CN112802477A - Customer service assistant tool service method and system based on voice-to-text conversion - Google Patents

Customer service assistant tool service method and system based on voice-to-text conversion Download PDF

Info

Publication number
CN112802477A
CN112802477A CN202011612549.8A CN202011612549A CN112802477A CN 112802477 A CN112802477 A CN 112802477A CN 202011612549 A CN202011612549 A CN 202011612549A CN 112802477 A CN112802477 A CN 112802477A
Authority
CN
China
Prior art keywords
voice
assistant
client
service
module
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.)
Pending
Application number
CN202011612549.8A
Other languages
Chinese (zh)
Inventor
张德昌
丁常坤
夏兵
王江淮
时代红
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.)
Kedaduochuang Cloud Technology Co ltd
Original Assignee
Kedaduochuang Cloud Technology 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 Kedaduochuang Cloud Technology Co ltd filed Critical Kedaduochuang Cloud Technology Co ltd
Priority to CN202011612549.8A priority Critical patent/CN112802477A/en
Publication of CN112802477A publication Critical patent/CN112802477A/en
Pending 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
    • G10L15/26—Speech to text systems
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04M—TELEPHONIC COMMUNICATION
    • H04M3/00—Automatic or semi-automatic exchanges
    • H04M3/42—Systems providing special services or facilities to subscribers
    • H04M3/50—Centralised arrangements for answering calls; Centralised arrangements for recording messages for absent or busy subscribers ; Centralised arrangements for recording messages
    • H04M3/51—Centralised call answering arrangements requiring operator intervention, e.g. call or contact centers for telemarketing

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Signal Processing (AREA)
  • Computational Linguistics (AREA)
  • Health & Medical Sciences (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • Acoustics & Sound (AREA)
  • Multimedia (AREA)
  • Telephonic Communication Services (AREA)

Abstract

本发明公开了一种基于语音文字转换的客服助理工具服务方法及系统，属于客服服务技术领域，包括以下步骤：S1：调起客户端；S2：语音采集；S3：语音发送；S4：语音转换处理；S5：语音识别；S6：识别结果返回；S7：识别结果展示；S8：停止展示。本发明通过设置助理服务端，通过助理服务端接收语音并返回识别结果，可以在助理服务端录音及保存整通电话的识别结果，便于质检等其他业务；通过接口调用ASR服务，可以更换服务提供商；客服人员可以随时复制聊天文字，或者翻看前面的聊天记录。

Figure 202011612549

The invention discloses a customer service assistant tool service method and system based on voice-to-text conversion, belonging to the technical field of customer service service, comprising the following steps: S1: call up a client; S2: voice collection; S3: voice transmission; S4: voice conversion processing; S5: speech recognition; S6: return of the recognition result; S7: display of the recognition result; S8: stop display. In the present invention, by setting up an assistant server, receiving voice through the assistant server and returning the recognition result, the assistant server can record and save the recognition result of the whole call, which is convenient for other services such as quality inspection; the ASR service can be called through the interface, and the service can be changed. Provider; customer service staff can copy the chat text at any time, or look at the previous chat records.

Figure 202011612549

Description

Customer service assistant tool service method and system based on voice-to-text conversion
Technical Field
The invention relates to the technical field of customer service, in particular to a customer service assistant tool service method and system based on voice-to-text conversion.
Background
Voice service personnel often need to record or confirm some information to the user while answering the customer's phone. When the amount of information is large, if no other auxiliary means or tools are provided and the memory is fully used, on one hand, the burden of customer service personnel is increased, and on the other hand, the inaccurate information causes the repeated inquiry and confirmation to the customer.
Customer service personnel sometimes need to enter the content spoken by the customer into related systems such as a CRM system and the like during the conversation, if all the content is typed and entered manually, more conversation time is occupied, or distraction is caused, and the working efficiency is not high enough. Therefore, a customer service assistant tool service method based on voice-to-text conversion is provided.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: how to show the content of the conversation between the customer service staff and the customer on the computer used by the customer service staff for the customer service staff to refer and copy, and provides a customer service assistant tool service method based on the speech-to-text conversion.
The invention solves the technical problems through the following technical scheme, and the invention comprises the following steps:
s1: calling client
When the customer service personnel receives the incoming call through the foreground system, the assistant client is called up to start to communicate with the customer;
s2: speech acquisition
The assistant client starts to collect audio after being started, wherein the audio comprises the voice of customer service personnel and the voice of a client;
s3: voice transmission
The assistant client sends the two collected voices to the assistant server in real time through the websocket interface;
s4: speech conversion processing
The assistant server or the assistant client is used for carrying out corresponding conversion processing on the collected voice so as to adapt to the websocket interface requirement of an ASR (automatic speech recognition technology) manufacturer;
s5: speech recognition
The assistant server side sends the processed audio data to an ASR service provider through a websocket interface for recognition, and receives a return result in real time;
s6: recognition result return
The assistant server returns the recognition result to the assistant client through the websocket interface;
s7: display of recognition results
Displaying the assistant client display interface through an independent window;
s8: stop showing
And after the call is finished, the assistant client stops collecting the audio data.
Further, in step S1, when the customer service personnel answers the incoming call event trigger, the foreground system invokes the assistant client through JavaScript, and transmits the current call information.
Further, in step S2, the assistant client calls the COM component provided by windows to collect Audio data by using Core Audio, where the collection client uses the loopback mode and the collection customer service person uses the capture mode.
Furthermore, in step S4, the ASR service websocket interface needs 8000hz, monaural, 16bit wide PCM audio data, and the collected audio data needs to be transcoded to convert the audio data into a format required by the ASR service websocket interface.
Furthermore, when an incoming call answering event is triggered, the assistant client is started, then the assistant server is connected and sends text information, the assistant server receives the text information and then starts a websocket connection, connects to the ASR service, creates a related data structure, and associates the two channels.
Furthermore, when the call end event is triggered, the assistant client sends an end mark to the assistant server, and the assistant server disconnects the websocket connection with the ASR service and clears the relevant resources.
The invention also provides a customer service assistant tool service system based on the voice-to-text conversion, which uses the service method to service the customer and comprises the following steps:
the client-side calling module is used for receiving an incoming call through the foreground system, calling the assistant client side and starting to communicate with the client;
the voice acquisition module is used for acquiring audio after the assistant client is started, and the audio comprises the voice of customer service personnel and the voice of a client;
the voice sending module is used for sending the two collected voices to the assistant server in real time through the websocket interface by the assistant client;
the voice conversion processing module is used for utilizing an assistant server or an assistant client to perform corresponding conversion processing on the collected voice so as to adapt to the websocket interface requirement of an ASR manufacturer;
the voice recognition module is used for recognizing the processed audio data through the ASR service provider and receiving a return result in real time;
the recognition result returning module is used for returning the recognition result to the assistant client through the websocket interface by using the assistant server;
the result display module is used for displaying the display interface of the assistant client through the independent window;
the display stopping module is used for stopping collecting the audio data after the call is finished;
the central processing module is used for sending instructions to other modules to complete related actions;
the client calling module, the voice acquisition module, the voice sending module, the voice conversion processing module, the voice recognition module, the recognition result returning module, the result display module and the display stopping module are all electrically connected with the central processing module.
Compared with the prior art, the invention has the following advantages: the customer service assistant tool service method based on the voice-character conversion is characterized in that an assistant server is arranged, and the assistant server receives the voice and returns the recognition result, so that the recognition result of the whole phone can be recorded and stored at the assistant server, and other services such as quality inspection and the like are facilitated; the ASR service is called through the interface, and the service provider can be replaced; the customer service personnel can copy the chat characters at any time or turn over the chat records in front, so that the system is worthy of being popularized and used.
Drawings
FIG. 1 is a schematic diagram illustrating an interaction flow between an assistant client and an assistant server according to a second embodiment of the present invention;
FIG. 2 is a diagram of an example of an independent window interface according to a second embodiment of the present invention.
Detailed Description
The following examples are given for the detailed implementation and specific operation of the present invention, but the scope of the present invention is not limited to the following examples.
Example one
The embodiment provides a technical scheme: a customer service assistant tool service method based on speech-to-text conversion comprises the following steps:
s1: calling client
When the customer service personnel receives the incoming call through the foreground system, the assistant client is called up to start to communicate with the customer;
s2: speech acquisition
The assistant client starts to collect audio after being started, wherein the audio comprises the voice of customer service personnel and the voice of a client;
s3: voice transmission
The assistant client sends the two collected voices to the assistant server in real time through the websocket interface;
s4: speech conversion processing
The assistant server or the assistant client is used for carrying out corresponding conversion processing on the collected voice so as to adapt to the websocket interface requirement of an ASR (automatic speech recognition technology) manufacturer;
s5: speech recognition
The assistant server side sends the processed audio data to an ASR service provider through a websocket interface for recognition, and receives a return result in real time;
s6: recognition result return
The assistant server returns the recognition result to the assistant client through the websocket interface;
s7: display of recognition results
Displaying the assistant client display interface through an independent window;
s8: stop showing
And after the call is finished, the assistant client stops collecting the audio data.
In step S1, when the customer service staff answers the incoming call event trigger, the foreground system invokes the assistant client through JavaScript, and transmits the current call information.
In step S2, the assistant client calls the COM component provided by the windows, and acquires Audio data by using Core Audio, where the voice of the client is acquired by using a loopback mode, and the voice of the service person is acquired by using a capture mode.
In step S4, the ASR service websocket interface needs to transcode the PCM audio data with 8000hz, mono channel, and 16bit wide, and converts the audio data into a format required by the ASR service websocket interface.
When an incoming call receiving event is triggered, the assistant client is connected with the assistant server and sends text information after being started, the assistant server starts a websocket connection after receiving the text information, is connected with the ASR service, creates a related data structure, and associates two channels.
When a call ending event is triggered, the assistant client sends an ending mark to the assistant server, and the assistant server disconnects the websocket connection with the ASR service and clears related resources.
The embodiment also provides a customer service assistant tool service system based on voice-to-text conversion, which uses the service method to service customers, and comprises the following steps:
the client-side calling module is used for receiving an incoming call through the foreground system, calling the assistant client side and starting to communicate with the client;
the voice acquisition module is used for acquiring audio after the assistant client is started, and the audio comprises the voice of customer service personnel and the voice of a client;
the voice sending module is used for sending the two collected voices to the assistant server in real time through the websocket interface by the assistant client;
the voice conversion processing module is used for utilizing an assistant server or an assistant client to perform corresponding conversion processing on the collected voice so as to adapt to the websocket interface requirement of an ASR manufacturer;
the voice recognition module is used for recognizing the processed audio data through the ASR service provider and receiving a return result in real time;
the recognition result returning module is used for returning the recognition result to the assistant client through the websocket interface by using the assistant server;
the result display module is used for displaying the display interface of the assistant client through the independent window;
the display stopping module is used for stopping collecting the audio data after the call is finished;
the central processing module is used for sending instructions to other modules to complete related actions;
the client calling module, the voice acquisition module, the voice sending module, the voice conversion processing module, the voice recognition module, the recognition result returning module, the result display module and the display stopping module are all electrically connected with the central processing module.
Example two
The invention aims to convert the voice of both telephone traffic parties into characters to be displayed in a customer service system, and mainly relates to the technologies of voice acquisition, audio conversion, voice recognition service and the like of a microphone and a sound card. The practical system should include an assistant client installed in the customer service personnel computer and an assistant server deployed in the server, and a websocket interface of speech recognition (ASR) provided by a third party manufacturer.
As shown in fig. 1, the main process steps of this embodiment are as follows:
s1: calling client
When customer service personnel hear an incoming call through a foreground system (such as using a browser), the assistant client is called up to start to communicate with the client;
s2: speech acquisition
The assistant client, upon starting, begins to capture speech, including the voice of the customer service person input to the computer from the microphone and the voice of the customer output to the headset from the computer sound card;
s3: voice transmission
The client side sends the two collected voices to the assistant server side in real time through the websocket interface;
s4: speech conversion processing
The assistant server is responsible for performing corresponding conversion processing on the voice so as to meet the websocket interface requirements of ASR manufacturers;
for example, a conventional Baidu ASR service interface requires to transmit PCM audio data with 8000hz, single channel, and 16bit wide, and the audio data transmitted from the assistant client generally cannot completely meet the requirement, so the assistant server needs to convert the data into a format completely meeting the interface requirement. After the audio format conversion is completed, the audio format can be sent to an ASR interface according to a certain frequency;
s5: speech recognition
The assistant server side sends the processed audio data to an ASR service provider through a websocket interface, and receives a return result in real time;
the conventional speech recognition mode is speech file transcription, while the customer service assistant needs real-time speech recognition, wherein the ASR service is required to provide real-time speech recognition, a real-time speech recognition interface is generally provided in a websocket interface mode, the assistant service end can send an audio data frame at a certain frequency, and the ASR service end returns a temporary recognition result and a final recognition result in real time;
s6: recognition result return
The assistant server returns the recognition result to the assistant client through the websocket interface;
s7: display of recognition results
The assistant client display interface can exist in a separate window, and the display form can be as shown in fig. 2;
the assistant client is a program which needs to be installed on the customer service computer, runs independently, and can provide a presentation interface.
S8: stop showing
And after the call is finished, the assistant client stops collecting data.
The specific implementation principle of this embodiment is as follows:
the client side is invoked: when the customer service personnel receives the incoming call event trigger, the assistant client can automatically register in the registry when being installed, the assistant client can be called up by the front end of the browser through JavaScript, and the assistant client is automatically connected to the assistant server after being started and transmits the current call information. .
Audio acquisition: the assistant client calls the COM component provided by windows and captures it using Core Audio. Wherein capturing client speech uses the loopback mode and capturing microphone recorded speech uses the capture mode.
Audio transcoding: since the ASR service websocket interface generally requires 8000hz, single-channel, 16bit wide PCM data, the captured data encoding is often related to the specific hardware of the current computer, such as 48000hz, dual-channel, which is common, transcoding is required. The transcoding function can be realized at the assistant client side or the assistant server side. The audio transcoding is realized by calling FFmpeg, and if the transcoding is realized by using the assistant client in view of saving network traffic, the FFmpeg is integrated in the assistant client; if transcoding is realized by the assistant server, the assistant server integrates FFmpeg, and the FFmpeg is used because the set of tools has high coding and decoding efficiency.
Interaction of the assistant client and the assistant server: the websocket is also used for interactions between the assistant client and the assistant server. When an incoming call receiving event is triggered and the assistant client is started, the assistant client is firstly connected with the assistant server and sends text information, wherein the text information comprises information such as the sampling rate, the sampling digit, the channel number and the like of audio collected by the current computer system. The assistant server, upon receiving the text message, initiates a websocket connection to the ASR service and creates a correlation data structure that correlates the two channels. The data structure includes an audio data buffer, a websocket connection channel with the assistant client, and a websocket connection channel with the ASR service. The audio data buffer is used for storing the audio data which is sent by the assistant client and is transcoded, the assistant server sends the audio data to the ASR service interface and fetches data from the buffer, and the buffer is used because the frequency of sending the data by the assistant client is not matched with the frequency of sending the data by the assistant server to the ASR service interface. Thereafter, the assistant client will send the audio data continuously at certain time intervals, and the assistant server sends the recognition result returned by the ASR service to the assistant client as text. When the call end event is triggered, the assistant client sends an end mark to the assistant server, and the assistant server disconnects the websocket connection with the ASR service and clears the related resources.
To sum up, in the customer service assistant tool service method based on the voice-to-text conversion according to the embodiment, by setting the assistant server, receiving the voice through the assistant server and returning the recognition result, the recognition result of the whole phone call can be recorded and saved at the assistant server, thereby facilitating other services such as quality inspection and the like; the ASR service is called through the interface, and the service provider can be replaced; the customer service personnel can copy the chat characters at any time or turn over the chat records in front, so that the system is worthy of being popularized and used.
Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (7)

1.一种基于语音文字转换的客服助理工具服务方法，其特征在于，包括以下步骤：1. a kind of customer service assistant tool service method based on voice-to-text conversion, is characterized in that, comprises the following steps: S1：调起客户端S1: call up the client 当客服人员通过前台系统接听到来电，调起助理客户端，开始与客户交流；When the customer service staff receives the call through the front desk system, they call up the assistant client and start to communicate with the customer; S2：语音采集S2: Voice capture 助理客户端启动后开始进行音频采集，包括客服人员的声音与客户的声音；After the assistant client is started, audio collection starts, including the voice of the customer service staff and the voice of the customer; S3：语音发送S3: Voice sending 助理客户端将采集到的两路语音通过websocket接口实时发送到助理服务端；The assistant client sends the collected two-way voice to the assistant server in real time through the websocket interface; S4：语音转换处理S4: Speech conversion processing 利用助理服务端或助理客户端对采集到的语音进行相应转换处理，以适应ASR服务厂商的websocket接口需要；Use the assistant server or assistant client to perform corresponding conversion processing on the collected voice to meet the needs of the websocket interface of the ASR service provider; S5：语音识别S5: Speech Recognition 助理服务端将处理后的音频数据通过websocket接口发送到ASR服务提供方进行识别，并实时接收返回结果；The assistant server sends the processed audio data to the ASR service provider through the websocket interface for identification, and receives the returned result in real time; S6：识别结果返回S6: The recognition result is returned 助理服务端将识别结果通过websocket接口返回给助理客户端；The assistant server returns the recognition result to the assistant client through the websocket interface; S7：识别结果展示S7: Display of recognition results 将助理客户端展示界面通过独立窗口进行展示；Display the assistant client display interface through a separate window; S8：停止展示S8: stop showing 通话结束后，助理客户端停止采集音频数据。After the call ends, the assistant client stops collecting audio data. 2.根据权利要求1所述的一种基于语音文字转换的客服助理工具服务方法，其特征在于：在所述步骤S1中，客服人员接听来话事件触发时，前台系统通过JavaScript调起助理客户端，并传递当前通话信息。2. a kind of customer service assistant tool service method based on voice-to-text conversion according to claim 1, is characterized in that: in described step S1, when customer service personnel answers the incoming call event trigger, the foreground system calls up the assistant customer by JavaScript terminal, and transmit the current call information. 3.根据权利要求2所述的一种基于语音文字转换的客服助理工具服务方法，其特征在于：在所述步骤S2中，助理客户端调用windows提供的COM组件，使用Core Audio进行对音频数据进行采集，其中采集客户语音使用loopback模式，采集客服人员语音使用capture模式。3. a kind of customer service assistant tool service method based on voice-to-text conversion according to claim 2, is characterized in that: in described step S2, assistant client calls the COM component that windows provides, uses Core Audio to carry out to audio data For collection, the loopback mode is used to collect the customer's voice, and the capture mode is used to collect the voice of the customer service personnel. 4.根据权利要求3所述的一种基于语音文字转换的客服助理工具服务方法，其特征在于：在所述步骤S4中，ASR服务websocket接口需要8000hz、单声道、位宽16bit的PCM音频数据，需要对采集到的音频数据进行转码，将音频数据转换成ASR服务websocket接口所需格式。4. a kind of customer service assistant tool service method based on voice-to-text conversion according to claim 3, is characterized in that: in described step S4, ASR service websocket interface needs the PCM audio frequency of 8000hz, monophonic, bit width 16bit Data, you need to transcode the collected audio data, and convert the audio data into the format required by the ASR service websocket interface. 5.根据权利要求4所述的一种基于语音文字转换的客服助理工具服务方法，其特征在于：当接听来电事件触发，所述助理客户端启动之后，首先连接所述助理服务端并发送文本信息，所述助理服务端接收到该文本信息之后启动一个websocket连接，连接到ASR服务，并创建相关数据结构，将两个通道关联起来。5. A kind of customer service assistant tool service method based on voice-to-text conversion according to claim 4, it is characterized in that: when an incoming call event is triggered, after the assistant client is started, first connect the assistant server and send the text information, the assistant server starts a websocket connection after receiving the text information, connects to the ASR service, and creates a related data structure to associate the two channels. 6.根据权利要求5所述的一种基于语音文字转换的客服助理工具服务方法，其特征在于：当通话结束事件触发，所述助理客户端发送结束标志给所述助理服务端，所述助理服务端则断开与ASR服务的websocket连接，并清理相关资源。6. A kind of customer service assistant tool service method based on voice-to-text conversion according to claim 5, is characterized in that: when the call end event is triggered, the assistant client sends an end sign to the assistant server, and the assistant The server disconnects the websocket connection to the ASR service and cleans up related resources. 7.一种基于语音文字转换的客服助理工具服务系统，利用如权利要求1～6任一所述的服务方法对客户进行服务，包括：7. A customer service assistant tool service system based on voice-to-text conversion, using the service method according to any one of claims 1 to 6 to serve customers, comprising: 客户端调起模块，用于通过前台系统接听到来电，调起助理客户端，开始与客户交流；The client mobilization module is used to receive calls through the front desk system, mobilize the assistant client, and start communicating with customers; 语音采集模块，用于在助理客户端启动后进行音频采集，包括客服人员的声音与客户的声音；The voice acquisition module is used to collect audio after the assistant client is started, including the voice of the customer service staff and the voice of the customer; 语音发送模块，用于通过助理客户端将采集到的两路语音通过websocket接口实时发送到助理服务端；The voice sending module is used to send the two collected voices to the assistant server in real time through the websocket interface through the assistant client; 语音转换处理模块，用于利用助理服务端或助理客户端对采集到的语音进行相应转换处理，以适应ASR厂商的websocket接口需要；The voice conversion processing module is used to use the assistant server or assistant client to perform corresponding conversion processing on the collected voice to meet the needs of the ASR manufacturer's websocket interface; 语音识别模块，用于通过ASR服务提供方对处理后的音频数据进行识别，并实时接收返回结果；The speech recognition module is used to recognize the processed audio data through the ASR service provider, and receive the returned result in real time; 识别结果返回模块，用于利用助理服务端将识别结果通过websocket接口返回给助理客户端；The identification result returning module is used to return the identification result to the assistant client through the websocket interface by using the assistant server; 结果展示模块，用于将助理客户端展示界面通过独立窗口进行展示；The result display module is used to display the assistant client display interface through an independent window; 展示停止模块，用于在通话结束后，停止采集音频数据；Display the stop module, which is used to stop collecting audio data after the call ends; 中央处理模块，用于向其他模块发出指令，完成相关动作；The central processing module is used to issue instructions to other modules to complete related actions; 所述客户端调起模块、语音采集模块、语音发送模块、语音转换处理模块、语音识别模块、识别结果返回模块、结果展示模块、展示停止模块均与中央处理模块电连接。The client activating module, voice collecting module, voice sending module, voice conversion processing module, voice recognition module, recognition result return module, result display module and display stop module are all electrically connected with the central processing module.
CN202011612549.8A 2020-12-30 2020-12-30 Customer service assistant tool service method and system based on voice-to-text conversion Pending CN112802477A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011612549.8A CN112802477A (en) 2020-12-30 2020-12-30 Customer service assistant tool service method and system based on voice-to-text conversion

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011612549.8A CN112802477A (en) 2020-12-30 2020-12-30 Customer service assistant tool service method and system based on voice-to-text conversion

Publications (1)

Publication Number Publication Date
CN112802477A true CN112802477A (en) 2021-05-14

Family

ID=75805742

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011612549.8A Pending CN112802477A (en) 2020-12-30 2020-12-30 Customer service assistant tool service method and system based on voice-to-text conversion

Country Status (1)

Country Link
CN (1) CN112802477A (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050131704A1 (en) * 1997-04-14 2005-06-16 At&T Corp. System and method for providing remote automatic speech recognition and text to speech services via a packet network
CN101699840A (en) * 2009-11-09 2010-04-28 南京希华通信技术有限公司 Intelligent speech interactive system in converged communication and method for implementing same
CN110289016A (en) * 2019-06-20 2019-09-27 深圳追一科技有限公司 A kind of voice quality detecting method, device and electronic equipment based on actual conversation
CN110648665A (en) * 2019-09-09 2020-01-03 北京左医科技有限公司 Session process recording system and method
CN110784591A (en) * 2019-09-25 2020-02-11 福建新大陆软件工程有限公司 Intelligent voice automatic detection method, device and system
CN111106996A (en) * 2019-12-28 2020-05-05 安徽微沃信息科技股份有限公司 WebSocket and cache-based multi-terminal online chat system

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20050131704A1 (en) * 1997-04-14 2005-06-16 At&T Corp. System and method for providing remote automatic speech recognition and text to speech services via a packet network
CN101699840A (en) * 2009-11-09 2010-04-28 南京希华通信技术有限公司 Intelligent speech interactive system in converged communication and method for implementing same
CN110289016A (en) * 2019-06-20 2019-09-27 深圳追一科技有限公司 A kind of voice quality detecting method, device and electronic equipment based on actual conversation
CN110648665A (en) * 2019-09-09 2020-01-03 北京左医科技有限公司 Session process recording system and method
CN110784591A (en) * 2019-09-25 2020-02-11 福建新大陆软件工程有限公司 Intelligent voice automatic detection method, device and system
CN111106996A (en) * 2019-12-28 2020-05-05 安徽微沃信息科技股份有限公司 WebSocket and cache-based multi-terminal online chat system

Similar Documents

Publication Publication Date Title
US9942400B2 (en) System and methods for analyzing multichannel communications including voice data
US9699307B2 (en) Method and system for automatically routing a telephonic communication
US7433818B2 (en) Subscriber terminal for providing speech-text encoding and telephony service
JP5532598B2 (en) Operator management system, method and program
US6490550B1 (en) System and method for IP-based communication transmitting speech and speech-generated text
JP2011087005A (en) Telephone call voice summary generation system, method therefor, and telephone call voice summary generation program
US12132855B2 (en) Presentation of communications
US9917939B1 (en) Automatically delaying playback of a voice message at a captioning device
CN101277338A (en) A method for recording downlink voice signals of a communication terminal and the communication terminal
CN111263016A (en) Communication assistance method, communication assistance device, computer equipment and computer-readable storage medium
CN111768786B (en) Deaf-mute conversation intelligent terminal platform and conversation method thereof
JP2019153099A (en) Conference assisting system, and conference assisting program
JPH07226931A (en) Multimedia conferencing equipment
CN103067579A (en) Auxiliary online voice chat method and device
CN112802477A (en) Customer service assistant tool service method and system based on voice-to-text conversion
US10356246B2 (en) Method and communications arrangement for operating a communications connection
JP2004173124A (en) Method for managing customer data
EP1889257B1 (en) A method and system for recording an electronic communication and extracting constituent audio data therefrom
JP2000004304A (en) A communication device that allows conversation by different means
US20080262844A1 (en) Method and system for analyzing separated voice data of a telephonic communication to determine the gender of the communicant
JPH11272663A (en) Minutes preparation device, preparation method and recording medium
TWM653713U (en) Telephone robot system
JP2005033522A (en) Speech contents reproducing apparatus, method, program, and recording medium with the program recorded thereon
JP2003069718A (en) System for supporting remote interaction between person handicapped in hearing and person having no difficulty in hearing
CN119110022A (en) A method and system for processing cloud phone call data based on big data technology

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
RJ01 Rejection of invention patent application after publication

Application publication date: 20210514

RJ01 Rejection of invention patent application after publication