集合中每个目标业务类型对应的概率。
概率表示将要执行对应目标业务类型的业务的可能性大小。概率越大，表示检测到对应事件后，将要执行对应目标业务类型的业务的可能性越大。例如，如果目标事件i、目标业务类型j、目标业务类型j对应的概率1、目标业务类型k、目标业务类型k对应的概率2之间具有映射关系，则该映射关系可以指明，如果确定检测到目标事件i发生，则预测将要执行目标业务类型j或者目标业务类型k的业务，将要执行目标业务类型j的业务的概率为概率1，将要执行目标业务类型k的业务的概率为概率2。其中，i为目标事件的标识，j和k为目标业务类型的标识。
示意性地，映射关系可以如下表6所示，其中，表6中的“/”表示无。基于表6，如果检测到对总开关的操作，可以获取业务类型集合为(导航、音乐、日程查询)，其中，导航对应的概率为0.6，音乐对应的概率为0.7，日程查询对应的概率为0.4。
表6
Figure PCTCN2020074988-appb-000006
Figure PCTCN2020074988-appb-000007
需要说明的一点是，表6所示的映射关系可以提供为多模态唤醒模型，该多模态唤醒模型的输入参数包括目标事件，该多模态唤醒模型的输出参数包括业务类型集合以及概率，该多模态唤醒模型可以用于根据检测到的目标事件对业务类型集合进行预测，用户可以在终端上运行该多模态唤醒模型，或者出售该多模态唤醒模型给第三方使用。
403、终端从该业务类型集合中，过滤掉概率不满足概率阈值的目标业务类型。
对于业务类型集合中的每个目标业务类型，终端可以对该目标业务类型对应的概率与概率阈值进行比较，如果目标业务类型对应的概率满足概率阈值，则终端会筛选出该目标业务类型，那么如果后续采集到的语音指令对应的第一业务的业务类型为该目标业务类型，会执行第一业务；如果目标业务类型对应的概率不满足概率阈值，则终端会过滤掉该目标业务类型，则后续不会执行该目标业务类型的业务。
在一种可能的实现中，可以为每个目标业务类型预先设置同一概率阈值，在终端中预先存储该概率阈值，则终端可以对每个目标业务类型与同一概率阈值进行比较。在另一种可能的实现中，可以为每个目标业务类型分别设置对应的概率阈值，向映射关系写入每个目标业务类型对应的概率阈值，则终端可以查询映射关系，得到每个目标业务类型对应的概率阈值，对每个目标业务类型与对应的概率阈值进行比较。其中，不同业务类型对应的概率阈值可以相同或不同，本实施例对此不做限定。
示例性地，映射关系可以包括下表7，如果业务类型集合为(导航，音乐，日程咨询)，根据上表6，得到导航对应的概率为0.6，音乐对应的概率为0.7，日程咨询对应的概率为0.4。根据表7，可以得到导航对应的概率阈值为0.5，音乐对应的概率阈值为0.5，日程咨询对应的概率阈值为0.5。对于导航来说，其概率0.6大于概率阈值0.5，对于音乐来说，其概率0.7大于概率阈值0.5，对于日程咨询来说，其概率0.4小于概率阈值0.5，因此会筛选出导航和音乐，而过滤掉日程咨询。
表7
目标业务类型 概率阈值
导航 0.5
音乐 0.5
电台 0.5
通讯 0.7
短信 0.7
微信 0.7
日程咨询 0.5
新闻 0.4
问答 0.4
空调 0.4
车控 0.8
系统 0.7
维修保养 0.5
如果目标业务类型的概率不满足概率阈值，表明该目标业务类型是用户的语音交互意图所针对的业务类型的可能性较小，如果后续处理该目标业务类型的业务，会导致误唤醒的概率较大，而如果误唤醒，会对用户产生干扰，并造成终端的负荷过大，因此通过过滤掉该目标业务类型，则后续不会响应于语义信息为该目标业务类型的业务的语音指令，从而降低误唤醒的概率，进而避免由于误唤醒而对用户产生的干扰以及对终端造成的负荷。
需要说明的一点是，步骤403为可选步骤，而非必选步骤。在一些可能的实施例中，也可以获取到一个或多个目标业务类型后，就根据获取到的所有目标业务类型执行下述步骤。
404、终端采集语音指令。
在一些可能的实施例中，终端可以当确定检测到目标事件发生时，启动监听，当经过监听时长时，结束监听。在监听期间，如果用户发出语音，终端可以通过麦克风，采集得到语音指令。其中，启动监听至结束监听的时间段可以称为接收窗口，监听时长可以根据实验、经验或需求设置，可以预先存储在终端中。可选地，可以为各个业务类型设置同一监听时长，也可以为不同业务类型设置不同的监听时长，在终端中存储业务类型与监听时长之间的映射关系，本实施例对此不做限定。
405、终端根据语音指令对应的语义信息，得到语义信息对应的第一业务。
在一些可能的实施例中，终端可以对语音指令进行语音识别(automatic speech recognition，ASR)，得到文本信息；对文本信息进行语义识别，得到语义信息；根据语义信息，查询得到第一业务。例如，如果语义信息为“小华，帮忙规划下到XX小区YY号楼的路线”，则第一 业务为“导航到XX小区YY号楼”，如果语义信息为“小华，帮忙放首ZZ歌曲”，则第一业务为“播放ZZ歌曲”。
406、如果该第一业务的业务类型为该业务类型集合中的任一目标业务类型，终端根据该语音指令执行该第一业务。
终端可以对第一业务的业务类型与业务类型集合中每个目标业务类型进行比较，如果第一业务的业务类型与任一目标业务类型相同，表明用户语音表达的业务类型处于预测的业务类型的范围之内，终端对业务类型预测正确，用户的确具有语音交互的意图，则唤醒成功，终端会激活语音交互功能，响应于语音指令，根据语音指令执行该第一业务，也即是，执行语音指令所表达的业务。示例性地，如果业务类型集合为(导航，音乐)，第一业务为“导航到XX小区YY号楼”，则第一业务的业务类型为导航，第一业务的业务类型与业务类型集合中的目标业务类型导航相同，则终端会导航到XX小区YY号楼。
407、如果该第一业务的业务类型与该业务类型集合中的每个目标业务类型均不同，终端丢弃该语音指令。
如果业务类型集合中不包括第一业务的业务类型，表明用户语音表达的业务类型处于预测的业务类型的范围之外，终端对业务类型预测不正确，用户并没有语音交互的意图，终端可以不响应语音指令，而是丢弃语音指令，从而避免根据语音指令进行业务处理会造成的误唤醒，并且节省语音指令占据的缓存空间。例如，如果业务类型集合为(导航，音乐)，而第一业务为“打开空调”，则第一业务的业务类型为空调，第一业务的业务类型与业务类型集合中的每个目标业务类型均不同，则终端不会响应语音指令，即，不会打开空调。
另外，终端可以在检测到目标事件发生时开始计时，如果记录的时长达到预设时长，而终端未接收到语音指令，则终端会退出监听。
需要说明的一点是，步骤407为可选步骤，而非必选步骤。
408、终端根据该语音指令对应的语义信息，更新该映射关系中的概率。
通过这种可选方式，每当目标事件发生时，可以根据用户本次表达的语义信息，对概率进行动态地调整，从而以自学习(self-learning)的方式，通过评估已预测的目标业务类型的正确性，通过迭代来不断修正概率，令映射关系可以随着目标事件的发生以及用户表达的语义，得到不断优化，逐渐更趋近于用户个人的行为习惯，保证映射关系更加精确。
具体来讲，更新方式可以包括下述方式(1)至方式(3)中的一项或多项。
方式(1)如果该第一业务的业务类型为该业务类型集合中的任一目标业务类型，增加该映射关系中该第一业务的业务类型对应的概率。
示例性地，如果确定检测到对总开关的操作后，业务类型集合为(导航，音乐)，而第一业务的业务类型为导航，则终端会增加导航对应的概率。
如果每次检测到目标事件X时，用户总是通过语音要求执行目标业务类型Y的业务，表明目标业务类型Y恰好是发生目标事件X后，用户具有语音交互意图的业务类型，那么通过这种可选方式，目标业务类型Y的概率会不断增长，因此后续再次检测到该目标事件时，目标业务类型Y的概率会满足概率阈值，使得目标业务类型Y会被筛选出来，那么如果语音指令对应的语义信息对应的第一业务为目标业务类型Y的业务，终端会响应语音指令，执行该目标业务类型Y的业务。
需要说明的是，如果该第一业务的业务类型与该业务类型集合中的每个目标业务类型均 不同，终端可以向该映射关系中，写入该第一业务的业务类型。具体地，如果映射关系中不包含目标事件，或者，映射关系中不包含第一业务的业务类型，或者，映射关系中目标事件并没有与第一业务的业务类型相互对应，则在这三种情况中的任一种情况下，终端可以向映射关系中，写入目标事件与第一业务的业务类型，以使映射关系中新增出该目标事件与第一业务的业务类型。
通过这种可选方式，下一次检测到目标事件时，可以查询该映射关系，得到第一业务的业务类型，将该第一业务的业务类型获取为目标业务类型。如此，如果终端在历史运行过程中，每当检测到事件X，用户通过语音表达出对业务类型Y进行语音交互的意图，通过向映射关系中写入事件X与业务类型Y，映射关系会新增事件X与业务类型Y，那么，一方面，可以随着语音交互过程的执行，挖掘出事件和业务类型之间的关联性，补充和完善映射关系。另一方面，终端可以随着业务的扩展，向映射关系补入新增的事件和新增的业务类型，提高映射关系的可扩展性和时效性。
此外，可选地，可以生成第一业务的业务类型对应的概率，向映射关系写入生成的概率。具体地，可以根据检测到目标事件的次数、语音指令的语义信息表示第一业务的业务类型的次数，确定概率，比如说，如果检测到A次目标事件，语义信息有B次表示第一业务的业务类型，可以获取A与B之间的比值，作为概率。例如，如果检测到10次事件X发生后，用户有7次通过语音表达出对业务类型Y进行语音交互的意图，可以获取业务类型Y对应的概率＝7/10＝0.7，则向映射关系写入业务类型Y以及概率0.7。当然，也可以将默认概率作为第一业务的业务类型对应的概率，向映射关系写入第一业务的业务类型以及默认概率，后续通过执行步骤408所示的过程，对默认概率进行调整。
方式(2)如果第一业务的业务类型与该业务类型集合中的每个目标业务类型均不同，减少该映射关系中该业务类型集合中的每个目标业务类型对应的概率。
示例性地，如果确定检测到对总开关的操作后，业务类型集合为(导航，音乐)，而第一业务的业务类型为空调，则终端会减少导航以及音乐对应的概率。
如果目标事件X与目标业务类型Y对应，而每次检测到目标事件X时，用户都没有通过语音要求执行目标业务类型Y的业务，表明目标业务类型Y并不是发生目标事件X后，用户具有语音交互意图的业务类型，那么通过这种可选方式，则目标业务类型Y的概率会不断减少，因此后续再次检测到该目标事件X时，目标业务类型Y的概率会不满足概率阈值，使得目标业务类型Y会被过滤掉，则终端不会处理目标业务类型Y的业务，从而避免误唤醒。
方式(3)如果该语义信息包含唤醒词，增加该映射关系中该第一业务的业务类型对应的概率。
示例性地，如果确定检测到对总开关的操作后，语义信息为“你好小华，导航到目的地某小区某号楼”，则终端会增加导航对应的概率。
如果目标事件X与目标业务类型Y对应，而每次检测到目标事件X时，用户都说出唤醒词，表明目标业务类型Y恰好是发生目标事件X后，用户具有语音交互意图的业务类型，那么通过这种可选方式，目标业务类型Y的概率会不断增长，因此后续再次检测到该目标事件时，目标业务类型Y的概率会满足概率阈值，使得目标业务类型Y会被筛选出来，那么如果语音指令表达出目标业务类型Y的语义信息，终端会响应于语音指令处理业务。
需要说明的一点是，步骤408为可选步骤，而非必选步骤。
本实施例提供了一种免唤醒词触发语音交互的方法，根据能够触发语音交互的目标事件，来预测用户具有语音交互意图的业务类型集合，如果语音指令表达的第一业务的业务类型为预测出的目标业务类型，则执行第一业务。通过免去了语音交互过程中用户需要频繁说出唤醒词的繁琐操作，从而解决了频繁说出唤醒词造成语音交互效率过低的问题，让操作更加便捷，并且让语音交互的流程更加自然和拟人化，从而提高了语音交互的用户体验。此外，目标事件涵盖了多个模态，任意模态的目标事件均能够触发对应业务类型的语音交互功能，从而在多种应用场景下，均可以支持免唤醒词的唤醒功能，扩展了应用范围。
结合上述方法实施例，以下示例性介绍本申请的一种具体的软件架构。
图5是本申请实施例提供的一种语音交互系统的软件架构图，该系统包括以下功能模块，每个模块可以为软件模块。
语音活动检测(voice activity detection,VAD)模块或前端语音(front-end speech)模块：用于采集音频信号，对采集到的音频信号进行降噪处理以及增强处理，并检测音频信号是否是语音指令还是非语音指令，如果音频信号是语音指令，则将语音指令输入至ASR模块，其中非语音指令可以是噪声信号、音乐信号等。
语音识别(automatic speech recognition,ASR)模块：用于从VAD模块或前端语音模块接收语音指令，将语音指令转换成文本信息，将文本信息输入对话理解模块或对话管理模块。
多模态检测模块：用于对目标事件进行检测，如果检测到目标事件，将目标事件输入用户意图预测模块。例如，多模态检测模块可以接收操作系统或者应用程序推送的通知消息，如：短信、来电、应用程序的推荐消息，告警消息；或者，用于检测一个或多个模态的操作：如对物理按键或界面的操作、语音指令；或者，用于检测环境变化或者业务变化，如：温度下降，空气污染超标，音乐即将结束等。
用户意图预测模块：用于从多模态检测模块接收目标事件，考虑用户操作连续性规则、用户查看、处理或应答的需求、环境或业务对用户感知的影响，预测用户语音交互的意图，输出业务类型集合以及业务类型集合中每个目标业务类型对应的概率。
对话理解(spoken language understanding，SLU)模块或对话管理(dialog management，DM)模块：用于根据语音识别模块的文本信息，识别用户意图，把用户意图转换成系统操作，并根据对话的上下文状态，获取对话的回复内容，将回复内容输出至答复生成模块或语音合成模块。
历史数据学习:基于用户的历史操作数据，对用户意图预测模块中的数据进行迭代更新。
答复生成(response generator，RG)模块/语音合成(text to speech，TTS)模块：用于从对话管理模块接收到的回复内容转换成文字信息，输出文字信息，或者将回复内容转换为语音指令，播放语音。
结合图5所示的系统架构，以终端为车载终端为例，该车载终端可以通过硬件和软件的结合实现，该车载终端的结构可以如图6所示，包括：
处理器(CPU)：用于访问内存或其它存储器上的各个功能模块，运行各个功能模块，另外还可以通过数据总线(D-BUS)，访问存储器和音频管理器。此外，处理器可以通过网络接口访问各种云服务以及云服务管理模块。处理器还可以通过网关访问控制器局域网络(英文： Controller Area Network，简称：CAN)总线，读取车辆以及车辆所载的各种设备的数据，以及控制车辆以及车辆所载的各种设备。
存储器包括内存和磁盘存储器，存储的内容包括图5所示的各个功能模块。
音频管理器用于对车载扬声器、麦克阵列或者其他音频设备进行管理。
以上介绍了本申请实施例的语音交互方法，以下介绍本申请实施例提供的语音交互装置，应理解，该语音交互装置具有上述语音交互方法中终端的任意功能。
图7是本申请实施例提供的一种语音交互装置的结构示意图，如图7所示，该装置包括：
确定模块701，用于执行步骤401；查询模块702，用于执行步骤402；采集模块703，用于执行步骤404；获取模块704，还用于执行步骤405；处理模块705，用于执行步骤406。
可选地，该确定模块701，用于确定检测到用户的第一操作；该查询模块702，用于执行步骤402中的情况(1)。
可选地，该确定模块701，用于从操作系统或应用程序接收通知消息；该查询模块702，用于执行步骤402中的情况(2)。
可选地，该确定模块701，用于确定当前的环境参数满足第一条件；该查询模块702，用于执行步骤402中的情况(3)。
可选地，该确定模块701，用于确定当前业务的进度满足第二条件；该查询模块702，用于执行步骤402中的情况(4)。
可选地，该装置还包括：写入模块，用于如果该第一业务的业务类型与该业务类型集合中的每个目标业务类型均不同，向该映射关系中，写入该第一业务的业务类型。
可选地，该查询模块702，还用于根据该目标事件，查询该映射关系，得到该业务类型集合以及该业务类型集合中每个目标业务类型对应的概率；
该装置还包括：过滤模块，用于执行步骤408。
可选地，该装置还包括：更新模块，用于执行步骤408。
可选地，更新模块，具体用于执行步骤408中方式(1)至方式(3)中的一项或多项。
可选地，该装置还包括：丢弃模块，用于执行步骤407。
需要说明的是：上述实施例提供的语音交互装置在语音交互时，仅以上述各功能模块的划分进行举例说明，实际应用中，可以根据需要而将上述功能分配由不同的功能模块完成，即将终端的内部结构划分成不同的功能模块，以完成以上描述的全部或者部分功能。另外，上述实施例提供的语音交互装置与语音交互方法实施例属于同一构思，其具体实现过程详见方法实施例，这里不再赘述。
上述所有可选技术方案，可以采用任意结合形成本申请的可选实施例，在此不再一一赘述。
在示例性实施例中，还提供了一种计算机可读存储介质，例如包括指令的存储器，上述指令可由终端的处理器执行以完成上述各个实施例中的语音交互方法。该计算机可读存储介质可以是非暂态的。例如，该计算机可读存储介质可以是只读存储器(Read-Only Memory，简称：ROM)、随机存取存储器(Random Access Memory，简称：RAM)、只读光盘(Compact Disc Read-Only Memory，简称：CD-ROM)、磁带、软盘和光数据存储设备等。
在示例性实施例中，还提供一种计算机程序产品，该计算机程序产品包括：计算机程序 代码，当该计算机程序代码被终端运行时，使得该终端执行上述各个实施例中的语音交互方法。
在示例性实施例中，提供一种芯片，包括处理器，用于从存储器中调用并运行该存储器中存储的指令，使得安装有该芯片的设备执行上述各个实施例中的语音交互方法。
在示例性实施例中，提供另一种芯片，包括：输入接口、输出接口、处理器和存储器，该输入接口、输出接口、该处理器以及该存储器之间通过内部连接通路相连，该处理器用于执行该存储器中的代码，当该代码被执行时，该处理器用于执行上述各个实施例中的语音交互方法。
在上述实施例中，可以全部或部分地通过软件、硬件、固件或者其任意组合来实现。当使用软件实现时，可以全部或部分地以计算机程序产品的形式实现。该计算机程序产品包括一个或多个计算机程序指令。在计算机上加载和执行该计算机程序指令时，全部或部分地产生按照本申请实施例该的流程或功能。该计算机可以是通用计算机、专用计算机、计算机网络、或者其他可编程装置。该计算机指令可以存储在计算机可读存储介质中，或者从一个计算机可读存储介质向另一个计算机可读存储介质传输，例如，该计算机程序指令可以从一个网站站点、计算机、服务器或数据中心通过有线或无线方式向另一个网站站点、计算机、服务器或数据中心进行传输。该计算机可读存储介质可以是计算机能够存取的任何可用介质或者是包含一个或多个可用介质集成的服务器、数据中心等数据存储设备。该可用介质可以是磁性介质(例如软盘、硬盘、磁带)、光介质(例如，数字视频光盘(digital video disc，DVD)、或者半导体介质(例如固态硬盘)等。
本申请中术语“和/或”，仅仅是一种描述关联对象的关联关系，表示可以存在三种关系，例如，A和/或B，可以表示：单独存在A，同时存在A和B，单独存在B这三种情况。另外，本申请中的字符“/”，一般表示前后关联对象是一种“或”的关系。
本申请中术语“多个”的含义是指两个或两个以上，例如，多个数据包是指两个或两个以上的数据包。
本申请中术语“第一”“第二”等字样用于对作用和功能基本相同的相同项或相似项进行区分，本领域技术人员可以理解，“第一”“第二”等字样不对数量和执行顺序进行限定。
本领域普通技术人员可以理解实现上述实施例的全部或部分步骤可以通过硬件来完成，也可以通过程序来指令相关的硬件完成，该的程序可以存储于一种计算机可读存储介质中，上述提到的存储介质可以是只读存储器，磁盘或光盘等。
以上该仅为本申请的可选实施例，并不用以限制本申请，凡在本申请的精神和原则之内，所作的任何修改、等同替换、改进等，均应包含在本申请的保护范围之内。

Claims (26)

  1. 一种语音交互方法，其特征在于，所述方法包括：
    确定检测到目标事件发生，所述目标事件为能够触发语音交互的事件；
    根据所述目标事件，查询映射关系，得到业务类型集合，所述业务类型集合包括一个或多个目标业务类型；
    采集语音指令；
    根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务；
    如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，根据所述语音指令执行所述第一业务。
  2. 根据权利要求1所述的方法，其特征在于，
    所述确定检测到目标事件发生，包括：确定检测到用户的第一操作；
    所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述第一操作，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为与一个或多个目标第二操作相对应的业务类型，所述一个或多个目标第二操作为所述第一操作相关联的连续性操作。
  3. 根据权利要求1所述的方法，其特征在于，
    所述确定检测到目标事件发生，包括：从操作系统或应用程序接收通知消息；
    所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：
    根据所述通知消息，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为与所述通知消息对应的消息查看或消息处理。
  4. 根据权利要求3所述的方法，其特征在于，所述通知消息包括来电通知、短信、即时通信消息以及告警消息中的至少一项，所述根据所述通知消息，查询所述映射关系，得到所述业务类型集合，包括下述至少一项：
    根据来电通知，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为接听来电；
    根据短信或即时通信消息，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为消息查看或消息回复；
    根据告警消息，查询映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为故障处理或信息查询。
  5. 根据权利要求1所述的方法，其特征在于，
    所述确定检测到目标事件发生，包括：确定当前的环境参数满足第一条件；
    所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述环境参数，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为调节 环境参数。
  6. 根据权利要求1所述的方法，其特征在于，
    所述确定检测到目标事件发生，包括：确定当前业务的进度满足第二条件；
    所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述当前业务，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为所述当前业务的业务类型。
  7. 根据权利要求1至6中任一项所述的方法，其特征在于，所述映射关系的建立过程包括：
    根据历史记录，得到与历史目标事件关联执行的历史业务，将所述历史业务的业务类型以及所述历史目标事件，写入所述映射关系；
    调用机器学习模型，将样本目标事件输入所述机器学习模型，输出业务类型，将输出的业务类型以及所述样本目标事件写入所述映射关系，所述机器学习模型用于根据事件预测业务类型。
  8. 根据权利要求1所述的方法，其特征在于，所述根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务之后，所述方法还包括：
    如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，向所述映射关系中，写入所述第一业务的业务类型。
  9. 根据权利要求1至8中任一项所述的方法，其特征在于，
    所述根据所述目标事件，查询映射关系，得到业务类型集合，包括：根据所述目标事件，查询所述映射关系，得到所述业务类型集合以及所述业务类型集合中每个目标业务类型对应的概率，概率表示将要执行对应目标业务类型的业务的可能性大小；
    所述如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，根据所述语音指令执行所述第一业务之前，所述方法还包括：从所述业务类型集合中，过滤掉概率不满足概率阈值的目标业务类型。
  10. 根据权利要求9所述的方法，其特征在于，所述根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务之后，所述方法还包括：
    根据所述语音指令对应的语义信息，更新所述映射关系中的概率。
  11. 根据权利要求10所述的方法，其特征在于，所述根据所述语音指令对应的语义信息，更新所述映射关系中的概率，包括下述任一项：
    如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，增加所述映射关系中所述第一业务的业务类型对应的概率；
    如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，减少所述映射关系中所述业务类型集合中的每个目标业务类型对应的概率；
    如果所述语义信息包含唤醒词，增加所述映射关系中所述第一业务的业务类型对应的概率。
  12. 根据权利要求1至11中任一项所述的方法，其特征在于，所述根据所述语音指令对应的语义信息，得到所述语义信息对应的第一业务之后，所述方法还包括：
    如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，丢弃所述语音指令。
  13. 一种语音交互装置，其特征在于，所述装置包括：
    确定模块，用于确定检测到目标事件发生，所述目标事件为能够触发语音交互的事件；
    查询模块，用于根据所述目标事件，查询映射关系，得到业务类型集合，所述业务类型集合包括一个或多个目标业务类型；
    采集模块，用于采集语音指令；
    获取模块，还用于根据所述语音指令对应的语义信息，得到所述语义信息对应的业务类型；
    业务执行模块，用于如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，根据所述语音指令执行所述第一业务。
  14. 根据权利要求13所述的装置，其特征在于，
    所述确定模块，用于确定检测到用户的第一操作；
    所述查询模块，用于根据所述第一操作，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为与一个或多个目标第二操作相对应的业务类型，所述一个或多个目标第二操作为所述第一操作相关联的连续性操作。
  15. 根据权利要求13所述的装置，其特征在于，
    所述确定模块，用于从操作系统或应用程序接收通知消息；
    所述查询模块，用于根据所述通知消息，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为与所述通知消息对应的消息查看或消息处理。
  16. 根据权利要求15所述的装置，其特征在于，所述通知消息包括来电通知、短信、即时通信消息以及告警消息中的至少一项，所述查询模块，用于执行下述至少一项：
    根据来电通知，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为接听来电；
    根据短信或即时通信消息，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为消息查看或消息回复；
    根据告警消息，查询映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为故障处理或信息查询。
  17. 根据权利要求13所述的装置，其特征在于，
    所述确定模块，用于确定当前的环境参数满足第一条件；
    所述查询模块，用于根据所述环境参数，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为调节环境参数。
  18. 根据权利要求13所述的装置，其特征在于，
    所述确定模块，用于确定当前业务的进度满足第二条件；
    所述查询模块，用于根据所述当前业务，查询所述映射关系，得到所述业务类型集合，所述业务类型集合包括的目标业务类型为所述当前业务的业务类型。
  19. 根据权利要求13至18中任一项所述的装置，其特征在于，所述映射关系的建立过程包括：
    根据历史记录，得到与历史目标事件关联执行的历史业务，将所述历史业务的业务类型以及所述历史目标事件，写入所述映射关系；
    调用机器学习模型，将样本目标事件输入所述机器学习模型，输出业务类型，将输出的业务类型以及所述样本目标事件写入所述映射关系，所述机器学习模型用于根据事件预测业务类型。
  20. 根据权利要求13所述的装置，其特征在于，所述装置还包括：
    写入模块，用于如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，向所述映射关系中，写入所述第一业务的业务类型。
  21. 根据权利要求13至20中任一项所述的装置，其特征在于，所述查询模块，还用于根据所述目标事件，查询所述映射关系，得到所述业务类型集合以及所述业务类型集合中每个目标业务类型对应的概率，概率表示将要执行对应目标业务类型的业务的可能性大小；
    所述装置还包括：过滤模块，用于从所述一个或多个目标业务类型中，过滤掉概率不满足概率阈值的目标业务类型。
  22. 根据权利要求21所述的装置，其特征在于，所述装置还包括：
    更新模块，用于根据所述语音指令对应的语义信息，更新所述映射关系中的概率。
  23. 根据权利要求22所述的装置，其特征在于，所述更新模块，用于执行下述任一项：
    如果所述第一业务的业务类型为所述业务类型集合中的任一目标业务类型，增加所述映射关系中所述第一业务的业务类型对应的概率；
    如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，减少所述映射关系中所述业务类型集合中的每个目标业务类型对应的概率；
    如果所述语义信息包含唤醒词，增加所述映射关系中所述第一业务的业务类型对应的概率。
  24. 根据权利要求13至23中任一项所述的装置，其特征在于，所述装置还包括：
    丢弃模块，用于如果所述第一业务的业务类型与所述业务类型集合中的每个目标业务类型均不同，丢弃所述语音指令。
  25. 一种终端，其特征在于，所述终端包括一个或多个处理器和一个或多个存储器，所述一个或多个存储器中存储有至少一条指令，所述指令由所述一个或多个处理器加载并执行以实现如权利要求1至权利要求12任一项所述的语音交互方法。
  26. 一种计算机可读存储介质，其特征在于，所述存储介质中存储有至少一条指令，所述指令由处理器加载并执行以实现如权利要求1至权利要求12任一项所述的语音交互方法。
PCT/CN2020/074988 2019-08-15 2020-02-13 语音交互方法、装置、终端及存储介质 Ceased WO2021027267A1 (zh)

Priority Applications (4)

Application Number Priority Date Filing Date Title
JP2021569122A JP7324313B2 (ja) 2019-08-15 2020-02-13 音声対話方法及び装置、端末、並びに記憶媒体
EP20803428.0A EP3933830B1 (en) 2019-08-15 2020-02-13 Speech interaction method and apparatus, terminal and storage medium
EP25184716.6A EP4664269A3 (en) 2019-08-15 2020-02-13 Voice interaction method and apparatus, terminal, and storage medium
US17/179,764 US11922935B2 (en) 2019-08-15 2021-02-19 Voice interaction method and apparatus, terminal, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910755150.6 2019-08-15
CN201910755150.6A CN112397062B (zh) 2019-08-15 2019-08-15 语音交互方法、装置、终端及存储介质

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US17/179,764 Continuation US11922935B2 (en) 2019-08-15 2021-02-19 Voice interaction method and apparatus, terminal, and storage medium

Publications (1)

Publication Number Publication Date
WO2021027267A1 true WO2021027267A1 (zh) 2021-02-18

Family

ID=74569776

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2020/074988 Ceased WO2021027267A1 (zh) 2019-08-15 2020-02-13 语音交互方法、装置、终端及存储介质

Country Status (5)

Country Link
US (1) US11922935B2 (zh)
EP (2) EP3933830B1 (zh)
JP (1) JP7324313B2 (zh)
CN (2) CN119296533A (zh)
WO (1) WO2021027267A1 (zh)

Cited By (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113364669A (zh) * 2021-06-02 2021-09-07 中国工商银行股份有限公司 消息处理方法、装置、电子设备及介质
CN113739382A (zh) * 2021-08-12 2021-12-03 武汉慧联无限科技有限公司 空调控制方法及装置、控制设备和存储介质
WO2023273321A1 (zh) * 2021-06-29 2023-01-05 荣耀终端有限公司 一种语音控制方法及电子设备
CN115691492A (zh) * 2022-10-29 2023-02-03 重庆长安汽车股份有限公司 一种车载语音控制系统及方法
WO2023040692A1 (zh) * 2021-09-14 2023-03-23 北京车和家信息技术有限公司 语音控制方法、装置、设备及介质
US11960914B2 (en) * 2021-11-19 2024-04-16 Samsung Electronics Co., Ltd. Methods and systems for suggesting an enhanced multimodal interaction
JP2024540681A (ja) * 2021-11-30 2024-10-31 華為技術有限公司 デバイス制御方法および装置
TWI918023B (zh) 2023-07-17 2026-03-11 美商博姆雲360公司 自適應及智慧提示系統及控制介面

Families Citing this family (24)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP7338489B2 (ja) * 2020-01-23 2023-09-05 トヨタ自動車株式会社 音声信号制御装置、音声信号制御システム及び音声信号制御プログラム
CN111667831B (zh) * 2020-06-08 2022-04-26 中国民航大学 基于管制员指令语义识别的飞机地面引导系统及方法
CN114765027A (zh) * 2021-01-15 2022-07-19 沃尔沃汽车公司 用于车辆语音控制的控制设备、车载系统和方法
CN116868158A (zh) * 2021-03-18 2023-10-10 深圳传音控股股份有限公司 智能交互方法、终端及存储介质
CN113099054A (zh) * 2021-03-30 2021-07-09 中国建设银行股份有限公司 语音交互的方法、装置、设备和计算机可读介质
CN113282355B (zh) * 2021-05-18 2025-03-04 Oppo广东移动通信有限公司 基于状态机的指令执行方法、装置、终端及存储介质
CN113609266B (zh) * 2021-07-09 2024-07-16 阿里巴巴创新公司 资源处理方法以及装置
CN115705844B (zh) * 2021-08-12 2025-11-25 上海擎感智能科技有限公司 语音交互配置方法、电子设备和计算机可读介质
CN113752966B (zh) * 2021-09-14 2022-12-23 合众新能源汽车有限公司 车机系统的交互方法、装置和计算机可读介质
CN116126509A (zh) * 2021-11-12 2023-05-16 华为技术有限公司 基于多设备提供服务的方法、相关装置及系统
CN114281967A (zh) * 2021-12-17 2022-04-05 深圳市欧瑞博科技股份有限公司 人机对话的智能处理方法、装置、电子设备及存储介质
CN116415061A (zh) * 2021-12-30 2023-07-11 华为技术有限公司 一种服务推荐方法及相关装置
CN114783434A (zh) * 2022-04-18 2022-07-22 国汽智控(北京)科技有限公司 人机交互系统及交互方法
KR20230150499A (ko) * 2022-04-22 2023-10-31 에스케이텔레콤 주식회사 사용자 의도의 매핑을 이용하는 대화시스템
CN115150507A (zh) * 2022-05-07 2022-10-04 Oppo广东移动通信有限公司 服务调度方法及系统、电子设备及计算机可读存储介质
US20240013776A1 (en) * 2022-07-11 2024-01-11 GM Global Technology Operations LLC System and method for scenario context-aware voice assistant auto-activation
CN117690423A (zh) * 2022-09-05 2024-03-12 华为技术有限公司 人机交互方法及相关装置
CN115531858B (zh) * 2022-11-16 2023-04-18 北京集度科技有限公司 一种交互方法、终端设备以及车辆
CN117922455A (zh) * 2023-03-20 2024-04-26 小米汽车科技有限公司 联动系统、方法、车辆、存储介质与芯片
CN118734796A (zh) * 2023-03-31 2024-10-01 北京罗克维尔斯科技有限公司 车辆控制方法、装置、设备及存储介质
CN116682427A (zh) * 2023-06-15 2023-09-01 一汽奔腾轿车有限公司 一种免唤醒车载语音交互系统
CN119232837A (zh) * 2023-06-29 2024-12-31 荣耀终端有限公司 语音控制方法、设备及存储介质
CN119785276B (zh) * 2025-03-12 2025-05-09 中科南京软件技术研究院 基于多模态大模型在人机协同环境中的意图理解方法
CN119865719A (zh) * 2025-03-25 2025-04-22 深圳三基同创电子有限公司 一种智能穿戴设备对讲功能的实现方法及系统

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030220793A1 (en) * 2002-03-06 2003-11-27 Canon Kabushiki Kaisha Interactive system and method of controlling same
EP1887482A1 (en) * 2006-08-08 2008-02-13 Accenture Global Services GmbH Mobile audio content delivery system
CN107293294A (zh) * 2016-03-31 2017-10-24 腾讯科技（深圳）有限公司 一种语音识别处理方法及装置
CN107424601A (zh) * 2017-09-11 2017-12-01 深圳怡化电脑股份有限公司 一种基于语音识别的信息交互系统、方法及其装置
CN107437416A (zh) * 2017-05-23 2017-12-05 阿里巴巴集团控股有限公司 一种基于语音识别的咨询业务处理方法及装置
CN109243450A (zh) * 2018-10-18 2019-01-18 深圳供电局有限公司 一种交互式的语音识别方法及系统
CN109473100A (zh) * 2018-11-12 2019-03-15 四川驹马科技有限公司 基于语音识别的业务场景语音人机交互方法及其系统

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP3963698B2 (ja) * 2001-10-23 2007-08-22 富士通テン株式会社 音声対話システム
JP4802522B2 (ja) * 2005-03-10 2011-10-26 日産自動車株式会社 音声入力装置および音声入力方法
BR102012024861B1 (pt) * 2011-09-30 2021-02-09 Apple Inc. sistema para desambiguar entrada de usuário para realizar uma tarefa
US11386886B2 (en) * 2014-01-28 2022-07-12 Lenovo (Singapore) Pte. Ltd. Adjusting speech recognition using contextual information
DE112014006614B4 (de) * 2014-04-22 2018-04-12 Mitsubishi Electric Corporation Benutzerschnittstellensystem, Benutzerschnittstellensteuereinrichtung, Benutzerschnittstellensteuerverfahren und Benutzerschnittstellensteuerprogramm
US20180039478A1 (en) * 2016-08-02 2018-02-08 Google Inc. Voice interaction services
CN107316643B (zh) * 2017-07-04 2021-08-17 科大讯飞股份有限公司 语音交互方法及装置
KR102428148B1 (ko) * 2017-08-31 2022-08-02 삼성전자주식회사 가전 기기의 음성 인식을 위한 시스템과 서버, 방법
CN109753264A (zh) * 2017-11-08 2019-05-14 阿里巴巴集团控股有限公司 一种任务处理方法和设备
US10636424B2 (en) * 2017-11-30 2020-04-28 Apple Inc. Multi-turn canned dialog
JP2019105868A (ja) * 2017-12-08 2019-06-27 エヌ・ティ・ティ・コムウェア株式会社 入力支援装置、入力支援方法、及びプログラム
US10051600B1 (en) * 2017-12-12 2018-08-14 Amazon Technologies, Inc. Selective notification delivery based on user presence detections
CN108337362A (zh) * 2017-12-26 2018-07-27 百度在线网络技术（北京）有限公司 语音交互方法、装置、设备和存储介质
CN108320742B (zh) * 2018-01-31 2021-09-14 广东美的制冷设备有限公司 语音交互方法、智能设备及存储介质
CN108597519B (zh) * 2018-04-04 2020-12-29 百度在线网络技术（北京）有限公司 一种话单分类方法、装置、服务器和存储介质
CN108694947B (zh) * 2018-06-27 2020-06-19 Oppo广东移动通信有限公司 语音控制方法、装置、存储介质及电子设备
CN109545206B (zh) 2018-10-29 2024-01-30 百度在线网络技术（北京）有限公司 智能设备的语音交互处理方法、装置和智能设备
CN109326289B (zh) * 2018-11-30 2021-10-22 深圳创维数字技术有限公司 免唤醒语音交互方法、装置、设备及存储介质
CN109285547B (zh) * 2018-12-04 2020-05-01 北京蓦然认知科技有限公司 一种语音唤醒方法、装置及系统
CN109671435B (zh) * 2019-02-21 2020-12-25 三星电子（中国）研发中心 用于唤醒智能设备的方法和装置

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20030220793A1 (en) * 2002-03-06 2003-11-27 Canon Kabushiki Kaisha Interactive system and method of controlling same
EP1887482A1 (en) * 2006-08-08 2008-02-13 Accenture Global Services GmbH Mobile audio content delivery system
CN107293294A (zh) * 2016-03-31 2017-10-24 腾讯科技（深圳）有限公司 一种语音识别处理方法及装置
CN107437416A (zh) * 2017-05-23 2017-12-05 阿里巴巴集团控股有限公司 一种基于语音识别的咨询业务处理方法及装置
CN107424601A (zh) * 2017-09-11 2017-12-01 深圳怡化电脑股份有限公司 一种基于语音识别的信息交互系统、方法及其装置
CN109243450A (zh) * 2018-10-18 2019-01-18 深圳供电局有限公司 一种交互式的语音识别方法及系统
CN109473100A (zh) * 2018-11-12 2019-03-15 四川驹马科技有限公司 基于语音识别的业务场景语音人机交互方法及其系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3933830A4

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113364669A (zh) * 2021-06-02 2021-09-07 中国工商银行股份有限公司 消息处理方法、装置、电子设备及介质
CN113364669B (zh) * 2021-06-02 2023-04-18 中国工商银行股份有限公司 消息处理方法、装置、电子设备及介质
WO2023273321A1 (zh) * 2021-06-29 2023-01-05 荣耀终端有限公司 一种语音控制方法及电子设备
CN113739382A (zh) * 2021-08-12 2021-12-03 武汉慧联无限科技有限公司 空调控制方法及装置、控制设备和存储介质
WO2023040692A1 (zh) * 2021-09-14 2023-03-23 北京车和家信息技术有限公司 语音控制方法、装置、设备及介质
US11960914B2 (en) * 2021-11-19 2024-04-16 Samsung Electronics Co., Ltd. Methods and systems for suggesting an enhanced multimodal interaction
JP2024540681A (ja) * 2021-11-30 2024-10-31 華為技術有限公司 デバイス制御方法および装置
JP7820516B2 (ja) 2021-11-30 2026-02-25 深▲ジェン▼引望智能技術有限公司 デバイス制御方法および装置
CN115691492A (zh) * 2022-10-29 2023-02-03 重庆长安汽车股份有限公司 一种车载语音控制系统及方法
TWI918023B (zh) 2023-07-17 2026-03-11 美商博姆雲360公司 自適應及智慧提示系統及控制介面

Also Published As

Publication number Publication date
EP3933830A1 (en) 2022-01-05
EP3933830A4 (en) 2022-06-08
EP4664269A2 (en) 2025-12-17
US11922935B2 (en) 2024-03-05
EP3933830B1 (en) 2025-07-30
JP7324313B2 (ja) 2023-08-09
EP4664269A3 (en) 2026-03-04
US20210183386A1 (en) 2021-06-17
CN112397062B (zh) 2024-10-18
CN119296533A (zh) 2025-01-10
CN112397062A (zh) 2021-02-23
JP2022534371A (ja) 2022-07-29

Similar Documents

Publication Publication Date Title
CN112397062B (zh) 语音交互方法、装置、终端及存储介质
US12190878B2 (en) Voice interaction method and apparatus
AU2019385366B2 (en) Voice control method and electronic device
US11871328B2 (en) Method for identifying specific position on specific route and electronic device
EP4064284A1 (en) Voice detection method, prediction model training method, apparatus, device, and medium
WO2021052263A1 (zh) 语音助手显示方法及装置
CN114697348B (zh) 分布式实现方法、分布式系统、可读介质及电子设备
WO2020244622A1 (zh) 一种通知的提示方法、终端及系统
WO2020192456A1 (zh) 一种语音交互方法及电子设备
CN114694646B (zh) 一种语音交互处理方法及相关装置
WO2020073288A1 (zh) 一种触发电子设备执行功能的方法及电子设备
US12217069B2 (en) Operation sequence adding method, electronic device, and system
CN111835904A (zh) 一种基于情景感知和用户画像开启应用的方法及电子设备
CN115333941B (zh) 获取应用运行情况的方法及相关设备
WO2020253694A1 (zh) 一种用于识别音乐的方法、芯片和终端
WO2023241482A1 (zh) 一种人机对话方法、设备及系统
WO2023098467A1 (zh) 语音解析方法、电子设备、可读存储介质及芯片系统
CN113487272A (zh) 日程活动冲突判断方法、电子设备及存储介质
CN118131891A (zh) 一种人机交互的方法和装置
CN121000813A (zh) 一种语音交互方法、电子设备和存储介质
CN117687814A (zh) 异常处理方法、系统以及存储介质

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 20803428

Country of ref document: EP

Kind code of ref document: A1

ENP Entry into the national phase

Ref document number: 2021569122

Country of ref document: JP

Kind code of ref document: A

Ref document number: 2020803428

Country of ref document: EP

Effective date: 20201117

NENP Non-entry into the national phase

Ref country code: DE

WWG Wipo information: grant in national office

Ref document number: 2020803428

Country of ref document: EP