WO2023246545A1 - 咳嗽监测方法及相关设备 - Google Patents

咳嗽监测方法及相关设备 Download PDF

Info

Publication number
WO2023246545A1
WO2023246545A1 PCT/CN2023/099674 CN2023099674W WO2023246545A1 WO 2023246545 A1 WO2023246545 A1 WO 2023246545A1 CN 2023099674 W CN2023099674 W CN 2023099674W WO 2023246545 A1 WO2023246545 A1 WO 2023246545A1
Authority
WO
WIPO (PCT)
Prior art keywords
cough
recording data
data
terminal device
intelligent terminal
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/CN2023/099674
Other languages
English (en)
French (fr)
Inventor
王伟
叶际隆
李靖
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 EP23826194.5A priority Critical patent/EP4521403A4/en
Publication of WO2023246545A1 publication Critical patent/WO2023246545A1/zh
Priority to US18/984,393 priority patent/US20250120611A1/en
Anticipated expiration legal-status Critical
Ceased legal-status Critical Current

Links

Classifications

    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/08—Measuring devices for evaluating the respiratory organs
    • A61B5/0823—Detecting or evaluating cough events
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
    • A61B5/6802—Sensor mounted on worn items
    • A61B5/6803—Head-worn items, e.g. helmets, masks, headphones or goggles
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
    • A61B5/6887—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient mounted on external non-worn devices, e.g. non-medical devices
    • A61B5/6898—Portable consumer electronic devices, e.g. music players, telephones, tablet computers
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B5/00—Measuring for diagnostic purposes; Identification of persons
    • A61B5/72—Signal processing specially adapted for physiological signals or for diagnostic purposes
    • A61B5/7235—Details of waveform analysis
    • A61B5/7264—Classification of physiological signals or data, e.g. using neural networks, statistical classifiers, expert systems or fuzzy systems
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B7/00—Instruments for auscultation
    • A61B7/003—Detecting lung or respiration noise
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/08—Mouthpieces; Microphones; Attachments therefor
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0204—Acoustic sensors
    • A—HUMAN NECESSITIES
    • A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
    • A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
    • A61B2562/00—Details of sensors; Constructional details of sensor housings or probes; Accessories for sensors
    • A61B2562/02—Details of sensors specially adapted for in-vivo measurements
    • A61B2562/0219—Inertial sensors, e.g. accelerometers, gyroscopes, tilt switches
    • 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
    • G10L25/00—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00
    • G10L25/48—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use
    • G10L25/51—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination
    • G10L25/66—Speech or voice analysis techniques not restricted to a single one of groups G10L15/00 - G10L21/00 specially adapted for particular use for comparison or discrimination for extracting parameters related to health condition
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/10—Earpieces; Attachments therefor ; Earphones; Monophonic headphones
    • H04R1/1041—Mechanical or electronic switches, or control elements
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
    • H04R1/00—Details of transducers, loudspeakers or microphones
    • H04R1/46—Special adaptations for use as contact microphones, e.g. on musical instrument, on stethoscope
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
    • H04R2460/00—Details of hearing devices, i.e. of ear- or headphones covered by H04R1/10 or H04R5/033 but not provided for in any of their subgroups, or of hearing aids covered by H04R25/00 but not provided for in any of its subgroups
    • H04R2460/03—Aspects of the reduction of energy consumption in hearing devices
    • H—ELECTRICITY
    • H04—ELECTRIC COMMUNICATION TECHNIQUE
    • H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS
    • H04R2460/00—Details of hearing devices, i.e. of ear- or headphones covered by H04R1/10 or H04R5/033 but not provided for in any of their subgroups, or of hearing aids covered by H04R25/00 but not provided for in any of its subgroups
    • H04R2460/13—Hearing devices using bone conduction transducers

Definitions

  • This application relates to the field of Internet technology, and in particular to a cough monitoring method and related equipment.
  • Cough is the most common symptom among patients in respiratory specialist clinics and community outpatient clinics. Cough is generally caused by inflammation of the trachea and bronchus, foreign bodies, and physical or chemical stimulation. Coughing has a protective effect in clearing foreign bodies and secretions from the respiratory tract, but frequent and severe coughing has a serious impact on patients' work, study, and quality of life.
  • the cough detector consists of a microphone and memory.
  • the cough monitor's microphone is turned on 24 hours a day to record audio data.
  • the microphone is always on, which on the one hand creates user privacy and security risks, and on the other hand leads to high power consumption of the device and high demand for storage resources.
  • This application provides a cough monitoring method and related equipment to reduce user privacy security risks and equipment power consumption.
  • the first aspect provides a cough monitoring method.
  • the method includes: the earphone responds to detecting a vibration signal, starts the microphone to record and obtains the recording data, and wears the earphone on the user's head and neck; the earphone detects whether the recording data includes a cough sound; if the recording data includes a cough sound, the earphone sends the recording data to the smart phone Terminal equipment, so that the intelligent terminal equipment analyzes and counts the user's cough information based on the recording data.
  • the earphones worn on the user's head and neck detect vibration signals, the microphone is activated for recording. This eliminates the need for the microphone to be turned on around the clock for recording, which can reduce user privacy and security risks, and reduce the power consumption and storage resource requirements of the earphones.
  • the headset detecting whether the recording data includes cough sound includes: the headset compares the similarity between the recording data and the cough sound data, and the cough sound data is the user's cough sound data that was previously recorded; if the recording data is different from the cough sound data, If the similarity between the cough sound data is greater than or equal to the threshold, the headset determines that the recording data includes cough sounds; if the similarity between the recording data and the cough sound data is less than the threshold, the headset determines that the recording data does not include cough sounds. Matching the pre-recorded user's cough sound data with the recording data can improve the accuracy of cough sound recognition.
  • the method further includes: the earphone records vibration data corresponding to the detected vibration signal.
  • the earphones send recording data to the smart terminal device so that the smart terminal device can analyze and collect cough information based on the recording data.
  • the earphones send recording data and vibration data to the smart terminal device so that the smart terminal device can analyze and collect cough information based on the recording data and vibration data. Analyze statistical cough information. Combining the vibration data corresponding to the vibration signal to collect cough information can improve the accuracy of cough statistical information.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • the method also includes: if the recording data does not include cough sounds, the earphones delete the recording data. This saves storage space and reduces the demand for storage resources.
  • the second aspect provides a cough monitoring method.
  • the method includes: the earphone detects a vibration signal, and the earphone is worn on the user's head and neck; in response to the vibration signal, the earphone sends an instruction message to the intelligent terminal device, so that the intelligent terminal device activates the microphone to record according to the instruction message to obtain the recording data, and When it is determined that the recording data includes cough sounds, the user's cough information is analyzed and counted based on the recording data.
  • the headset detects a vibration signal, an instruction message instructing recording is sent to the smart terminal device, thereby eliminating the need to turn on the microphone for recording around the clock, which can reduce user privacy and security risks, as well as power consumption and storage resource consumption.
  • recording and detecting recording data by a terminal device can reduce the demand for the computing power and storage capacity of the headset and reduce the cost of the headset.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • the third aspect provides a cough monitoring method.
  • the method includes: the intelligent terminal device receives an instruction message sent by the earphone, which is worn on the user's head and neck, and the instruction message is generated by the vibration signal detected by the earphone; in response to the instruction message, the intelligent terminal device activates the microphone to record, and obtains the recording data; The smart terminal device detects and determines that the recording data includes cough sounds; the smart terminal device analyzes and counts the user's cough information based on the recording data.
  • the intelligent terminal device detects and determines that the recorded data includes cough sounds including: the intelligent terminal device compares the similarity between the recorded data and the cough sound data, and the cough sound data is the cough sound data of a previously recorded user; The intelligent terminal device determines that the similarity between the recording data and the cough sound data is greater than or equal to the threshold, and the intelligent terminal device determines that the recording data includes the cough sound.
  • the method also includes: the intelligent terminal device receives vibration data sent by the earphone, and the vibration data is data corresponding to the vibration signal detected by the earphone recording; the intelligent terminal device analyzes and counts the cough information according to the recording data, including: The smart terminal device analyzes and collects cough information based on recording data and vibration data.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • the fourth aspect provides a cough monitoring method.
  • the method includes: the earphone detects a vibration signal, and the earphone is worn on the user's head and neck; in response to the vibration signal, the earphone sends an instruction message to the intelligent terminal device; the intelligent terminal device activates the microphone to record in response to the instruction message, and obtains the recording data; the intelligent terminal The device detects and determines that the recording data includes cough sounds; the smart terminal device analyzes and counts the user's cough information based on the recording data.
  • the intelligent terminal device detects and determines that the recorded data includes cough sounds including: the intelligent terminal device compares the similarity between the recorded data and the cough sound data, and the cough sound data is the cough sound data of a previously recorded user; The intelligent terminal device determines that the similarity between the recording data and the cough sound data is greater than or equal to the threshold, and the intelligent terminal device determines that the recording data includes the cough sound.
  • the method also includes: the intelligent terminal device receives vibration data sent by the earphones, where the vibration data is data corresponding to the vibration signals detected by the earphones; the intelligent terminal device analyzes and counts coughs according to the recording data
  • the information includes: the intelligent terminal device analyzes and collects cough information based on recording data and vibration data.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • the intelligent terminal device determines that the recording data does not include cough sounds, it deletes the recording data.
  • the fifth aspect provides a cough monitoring system, characterized in that the system includes headphones and an intelligent terminal device.
  • the earphones are worn on the user's head and neck and are used to detect vibration signals; the earphones are also used to activate the microphone to record when a vibration signal is detected to obtain recording data; the earphones are also used to detect whether the recording data includes cough sounds; The earphone is also used to send recording data to the smart terminal device when the recording data includes cough sounds; the smart terminal device is used to analyze and count the user's cough information based on the recording data.
  • the earphones are specifically used to compare the similarity between the recording data and the cough sound data.
  • the cough sound data is the user's cough sound data that was previously recorded; if the similarity between the recording data and the cough sound data is If the degree is greater than or equal to the threshold, the headset determines that the recording data includes cough sounds; if the similarity between the recording data and the cough sound data is less than the threshold, the headset determines that the recording data does not include cough sounds.
  • the earphone is also used to record vibration data corresponding to the detected vibration signal.
  • the headset is also used to send recording data to the smart terminal device, so that the smart terminal device can analyze and collect cough information based on the recording data and vibration data.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • the earphone is also used to delete the recording data when the recording data does not include cough sounds.
  • a sixth aspect provides a cough monitoring system, characterized in that the system includes headphones and an intelligent terminal device; wherein,
  • Earphones worn on the user’s head and neck, are used to detect vibration signals
  • Headset used to send an instruction message to the smart terminal device when a vibration signal is detected
  • An intelligent terminal device is used to activate the microphone for recording according to the instruction message and obtain the recording data
  • the smart terminal device is also used to analyze and compile statistics on the user's cough information based on the recording data when it is determined that the recording data includes cough sounds.
  • the smart terminal device is specifically used to compare the similarity between the recording data and the cough sound data.
  • the cough sound data is the user's cough sound data that was previously recorded, and determines the similarity between the recording data and the cough sound data. When the similarity between them is greater than or equal to the threshold, it is determined that the recording data includes cough sounds.
  • the smart terminal device is also used to receive vibration data sent by the earphones.
  • the vibration data is the data corresponding to the vibration signals detected by the earphone recording; the smart terminal device analyzes and collects cough information based on the recording data: the smart terminal The device analyzes and collects cough information based on recording data and vibration data.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • the intelligent terminal device determines that the recording data does not include cough sounds, it deletes the recording data.
  • a seventh aspect provides an earphone.
  • the headset includes: a vibration detection module for detecting vibration signals; a recording module for starting a microphone to record when the vibration detection module detects a vibration signal to obtain recording data; a cough sound detection module The block is used to detect whether the recording data includes cough sounds; the sending module is used to send the recording data to the intelligent terminal device when it is determined that the recording data includes cough sounds, so that the intelligent terminal device analyzes and counts the user's cough information based on the recording data.
  • the cough sound detection module is specifically used to compare the similarity between the recording data and the cough sound data.
  • the cough sound data is the cough sound data of the user that was previously recorded; and is used to compare the recording data with the cough sound data.
  • the similarity between the sound data is greater than or equal to the threshold, it is determined that the recording data includes a cough sound; or when the similarity between the recording data and the cough sound data is less than the threshold, it is determined that the recording data does not include a cough sound.
  • the headset further includes: a recording module, configured to record vibration data corresponding to the detected vibration signal.
  • the sending module is also used to send vibration data to the intelligent terminal device, so that the intelligent terminal device analyzes and counts cough information based on the recording data and vibration data.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • An eighth aspect provides an earphone.
  • the headset includes: a vibration detection module, used to detect vibration signals; a sending module, used to send an instruction message to an intelligent terminal device when a vibration signal is detected, so that the intelligent terminal device activates the microphone to record according to the instruction message to obtain recording data, and When it is determined that the recording data includes cough sounds, the user's cough information is analyzed and counted based on the recording data.
  • a ninth aspect provides a cough monitoring device.
  • the device includes: a receiving module, used to receive an instruction message sent by an earphone, which is worn on the user's head and neck; the instruction message is generated by the earphone detecting a vibration signal; a recording module, used to activate a microphone for recording when receiving the instruction message, Obtain the recording data; the detection module is used to detect and determine that the recording data includes cough sounds; the analysis and statistics module is used to analyze and count the user's cough information based on the recording data.
  • the detection module is specifically used to compare the similarity between the recording data and the cough sound data.
  • the cough sound data is the cough sound data of the user previously recorded; determine the similarity between the recording data and the cough sound data. If the similarity is greater than or equal to the threshold, it is determined that the recording data includes cough sounds.
  • the receiving module is also used to receive vibration data sent by the earphone, where the vibration data is data corresponding to the vibration signal detected by the earphone recording.
  • the analysis and statistics module is used to analyze and collect statistics on cough information based on recording data and vibration data.
  • the device includes: a deletion module configured to delete the recording data when the recording data does not include cough sounds.
  • a tenth aspect provides a cough monitoring device.
  • the device includes a processor and memory.
  • the processor is coupled to the memory, and the processor is configured to perform any of the above-mentioned first to third aspects or any possible implementation of the first to third aspects based on instructions stored in the memory. Monitoring methods.
  • An eleventh aspect provides a computer-readable storage medium.
  • the computer-readable storage medium includes instructions that, when the computer-readable storage medium is run on a computer, cause the computer to execute any of the above-mentioned first to third aspects or any possible implementation of the first to third aspects. Cough monitoring methods in .
  • Figure 1 is a schematic structural diagram of an embodiment of a cough monitoring system provided by this application.
  • Figure 2 is a schematic flow chart of the first embodiment of the cough monitoring method provided by this application.
  • Figure 3 is a schematic flow chart of the second embodiment of the cough monitoring method provided by this application.
  • Figure 4 is a schematic flow chart of the third embodiment of the cough monitoring method provided by this application.
  • Figure 5 is a schematic flow chart of the fourth embodiment of the cough monitoring method provided by this application.
  • Figure 6 is a schematic flow chart of the fifth embodiment of the cough monitoring method provided by this application.
  • Figure 7 is a schematic flow chart of the sixth embodiment of the cough monitoring method provided by this application.
  • Figure 8 is a schematic structural diagram of an embodiment of the earphone provided by the present application.
  • Figure 9 is a schematic structural diagram of another embodiment of the earphone provided by the present application.
  • Figure 10 is a schematic structural diagram of an embodiment of the cough monitoring device provided by the present application.
  • Figure 11 is a schematic structural diagram of an embodiment of a cough monitoring device provided by this application.
  • This application provides a cough monitoring method and related equipment to reduce user privacy security risks and equipment power consumption.
  • first, second, third, etc. may be used in this application to describe various messages/frames, requests and terminal devices, these messages/frames, requests and terminal devices should not be limited to these terms. . These terms are only used to distinguish messages/frames, requests and end devices from each other.
  • the first terminal device may also be called a second terminal device, and similarly, the second terminal device may also be called a first terminal device.
  • the words “if” or “if” as used herein may be interpreted as “when” or “when” or “in response to determination” or “in response to detection.”
  • the phrase “if determined” or “if (stated condition or event) is detected” may be interpreted as “when determined” or “in response to determining” or “when (stated condition or event) is detected )” or “in response to detecting (a stated condition or event)”.
  • Figure 1 is a schematic structural diagram of an embodiment of a cough monitoring system provided by this application.
  • the cough monitoring system in this embodiment includes headphones and an intelligent terminal device.
  • the earphone has a vibration detection function.
  • the earphone specifically includes a vibration sensor (not shown) for detecting vibration signals.
  • Smart terminal devices are used to analyze cough information.
  • the earphones are worn on the user's head and neck. When the user coughs, the vocal cords and head will vibrate, so the headphones worn on the user's head or neck can accurately detect the vibration signal when the user coughs.
  • the headphones can be bone conduction headphones.
  • Bone conduction headphones are generally worn on the user's head, close to the user's skull.
  • the vibration of the skull produced when the user coughs can be accurately detected by the vibration sensor of the bone conduction headphones.
  • the earphones can also be neck-mounted earphones, and the vibration sensor can be arranged on the neck-mounted part of the earphones, so that the vibration sensor is close to the user's vocal cords, and the vibration of the vocal cords generated when the user coughs can be accurately detected by the vibration sensor of the neck-mounted part.
  • Smart terminal devices can be terminal devices with computing power such as smartphones or tablet computers.
  • a communication connection is established between the headset and the smart terminal device, and the headset and the smart terminal device can interact with each other based on the communication connection.
  • the headset and the smart terminal device can be connected via Bluetooth.
  • the headset and the smart terminal device can also be connected through a wireless local area network (WLAN).
  • WLAN wireless local area network
  • the smart terminal device serves as a wireless hotspot, and the headset is connected to the wireless hotspot to connect with the smart terminal device.
  • the headset and the smart terminal device can also be connected through near field communication (NFC).
  • NFC near field communication
  • the headset After detecting the vibration signal, the headset can activate its own microphone to record and obtain the recording data. The headset detects whether the recording data contains cough sounds. After detecting the vibration signal, the headset can also notify the smart terminal device to turn on the microphone of the smart terminal device for recording to obtain the recording data, and the smart terminal device detects whether the recording data contains a cough sound.
  • the earphone After the earphone detects the vibration signal, the earphone records to obtain the recording data, the earphone sends the recording data to the smart terminal device, and the smart terminal device detects whether the recording data contains a cough. sound.
  • the following describes the earphone recording and cough sound detection, and the smart terminal device recording and cough sound detection respectively.
  • Figure 2 is a schematic flow chart of the first embodiment of the cough monitoring method provided by this application. This embodiment includes the following steps:
  • the earphone In response to detecting the vibration signal, the earphone activates the microphone to record and obtain the recording data, and the earphone is worn on the user's head and neck.
  • the headset's vibration sensor After the headset's vibration sensor detects a vibration signal, the headset starts recording with the headset's microphone.
  • the vibration sensor generates mechanical vibration under the influence of external environmental vibration, and converts the mechanical vibration amount into an electrical signal to detect the vibration signal.
  • the vibration sensor is passively triggered to detect vibration signals and can remain in a low power consumption state when not triggered.
  • the microphone is turned on for recording only after the headset detects a vibration signal, and the microphone does not need to be turned on continuously for recording, which can not only reduce the power consumption of the headset, but also protect user privacy.
  • the time when the headset ends recording can be determined based on the vibration signal. For example, if the headset does not detect a vibration signal within a preset time period after the last time it detected a vibration signal, the headset can stop recording to obtain recording data.
  • the preset time period may be, for example, 30 seconds, 1 minute, 2 minutes, or 5 minutes, etc., and is not limited here.
  • the recording data includes the collection time of the recording data.
  • the collection time specifically includes the start time and end time.
  • the collection time of the recording data is used to analyze statistical cough information.
  • the headset does not turn on the microphone every time it detects a vibration signal. For example, when the headset detects a vibration signal, the microphone is already turned on, and there is no need to turn on the microphone again.
  • S202 The headset detects whether the recording data includes cough sounds.
  • Cough is generally sudden and explosive.
  • the cough is in the explosive stage at the beginning, and it has the characteristics of short duration, strong energy and rapid increase in sound amplitude.
  • After the explosive stage it enters a relatively stable stage. This stage lasts longer than the explosive stage, but the energy is weaker than the explosive stage.
  • cough sounds have characteristics that are different from other speech signals.
  • At least one characteristic parameter that can characterize a cough sound can be extracted from the recording data, and whether the recording data includes a cough sound is identified based on these characteristic parameters and a corresponding detection algorithm.
  • Characteristic parameters that characterize cough sounds include, for example, zero-crossing rate, short-time energy, perceptual linear predictive coefficient (perceptual linear predictive coefficient, LPL), linear predictive cepstral coefficient (linear predictive cepstral coefficient, LPCC) and Mel frequency cepstral coefficient (Mel -At least one of -frequency cepstral coefficients, MFCC).
  • the detection algorithm can be Fisher's discriminant method, dynamic time normalization, least neighbor method, hidden Markov model, Gaussian mixture model, piecewise Gaussian model, artificial neural network or support vector machine and other algorithms.
  • the function of the earphones to detect whether the recording data includes cough sounds is to determine whether to continue to save the recording in the earphones. data, or whether to send the recording data to the smart terminal device.
  • the headset detects that the recording data includes a cough sound
  • the headset can continue to save the recording data until the smart terminal device pulls the recording data from the headset and sends the recording data to the smart terminal device, that is, executing S203.
  • the headset may also send the recording data to the smart terminal device when the headset detects that the recording data includes a cough sound; and when the headset determines that the recording data does not include a cough sound, perform S204.
  • the detection algorithm and characteristic parameters used by the headset to detect whether the recording data includes cough sound can take into account the headset's computing power and accuracy.
  • the feature parameters and detection algorithm that require the least computing power can be selected.
  • the feature parameter can choose the zero-crossing rate
  • the detection algorithm can choose the Fisher discriminant algorithm.
  • the detection algorithm and characteristic parameters used by the earphones can be selected according to actual needs, and there are no restrictions here.
  • the earphones in order to improve the detection accuracy of cough sounds in recorded data, can pre-record and save the user's cough sound data, and use the recorded data to match the cough sound data to determine whether the recorded data includes Coughing sound.
  • the headset microphone is activated to record the cough sound data of the user's active cough, and save the cough sound data.
  • the smart terminal device collects the cough sound data of the user's active cough and sends the cough sound data to the headset for storage.
  • the cough sound data can be original audio data, or extracted data corresponding to characteristic parameters that can characterize the user's cough sound.
  • the cough sound data may include cough sounds recorded by the user's multiple active coughs, or data corresponding to the characteristic parameters of the cough sounds recorded from multiple active coughs, thereby increasing the number of samples and improving the accuracy of cough sound detection and recognition.
  • Headphones compare the similarity between recording data and cough sound data. If the similarity between the recording data and the cough sound data is greater than or equal to the threshold, the headset determines that the recording data includes the cough sound. If the similarity between the recording data and the cough sound data is less than the threshold, the headset determines that the recording data does not include the cough sound.
  • the similarity can be indicated by indicators such as cosine similarity, Euclidean distance, or Manhattan distance between the recording data and the cough sound data.
  • the headset sends the recording data to the smart terminal device, so that the smart terminal device analyzes and counts the user's cough information based on the recording data.
  • the headset can periodically send the collected recording data to the smart terminal device.
  • the headset can also collect the recording data and then send the recording data to the smart terminal device.
  • the smart terminal device pulls the recording data from the earphones.
  • the detection algorithm used by the smart terminal device can be a more accurate algorithm, and the characteristic parameters can be a combination of multiple characteristic parameters that can more accurately characterize cough sounds.
  • the algorithm can be a hidden Markov model, an artificial neural network or a support vector machine, etc.
  • the characteristic parameters can include zero-crossing rate, short-term energy and Mel frequency cepstrum coefficient.
  • the detection algorithm and characteristic parameters used by smart terminal devices can be selected according to actual needs, and there are no restrictions here.
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend and cough duration.
  • a cough sound in the recording data is detected, the number of coughs is increased by 1, and the cough time corresponding to the cough sound is recorded.
  • further information such as cough frequency, cough trend and cough duration can be obtained.
  • Cough frequency is, for example, the number of coughs per minute, every 5 minutes, 10 minutes, 30 minutes, 1 hour, 6 hours, 12 hours or 24 hours Sum.
  • the cough trend may be an increase or decrease trend in the sum of the number of coughs in a time period relative to the sum of the number of coughs in a previous time period, such as a trend in the number of coughs per hour.
  • the cough duration can refer to the duration corresponding to when cough sounds appear in a concentrated manner, or it can be the duration between the earliest cough sound detected in the recording data and the latest cough sound.
  • the cough information can be the user's cough data analyzed from the recording data collected when the user last coughed, or it can be a preset time period (such as 6 hours, 12 hours, 24 hours, 2 days, 7 days, the same day, and the week). Or the total user cough data collected within the current month, etc.).
  • the cough information obtained from the analysis and statistics of the smart terminal device can be displayed on the cough monitoring client of the smart terminal device, so that the user can intuitively know the cough situation and physical status.
  • the local recording data can be deleted to release the storage space of the headset.
  • the vibration of the user's head and neck is not caused by coughing, so the cough sound may not be included in the recording data.
  • the recording data can be deleted to free up the storage space of the headset.
  • the earphones only turn on the microphone for recording after detecting the vibration signal, which can reduce user privacy and security risks and also reduce the power consumption of the earphones.
  • the headset After the headset detects that the recording data contains cough sounds, it will send the recording data to the smart terminal device. Otherwise, the recording data will be deleted, which can reduce the occupation of the headset storage resources and reduce unnecessary data transmission between the headset and the smart terminal device. Reduce headset power consumption.
  • the sounds recorded may also include some sounds from the user's environment. Sounds in the environment may cause false detections, such as identifying the collected cough sounds of other people as the user's cough sounds, etc., thus affecting the accuracy of cough sound detection.
  • this application also combines the vibration data corresponding to the vibration signals detected by the earphones to analyze and collect cough information.
  • Figure 3 is a schematic flow chart of the second embodiment of the cough monitoring method provided by this application. To simplify the description, the similarities between this embodiment and the first embodiment of the cough monitoring method will not be described again. This embodiment includes the following steps:
  • the earphone responds to detecting the vibration signal, records the vibration data corresponding to the vibration signal, and starts the microphone to record to obtain the recording data.
  • the earphone is worn on the user's head and neck.
  • the vibration data includes, for example, the time when the vibration signal was detected.
  • the vibration data may also include vibration characteristic values such as time domain characteristic values and/or frequency domain characteristic values of the vibration signal.
  • Time domain characteristic values include, for example, the mean, variance, kurtosis or peak value of the vibration signal.
  • Frequency domain feature values include, for example, frequency or energy.
  • the collection time of the vibration signal is recorded, and the time domain characteristic value and/or frequency domain characteristic value of the vibration signal can also be recorded to obtain vibration data.
  • the acquisition time of the vibration data coincides at least partially with the acquisition time of the recording data.
  • the vibration data includes, for example, data corresponding to all vibration signals between the time when the vibration signal triggering the microphone is triggered and the time when the last vibration signal is collected before the end of the recording data.
  • S302 The headset detects whether the recording data includes cough sounds.
  • the headset can also combine vibration data to detect whether the recording data includes cough sounds. For example, based on the time of the detected vibration signal, a recording segment within a preset time period corresponding to the recording data is obtained, and whether the recording segment includes a cough sound is detected. For another example, after the headset detects that the recording data includes a cough sound, it further determines whether there is data corresponding to the vibration signal detected in the time period corresponding to the cough sound in the vibration data. If so, the recording data packet can be determined. includes a cough sound; if it does not exist, it can be determined that the cough sound is a false detection. If it is determined based on the vibration data that the cough sounds detected in the recording data are false detections, it can be determined that the cough sound is not included in the recording data. This can improve the efficiency and accuracy of earphones in detecting cough sounds.
  • the headset sends the recording data and vibration data to the intelligent terminal device, so that the intelligent terminal device analyzes and counts the user's cough information based on the recording data and vibration data.
  • the vibration signals detected by the earphones are not always caused by the user's cough, the user's cough must be accompanied by the vibration of the user's vocal cords and skull, so that the corresponding vibration data can be recorded by the earphones. Therefore, combined with vibration data, sounds similar to cough characteristics or cough sounds of other people in the environment collected in the recording data can be eliminated, thereby improving the accuracy of cough sound detection.
  • the smart terminal device detects that the recording data includes a cough sound, it further determines whether there is data corresponding to the vibration signal detected in the time period corresponding to the cough sound in the vibration data. If it exists, it can be determined that the cough sound is accurate and the cough sound is correct. The number of coughs in the information is increased by 1, and the time corresponding to the cough sound is recorded; if it does not exist, it can be determined that the cough sound is a false detection, and the cough information will not be updated for the time being.
  • the intelligent terminal device can further combine the vibration characteristics to determine whether the detected cough sound is accurate. For example, when data corresponding to the vibration signal is detected in the time period corresponding to the cough sound in the vibration data, and at least part of the vibration characteristic values is greater than the threshold, the cough sound is determined to be accurate. It can be understood that different vibration characteristic values correspond to different thresholds.
  • S304 The headset deletes the recording data and vibration data.
  • the recording data and vibration data can be deleted to free up the storage space of the headset.
  • the earphones only turn on the microphone for recording after detecting the vibration signal, which can reduce user privacy and security risks and also reduce the power consumption of the earphones.
  • the headset After the headset detects that the recording data contains cough sounds, it will send the recording data to the smart terminal device. Otherwise, it will delete the recording data and vibration data, which can reduce the occupation of the headset storage resources and reduce unnecessary data between the headset and the smart terminal device. transmission, thereby reducing headset power consumption.
  • vibration data to determine whether the recording data includes cough sounds can improve the accuracy of cough sound recognition.
  • FIG. 4 is a schematic flow chart of the third embodiment of the cough monitoring method provided by the present application. This embodiment includes the following steps:
  • the headset detects a vibration signal, and the headset is worn on the user's head and neck.
  • the headset In response to the vibration signal, the headset sends an instruction message to the intelligent terminal device.
  • the instruction message is used to instruct the smart terminal device to turn on the microphone for recording.
  • the headset does not send an instruction message for starting the microphone to the smart terminal device every time it detects a vibration signal. If the microphone of the smart terminal device is already turned on when the headset detects a vibration signal, that is, before the headset instructs the smart terminal device to end recording, the headset does not need to send an instruction message to the smart terminal device again.
  • S403 The smart terminal device activates the microphone to record in response to the instruction message, and obtains the recording data.
  • the smart terminal device After receiving the instruction message, the smart terminal device starts the microphone to record.
  • Example of conditions for ending recording on a smart terminal device For example, the smart terminal device receives a message sent by the earphone to indicate the end of recording.
  • the message used to indicate the end of recording is, for example, generated after the headset does not detect a vibration signal within a preset time period after the last time it detected a vibration signal.
  • the preset time period may be, for example, 30 seconds, 1 minute, 2 minutes, or 5 minutes, etc., and is not limited here.
  • S404 The smart terminal device detects and determines that the recording data includes cough sounds.
  • the method of detecting cough sounds by smart terminal devices is similar to S203, so it will not be described again here.
  • S405 The intelligent terminal device analyzes and counts the user's cough information based on the recording data.
  • S404 and S405 can be implemented in the same step, that is, when the intelligent terminal device detects the cough sound in the recording data, it simultaneously analyzes and counts the cough information. For example, when a cough sound in the recording data is detected, the number of coughs in the cough information is increased by 1, and the time corresponding to the cough sound is recorded; if no cough sound is detected in the recording data after the detection of the recording data is completed, then Cough information is not updated.
  • the recording data can be deleted, thereby saving storage space of the smart terminal device.
  • the smart terminal device activates the microphone for recording only after receiving the instruction message sent by the earphone due to detection of a vibration signal, which can not only reduce user privacy security risks, but also reduce the power consumption of the smart terminal device.
  • recording and cough sound detection are performed by smart terminal devices, which can reduce the requirements for the storage resources and computing resources of the earphones, and can reduce the cost of the earphones.
  • FIG. 5 is a schematic flow chart of the fourth embodiment of the cough monitoring method provided by the present application. This embodiment includes the following steps:
  • S501 The headset detects a vibration signal, and the headset is worn on the user's head and neck.
  • the instruction message is used to instruct the smart terminal device to turn on the microphone for recording.
  • S503 The smart terminal device activates the microphone to record in response to the instruction message, and obtains recording data.
  • the smart terminal device After receiving the instruction message, the smart terminal device starts the microphone to record.
  • the condition for the smart terminal device to end the recording is, for example, that the smart terminal device receives a message sent by the earphone indicating to end the recording.
  • the message used to indicate the end of recording is, for example, generated after the headset does not detect a vibration signal within a preset time period after the last time it detected a vibration signal.
  • the preset time period may be, for example, 30 seconds, 1 minute, 2 minutes, or 5 minutes, etc., and is not limited here.
  • Vibration data is the data recorded when the headset detects a vibration signal.
  • vibration data please refer to the relevant description of S301, so we will not repeat them here.
  • S505 The headset sends vibration data to the smart terminal device.
  • the vibration data and the message used to indicate the end of recording can be sent to the smart terminal device together by the headset.
  • the vibration data and the message indicating the end of recording can also be sent separately from the earphones to the smart terminal device.
  • the message indicating the end of recording can be sent first and then the vibration data, or the reverse order of sending can be used. There is no restriction here. .
  • S506 The intelligent terminal device analyzes and counts the user's cough information based on the recording data and vibration data.
  • the method of detecting cough sounds and analyzing statistical cough information by the smart terminal device is similar to that of S203, so it will not be described again here.
  • the smart terminal device activates the microphone for recording only after receiving the instruction message sent by the earphone due to detection of a vibration signal, which can not only reduce user privacy security risks, but also reduce the power consumption of the smart terminal device.
  • recording and cough sound detection are performed by smart terminal devices, which can reduce the requirements for the storage resources and computing resources of the earphones, and can reduce the cost of the earphones.
  • combining vibration data to determine whether the recording data includes cough sounds can improve the accuracy of cough sound recognition.
  • Figure 6 is a schematic flow chart of the fifth embodiment of the cough monitoring method provided by the present application.
  • the execution subject of this embodiment is the earphone. This embodiment includes the following steps:
  • the headset detects a vibration signal, and the headset is worn on the user's head and neck.
  • the headset In response to the vibration signal, the headset sends an instruction message to the smart terminal device, so that the smart terminal device activates the microphone to record according to the instruction message to obtain the recording data, and when it is determined that the recording data includes cough sounds, analyze and count the user's cough information based on the recording data .
  • Figure 7 is a schematic flow chart of the sixth embodiment of the cough monitoring method provided by the present application.
  • the execution subject of this embodiment is an intelligent terminal device. This embodiment includes the following steps:
  • the intelligent terminal device receives the instruction message sent by the earphone.
  • the earphone is worn on the user's head and neck.
  • the instruction message is generated by the vibration signal detected by the earphone.
  • the smart terminal device In response to the instruction message, the smart terminal device starts the microphone to record, and obtains the recording data.
  • S703 The smart terminal device detects and determines that the recording data includes cough sounds.
  • S704 The intelligent terminal device analyzes and counts the user's cough information based on the recording data.
  • FIG. 8 is a schematic structural diagram of an embodiment of the earphone provided by the present application.
  • the Headset 800 includes:
  • Vibration detection module 801 is used to detect vibration signals.
  • the recording module 802 is used to activate the microphone for recording when the vibration detection module 801 detects a vibration signal, and obtain recording data.
  • the cough sound detection module 803 is used to detect whether the recording data includes cough sounds.
  • the sending module 804 is configured to send the recording data to the intelligent terminal device when it is determined that the recording data includes cough sounds, so that the intelligent terminal device analyzes and counts the user's cough information based on the recording data.
  • the cough sound detection module 803 is specifically used to compare the similarity between the recording data and the cough sound data.
  • the cough sound data is the user's cough sound data that was previously recorded; between the recording data and the cough sound data When the similarity between them is greater than or equal to the threshold, it is determined that the recording data includes a cough sound; or when the similarity between the recording data and the cough sound data is less than the threshold, it is determined that the recording data does not include a cough sound.
  • the headset further includes: a recording module 805, configured to record vibration data corresponding to the detected vibration signal.
  • the sending module 804 is also used to send vibration data to the intelligent terminal device, so that the intelligent terminal device can root Cough information is analyzed and analyzed based on recording data and vibration data.
  • the recording data includes audio data and the collection time of the audio data
  • the cough information includes at least one of cough time, cough number, cough frequency, cough trend, and cough duration.
  • the execution action of the earphone is implemented by the earphone 900 .
  • Figure 9 is a schematic structural diagram of another embodiment of the earphone provided by the present application.
  • the earphone 900 includes: a vibration detection module 901 for detecting vibration signals.
  • the sending module 902 is used to send an instruction message to the intelligent terminal device when a vibration signal is detected, so that the intelligent terminal device activates the microphone to record according to the instruction message to obtain the recording data, and analyzes statistics based on the recording data when it is determined that the recording data includes cough sounds. User's cough information.
  • the sending module 902 is also configured to send vibration data to the intelligent terminal device, so that the intelligent terminal device can analyze and collect cough information of the user based on the recording data and vibration data.
  • Vibration data is corresponding data recorded when the vibration detection module 901 detects a vibration signal.
  • FIG. 10 is a schematic structural diagram of an embodiment of a cough monitoring device provided by this application.
  • the device 1000 includes:
  • the receiving module 1001 is used to receive an instruction message sent by the earphone.
  • the earphone is worn on the user's head and neck.
  • the instruction message is generated when the earphone detects a vibration signal.
  • the recording module 1002 is used to start the microphone to record when receiving the instruction message, and obtain the recording data.
  • the detection module 1003 is used to detect and determine that the recording data includes cough sounds,
  • the analysis and statistics module 1004 is used to analyze and count the user's cough information based on the recording data.
  • the detection module 1003 is specifically used to compare the similarity between the recording data and the cough sound data.
  • the cough sound data is the user's cough sound data that was previously recorded; determine the difference between the recording data and the cough sound data.
  • the similarity is greater than or equal to the threshold, and it is determined that the recording data includes cough sounds.
  • the receiving module 1001 is also used to receive vibration data sent by the earphone, where the vibration data is data corresponding to the vibration signal detected by the earphone recording.
  • the analysis and statistics module 1004 is used to analyze and collect statistics on cough information based on recording data and vibration data.
  • the device 1000 includes: a deletion module 1005, configured to delete the recording data when the recording data does not include cough sounds.
  • FIG 11 is a schematic structural diagram of an embodiment of a cough monitoring device provided by this application.
  • the cough detection device 1100 includes a processor 1101 and a memory 1102.
  • the processor 1101 is coupled to the memory 1102, and the processor 1101 is configured to, based on instructions stored in the memory 1102, execute any of the cough monitoring methods performed by the earphones in the above-mentioned Figures 2 to 6, or Figure 3, Figure 4 or Figure 7 Cough monitoring method performed by intelligent terminal equipment.
  • This application also provides a computer-readable storage medium on which a computer program is stored.
  • the computer program is executed by a computer, the cough monitoring method process of any of the above method embodiments is implemented.
  • the disclosed systems, devices and methods can be implemented in other ways.
  • the device embodiments described above are only illustrative.
  • the division of the units is only a logical function division. In actual implementation, there may be other division methods, for example, multiple units or components may be combined.
  • the integration can either be integrated into another system, or some features can be ignored, or not implemented.
  • the coupling or direct coupling or communication connection between each other shown or discussed may be through some interfaces, and the indirect coupling or communication connection of the devices or units may be in electrical or other forms.
  • the units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or they may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
  • each functional unit in each embodiment of the present application can be integrated into one processing unit, each unit can exist physically alone, or two or more units can be integrated into one unit.
  • the above integrated units can be implemented in the form of hardware or software functional units.
  • the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it may be stored in a computer-readable storage medium.
  • the computer software product is stored in a storage medium and includes a number of instructions to enable a computer device (which can be a personal computer, Server, or network device, etc.) executes all or part of the steps of the methods described in various embodiments of this application.
  • the aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, read-only memory), random access memory (RAM, random access memory), magnetic disk or optical disk and other media that can store program code. .

Landscapes

  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Public Health (AREA)
  • Heart & Thoracic Surgery (AREA)
  • Biomedical Technology (AREA)
  • Surgery (AREA)
  • Animal Behavior & Ethology (AREA)
  • Medical Informatics (AREA)
  • Molecular Biology (AREA)
  • Veterinary Medicine (AREA)
  • Pathology (AREA)
  • Biophysics (AREA)
  • Pulmonology (AREA)
  • Signal Processing (AREA)
  • Physiology (AREA)
  • Acoustics & Sound (AREA)
  • Artificial Intelligence (AREA)
  • Multimedia (AREA)
  • Psychiatry (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Mathematical Physics (AREA)
  • Fuzzy Systems (AREA)
  • Evolutionary Computation (AREA)
  • Epidemiology (AREA)
  • Computational Linguistics (AREA)
  • Audiology, Speech & Language Pathology (AREA)
  • Human Computer Interaction (AREA)
  • Headphones And Earphones (AREA)
  • Circuit For Audible Band Transducer (AREA)

Abstract

公开了一种咳嗽监测方法及相关设备，以降低用户隐私安全风险和设备功耗。该方法包括：耳机响应于检测到振动信号，启动麦克风进行录音得到录音数据，耳机佩戴于用户头颈部；耳机检测录音数据是否包括咳嗽音；若录音数据包括咳嗽音，耳机发送录音数据至智能终端设备，以使智能终端设备根据录音数据分析统计用户的咳嗽信息。

Description

咳嗽监测方法及相关设备
本申请要求于2022年6月20日提交中国专利局、申请号为202210697764.5、发明名称为“咳嗽监测方法及相关设备”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
本申请涉及互联网技术领域，特别是涉及一种咳嗽监测方法及相关设备。
背景技术
咳嗽是呼吸专科门诊和社区门诊患者最常见的症状。咳嗽一般由气管、支气管炎症、异物、物理或化学性刺激引起。咳嗽具有清除呼吸道异物和分泌物的保护性作用，但频繁剧烈的咳嗽对患者的工作、学习和生活质量造成严重影响。
咳嗽的病因复杂，但随着近年来医学的发展，国内外学者对咳嗽也有了更深入的认识。不同的疾病咳嗽会呈现不同的咳嗽表现，一般夜间咳嗽为主的患者会首先考虑咳嗽变异性哮喘的诊断；冬春季发作的咳嗽会考虑慢性支气管炎的诊断。在临床诊断中，医生会重点关注咳嗽发生的时间、频率、持续时长等信息，并对疾病类型及严重程度开展评估。因此，开展咳嗽的连续监测对疾病诊断和评估具有重要价值。
目前一般通过咳嗽监测仪实现咳嗽的连续监测。咳嗽检测仪由麦克风和存储器组成。咳嗽监测仪的麦克风24小时开启录音记录音频数据。然而麦克风常开，一方面存储用户隐私安全风险，另一方面导致设备功耗大，以及存储资源需求大。
发明内容
本申请提供了一种咳嗽监测方法及相关设备，以降低用户隐私安全风险和设备功耗。
第一方面提供一种咳嗽监测方法。该方法包括：耳机响应于检测到振动信号，启动麦克风进行录音得到录音数据，耳机佩戴于用户头颈部；耳机检测录音数据是否包括咳嗽音；若录音数据包括咳嗽音，耳机发送录音数据至智能终端设备，以使智能终端设备根据录音数据分析统计用户的咳嗽信息。通过由佩戴于用户头颈部的耳机检测振动信号时，启动麦克风进行录音，从而无需麦克风全天候开启录音，能够降低用户隐私安全风险，并且降低耳机的功耗和存储资源的需求。
在一种可能的实现方式中，耳机检测录音数据是否包括咳嗽音包括：耳机比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；若录音数据与咳嗽音数据之间的相似度大于或等于阈值，耳机确定录音数据包括咳嗽音；若录音数据与咳嗽音数据之间的相似度小于阈值，耳机确定录音数据不包括咳嗽音。与预先录制的用户的咳嗽音数据与录音数据进行匹配，能够提高咳嗽音的识别准确率。
在一种可能的实现方式中，该方法还包括：耳机记录检测到的振动信号对应的振动数据。耳机发送录音数据至智能终端设备，以使智能终端设备根据录音数据分析统计咳嗽信息包括：耳机发送录音数据和振动数据至智能终端设备，以使智能终端设备根据录音数据和振动数据 分析统计咳嗽信息。结合振动信号对应的振动数据统计咳嗽信息，能够提高咳嗽统计信息的准确率。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
在一种可能的实现方式中，该方法还包括：若录音数据不包括咳嗽音，则耳机删除录音数据。从而节省存储空间，降低对存储资源的需求。
第二方面提供一种咳嗽监测方法。该方法包括：耳机检测到振动信号，耳机佩戴于用户头颈部；响应于振动信号，耳机向智能终端设备发送指示消息，以使智能终端设备根据指示消息启动麦克风进行录音得到录音数据，并在确定录音数据包括咳嗽音时根据录音数据分析统计用户的咳嗽信息。在耳机检测到振动信号时，向智能终端设备发送指示录音的指示消息，从而无需麦克风全天候开启录音，能够降低用户隐私安全风险，并且功耗和存储资源的消耗。并且，由只能终端设备录音和检测录音数据，能够降低对耳机的计算能力和存储能力的需求，降低耳机成本。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
第三方面提供一种咳嗽监测方法。该方法包括：智能终端设备接收耳机发送的指示消息，耳机佩戴于用户头颈部，指示消息为耳机检测到振动信号生成的；响应于指示消息，智能终端设备启动麦克风进行录音，得到录音数据；智能终端设备检测确定录音数据包括咳嗽音；智能终端设备根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，智能终端设备检测确定录音数据包括咳嗽音包括：智能终端设备比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；智能终端设备确定录音数据与咳嗽音数据之间的相似度大于或等于阈值，智能终端设备确定录音数据包括咳嗽音。
在一种可能的实现方式中，该方法还包括：智能终端设备接收耳机发送的振动数据，振动数据为耳机记录检测到的振动信号对应的数据；智能终端设备根据录音数据分析统计咳嗽信息包括：智能终端设备根据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
第四方面提供一种咳嗽监测方法。该方法包括：耳机检测到振动信号，耳机佩戴于用户头颈部；响应于振动信号，耳机向智能终端设备发送指示消息；智能终端设备响应于指示消息启动麦克风进行录音，得到录音数据；智能终端设备检测确定录音数据包括咳嗽音；智能终端设备根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，智能终端设备检测确定录音数据包括咳嗽音包括：智能终端设备比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；智能终端设备确定录音数据与咳嗽音数据之间的相似度大于或等于阈值，智能终端设备确定录音数据包括咳嗽音。
在一种可能的实现方式中，该方法还包括：智能终端设备接收耳机发送的振动数据，振动数据为耳机记录检测到的振动信号对应的数据；智能终端设备根据录音数据分析统计咳嗽 信息包括：智能终端设备根据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
在一种可能的实现方式中，智能终端设备在确定录音数据不包括咳嗽音时，删除录音数据。
第五方面提供一种咳嗽监测系统，其特征在于，系统包括耳机和智能终端设备。其中，耳机，佩戴于用户头颈部，用于检测振动信号；耳机，还用于在检测到振动信号时，启动麦克风进行录音得到录音数据；耳机，还用于检测录音数据是否包括咳嗽音；耳机，还用于在录音数据包括咳嗽音时向智能终端设备发送录音数据；智能终端设备，用于根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，耳机具体用于比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；若录音数据与咳嗽音数据之间的相似度大于或等于阈值，耳机确定录音数据包括咳嗽音；若录音数据与咳嗽音数据之间的相似度小于阈值，耳机确定录音数据不包括咳嗽音。
在一种可能的实现方式中，耳机还用于记录检测到的振动信号对应的振动数据。耳机还用于发送录音数据至智能终端设备，以使智能终端设备根据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
在一种可能的实现方式中，耳机还用于在录音数据不包括咳嗽音时，耳机删除录音数据。
第六方面提供一种咳嗽监测系统，其特征在于，系统包括耳机和智能终端设备；其中，
耳机，佩戴于用户头颈部，用于检测振动信号；
耳机，用于在检测到振动信号时，向智能终端设备发送指示消息；
智能终端设备，用于根据指示消息启动麦克风进行录音，得到录音数据；
智能终端设备，还用于在检测确定录音数据包括咳嗽音时，根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，智能终端设备具体用于比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据，并在确定录音数据与咳嗽音数据之间的相似度大于或等于阈值时，确定录音数据包括咳嗽音。
在一种可能的实现方式中，智能终端设备还用于接收耳机发送的振动数据，振动数据为耳机记录检测到的振动信号对应的数据；智能终端设备根据录音数据分析统计咳嗽信息包括：智能终端设备根据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
在一种可能的实现方式中，智能终端设备在确定录音数据不包括咳嗽音时，删除录音数据。
第七方面提供一种耳机。该耳机包括：振动检测模块，用于检测振动信号；录音模块，用于在振动检测模块检测到振动信号时启动麦克风进行录音，得到录音数据；咳嗽音检测模 块，用于检测录音数据是否包括咳嗽音；发送模块，用于在确定录音数据包括咳嗽音时发送录音数据至智能终端设备，以使智能终端设备根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，咳嗽音检测模块具体用于比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；以及用于在录音数据与咳嗽音数据之间的相似度大于或等于阈值时，确定录音数据包括咳嗽音；或在录音数据与咳嗽音数据之间的相似度小于阈值时，确定录音数据不包括咳嗽音。
在一种可能的实现方式中，耳机还包括：记录模块，用于记录检测到的振动信号对应的振动数据。发送模块，还用于发送振动数据至智能终端设备，以使智能终端设备根据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
第八方面提供一种耳机。该耳机包括：振动检测模块，用于检测振动信号；发送模块，用于在检测到振动信号时向智能终端设备发送指示消息，以使智能终端设备根据指示消息启动麦克风进行录音得到录音数据，并在确定录音数据包括咳嗽音时根据录音数据分析统计用户的咳嗽信息。
第九方面提供一种咳嗽监测装置。该装置包括：接收模块，用于接收耳机发送的指示消息，耳机佩戴于用户头颈部，指示消息为耳机检测到振动信号生成的；录音模块，用于接收到指示消息时启动麦克风进行录音，得到录音数据；检测模块，用于检测确定录音数据包括咳嗽音；分析统计模块，用于根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，检测模块具体用于比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；确定录音数据与咳嗽音数据之间的相似度大于或等于阈值，确定录音数据包括咳嗽音。
在一种可能的实现方式中，接收模块还用于接收耳机发送的振动数据，振动数据为耳机记录检测到的振动信号对应的数据。分析统计模块，用于根据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，该装置包括：删除模块，用于在录音数据不包括咳嗽音时删除录音数据。
第十方面提供一种咳嗽监测设备。该设备包括处理器和存储器。处理器耦接存储器，处理器被配置为基于存储在存储器中的指令，执行上述的第一方面至第三方面中的任意方面或第一方面至第三方面的任意可能的实现方式中的咳嗽监测方法。
第十一方面提供一种计算机可读存储介质。计算机可读存储介质包括指令，当计算机可读存储介质在计算机上运行时，使得计算机执行上述的第一方面至第三方面中的任意方面或第一方面至第三方面的任意可能的实现方式中的咳嗽监测方法。
附图说明
图1为本申请提供的咳嗽监测系统一实施例的结构示意图；
图2为本申请提供的咳嗽监测方法第一实施例的流程示意图；
图3为本申请提供的咳嗽监测方法第二实施例的流程示意图；
图4为本申请提供的咳嗽监测方法第三实施例的流程示意图；
图5为本申请提供的咳嗽监测方法第四实施例的流程示意图；
图6为本申请提供的咳嗽监测方法第五实施例的流程示意图；
图7为本申请提供的咳嗽监测方法第六实施例的流程示意图；
图8为本申请提供的耳机一实施例的结构示意图；
图9为本申请提供的耳机另一实施例的结构示意图；
图10为本申请提供的咳嗽监测装置一实施例的结构示意图；
图11为本申请提供咳嗽监测设备一实施例的结构示意图。
具体实施方式
本申请提供了一种咳嗽监测方法及相关设备，以降低用户隐私安全风险和设备功耗。
在本申请中使用的术语是仅仅出于描述特定实施例的目的，而非旨在限制本申请。在本申请和所附权利要求书中所使用的单数形式的“一种”、“所述”和“该”也旨在包括多数形式，除非上下文清楚地表示其他含义。还应当理解，本文中使用的术语“和/或”是指并包含一个或多个相关联的列出项目的任何或所有可能组合。本文中字符“/”，一般表示前后关联对象是一种“或”的关系。
应当理解，尽管在本申请中可能采用术语第一、第二、第三等来描述各种报文/帧、请求和终端设备，但这些报文/帧、请求和终端设备不应限于这些术语。这些术语仅用来将报文/帧、请求和终端设备彼此区分开。例如，在不脱离本申请范围的情况下，第一终端设备也可以被称为第二终端设备，类似地，第二终端设备也可以被称为第一终端设备。
取决于语境，如在此所使用的词语“如果”或“若”可以被解释成为“在……时”或“当……时”或“响应于确定”或“响应于检测”。类似地，取决于语境，短语“如果确定”或“如果检测(陈述的条件或事件)”可以被解释成为“当确定时”或“响应于确定”或“当检测(陈述的条件或事件)时”或“响应于检测(陈述的条件或事件)”。
本申请中，“在……时”并非严格限制为“与此同时”的含义，还具有“在……之后”的含义。
如图1所示，图1为本申请提供的咳嗽监测系统一实施例的结构示意图。本实施例中的咳嗽监测系统包括耳机和智能终端设备。本实施例中，耳机具有振动检测功能。耳机具体例如包括振动传感器(图未示)，用于检测振动信号。智能终端设备用于分析咳嗽信息。
耳机佩戴于用户的头颈部。用户咳嗽时声带和头部会发生振动，从而佩戴于用户头部或者颈部的耳机能够在用户咳嗽时准确地检测到振动信号。
耳机可以是骨传导耳机。骨传导耳机一般佩戴于用户的头部，贴近用户头骨，用户咳嗽时产生的头骨振动能够被骨传导耳机的振动传感器准确地检测到。耳机还可以是挂脖式耳机，振动传感器可以设置于耳机的挂脖部分，从而振动传感器靠近用户声带，在用户咳嗽时产生的声带振动能够被挂脖式部分的振动传感器准确地检测到。
智能终端设备可以是智能手机或平板电脑等具有算力的终端设备。
耳机和智能终端设备建立有通信连接，基于通信连接耳机和智能终端设备可以进行数据交互。在一些实施方式中，耳机和智能终端设备可以通过蓝牙连接。在另一些实施方式中， 耳机和智能终端设备也可以通过无线局域网(wireless local area network，WLAN)连接，智能终端设备作为无线热点，耳机接入无线热点实现与智能终端设备的连接。在另一些实施方式中，耳机和智能终端设备还可以通过近场通信(near field communication，NFC)连接。
耳机在检测到振动信号之后，可以启动自身的麦克风进行录音得到录音数据，由耳机检测录音数据中是否包含咳嗽音。耳机也可以在检测到振动信号之后，通知智能终端设备开启智能终端设备的麦克风进行录音得到录音数据，由智能终端设备检测录音数据中是否包含咳嗽音。当然，在一些其他的实施方式中，也可以是耳机在检测到振动信号之后，由耳机录音得到录音数据，耳机将录音数据发送至智能终端设备，由智能终端设备检测该录音数据中是否包含咳嗽音。
以下分别对耳机录音和检测咳嗽音，和智能终端设备录音和检测咳嗽音进行描述。
如图2所示，图2为本申请提供的咳嗽监测方法第一实施例的流程示意图。本实施例包括如下步骤：
S201：耳机响应于检测到振动信号，启动麦克风进行录音得到录音数据，耳机佩戴于用户头颈部。
耳机在耳机的振动传感器检测到振动信号后，启动耳机的麦克风录音。
振动传感器在外界环境振动的影响下产生机械振动，并将机械振动量转换为电信号，实现振动信号的检测。振动传感器为被动触发检测振动信号的，在未被触发时能够保持在低功耗状态。在耳机检测到振动信号后才开启麦克风进行录音，也无需麦克风持续开启录音，既能够降低耳机功耗，又能够保护用户隐私。
耳机结束录音的时间可以根据振动信号而定。例如，耳机在上一次检测到振动信号之后的预设时间段内未检测到振动信号，耳机可以停止录音，从而得到录音数据。预设时间段例如可以是30秒、1分钟、2分钟或5分钟等，此处不做限制。
录音数据包括录音数据的采集时间。采集时间具体包括开始时间和结束时间等。录音数据的采集时间用于分析统计咳嗽信息。
可以理解，耳机并非每次检测到振动信号都启动麦克风，例如耳机检测到振动信号时麦克风已经开启，则无需再次开启麦克风。
S202：耳机检测录音数据是否包括咳嗽音。
咳嗽一般具有突发性和爆发性，咳嗽刚开始时即为爆发阶段，具有时间短、能量强和音幅值迅速增大等特点。爆发阶段之后进入相对平稳的阶段，该阶段持续时间较爆发阶段长，但能量弱于爆发阶段。
因而，咳嗽音具有区别于其他语音信号的特征。可以从录音数据中提取至少一个能够表征咳嗽音的特征参数，基于这些特征参数和相应的检测算法识别录音数据中是否包括咳嗽音。表征咳嗽音的特征参数例如包括过零率、短时能量、感知线性预测系数(perceptual linear predictive，LPL)、线性预测倒谱系数(linear predictive cepstral coefficient，LPCC)和梅尔频率倒谱系数(Mel-frequency cepstral coefficients，MFCC)中的至少一者。
检测算法可以为Fisher判别法、动态时间归整、最小近邻法、隐马尔可夫模型、高斯混合模型、分段高斯模型、人工神经网络或支持向量机等算法。
本实施例中耳机检测录音数据是否包括咳嗽音的作用为判断是否在耳机中继续保存录音 数据，或是否将录音数据发送至智能终端设备。具体而言，在耳机检测到录音数据中包括咳嗽音时，耳机可以继续保存录音数据，直至智能终端设备从耳机拉取录音数据时，将录音数据发送至智能终端设备，即执行S203，当然，耳机也可以在在耳机检测到录音数据中包括咳嗽音时即将录音数据发送至智能终端设备；而在耳机确定录音数据不包括咳嗽音时，执行S204。
由于智能终端设备在接收到咳嗽音数据后会根据录音数据进一步分析统计咳嗽信息，那么耳机检测录音数据是否包括咳嗽音所使用的检测算法和特征参数可以综合考虑耳机计算能力和准确率。可以在满足一定的咳嗽音检测准确率的条件下，选择对计算能力要求最小的特征参数和检测算法，例如特征参数可以选择过零率，检测算法可以选择Fisher判别算法。耳机使用的检测算法和特征参数可根据实际需求进行选择，此处不做限制。
在一种可能的实现方式中，为了提高录音数据中咳嗽音的检测准确率，耳机可以预先录制和保存用户的咳嗽音数据，并使用录音数据与咳嗽音数据进行匹配以判定录音数据中是否包括咳嗽音。
具体地，耳机在佩戴于用户头颈部，且与智能终端设备连接时，启动耳机麦克风录制用户主动咳嗽的咳嗽音数据，并保存咳嗽音数据。或者智能终端设备录取用户主动咳嗽的咳嗽音数据，将咳嗽音数据发送给耳机进行保存。咳嗽音数据可以是原始的音频数据，也可以是提取的能够表征用户咳嗽音的特征参数对应的数据。咳嗽音数据可以包括用户多次主动咳嗽录制到的咳嗽音，或者包括从多次主动咳嗽录制到的咳嗽音的特征参数对应的数据，从而增加样本数量，能够提高咳嗽音检测识别的准确率。
耳机比对录音数据与咳嗽音数据的相似度。若录音数据与咳嗽音数据之间的相似度大于或等于阈值，耳机确定录音数据包括咳嗽音。若录音数据与咳嗽音数据之间的相似度小于阈值，耳机确定录音数据不包括咳嗽音。相似度可以通过录音数据与咳嗽音数据之间的余弦相似度、欧几里得距离或曼哈顿距离等指标指示。
S203：耳机发送录音数据至智能终端设备，以使智能终端设备根据录音数据分析统计用户的咳嗽信息。
耳机可以周期性地将采集到的录音数据发送至智能终端设备。耳机也可以采集到录音数据后就将录音数据发送至智能终端设备。在另一种可能的实现方式中，可以是智能终端设备上运行的咳嗽监测客户端在刷新时，由智能终端设备从耳机拉取录音数据。
由于智能终端设备具有更强的计算能力和存储能力，可以由智能终端设备对录音数据进行更加精确的分析统计得到用户的咳嗽信息。智能终端设备使用的检测算法可以为更加精确的算法，特征参数可以为能够更加准确表征咳嗽音的多个特征参数的组合。例如算法可以为隐马尔可夫模型、工神经网络或支持向量机等，特征参数可以包括过零率、短时能量和梅尔频率倒谱系数等。智能终端设备使用的检测算法和特征参数可根据实际需求进行选择，此处不做限制。
咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。当检测到录音数据中的一个咳嗽音时，咳嗽次数加1，并记录该咳嗽音对应的咳嗽时间。根据咳嗽次数和咳嗽时间可以进一步得到咳嗽频率、咳嗽趋势和咳嗽时长等信息。咳嗽频率例如是每分钟、每5分钟、10分钟、30分钟、1小时、6小时、12小时或24小时内的咳嗽次数 的总和。咳嗽趋势可以是一个时间段内的咳嗽次数之和相对于先前的时间段内的咳嗽次数之和的增减变化趋势，例如每小时内咳嗽次数的变化趋势等。咳嗽时长可以是指咳嗽音集中出现时对应的时长，也可以是录音数据中检测到的最早的咳嗽音到最晚的咳嗽音之间的时长。
咳嗽信息可以是用户上次咳嗽时采集到的录音数据分析到的用户咳嗽数据，可也可以是预设时间段(例如6小时、12小时、24小时，2天，7天、当天、当周或当月等)内统计到的总的用户咳嗽数据。
智能终端设备分析统计得到的咳嗽信息可以显示于智能终端设备的咳嗽监测客户端上，从而用户能够直观地知晓咳嗽情况和身体状态。
可选地，在耳机将录音数据发送到智能终端设备之后，可以删除本地的录音数据，以释放耳机的存储空间。
S204：耳机删除录音数据。
在一些情况下，用户头颈部的振动并非由咳嗽引起的，那么录音数据中可能不包括咳嗽音。在录音数据不存在咳嗽音时，可以将该段录音数据删除，以释放耳机的存储空间。
本实施例中，耳机在检测到振动信号后才开启麦克风进行录音，能够降低用户隐私安全风险，还能够降低耳机功耗。耳机在检测到录音数据中包含咳嗽音后将录音数据发送至智能终端设备，否则删除录音数据，能够降低对耳机存储资源的占用，并且减少耳机与智能终端设备之间不必要的数据传输，进而降低耳机功耗。
耳机在开启麦克风录音期间，录取到的声音可能还包括一些用户所处的环境中的声音。环境中的声音可能会造成误检，例如将采集到的其他人的咳嗽音识别为用户的咳嗽音等，从而影响咳嗽音检测的准确率。
因此，本申请还结合耳机检测到的振动信号对应的振动数据进行咳嗽信息的分析统计。如图3所示，图3为本申请提供的咳嗽监测方法第二实施例的流程示意图。为使描述简洁，本实施例与咳嗽监测方法第一实施例类似之处不再赘述。本实施例包括如下步骤：
S301：耳机响应于检测到振动信号，记录振动信号对应的振动数据，并启动麦克风进行录音得到录音数据，耳机佩戴于用户头颈部。
振动数据例如包括检测到振动信号时的时间。振动数据还可以包括振动信号时域特征值和/或频域特征值等振动特征值。时域特征值例如包括振动信号的均值、方差、峭度或峰值等。频域特征值例如包括频率或能量等。
耳机每次检测到振动信号时，记录该振动信号的采集时间，还可以记录该振动信号的时域特征值和/或频域特征值，从而得到振动数据。
振动数据的采集时间与录音数据的采集时间至少部分重合。振动数据例如包括触发启动麦克风的振动信号的时刻，至录音数据结束前采集到的最后一次的振动信号的时刻之间的所有振动信号对应的数据。
S302：耳机检测录音数据是否包括咳嗽音。
可选地，耳机还可以结合振动数据检测录音数据中是否包括咳嗽音。例如，根据检测到的振动信号的时间，获取录音数据相应的时间的预设时长内的录音片段，检测该录音片段是否包括咳嗽音。还例如，耳机在检测到录音数据中包括咳嗽音后，进一步判断振动数据中该咳嗽音对应的时间段内是否存在检测到振动信号对应的数据，若存在，可以确定录音数据包 括咳嗽音；若不存在，可以确定该咳嗽音属于误检，若根据振动数据确定录音数据中检测到的咳嗽音均属于误检，可以能够确定录音数据中不包括咳嗽音。从而可以提高耳机检测咳嗽音的效率和准确率。
在录音数据中包括咳嗽音时，执行S303；而在录音数据不包括咳嗽音时，执行S304。
S303：耳机发送录音数据和振动数据至智能终端设备，以使智能终端设备根据录音数据和振动数据分析统计用户的咳嗽信息。
虽然耳机检测到振动信号并非都是由用户咳嗽引起的，但用户咳嗽必然伴随着用户声带和头骨的振动，从而能够被耳机记录相应的振动数据。因而，结合振动数据，能够剔除录音数据中采集到的环境中与咳嗽特征类似的声音或者其他人的咳嗽音，从而提高咳嗽音的检测准确率。
具体地，智能终端设备检测到录音数据中包括咳嗽音后，进一步判断振动数据中该咳嗽音对应的时间段内是否存在检测到振动信号对应的数据，若存在，可以确定该咳嗽音准确，咳嗽信息中的咳嗽次数加1，并记录该咳嗽音对应的时间；若不存在，可以确定该咳嗽音属于误检，暂不更新咳嗽信息。
当然，在振动数据还包括振动信号的振动特征值时，智能终端设备还可以进一步结合振动特征确定检测到的咳嗽音是否准确。例如，在振动数据中该咳嗽音对应的时间段内存在检测到振动信号对应的数据，且振动特征值中的至少部分值大于阈值时，确定该咳嗽音准确。可以理解，不同的振动特征值对应于不同的阈值。
S304：耳机删除录音数据和振动数据。
在录音数据不存在咳嗽音时，可以将该段录音数据和振动数据删除，以释放耳机的存储空间。
本实施例中，耳机在检测到振动信号后才开启麦克风进行录音，能够降低用户隐私安全风险，还能够降低耳机功耗。耳机在检测到录音数据中包含咳嗽音后将录音数据发送至智能终端设备，否则删除录音数据和振动数据，能够降低对耳机存储资源的占用，并且减少耳机与智能终端设备之间不必要的数据传输，进而降低耳机功耗。进一步地，结合振动数据判断录音数据中是否包括咳嗽音，能够提高咳嗽音识别的准确率。
耳机在检测到振动信号后，除了如咳嗽监测方法第一和第二实施例那样开启自身的麦克风进行录音，并检测录音数据中是否包括咳嗽音，还可以不通过自身录音和检测咳嗽音，而是指示智能终端设备开启麦克风录音，并检测录音数据中的咳嗽音。如图4所示，图4为本申请提供的咳嗽监测方法第三实施例的流程示意图。本实施例包括如下步骤：
S401：耳机检测到振动信号，耳机佩戴于用户头颈部。
S402：响应于振动信号，耳机向智能终端设备发送指示消息。
指示消息用于指示智能终端设备开启麦克风进行录音。
可以理解，耳机并非每次检测到振动信号都向智能终端设备发送用于启动麦克风的指示消息。若耳机检测到振动信号时智能终端设备的麦克风已经开启，也即在耳机指示智能终端设备结束录音之前，耳机无需再次向智能终端设备发送指示消息。
S403：智能终端设备响应于指示消息启动麦克风进行录音，得到录音数据。
智能终端设备接收到指示消息后启动麦克风进行录音。智能终端设备结束录音的条件例 如是智能终端设备接收到耳机发送的用于指示结束录音的消息。用于指示结束录音的消息例如是耳机在上一次检测到振动信号之后的预设时间段内未检测到振动信号后生成的。预设时间段例如可以是30秒、1分钟、2分钟或5分钟等，此处不做限制。
S404：智能终端设备检测确定录音数据包括咳嗽音。
智能终端设备检测咳嗽音的方法与S203类似，故在此不再赘述。
S405：智能终端设备根据录音数据分析统计用户的咳嗽信息。
智能终端设备统计分析咳嗽信息的方法与S203类似，故在此不再赘述。
S404和S405可以是同一个步骤实现的，即智能终端设备在检测录音数据中的咳嗽音时，同步进行咳嗽信息的分析统计。例如，在检测到录音数据中的咳嗽音时，咳嗽信息中的咳嗽次数加1，并记录该咳嗽音对应的时间；若完成录音数据的检测后没有检测到该录音数据中存在咳嗽音，则不更新咳嗽信息。
可选地，在智能终端设备完成录音数据的检测之后，可以删除该录音数据，从而节省智能终端设备的存储空间。
本实施例中，智能终端设备在接收到耳机因检测到振动信号发出的指示消息后，才启动麦克风进行录音，既能够降低用户隐私安全风险，还能够降低智能终端设备功耗。并且，由智能终端设备进行录音和咳嗽音的检测，能够降低对耳机的存储资源和计算资源的要求，能够降低耳机的成本。
同样地，智能终端也可以结合耳机采集到的振动数据进行录音数据中的咳嗽音的检测和分析统计。如图5所示，图5为本申请提供的咳嗽监测方法第四实施例的流程示意图。本实施例包括如下步骤：
S501：耳机检测到振动信号，耳机佩戴于用户头颈部。
S502：响应于振动信号，耳机向智能终端设备发送指示消息。
指示消息用于指示智能终端设备开启麦克风进行录音。
S503：智能终端设备响应于指示消息启动麦克风进行录音，得到录音数据。
智能终端设备接收到指示消息后启动麦克风进行录音。智能终端设备结束录音的条件例如是智能终端设备接收到耳机发送的用于指示结束录音的消息。用于指示结束录音的消息例如是耳机在上一次检测到振动信号之后的预设时间段内未检测到振动信号后生成的。预设时间段例如可以是30秒、1分钟、2分钟或5分钟等，此处不做限制。
S504：耳机记录振动信号对应的振动数据。
振动数据为耳机检测到振动信号时记录的数据。振动数据可参阅S301的相关描述，故此处不再赘述。
需要说明的是，S504与S502和S503在顺序上没有先后之分，耳机记录振动数据是一个持续的过程，在耳机检测到用于启动智能终端设备麦克风的振动信号，至耳机指示智能终端设备结束录音期间检测到的所有振动信号都会进行记录，从而得到振动数据。
S505：耳机向智能终端设备发送振动数据。
振动数据和用于指示结束录音的消息可以是耳机一同发送到智能终端设备的。振动数据和用于指示结束录音的消息也可以是耳机分开发送到智能终端设备的，例如可以先发送用于指示结束录音的消息再发送振动数据，也可以采用相反的发送顺序，此处不作限制。
S506：智能终端设备根据录音数据和振动数据分析统计用户的咳嗽信息。
智能终端设备检测咳嗽音和分析统计咳嗽信息的方法与S203类似，故在此不再赘述。
本实施例中，智能终端设备在接收到耳机因检测到振动信号发出的指示消息后，才启动麦克风进行录音，既能够降低用户隐私安全风险，还能够降低智能终端设备功耗。并且，由智能终端设备进行录音和咳嗽音的检测，能够降低对耳机的存储资源和计算资源的要求，能够降低耳机的成本。进一步地，结合振动数据判断录音数据中是否包括咳嗽音，能够提高咳嗽音识别的准确率。
如图6所示，图6为本申请提供的咳嗽监测方法第五实施例的流程示意图。本实施例的执行主体为耳机。本实施例包括如下步骤：
S601：耳机检测到振动信号，耳机佩戴于用户头颈部。
S602：响应于振动信号，耳机向智能终端设备发送指示消息，以使智能终端设备根据指示消息启动麦克风进行录音得到录音数据，并在确定录音数据包括咳嗽音时根据录音数据分析统计用户的咳嗽信息。
本实施例耳机的相关操作可参阅咳嗽监测方法第三实施例或咳嗽监测方法第四实施例的相关内容，故此处不再赘述。
如图7所示，图7为本申请提供的咳嗽监测方法第六实施例的流程示意图。本实施例的执行主体为智能终端设备。本实施例包括如下步骤：
S701：智能终端设备接收耳机发送的指示消息，耳机佩戴于用户头颈部，指示消息为耳机检测到振动信号生成的。
S702：响应于指示消息，智能终端设备启动麦克风进行录音，得到录音数据。
S703：智能终端设备检测确定录音数据包括咳嗽音。
S704：智能终端设备根据录音数据分析统计用户的咳嗽信息。
本实施例智能终端设备的相关操作可参阅咳嗽监测方法第三实施例或咳嗽监测方法第四实施例的相关内容，故此处不再赘述。
上述的咳嗽监测方法第一实施例或第二实施例由耳机800实现。如图8所示，图8为本申请提供的耳机一实施例的结构示意图。该耳机800包括：
振动检测模块801，用于检测振动信号。
录音模块802，用于在振动检测模块801检测到振动信号时启动麦克风进行录音，得到录音数据。
咳嗽音检测模块803，用于检测录音数据是否包括咳嗽音。
发送模块804，用于在确定录音数据包括咳嗽音时发送录音数据至智能终端设备，以使智能终端设备根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，咳嗽音检测模块803具体用于比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；在录音数据与咳嗽音数据之间的相似度大于或等于阈值时，确定录音数据包括咳嗽音；或在录音数据与咳嗽音数据之间的相似度小于阈值时，确定录音数据不包括咳嗽音。
在一种可能的实现方式中，耳机还包括：记录模块805，用于记录检测到的振动信号对应的振动数据。发送模块804，还用于发送振动数据至智能终端设备，以使智能终端设备根 据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，录音数据包括音频数据和音频数据的采集时间，咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
上述的咳嗽监测方法第三实施例、第四实施例或第五实施例中耳机的执行动作由耳机900实现。如图9所示，图9为本申请提供的耳机另一实施例的结构示意图。该耳机900包括：振动检测模块901，用于检测振动信号。发送模块902，用于在检测到振动信号时向智能终端设备发送指示消息，以使智能终端设备根据指示消息启动麦克风进行录音得到录音数据，并在确定录音数据包括咳嗽音时根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，发送模块902还用于向智能终端设备发送振动数据，以使智能终端设备根据录音数据和振动数据进行用户的咳嗽信息的分析统计。振动数据是振动检测模块901检测到振动信号时记录的相应的数据。
上述的咳嗽监测方法第三实施例、第四实施例或第五实施例中智能终端设备的执行动作由咳嗽检测装置1000实现。如图10所示，图10为本申请提供的咳嗽监测装置一实施例的结构示意图。该装置1000包括：
接收模块1001，用于接收耳机发送的指示消息，耳机佩戴于用户头颈部，指示消息为耳机检测到振动信号生成的。
录音模块1002，用于接收到指示消息时启动麦克风进行录音，得到录音数据.
检测模块1003，用于检测确定录音数据包括咳嗽音，
分析统计模块1004，用于根据录音数据分析统计用户的咳嗽信息。
在一种可能的实现方式中，检测模块1003具体用于比对录音数据与咳嗽音数据的相似度，咳嗽音数据为在先录制的用户的咳嗽音数据；确定录音数据与咳嗽音数据之间的相似度大于或等于阈值，确定录音数据包括咳嗽音。
在一种可能的实现方式中，接收模块1001还用于接收耳机发送的振动数据，振动数据为耳机记录检测到的振动信号对应的数据。分析统计模块1004，用于根据录音数据和振动数据分析统计咳嗽信息。
在一种可能的实现方式中，该装置1000包括：删除模块1005，用于在录音数据不包括咳嗽音时删除录音数据。
如图11所示，图11为本申请提供咳嗽监测设备一实施例的结构示意图。该咳嗽检测设备1100包括处理器1101和存储器1102。处理器1101耦接存储器1102，处理器1101被配置为基于存储在存储器1102中的指令，执行上述图2至图6中任意的由耳机执行的咳嗽监测方法，或者图3、图4或图7中由智能终端设备执行的咳嗽监测方法。
本申请还提供了一种计算机可读存储介质，其上存储有计算机程序，该计算机程序被计算机执行时实现上述任一方法实施例的咳嗽监测方法流程。
所属领域的技术人员可以清楚地了解到，为描述的方便和简洁，上述描述的系统，装置和单元的具体工作过程，可以参考前述方法实施例中的对应过程，在此不再赘述。
在本申请所提供的几个实施例中，应该理解到，所揭露的系统，装置和方法，可以通过其它的方式实现。例如，以上所描述的装置实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，例如多个单元或组件可以结 合或者可以集成到另一个系统，或一些特征可以忽略，或不执行。另一点，所显示或讨论的相互之间的耦合或直接耦合或通信连接可以是通过一些接口，装置或单元的间接耦合或通信连接，可以是电性或其它的形式。
所述作为分离部件说明的单元可以是或者也可以不是物理上分开的，作为单元显示的部件可以是或者也可以不是物理单元，即可以位于一个地方，或者也可以分布到多个网络单元上。可以根据实际的需要选择其中的部分或者全部单元来实现本实施例方案的目的。
另外，在本申请各个实施例中的各功能单元可以集成在一个处理单元中，也可以是各个单元单独物理存在，也可以两个或两个以上单元集成在一个单元中。上述集成的单元既可以采用硬件的形式实现，也可以采用软件功能单元的形式实现。
所述集成的单元如果以软件功能单元的形式实现并作为独立的产品销售或使用时，可以存储在一个计算机可读取存储介质中。基于这样的理解，本申请的技术方案的全部或部分可以以软件产品的形式体现出来，该计算机软件产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机，服务器，或者网络设备等)执行本申请各个实施例所述方法的全部或部分步骤。而前述的存储介质包括：U盘、移动硬盘、只读存储器(ROM，read-only memory)、随机存取存储器(RAM，random access memory)、磁碟或者光盘等各种可以存储程序代码的介质。

Claims (21)

  1. 一种咳嗽监测方法，其特征在于，所述方法包括：
    耳机响应于检测到振动信号，启动麦克风进行录音得到录音数据，所述耳机佩戴于用户头颈部；
    所述耳机检测所述录音数据是否包括咳嗽音；
    若所述录音数据包括所述咳嗽音，所述耳机发送所述录音数据至智能终端设备，以使所述智能终端设备根据所述录音数据分析统计所述用户的咳嗽信息。
  2. 根据权利要求1所述的方法，其特征在于，所述耳机检测所述录音数据是否包括所述咳嗽音包括：
    所述耳机比对所述录音数据与咳嗽音数据的相似度，所述咳嗽音数据为在先录制的所述用户的咳嗽音数据；
    若所述录音数据与所述咳嗽音数据之间的相似度大于或等于阈值，所述耳机确定所述录音数据包括所述咳嗽音；
    若所述录音数据与所述咳嗽音数据之间的相似度小于所述阈值，所述耳机确定所述录音数据不包括所述咳嗽音。
  3. 根据权利要求1或2所述的方法，其特征在于，所述方法还包括：
    所述耳机记录检测到的所述振动信号对应的振动数据；
    所述耳机发送所述录音数据至智能终端设备，以使所述智能终端设备根据所述录音数据分析统计咳嗽信息包括：
    所述耳机发送所述录音数据和所述振动数据至智能终端设备，以使所述智能终端设备根据所述录音数据和所述振动数据分析统计咳嗽信息。
  4. 根据权利要求1至3中任一项所述的方法，其特征在于，所述录音数据包括音频数据和所述音频数据的采集时间，所述咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
  5. 根据权利要求1至4中任一项所述的方法，其特征在于，所述方法还包括：
    若所述录音数据不包括所述咳嗽音，则所述耳机删除所述录音数据。
  6. 一种咳嗽监测方法，其特征在于，所述方法包括：
    耳机检测到振动信号，所述耳机佩戴于用户头颈部；
    响应于所述振动信号，所述耳机向智能终端设备发送指示消息，以使所述智能终端设备根据所述指示消息启动麦克风进行录音得到录音数据，并在确定所述录音数据包括咳嗽音时根据所述录音数据分析统计所述用户的咳嗽信息。
  7. 一种咳嗽监测方法，其特征在于，所述方法包括：
    智能终端设备接收耳机发送的指示消息，所述耳机佩戴于用户头颈部，所述指示消息为所述耳机检测到振动信号生成的；
    响应于所述指示消息，所述智能终端设备启动麦克风进行录音，得到录音数据；
    所述智能终端设备检测确定所述录音数据包括咳嗽音；
    所述智能终端设备根据所述录音数据分析统计所述用户的咳嗽信息。
  8. 根据权利要求7所述的方法，其特征在于，所述智能终端设备检测确定所述录音数据 包括咳嗽音包括：
    所述智能终端设备比对所述录音数据与咳嗽音数据的相似度，所述咳嗽音数据为在先录制的所述用户的咳嗽音数据；
    所述智能终端设备确定所述录音数据与所述咳嗽音数据之间的相似度大于或等于阈值，所述智能终端设备确定所述录音数据包括所述咳嗽音。
  9. 根据权利要求7或8所述的方法，其特征在于，所述方法还包括：
    所述智能终端设备接收所述耳机发送的振动数据，所述振动数据为所述耳机记录检测到的所述振动信号对应的数据；
    所述智能终端设备根据所述录音数据分析统计咳嗽信息包括：
    所述智能终端设备根据所述录音数据和所述振动数据分析统计所述咳嗽信息。
  10. 根据权利要求7至9中任一项所述的方法，其特征在于，录音数据包括音频数据和所述音频数据的采集时间，所述咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
  11. 一种咳嗽监测方法，其特征在于，所述方法包括：
    耳机检测到振动信号，所述耳机佩戴于用户头颈部；
    响应于所述振动信号，所述耳机向智能终端设备发送指示消息；
    所述智能终端设备响应于所述指示消息启动麦克风进行录音，得到录音数据；
    智能终端设备检测确定所述录音数据包括咳嗽音；
    所述智能终端设备根据所述录音数据分析统计所述用户的咳嗽信息。
  12. 一种咳嗽监测系统，其特征在于，所述系统包括耳机和智能终端设备；其中，
    所述耳机，佩戴于用户头颈部，用于检测振动信号；
    所述耳机，还用于在检测到振动信号时启动麦克风进行录音得到录音数据；
    所述耳机，还用于检测所述录音数据是否包括咳嗽音；
    所述耳机，还用于在所述录音数据包括咳嗽音时向所述智能终端设备发送所述录音数据；
    所述智能终端设备，用于根据所述录音数据分析统计所述用户的咳嗽信息。
  13. 一种咳嗽监测系统，其特征在于，所述系统包括耳机和智能终端设备；其中，
    所述耳机，佩戴于用户头颈部，用于检测振动信号；
    所述耳机，用于在检测到所述振动信号时，向智能终端设备发送指示消息；
    所述智能终端设备，用于根据所述指示消息启动麦克风进行录音，得到录音数据；
    所述智能终端设备，还用于在检测确定所述录音数据包括咳嗽音时，根据所述录音数据分析统计所述用户的咳嗽信息。
  14. 一种耳机，其特征在于，所述耳机包括：
    振动检测模块，用于检测振动信号；
    录音模块，用于在所述振动检测模块检测到振动信号时启动麦克风进行录音，得到录音数据；
    咳嗽音检测模块，用于检测所述录音数据是否包括咳嗽音；
    发送模块，用于在确定所述录音数据包括所述咳嗽音时发送所述录音数据至智能终端设备，以使所述智能终端设备根据所述录音数据分析统计所述用户的咳嗽信息。
  15. 根据权利要求14所述的耳机，其特征在于，所述咳嗽音检测模块具体用于：
    比对所述录音数据与咳嗽音数据的相似度，所述咳嗽音数据为在先录制的所述用户的咳嗽音数据；
    在所述录音数据与所述咳嗽音数据之间的相似度大于或等于阈值时，确定所述录音数据包括所述咳嗽音；或在所述录音数据与所述咳嗽音数据之间的相似度小于所述阈值时，确定所述录音数据不包括所述咳嗽音。
  16. 根据权利要求14或15所述的耳机，其特征在于，所述耳机还包括：
    记录模块，用于记录检测到的所述振动信号对应的振动数据；
    所述发送模块，还用于发送所述振动数据至智能终端设备，以使所述智能终端设备根据所述录音数据和所述振动数据分析统计咳嗽信息。
  17. 根据权利要求14至16中任一项所述的耳机，其特征在于，所述录音数据包括音频数据和所述音频数据的采集时间，所述咳嗽信息包括咳嗽时间、咳嗽次数、咳嗽频率、咳嗽趋势和咳嗽时长中的至少一者。
  18. 一种耳机，其特征在于，所述耳机包括：
    振动检测模块，用于检测振动信号；
    发送模块，用于在检测到所述振动信号时向智能终端设备发送指示消息，以使所述智能终端设备根据所述指示消息启动麦克风进行录音得到录音数据，并在确定所述录音数据包括咳嗽音时根据所述录音数据分析统计所述用户的咳嗽信息。
  19. 一种咳嗽监测装置，其特征在于，所述装置包括：
    接收模块，用于接收耳机发送的指示消息，所述耳机佩戴于用户头颈部，所述指示消息为所述耳机检测到振动信号生成的；
    录音模块，用于接收到所述指示消息时启动麦克风进行录音，得到录音数据；
    检测模块，用于检测确定所述录音数据包括咳嗽音；
    分析统计模块，用于根据所述录音数据分析统计所述用户的咳嗽信息。
  20. 一种咳嗽监测设备，其特征在于，所述设备包括处理器和存储器，所述处理器耦接所述存储器，所述处理器被配置为基于存储在所述存储器中的指令，执行如权利要求1-10中任一项所述的咳嗽监测方法。
  21. 一种计算机可读存储介质，其特征在于，包括指令，当所述计算机可读存储介质在计算机上运行时，使得所述计算机执行如权利要求1-10中任一项所述的咳嗽监测方法。
PCT/CN2023/099674 2022-06-20 2023-06-12 咳嗽监测方法及相关设备 Ceased WO2023246545A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP23826194.5A EP4521403A4 (en) 2022-06-20 2023-06-12 COUGH MONITORING METHOD AND ASSOCIATED DEVICE
US18/984,393 US20250120611A1 (en) 2022-06-20 2024-12-17 Cough monitoring method and related device

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210697764.5A CN117316192A (zh) 2022-06-20 2022-06-20 咳嗽监测方法及相关设备
CN202210697764.5 2022-06-20

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US18/984,393 Continuation US20250120611A1 (en) 2022-06-20 2024-12-17 Cough monitoring method and related device

Publications (1)

Publication Number Publication Date
WO2023246545A1 true WO2023246545A1 (zh) 2023-12-28

Family

ID=89254047

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2023/099674 Ceased WO2023246545A1 (zh) 2022-06-20 2023-06-12 咳嗽监测方法及相关设备

Country Status (4)

Country Link
US (1) US20250120611A1 (zh)
EP (1) EP4521403A4 (zh)
CN (1) CN117316192A (zh)
WO (1) WO2023246545A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN120586213A (zh) * 2025-06-10 2025-09-05 泰州市人民医院 一种呼吸护理用雾化装置及雾化控制系统

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109346075A (zh) * 2018-10-15 2019-02-15 华为技术有限公司 通过人体振动识别用户语音以控制电子设备的方法和系统
CN111150405A (zh) * 2020-02-10 2020-05-15 浙江省疾病预防控制中心 一种带监测咳嗽功能的智能医学观察腕表
CN111557664A (zh) * 2020-03-23 2020-08-21 广东艾诗凯奇智能科技有限公司 颈部按摩仪及其健康检测方法以及计算机存储介质
US20210386320A1 (en) * 2020-06-15 2021-12-16 Cirrus Logic International Semiconductor Ltd. Cough detection

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9516442B1 (en) * 2012-09-28 2016-12-06 Apple Inc. Detecting the positions of earbuds and use of these positions for selecting the optimum microphones in a headset
CN104125523A (zh) * 2014-08-01 2014-10-29 周祥宇 一种动感耳机系统及其使用方法
WO2021229423A1 (en) * 2020-05-11 2021-11-18 Porubcan Jan Device for detecting facial contact, in particular for preventing infection from hands
US11862188B2 (en) * 2020-10-22 2024-01-02 Google Llc Method for detecting and classifying coughs or other non-semantic sounds using audio feature set learned from speech

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109346075A (zh) * 2018-10-15 2019-02-15 华为技术有限公司 通过人体振动识别用户语音以控制电子设备的方法和系统
CN111150405A (zh) * 2020-02-10 2020-05-15 浙江省疾病预防控制中心 一种带监测咳嗽功能的智能医学观察腕表
CN111557664A (zh) * 2020-03-23 2020-08-21 广东艾诗凯奇智能科技有限公司 颈部按摩仪及其健康检测方法以及计算机存储介质
US20210386320A1 (en) * 2020-06-15 2021-12-16 Cirrus Logic International Semiconductor Ltd. Cough detection

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP4521403A4

Also Published As

Publication number Publication date
CN117316192A (zh) 2023-12-29
EP4521403A4 (en) 2025-08-13
EP4521403A1 (en) 2025-03-12
US20250120611A1 (en) 2025-04-17

Similar Documents

Publication Publication Date Title
Sun et al. SymDetector: detecting sound-related respiratory symptoms using smartphones
EP3599560A1 (en) Retroactive information searching enabled by neural sensing
EP3954278A1 (en) Apnea monitoring method and device
CN113925464B (zh) 一种基于移动设备检测睡眠呼吸暂停的方法
WO2022199405A1 (zh) 一种语音控制方法和装置
EP3591540B1 (en) Retroactive sound identification system
CN109412544B (zh) 一种智能穿戴设备的语音采集方法、装置及相关组件
CN110992953A (zh) 一种语音数据处理方法、装置、系统及存储介质
WO2019153972A1 (zh) 信息推送方法及相关产品
CN103543814B (zh) 信号处理装置以及信号处理方法
US20250120611A1 (en) Cough monitoring method and related device
CN114093357B (zh) 控制方法、智能终端及可读存储介质
CN112053689A (zh) 基于眼球和语音指令的操作设备的方法和系统及服务器
JP2019124952A (ja) 情報処理装置、情報処理方法、およびプログラム
CN111312293A (zh) 一种基于深度学习对呼吸暂停症患者的识别方法及系统
CN106774915A (zh) 一种可穿戴设备通信消息的收发控制方法及可穿戴设备
CN111415442A (zh) 一种门禁控制方法、电子设备及存储介质
CN111028838A (zh) 一种语音唤醒方法、设备及计算机可读存储介质
Rahman et al. Efficient online cough detection with a minimal feature set using smartphones for automated assessment of pulmonary patients
CN113039601A (zh) 一种语音控制方法、装置、芯片、耳机及系统
CN119968674A (zh) 一种语音控制方法及终端设备
CN114287888A (zh) 一种通过声音采集检测多人睡眠质量的方法
CN106791137A (zh) 一种可穿戴设备的通话控制方法及可穿戴设备
WO2018108284A1 (en) Audio recording device for presenting audio speech missed due to user not paying attention and method thereof
CN116416980A (zh) 一种语音指令处理方法、控制系统及智能沙发

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: 23826194

Country of ref document: EP

Kind code of ref document: A1

WWE Wipo information: entry into national phase

Ref document number: 2023826194

Country of ref document: EP

ENP Entry into the national phase

Ref document number: 2023826194

Country of ref document: EP

Effective date: 20241206

NENP Non-entry into the national phase

Ref country code: DE