CN116249062A - Hearing-aid equipment state intelligent quality inspection method, system and medium - Google Patents
Hearing-aid equipment state intelligent quality inspection method, system and medium Download PDFInfo
- Publication number
- CN116249062A CN116249062A CN202310507568.1A CN202310507568A CN116249062A CN 116249062 A CN116249062 A CN 116249062A CN 202310507568 A CN202310507568 A CN 202310507568A CN 116249062 A CN116249062 A CN 116249062A
- Authority
- CN
- China
- Prior art keywords
- sound
- information
- hearing
- hearing aid
- preset
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 86
- 238000007689 inspection Methods 0.000 title claims abstract description 82
- 238000012545 processing Methods 0.000 claims abstract description 123
- 230000033001 locomotion Effects 0.000 claims abstract description 94
- 206010011878 Deafness Diseases 0.000 claims abstract description 83
- 230000010370 hearing loss Effects 0.000 claims abstract description 82
- 231100000888 hearing loss Toxicity 0.000 claims abstract description 82
- 208000016354 hearing loss disease Diseases 0.000 claims abstract description 82
- 238000012937 correction Methods 0.000 claims abstract description 72
- 230000008569 process Effects 0.000 claims abstract description 57
- 230000002159 abnormal effect Effects 0.000 claims description 62
- 238000001514 detection method Methods 0.000 claims description 61
- 230000005236 sound signal Effects 0.000 claims description 53
- 238000007781 pre-processing Methods 0.000 claims description 16
- 238000012544 monitoring process Methods 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 14
- 230000001133 acceleration Effects 0.000 claims description 12
- 230000005484 gravity Effects 0.000 claims description 12
- 230000004044 response Effects 0.000 claims description 12
- 238000003908 quality control method Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000004931 aggregating effect Effects 0.000 claims description 4
- 230000000694 effects Effects 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000012549 training Methods 0.000 description 20
- 238000010586 diagram Methods 0.000 description 8
- 230000002776 aggregation Effects 0.000 description 4
- 238000004220 aggregation Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 4
- 230000006870 function Effects 0.000 description 3
- 230000007488 abnormal function Effects 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012372 quality testing Methods 0.000 description 1
Images
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04R—LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; DEAF-AID SETS; PUBLIC ADDRESS SYSTEMS
- H04R29/00—Monitoring arrangements; Testing arrangements
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention discloses a hearing-aid equipment state intelligent quality inspection method, a system and a medium, wherein the method comprises the following steps: carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, carrying out pickup direction processing judgment according to the sound azimuth information, obtaining a user hearing loss value according to audiogram data processing, further obtaining a first compensation gain value, carrying out analysis and recognition on motion parameter data to obtain a motion compensation correction factor, correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value, combining the pickup direction processing result with the second compensation gain value processing to obtain a hearing aid deviation index, and finally judging a quality inspection result of the hearing aid according to a threshold comparison result of the deviation index; the invention can realize intelligent quality inspection of the state of the hearing aid equipment, thereby realizing the effect of intelligent adjustment of the hearing aid equipment.
Description
Technical Field
The invention relates to the technical field of intelligent quality inspection, in particular to a hearing aid equipment state intelligent quality inspection method, system and medium.
Background
For deaf patients, wearing hearing devices is the best way to help them improve hearing. The adjustment parameters required to be set by the hearing aid device aiming at different activity scenes of different users are different, and at present, most hearing aid devices in the market are single in function, so that the functions of intelligent quality inspection and self-adaptive adjustment on the state of the hearing aid device based on the hearing loss condition and the current activity state of the user cannot be realized.
In view of the above problems, an effective technical solution is currently needed.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method, a system and a medium for intelligent quality inspection of a state of a hearing aid device, which are capable of performing azimuth recognition on a sound signal, then processing acquired audiogram data and motion parameter data of a user to obtain a second compensation gain value, and finally processing the combination of an azimuth recognition result and the second compensation gain value to obtain a quality inspection result of the hearing aid device.
The invention provides an intelligent hearing aid device state quality inspection method, which comprises the following steps:
collecting sound signals of hearing-aid equipment, and preprocessing the sound signals to obtain first sound process information;
Carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, and carrying out pickup direction processing judgment according to the sound azimuth information;
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to acquire a hearing loss value of the user, and processing to acquire a first compensation gain value based on the hearing loss value of the user;
acquiring motion parameter data, analyzing and identifying the motion parameter data to acquire corresponding motion compensation correction factors;
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
and processing according to the pick-up direction processing result and combining the second compensation gain value to obtain a deviation index of the hearing aid equipment, performing threshold comparison according to the deviation index of the hearing aid equipment and a preset deviation index threshold, and judging a quality inspection result of the hearing aid equipment according to the threshold comparison result.
In this scheme, gather hearing aid device's sound signal to carry out preliminary treatment to the sound signal and obtain first sound process information, specifically include:
collecting a sound signal of hearing-aid equipment, and carrying out noise reduction treatment on the sound signal to obtain a noise-reduced sound signal;
and carrying out real-time preprocessing on the noise reduction sound signal to obtain first sound process information, wherein the first sound process information comprises sound loudness information, sound frequency band information, sound velocity information, transmission distance information and sound receiving time information.
In this scheme, will carry out the position discernment with first sound process information obtains sound position information, carries out pickup direction processing according to sound position information and judges, specifically includes:
inputting the first sound process information into a preset sound azimuth recognition model to obtain sound azimuth information corresponding to the first sound process information;
processing according to the sound azimuth information and preset direction vector information to obtain a sound direction deviation degree value, and comparing the sound direction deviation degree value with a preset sound direction deviation degree threshold value;
if the threshold comparison result does not meet the preset sound direction deviation threshold comparison requirement, the pickup direction quality inspection result is not qualified, pickup direction deviation information is generated and fed back, and the sound azimuth information is further corrected;
and if the threshold comparison result meets the preset threshold comparison requirement of the sound direction deviation degree, generating qualified pickup direction quality inspection information and feeding back the qualified pickup direction quality inspection information.
In this scheme, the obtaining the audiogram data of the user, inputting the audiogram data into a preset hearing loss detection model for processing to obtain a hearing loss value of the user, and obtaining a first compensation gain value based on the processing of the hearing loss value of the user specifically includes:
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing, and acquiring a hearing loss value of the user;
Acquiring a preset hearing loss compensation model;
dividing the sound signal into sound frequency band signals of different frequency band intervals according to the sound frequency band information;
inputting the hearing loss value of the user and the first sound process information corresponding to the sound frequency band signals into the hearing loss compensation model for processing according to each frequency band interval, and obtaining a sound band compensation gain value corresponding to the frequency band interval;
and aggregating the corresponding sound segment compensation gain values of each frequency band interval to obtain a first compensation gain value.
In this scheme, obtain motion parameter data and carry out analysis discernment, obtain corresponding motion compensation correction factor, specifically include:
acquiring motion parameter information of a user, wherein the motion parameter information comprises acceleration parameters, vibration parameters, gravity parameters, speed parameters and inclination angle parameters;
and inputting the motion parameter information into a preset inertia recognition model for processing to obtain a motion compensation correction factor.
In this scheme, the correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value specifically includes:
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
The correction formula of the second compensation gain value is as follows:
wherein ,
for the second compensation gain value,/>
For the motion compensation correction factor +.>
For the first compensation gain value,/>
Is a preset characteristic coefficient.
In this scheme, according to pickup direction processing result combines the second compensation gain value to handle, obtain hearing aid equipment deviation degree index, according to hearing aid equipment deviation degree index carries out threshold value contrast with preset deviation degree index threshold value, judges hearing aid equipment's quality testing result according to threshold value contrast result, specifically includes:
inputting the pickup direction deviation information and the second compensation gain value into a preset hearing-aid equipment performance recognition model for processing to obtain a hearing-aid equipment deviation index;
threshold value comparison is carried out according to the deviation index of the hearing aid equipment and a preset deviation index threshold value;
if the threshold comparison result meets the preset requirement, the quality inspection result of the hearing aid equipment is qualified;
otherwise, the quality inspection result of the hearing aid device is unqualified.
In this scheme, still include:
acquiring user operation information of a user using hearing-aid equipment and hearing-aid equipment performance monitoring information under a preset scene, wherein the user operation information comprises key operation frequency information and abnormal feedback information, and the hearing-aid equipment performance monitoring information comprises performance abnormal information and response frequency abnormal information;
Inputting the key operation frequency information, the abnormal feedback information, the performance abnormal information and the response frequency abnormal information into a hearing aid performance abnormal detection model of a user for processing to obtain a hearing aid performance abnormal detection value;
and carrying out threshold comparison according to the hearing aid performance abnormal detection value and a preset performance detection threshold value, and judging the condition of using hearing aid equipment by a user according to a threshold comparison result.
The second aspect of the present invention also provides a hearing-aid device state intelligent quality inspection system, which comprises a memory and a processor, wherein the memory comprises a hearing-aid device state intelligent quality inspection method program, and the hearing-aid device state intelligent quality inspection method program when executed by the processor realizes the following steps:
collecting sound signals of hearing-aid equipment, and preprocessing the sound signals to obtain first sound process information;
carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, and carrying out pickup direction processing judgment according to the sound azimuth information;
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to acquire a hearing loss value of the user, and processing to acquire a first compensation gain value based on the hearing loss value of the user;
Acquiring motion parameter data, analyzing and identifying the motion parameter data to acquire corresponding motion compensation correction factors;
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
and processing according to the pick-up direction processing result and combining the second compensation gain value to obtain a deviation index of the hearing aid equipment, performing threshold comparison according to the deviation index of the hearing aid equipment and a preset deviation index threshold, and judging a quality inspection result of the hearing aid equipment according to the threshold comparison result.
A third aspect of the present invention provides a computer-readable storage medium, in which a hearing aid device state intelligent quality inspection method program is included, which when executed by a processor, implements the steps of the hearing aid device state intelligent quality inspection method according to any one of the above.
The invention discloses a hearing-aid equipment state intelligent quality inspection method, a system and a medium.
Drawings
FIG. 1 shows a flow chart of a hearing aid device status intelligent quality control method of the present invention;
FIG. 2 shows a flow chart of the intelligent quality inspection method for hearing aid device status of the present invention for preprocessing sound signals;
FIG. 3 shows a flow chart of the intelligent quality inspection method for the state of hearing-aid equipment for judging the pickup direction;
fig. 4 shows a block diagram of a hearing aid device status intelligent quality control system according to the present invention.
Detailed Description
In order that the above-recited objects, features and advantages of the present invention will be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description. It should be noted that, in the case of no conflict, the embodiments of the present application and the features in the embodiments may be combined with each other.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced in other ways than those described herein, and therefore the scope of the present invention is not limited to the specific embodiments disclosed below.
Fig. 1 shows a flowchart of a hearing aid device state intelligent quality inspection method.
As shown in fig. 1, the application discloses a hearing aid device state intelligent quality inspection method, which comprises the following steps:
s101, collecting sound signals of hearing-aid equipment, and preprocessing the sound signals to obtain first sound process information;
s102, carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, and carrying out pickup direction processing judgment according to the sound azimuth information;
s103, obtaining audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to obtain a hearing loss value of the user, and processing to obtain a first compensation gain value based on the hearing loss value of the user;
s104, acquiring motion parameter data, analyzing and identifying the motion parameter data, and acquiring corresponding motion compensation correction factors;
s105, correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
s106, processing is carried out according to the pickup direction processing result and the second compensation gain value, a deviation index of the hearing aid equipment is obtained, threshold comparison is carried out according to the deviation index of the hearing aid equipment and a preset deviation index threshold, and a quality inspection result of the hearing aid equipment is judged according to the threshold comparison result.
In order to determine the quality inspection result of the hearing aid device, the sound effect, performance, hearing effect and user movement condition of the hearing aid device are processed, corrected and compared, so that the hearing aid and the quality inspection result of the device are obtained through processing multiple elements, multiple information and multiple parameters of the hearing aid device, azimuth information is obtained through processing sound signals of the hearing aid device and identifying sound azimuth, meanwhile, hearing loss values are obtained according to hearing loss condition detection among hearing map data of the user and are processed, relevant parameters of movement of the hearing aid device worn by the user are obtained and are processed, correction and compensation processing is carried out according to movement compensation correction factors and pickup directions respectively, finally, the deviation degree index of the hearing aid device is obtained, and then the quality inspection result of the hearing aid device is obtained through threshold comparison according to the deviation degree index of the hearing aid device and a preset deviation degree index threshold value, so that the intelligent quality inspection technology of the hearing aid device is realized.
Fig. 2 shows a flow chart of preprocessing a sound signal of a hearing aid device state intelligent quality control method of the present invention.
As shown in fig. 2, according to an embodiment of the present invention, further includes:
S201, collecting sound signals of hearing-aid equipment, and carrying out noise reduction processing on the sound signals to obtain noise-reduced sound signals;
s202, carrying out real-time preprocessing on the noise reduction sound signal to obtain first sound process information, wherein the first sound process information comprises sound loudness information, sound frequency band information, sound velocity information, transmission distance information and sound receiving time information.
It should be noted that, noise reduction processing is performed on the sound signal to obtain a noise reduction sound signal, and time-frequency conversion preprocessing is performed on the noise reduction sound signal to obtain first sound process information.
Fig. 3 shows a flow chart of the intelligent quality inspection method for the state of hearing-aid equipment for judging the pickup direction.
As shown in fig. 3, according to an embodiment of the present invention, the method for performing azimuth recognition on the first sound process information to obtain sound azimuth information, and performing pickup direction processing judgment according to the sound azimuth information specifically includes:
s301, inputting the first sound process information into a preset sound direction recognition model for processing to obtain sound direction information corresponding to the first sound process information;
s302, processing according to the sound azimuth information and preset direction vector information to obtain a sound direction deviation degree value, and comparing the sound direction deviation degree value with a preset sound direction deviation degree threshold value;
S303, if the threshold comparison result does not meet the preset sound direction deviation threshold comparison requirement, the pickup direction quality inspection result is not qualified, pickup direction deviation information is generated and fed back, and the sound azimuth information is further corrected;
s304, if the threshold comparison result meets the preset sound direction deviation threshold comparison requirement, generating pickup direction quality inspection qualified information and feeding back.
It should be noted that, through the sound loudness information, sound frequency band information, sound velocity information, transmission distance information, sound receiving time information and sound azimuth information of the obtained historical sample process information being input into the initial sound azimuth recognition model for azimuth recognition training, a trained sound azimuth recognition model is obtained, the obtained first sound process information is input into the trained sound azimuth recognition model for processing to obtain corresponding sound azimuth information, the sound azimuth recognition model is a model obtained by training the first sound process information and the sound azimuth information of a large number of historical samples, the corresponding output sound azimuth information can be obtained through inputting relevant information, the sound azimuth information and the preset direction vector information are processed to obtain the sound azimuth deviation value, namely the deviation of the actual sound azimuth and the preset direction vector is obtained, the sound azimuth deviation value and the preset sound azimuth deviation threshold value are compared, in the scheme, the preset deviation threshold value is set to be smaller than 0.85, if the sound azimuth deviation value exceeds the threshold value range, the threshold value contrast result does not meet the preset sound azimuth deviation threshold value contrast requirement, the sound azimuth information is generated, otherwise, the sound azimuth deviation information is further corrected, and the sound pickup requirement is further met.
According to an embodiment of the present invention, the obtaining audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to obtain a hearing loss value of the user, and obtaining a first compensation gain value based on the processing of the hearing loss value of the user, includes:
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing, and acquiring a hearing loss value of the user;
acquiring a preset hearing loss compensation model;
dividing the sound signal into sound frequency band signals of different frequency band intervals according to the sound frequency band information;
inputting the hearing loss value of the user and the first sound process information corresponding to the sound frequency band signals into the hearing loss compensation model for processing according to each frequency band interval, and obtaining a sound band compensation gain value corresponding to the frequency band interval;
and aggregating the corresponding sound segment compensation gain values of each frequency band interval to obtain a first compensation gain value.
In order to accurately judge the hearing loss of the user, a large amount of hearing diagram data can be obtained through a third party user hearing database, the hearing diagram data is input into a preset hearing loss detection model for processing, a user hearing loss value is obtained, the hearing loss detection model is a model obtained through training of the obtained hearing diagram data of a large amount of historical samples and the hearing loss value, a corresponding output user hearing loss value can be obtained through processing of input related information, a preset hearing loss compensation model is obtained, sound signals are divided into sound frequency band signals of different frequency band intervals according to sound frequency band information, in the embodiment of the scheme, the sound signals are averaged into sound frequency band signals of 32 frequency band intervals according to the sound frequency range in the sound frequency band information, first sound process information corresponding to the hearing loss value and the sound frequency band signal is input into the hearing loss compensation model for processing according to each frequency band interval, the hearing loss compensation gain value corresponding to each frequency band interval is obtained through training of the obtained first sound process information, the hearing loss value and the corresponding sound band compensation gain value of the obtained through training of the obtained first sound process information of the historical samples, and the corresponding gain value of the sound band compensation gain value is obtained through processing of the corresponding audio band compensation gain value;
The aggregation formula of the first compensation gain value is as follows:
wherein ,
for the first compensation gain value,/>
For the preset aggregation parameter corresponding to the ith frequency band interval, < > the first frequency band interval>
And compensating gain values for the sound segments corresponding to the ith frequency band interval, wherein n is the number of the frequency band intervals.
According to an embodiment of the present invention, the acquiring motion parameter data and analyzing and identifying the motion parameter data to obtain a corresponding motion compensation correction factor specifically includes:
acquiring motion parameter information of a user, wherein the motion parameter information comprises acceleration parameters, vibration parameters, gravity parameters, speed parameters and inclination angle parameters;
and inputting the motion parameter information into a preset inertia recognition model for processing to obtain a motion compensation correction factor.
It should be noted that, the surrounding noise decibel values of the wearer in different active scenes are different, for example, the surrounding noise decibel values in the sleep state, the motion state and the driving state are different, and the gain value for compensating the sound by the hearing aid device is different, so that the motion parameter information of the user needs to be acquired, so as to judge the current active scene of the user, so as to be convenient for correcting the first compensation gain value of the sound, the motion parameter information is input into a preset inertia recognition model to be processed to obtain the motion compensation correction factor, and the preset inertia recognition model is a model obtained by training the motion parameter information of a large number of acquired historical samples and the corresponding motion compensation correction factor, and the motion compensation correction factor corresponding to the output can be obtained by inputting relevant information to be processed.
According to an embodiment of the present invention, the correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value specifically includes:
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
the correction formula of the second compensation gain value is as follows:
wherein ,
for the second compensation gain value,/>
For the motion compensation correction factor +.>
For the first compensation gain value,/>
Is a preset characteristic coefficient (the characteristic coefficient is obtained through a third party database).
It should be noted that, correcting the first compensation gain value according to the motion compensation correction factor to obtain the second compensation gain value, so as to carry out compensation weighting on the performance of the hearing aid device and the motion factor, and improve the accuracy of quality inspection on the parameters of the hearing aid device.
According to the embodiment of the invention, the processing is performed according to the pickup direction processing result in combination with the second compensation gain value to obtain a deviation index of the hearing aid device, threshold comparison is performed according to the deviation index of the hearing aid device and a preset deviation index threshold, and a quality inspection result of the hearing aid device is judged according to the threshold comparison result, which specifically comprises:
Inputting the pickup direction deviation information and the second compensation gain value into a preset hearing-aid equipment performance recognition model for processing to obtain a hearing-aid equipment deviation index;
threshold value comparison is carried out according to the deviation index of the hearing aid equipment and a preset deviation index threshold value;
if the threshold comparison result meets the preset requirement, the quality inspection result of the hearing aid equipment is qualified;
otherwise, the quality inspection result of the hearing aid device is unqualified.
It should be noted that, the pickup direction deviation information and the second compensation gain value are input into a preset hearing-aid device performance recognition model for processing calculation, so as to obtain a hearing-aid device deviation index, then the deviation index is subjected to threshold comparison with a preset deviation index threshold, and the quality inspection result of the hearing-aid device is judged according to the threshold comparison result;
the calculation formula of the hearing aid deviation index is as follows:
wherein ,
for hearing aid deviation index, +.>
For pick-up direction deviation information, +.>
For the second compensation gain value,/>
、/>
Is a preset characteristic coefficient.
According to an embodiment of the present invention, further comprising:
collecting user operation information of a user using hearing-aid equipment and hearing-aid equipment performance monitoring information, wherein the user operation information comprises key operation frequency information and abnormal feedback information, and the hearing-aid equipment performance monitoring information comprises performance abnormal information and response frequency abnormal information;
Inputting the key operation frequency information, the abnormal feedback information, the performance abnormal information and the response frequency abnormal information into a hearing aid performance abnormal detection model of a user for processing to obtain a hearing aid performance abnormal detection value;
and carrying out threshold comparison according to the hearing aid performance abnormal detection value and a preset performance detection threshold value, and judging the condition of using hearing aid equipment by a user according to a threshold comparison result.
It should be noted that, the abnormal detection of the performance of the hearing aid device may be further performed according to the user operation information and the performance monitoring information of the hearing aid device, where the user operation information includes key operation frequency information and abnormal feedback information, the performance monitoring information of the hearing aid device includes performance abnormal information and response frequency abnormal information, and the hearing aid performance abnormal detection value is obtained by inputting the key operation frequency information, the abnormal feedback information, the performance abnormal information and the response frequency abnormal information into a hearing aid performance abnormal detection model of the user for processing, where the hearing aid performance abnormal detection model is a model obtained by training the obtained user operation information, the hearing aid performance monitoring information and the corresponding hearing aid performance abnormal detection value of a large number of historical samples, and the hearing aid performance abnormal detection value can be obtained by inputting relevant information for processing. And comparing the hearing aid performance abnormal detection value with a preset performance detection threshold value according to the threshold value, wherein the preset performance detection threshold value is set to be not less than 0.8.
According to an embodiment of the present invention, further comprising:
threshold value comparison is carried out according to the deviation index of the hearing aid equipment and a preset deviation index threshold value;
if the threshold comparison result does not meet the preset deviation index threshold comparison requirement, prompting abnormal functions of the hearing aid equipment, and generating hearing aid equipment performance feedback information;
correcting the sound azimuth information and the second compensation gain value according to the hearing aid device performance feedback information to obtain a sound azimuth information correction value and a second compensation gain correction value;
and inputting the sound azimuth information correction value and the second compensation gain correction value into a hearing aid device state identification model to obtain state adjustment parameters, and automatically adjusting the hearing aid device.
If the deviation index of the hearing aid device exceeds the preset threshold range, the quality inspection result of the hearing aid device is unqualified, hearing aid device performance feedback information is generated, sound azimuth information and a second compensation gain value are corrected according to the hearing aid device performance feedback information, sound azimuth information correction value and second compensation gain correction value are obtained, the sound azimuth information correction value and the second compensation gain correction value are input into a hearing aid device state recognition model, state adjustment parameters are obtained, the hearing aid device is automatically adjusted, the hearing aid device state recognition model is a model obtained by training the obtained sound azimuth information correction value and the second compensation gain correction value of a large number of historical samples and the corresponding state adjustment parameters, the corresponding output state adjustment parameters can be obtained by inputting relevant information for processing, and the hearing aid device is automatically adjusted.
According to an embodiment of the present invention, further comprising:
acquiring positioning information of hearing-aid equipment;
inputting positioning information, acceleration parameters, speed parameters and gravity parameters into a danger detection model for recognition processing to obtain a danger alarm index;
threshold value comparison is carried out on the dangerous alarm index value and a preset dangerous alarm index preset value, and a threshold value comparison result is obtained;
if the threshold comparison result meets the requirement, sending a voice request for dialing an emergency contact person telephone, and acquiring a voice signal of a wearer;
inputting the voice signal into a voice recognition model for voice recognition processing to obtain a voice recognition result;
if the voice recognition result accords with the preset semantic scene or the voice signal of the wearer is not obtained, automatically making an emergency contact call and sending positioning information to the emergency contact.
It should be noted that, the positioning information, the acceleration parameter, the speed parameter and the gravity parameter are input into a danger detection model for recognition processing, so as to obtain a danger alarm index, the preset danger detection model is a model obtained by training the obtained positioning information, the acceleration parameter, the speed parameter and the gravity parameter of a large amount of history samples, and the corresponding danger alarm index, the corresponding output danger alarm index can be obtained by inputting related information for processing, the danger alarm index threshold is set to 1 to 3 stages, 3 stages are lowest, 1 stage is highest, when the danger alarm index value is 3 stages, the user is in a dangerous state, for example, when the user is in a high-speed driving process, the hearing aid device detects that the acceleration parameter and the gravity parameter have instant large mutation, then the user is likely to encounter dangerous emergency brake, the hearing aid device sends a voice request for dialing an emergency contact phone, meanwhile, the voice signal of the wearer is input into the voice recognition model for voice recognition processing, so as to obtain a voice recognition result, if the voice recognition result accords with the preset semantic scene or the voice signal of the wearer is not obtained, the emergency contact phone is automatically dialed, and the positioning contact phone is in a dangerous state, for example, the user is in an emergency contact phone is dialed, and the voice request is set to be dialed, and the emergency contact phone is called. Whether to dial an emergency contact call or not, the preset semantic scenario may be set as: dialing, wherein the preset voice recognition model is obtained by training the acquired voice information of a large number of historical samples and the corresponding voice recognition results, and the corresponding output voice recognition results can be obtained by inputting related information for processing.
Fig. 4 shows a block diagram of a hearing aid device status intelligent quality control system according to the present invention.
As shown in fig. 4, the invention discloses a hearing aid device state intelligent quality inspection method system 4, which comprises a memory 41 and a processor 42, wherein the memory comprises a hearing aid device state intelligent quality inspection method program, and the hearing aid device state intelligent quality inspection method program realizes the following steps when being executed by the processor:
collecting sound signals of hearing-aid equipment, and preprocessing the sound signals to obtain first sound process information;
carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, and carrying out pickup direction processing judgment according to the sound azimuth information;
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to acquire a hearing loss value of the user, and processing to acquire a first compensation gain value based on the hearing loss value of the user;
acquiring motion parameter data, analyzing and identifying the motion parameter data to acquire corresponding motion compensation correction factors;
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
and processing according to the pick-up direction processing result and combining the second compensation gain value to obtain a deviation index of the hearing aid equipment, performing threshold comparison according to the deviation index of the hearing aid equipment and a preset deviation index threshold, and judging a quality inspection result of the hearing aid equipment according to the threshold comparison result.
In order to determine the quality inspection result of the hearing aid device, the sound effect, performance, hearing effect and user movement condition of the hearing aid device are processed, corrected and compared, so that the hearing aid and the quality inspection result of the device are obtained through processing multiple elements, multiple information and multiple parameters of the hearing aid device, azimuth information is obtained through processing sound signals of the hearing aid device and identifying sound azimuth, meanwhile, hearing loss values are obtained according to hearing loss condition detection among hearing map data of the user and are processed, relevant parameters of movement of the hearing aid device worn by the user are obtained and are processed, correction and compensation processing is carried out according to movement compensation correction factors and pickup directions respectively, finally, the deviation degree index of the hearing aid device is obtained, and then the quality inspection result of the hearing aid device is obtained through threshold comparison according to the deviation degree index of the hearing aid device and a preset deviation degree index threshold value, so that the intelligent quality inspection technology of the hearing aid device is realized.
According to an embodiment of the present invention, further comprising:
collecting a sound signal of hearing-aid equipment, and carrying out noise reduction treatment on the sound signal to obtain a noise-reduced sound signal;
and carrying out real-time preprocessing on the noise reduction sound signal to obtain first sound process information, wherein the first sound process information comprises sound loudness information, sound frequency band information, sound velocity information, transmission distance information and sound receiving time information.
It should be noted that, noise reduction processing is performed on the sound signal to obtain a noise reduction sound signal, and time-frequency conversion preprocessing is performed on the noise reduction sound signal to obtain first sound process information.
According to an embodiment of the present invention, the performing azimuth recognition on the first sound process information to obtain sound azimuth information, and performing pickup direction processing and judgment according to the sound azimuth information specifically includes:
inputting the first sound process information into a preset sound azimuth recognition model to obtain sound azimuth information corresponding to the first sound process information;
processing according to the sound azimuth information and preset direction vector information to obtain a sound direction deviation degree value, and comparing the sound direction deviation degree value with a preset sound direction deviation degree threshold value;
if the threshold comparison result does not meet the preset sound direction deviation threshold comparison requirement, the pickup direction quality inspection result is not qualified, pickup direction deviation information is generated and fed back, and the sound azimuth information is further corrected;
and if the threshold comparison result meets the preset threshold comparison requirement of the sound direction deviation degree, generating qualified pickup direction quality inspection information and feeding back the qualified pickup direction quality inspection information.
It should be noted that, through the sound loudness information, sound frequency band information, sound velocity information, transmission distance information, sound receiving time information and sound azimuth information of the obtained historical sample process information being input into the initial sound azimuth recognition model for azimuth recognition training, a trained sound azimuth recognition model is obtained, the obtained first sound process information is input into the trained sound azimuth recognition model for processing to obtain corresponding sound azimuth information, the sound azimuth recognition model is a model obtained by training the first sound process information and the sound azimuth information of a large number of historical samples, the corresponding output sound azimuth information can be obtained through inputting relevant information, the sound azimuth information and the preset direction vector information are processed to obtain the sound azimuth deviation value, namely the deviation of the actual sound azimuth and the preset direction vector is obtained, the sound azimuth deviation value and the preset sound azimuth deviation threshold value are compared, in the scheme, the preset deviation threshold value is set to be smaller than 0.85, if the sound azimuth deviation value exceeds the threshold value range, the threshold value contrast result does not meet the preset sound azimuth deviation threshold value contrast requirement, the sound azimuth information is generated, otherwise, the sound azimuth deviation information is further corrected, and the sound pickup requirement is further met.
According to an embodiment of the present invention, the obtaining audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to obtain a hearing loss value of the user, and obtaining a first compensation gain value based on the processing of the hearing loss value of the user, includes:
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing, and acquiring a hearing loss value of the user;
acquiring a preset hearing loss compensation model;
dividing the sound signal into sound frequency band signals of different frequency band intervals according to the sound frequency band information;
inputting the hearing loss value of the user and the first sound process information corresponding to the sound frequency band signals into the hearing loss compensation model for processing according to each frequency band interval, and obtaining a sound band compensation gain value corresponding to the frequency band interval;
and aggregating the corresponding sound segment compensation gain values of each frequency band interval to obtain a first compensation gain value.
In order to accurately judge the hearing loss of the user, a large amount of hearing diagram data can be obtained through a third party user hearing database, the hearing diagram data is input into a preset hearing loss detection model for processing, a user hearing loss value is obtained, the hearing loss detection model is a model obtained through training of the obtained hearing diagram data of a large amount of historical samples and the hearing loss value, a corresponding output user hearing loss value can be obtained through processing of input related information, a preset hearing loss compensation model is obtained, sound signals are divided into sound frequency band signals of different frequency band intervals according to sound frequency band information, in the embodiment of the scheme, the sound signals are averaged into sound frequency band signals of 32 frequency band intervals according to the sound frequency range in the sound frequency band information, first sound process information corresponding to the hearing loss value and the sound frequency band signal is input into the hearing loss compensation model for processing according to each frequency band interval, the hearing loss compensation gain value corresponding to each frequency band interval is obtained through training of the obtained first sound process information, the hearing loss value and the corresponding sound band compensation gain value of the obtained through training of the obtained first sound process information of the historical samples, and the corresponding gain value of the sound band compensation gain value is obtained through processing of the corresponding audio band compensation gain value;
The aggregation formula of the first compensation gain value is as follows:
wherein ,
for the first compensation gain value,/>
For the preset aggregation parameter corresponding to the ith frequency band interval, < > the first frequency band interval>
And compensating gain values for the sound segments corresponding to the ith frequency band interval, wherein n is the number of the frequency band intervals.
According to an embodiment of the present invention, the acquiring motion parameter data and analyzing and identifying the motion parameter data to obtain a corresponding motion compensation correction factor specifically includes:
acquiring motion parameter information of a user, wherein the motion parameter information comprises acceleration parameters, vibration parameters, gravity parameters, speed parameters and inclination angle parameters;
and inputting the motion parameter information into a preset inertia recognition model for processing to obtain a motion compensation correction factor.
It should be noted that, the surrounding noise decibel values of the wearer in different active scenes are different, for example, the surrounding noise decibel values in the sleep state, the motion state and the driving state are different, and the gain value for compensating the sound by the hearing aid device is different, so that the motion parameter information of the user needs to be acquired, so as to judge the current active scene of the user, so as to be convenient for correcting the first compensation gain value of the sound, the motion parameter information is input into a preset inertia recognition model to be processed to obtain the motion compensation correction factor, and the preset inertia recognition model is a model obtained by training the motion parameter information of a large number of acquired historical samples and the corresponding motion compensation correction factor, and the motion compensation correction factor corresponding to the output can be obtained by inputting relevant information to be processed.
According to an embodiment of the present invention, the correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value specifically includes:
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
the correction formula of the second compensation gain value is as follows:
wherein ,
for the second compensation gain value,/>
For the motion compensation correction factor +.>
For the first compensation gain value,/>
Is a preset characteristic coefficient (the characteristic coefficient is obtained through a third party database).
It should be noted that, correcting the first compensation gain value according to the motion compensation correction factor to obtain the second compensation gain value, so as to carry out compensation weighting on the performance of the hearing aid device and the motion factor, and improve the accuracy of quality inspection on the parameters of the hearing aid device.
According to the embodiment of the invention, the processing is performed according to the pickup direction processing result in combination with the second compensation gain value to obtain a deviation index of the hearing aid device, threshold comparison is performed according to the deviation index of the hearing aid device and a preset deviation index threshold, and a quality inspection result of the hearing aid device is judged according to the threshold comparison result, which specifically comprises:
Inputting the pickup direction deviation information and the second compensation gain value into a preset hearing-aid equipment performance recognition model for processing to obtain a hearing-aid equipment deviation index;
threshold value comparison is carried out according to the deviation index of the hearing aid equipment and a preset deviation index threshold value;
if the threshold comparison result meets the preset requirement, the quality inspection result of the hearing aid equipment is qualified;
otherwise, the quality inspection result of the hearing aid device is unqualified.
It should be noted that, the pickup direction deviation information and the second compensation gain value are input into a preset hearing-aid device performance recognition model for processing calculation, so as to obtain a hearing-aid device deviation index, then the deviation index is subjected to threshold comparison with a preset deviation index threshold, and the quality inspection result of the hearing-aid device is judged according to the threshold comparison result;
the calculation formula of the hearing aid deviation index is as follows:
wherein ,
for hearing aid deviation index, +.>
For pick-up direction deviation information, +.>
For the second compensation gain value,/>
、/>
Is a preset characteristic coefficient. />
According to an embodiment of the present invention, further comprising:
collecting user operation information of a user using hearing-aid equipment and hearing-aid equipment performance monitoring information, wherein the user operation information comprises key operation frequency information and abnormal feedback information, and the hearing-aid equipment performance monitoring information comprises performance abnormal information and response frequency abnormal information;
Inputting the key operation frequency information, the abnormal feedback information, the performance abnormal information and the response frequency abnormal information into a hearing aid performance abnormal detection model of a user for processing to obtain a hearing aid performance abnormal detection value;
and carrying out threshold comparison according to the hearing aid performance abnormal detection value and a preset performance detection threshold value, and judging the condition of using hearing aid equipment by a user according to a threshold comparison result.
It should be noted that, the abnormal detection of the performance of the hearing aid device may be further performed according to the user operation information and the performance monitoring information of the hearing aid device, where the user operation information includes key operation frequency information and abnormal feedback information, the performance monitoring information of the hearing aid device includes performance abnormal information and response frequency abnormal information, and the hearing aid performance abnormal detection value is obtained by inputting the key operation frequency information, the abnormal feedback information, the performance abnormal information and the response frequency abnormal information into a hearing aid performance abnormal detection model of the user for processing, where the hearing aid performance abnormal detection model is a model obtained by training the obtained user operation information, the hearing aid performance monitoring information and the corresponding hearing aid performance abnormal detection value of a large number of historical samples, and the hearing aid performance abnormal detection value can be obtained by inputting relevant information for processing. And comparing the hearing aid performance abnormal detection value with a preset performance detection threshold value according to the threshold value, wherein the preset performance detection threshold value is set to be not less than 0.8.
According to an embodiment of the present invention, further comprising:
threshold value comparison is carried out according to the deviation index of the hearing aid equipment and a preset deviation index threshold value;
if the threshold comparison result does not meet the preset deviation index threshold comparison requirement, prompting abnormal functions of the hearing aid equipment, and generating hearing aid equipment performance feedback information;
correcting the sound azimuth information and the second compensation gain value according to the hearing aid device performance feedback information to obtain a sound azimuth information correction value and a second compensation gain correction value;
and inputting the sound azimuth information correction value and the second compensation gain correction value into a hearing aid device state identification model to obtain state adjustment parameters, and automatically adjusting the hearing aid device.
If the deviation index of the hearing aid device exceeds the preset threshold range, the quality inspection result of the hearing aid device is unqualified, hearing aid device performance feedback information is generated, sound azimuth information and a second compensation gain value are corrected according to the hearing aid device performance feedback information, sound azimuth information correction value and second compensation gain correction value are obtained, the sound azimuth information correction value and the second compensation gain correction value are input into a hearing aid device state recognition model, state adjustment parameters are obtained, the hearing aid device is automatically adjusted, the hearing aid device state recognition model is a model obtained by training the obtained sound azimuth information correction value and the second compensation gain correction value of a large number of historical samples and the corresponding state adjustment parameters, the corresponding output state adjustment parameters can be obtained by inputting relevant information for processing, and the hearing aid device is automatically adjusted.
According to an embodiment of the present invention, further comprising:
acquiring positioning information of hearing-aid equipment;
inputting positioning information, acceleration parameters, speed parameters and gravity parameters into a danger detection model for recognition processing to obtain a danger alarm index;
threshold value comparison is carried out on the dangerous alarm index value and a preset dangerous alarm index preset value, and a threshold value comparison result is obtained;
if the threshold comparison result meets the requirement, sending a voice request for dialing an emergency contact person telephone, and acquiring a voice signal of a wearer;
inputting the voice signal into a voice recognition model for voice recognition processing to obtain a voice recognition result;
if the voice recognition result accords with the preset semantic scene or the voice signal of the wearer is not obtained, automatically making an emergency contact call and sending positioning information to the emergency contact.
It should be noted that, the positioning information, the acceleration parameter, the speed parameter and the gravity parameter are input into a danger detection model for recognition processing, so as to obtain a danger alarm index, the preset danger detection model is a model obtained by training the obtained positioning information, the acceleration parameter, the speed parameter and the gravity parameter of a large amount of history samples, and the corresponding danger alarm index, the corresponding output danger alarm index can be obtained by inputting related information for processing, the danger alarm index threshold is set to 1 to 3 stages, 3 stages are lowest, 1 stage is highest, when the danger alarm index value is 3 stages, the user is in a dangerous state, for example, when the user is in a high-speed driving process, the hearing aid device detects that the acceleration parameter and the gravity parameter have instant large mutation, then the user is likely to encounter dangerous emergency brake, the hearing aid device sends a voice request for dialing an emergency contact phone, meanwhile, the voice signal of the wearer is input into the voice recognition model for voice recognition processing, so as to obtain a voice recognition result, if the voice recognition result accords with the preset semantic scene or the voice signal of the wearer is not obtained, the emergency contact phone is automatically dialed, and the positioning contact phone is in a dangerous state, for example, the user is in an emergency contact phone is dialed, and the voice request is set to be dialed, and the emergency contact phone is called. Whether to dial an emergency contact call or not, the preset semantic scenario may be set as: dialing, wherein the preset voice recognition model is obtained by training the acquired voice information of a large number of historical samples and the corresponding voice recognition results, and the corresponding output voice recognition results can be obtained by inputting related information for processing.
A third aspect of the present invention provides a computer readable storage medium, in which a hearing aid device state intelligent quality inspection method program is included, which when executed by a processor, implements the steps of the hearing aid device state intelligent quality inspection method according to any one of the above.
The invention discloses a hearing-aid equipment state intelligent quality inspection method, a system and a medium, wherein the method comprises the following steps: collecting sound signals of hearing-aid equipment, preprocessing the sound signals to obtain first sound process information, carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, carrying out pickup direction processing judgment according to the sound azimuth information to obtain user audiogram data, inputting the audiogram data into a preset hearing loss detection model to be processed to obtain user hearing loss values, processing the hearing loss values based on the user hearing loss values to obtain first compensation gain values, obtaining motion parameter data, carrying out analysis and recognition to obtain corresponding motion compensation correction factors, correcting the first compensation gain values according to the motion compensation correction factors to obtain second compensation gain values, processing according to pickup direction processing results and the second compensation gain values to obtain hearing-aid equipment deviation degree indexes, carrying out threshold comparison according to hearing-aid equipment deviation degree indexes and preset deviation degree index thresholds, and judging quality inspection results of the hearing-aid equipment according to threshold comparison results; the invention can realize intelligent quality inspection of the state of the hearing aid equipment, thereby realizing the effect of intelligent adjustment of the hearing aid equipment.
In the several embodiments provided in this application, it should be understood that the disclosed apparatus and method may be implemented in other ways. The above described device embodiments are only illustrative, e.g. the division of the units is only one logical function division, and there may be other divisions in practice, such as: multiple units or components may be combined or may be integrated into another system, or some features may be omitted, or not performed. In addition, the various components shown or discussed may be coupled or directly coupled or communicatively coupled to each other via some interface, whether indirectly coupled or communicatively coupled to devices or units, whether electrically, mechanically, or otherwise.
The units described above as separate components may or may not be physically separate, and components shown as units may or may not be physical units; can be located in one place or distributed to a plurality of network units; some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in each embodiment of the present invention may be integrated in one processing unit, or each unit may be separately used as one unit, or two or more units may be integrated in one unit; the integrated units may be implemented in hardware or in hardware plus software functional units.
Those of ordinary skill in the art will appreciate that: all or part of the steps for implementing the above method embodiments may be implemented by hardware related to program instructions, and the foregoing program may be stored in a computer readable storage medium, where the program, when executed, performs steps including the above method embodiments; and the aforementioned storage medium includes: a mobile storage device, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk or an optical disk, or the like, which can store program codes.
Alternatively, the above-described integrated units of the present invention may be stored in a computer-readable storage medium if implemented in the form of software functional modules and sold or used as separate products. Based on such understanding, the technical solutions of the embodiments of the present invention may be embodied in essence or a part contributing to the prior art in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the methods described in the embodiments of the present invention. And the aforementioned storage medium includes: a removable storage device, ROM, RAM, magnetic or optical disk, or other medium capable of storing program code.
Claims (10)
1. The intelligent hearing aid equipment state quality inspection method is characterized by comprising the following steps of:
collecting sound signals of hearing-aid equipment, and preprocessing the sound signals to obtain first sound process information;
carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, and carrying out pickup direction processing judgment according to the sound azimuth information;
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to acquire a hearing loss value of the user, and processing to acquire a first compensation gain value based on the hearing loss value of the user;
acquiring motion parameter data, analyzing and identifying the motion parameter data to acquire corresponding motion compensation correction factors;
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
and processing according to the pick-up direction processing result and combining the second compensation gain value to obtain a deviation index of the hearing aid equipment, performing threshold comparison according to the deviation index of the hearing aid equipment and a preset deviation index threshold, and judging a quality inspection result of the hearing aid equipment according to the threshold comparison result.
2. The method for intelligent quality inspection of hearing aid device status according to claim 1, wherein the steps of collecting a sound signal of the hearing aid device and preprocessing the sound signal to obtain first sound process information include:
Collecting a sound signal of hearing-aid equipment, and carrying out noise reduction treatment on the sound signal to obtain a noise-reduced sound signal;
and carrying out real-time preprocessing on the noise reduction sound signal to obtain first sound process information, wherein the first sound process information comprises sound loudness information, sound frequency band information, sound velocity information, transmission distance information and sound receiving time information.
3. The intelligent quality control method for a hearing aid device according to claim 2, wherein the step of performing azimuth recognition on the first sound process information to obtain sound azimuth information, and performing pickup direction processing judgment according to the sound azimuth information specifically comprises:
inputting the first sound process information into a preset sound azimuth recognition model to obtain sound azimuth information corresponding to the first sound process information;
processing according to the sound azimuth information and preset direction vector information to obtain a sound direction deviation degree value, and comparing the sound direction deviation degree value with a preset sound direction deviation degree threshold value;
if the threshold comparison result does not meet the preset sound direction deviation threshold comparison requirement, the pickup direction quality inspection result is not qualified, pickup direction deviation information is generated and fed back, and the sound azimuth information is further corrected;
And if the threshold comparison result meets the preset threshold comparison requirement of the sound direction deviation degree, generating qualified pickup direction quality inspection information and feeding back the qualified pickup direction quality inspection information.
4. The method for intelligent quality inspection of hearing aid device status according to claim 3, wherein the acquiring the audiogram data of the user, inputting the audiogram data into a preset hearing loss detection model for processing to acquire a hearing loss value of the user, and acquiring a first compensation gain value based on the hearing loss value processing of the user, specifically comprises:
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing, and acquiring a hearing loss value of the user;
acquiring a preset hearing loss compensation model;
dividing the sound signal into sound frequency band signals of different frequency band intervals according to the sound frequency band information;
inputting the hearing loss value of the user and the first sound process information corresponding to the sound frequency band signals into the hearing loss compensation model for processing according to each frequency band interval, and obtaining a sound band compensation gain value corresponding to the frequency band interval;
and aggregating the corresponding sound segment compensation gain values of each frequency band interval to obtain a first compensation gain value.
5. The intelligent quality control method for hearing aid device state according to claim 4, wherein the steps of acquiring the motion parameter data and analyzing and identifying the motion parameter data to obtain the corresponding motion compensation correction factor include:
Acquiring motion parameter information of a user, wherein the motion parameter information comprises acceleration parameters, vibration parameters, gravity parameters, speed parameters and inclination angle parameters;
and inputting the motion parameter information into a preset inertia recognition model for processing to obtain a motion compensation correction factor.
6. The intelligent quality control method for a hearing aid device state according to claim 5, wherein the correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value specifically includes:
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
the correction formula of the second compensation gain value is as follows:
wherein ,
for the second compensation gain value,/>
For the motion compensation correction factor +.>
For the first compensation gain value,
is a preset characteristic coefficient.
7. The intelligent quality inspection method for the state of hearing-aid equipment according to claim 6, wherein the processing result according to the pick-up direction is combined with the second compensation gain value to obtain a hearing-aid equipment deviation index, threshold comparison is performed according to the hearing-aid equipment deviation index and a preset deviation index threshold, and the quality inspection result of the hearing-aid equipment is judged according to the threshold comparison result, and the method specifically comprises the following steps:
Inputting the pickup direction deviation information and the second compensation gain value into a preset hearing-aid equipment performance recognition model for processing to obtain a hearing-aid equipment deviation index;
threshold value comparison is carried out according to the deviation index of the hearing aid equipment and a preset deviation index threshold value;
if the threshold comparison result meets the preset requirement, the quality inspection result of the hearing aid equipment is qualified;
otherwise, the quality inspection result of the hearing aid device is unqualified.
8. The hearing device status intelligent quality control method of claim 1, further comprising:
acquiring user operation information of a user using hearing-aid equipment and hearing-aid equipment performance monitoring information under a preset scene, wherein the user operation information comprises key operation frequency information and abnormal feedback information, and the hearing-aid equipment performance monitoring information comprises performance abnormal information and response frequency abnormal information;
inputting the key operation frequency information, the abnormal feedback information, the performance abnormal information and the response frequency abnormal information into a hearing aid performance abnormal detection model of a user for processing to obtain a hearing aid performance abnormal detection value;
and carrying out threshold comparison according to the hearing aid performance abnormal detection value and a preset performance detection threshold value, and judging the condition of using hearing aid equipment by a user according to a threshold comparison result.
9. The intelligent quality inspection system for the state of the hearing aid device is characterized by comprising a memory and a processor, wherein the memory comprises an intelligent quality inspection method program for the state of the hearing aid device, and the intelligent quality inspection method program for the state of the hearing aid device realizes the following steps when being executed by the processor:
collecting sound signals of hearing-aid equipment, and preprocessing the sound signals to obtain first sound process information;
carrying out azimuth recognition on the first sound process information to obtain sound azimuth information, and carrying out pickup direction processing judgment according to the sound azimuth information;
acquiring audiogram data of a user, inputting the audiogram data into a preset hearing loss detection model for processing to acquire a hearing loss value of the user, and processing to acquire a first compensation gain value based on the hearing loss value of the user;
acquiring motion parameter data, analyzing and identifying the motion parameter data to acquire corresponding motion compensation correction factors;
correcting the first compensation gain value according to the motion compensation correction factor to obtain a second compensation gain value;
and processing according to the pick-up direction processing result and combining the second compensation gain value to obtain a deviation index of the hearing aid equipment, performing threshold comparison according to the deviation index of the hearing aid equipment and a preset deviation index threshold, and judging a quality inspection result of the hearing aid equipment according to the threshold comparison result.
10. A computer readable storage medium, characterized in that a hearing aid device state intelligent quality inspection method program is included in the computer readable storage medium, and the steps of the hearing aid device state intelligent quality inspection method according to any one of claims 1 to 8 are implemented when the hearing aid device state intelligent quality inspection method program is executed by a processor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310507568.1A CN116249062B (en) | 2023-05-08 | 2023-05-08 | Hearing-aid equipment state intelligent quality inspection method, system and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310507568.1A CN116249062B (en) | 2023-05-08 | 2023-05-08 | Hearing-aid equipment state intelligent quality inspection method, system and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116249062A true CN116249062A (en) | 2023-06-09 |
| CN116249062B CN116249062B (en) | 2023-07-25 |
Family
ID=86631621
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310507568.1A Active CN116249062B (en) | 2023-05-08 | 2023-05-08 | Hearing-aid equipment state intelligent quality inspection method, system and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116249062B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150124985A1 (en) * | 2013-11-06 | 2015-05-07 | Samsung Electronics Co., Ltd. | Device and method for detecting change in characteristics of hearing aid |
| CN109218951A (en) * | 2018-09-25 | 2019-01-15 | 深圳市博音科技有限公司 | A kind of hearing-aid method and system with autonomous inspection correcting function |
| CN110611872A (en) * | 2019-10-09 | 2019-12-24 | 深圳市博音科技有限公司 | Multi-band gain compensation based self-correction hearing aid system and method |
| US20210227340A1 (en) * | 2020-01-17 | 2021-07-22 | Sonova Ag | Compensating Hidden Hearing Losses by Attenuating High Sound Pressure Levels |
| US20220189278A1 (en) * | 2020-12-16 | 2022-06-16 | Sivantos Pte. Ltd. | Method for operating a hearing system |
| US20220408199A1 (en) * | 2021-06-18 | 2022-12-22 | Starkey Laboratories, Inc. | Self-check protocol for use by ear-wearable electronic devices |
| WO2023016208A1 (en) * | 2021-08-13 | 2023-02-16 | Oppo广东移动通信有限公司 | Audio signal compensation method and apparatus, earbud, and storage medium |
| CN115802267A (en) * | 2023-02-09 | 2023-03-14 | 杭州兆华电子股份有限公司 | Automatic calibration method and system for acoustic characteristics of hearing aid |
-
2023
- 2023-05-08 CN CN202310507568.1A patent/CN116249062B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20150124985A1 (en) * | 2013-11-06 | 2015-05-07 | Samsung Electronics Co., Ltd. | Device and method for detecting change in characteristics of hearing aid |
| CN109218951A (en) * | 2018-09-25 | 2019-01-15 | 深圳市博音科技有限公司 | A kind of hearing-aid method and system with autonomous inspection correcting function |
| CN110611872A (en) * | 2019-10-09 | 2019-12-24 | 深圳市博音科技有限公司 | Multi-band gain compensation based self-correction hearing aid system and method |
| US20210227340A1 (en) * | 2020-01-17 | 2021-07-22 | Sonova Ag | Compensating Hidden Hearing Losses by Attenuating High Sound Pressure Levels |
| US20220189278A1 (en) * | 2020-12-16 | 2022-06-16 | Sivantos Pte. Ltd. | Method for operating a hearing system |
| US20220408199A1 (en) * | 2021-06-18 | 2022-12-22 | Starkey Laboratories, Inc. | Self-check protocol for use by ear-wearable electronic devices |
| WO2023016208A1 (en) * | 2021-08-13 | 2023-02-16 | Oppo广东移动通信有限公司 | Audio signal compensation method and apparatus, earbud, and storage medium |
| CN115802267A (en) * | 2023-02-09 | 2023-03-14 | 杭州兆华电子股份有限公司 | Automatic calibration method and system for acoustic characteristics of hearing aid |
Non-Patent Citations (1)
| Title |
|---|
| 陶仁霞;李进;刘巧云;赵航;: "4～7岁双耳双模式助听儿童声源定位能力研究", 听力学及言语疾病杂志, no. 03 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116249062B (en) | 2023-07-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10721571B2 (en) | Separating and recombining audio for intelligibility and comfort | |
| CN110418232B (en) | Volume adjusting method and device and computer readable storage medium | |
| CN102124758B (en) | Hearing aid, hearing assistance system, walking detection method, and hearing assistance method | |
| EP2603018B1 (en) | Hearing aid with speaking activity recognition and method for operating a hearing aid | |
| CN107734126B (en) | Voice adjusting method, device, terminal and storage medium | |
| CN109461455B (en) | System and method for eliminating howling | |
| CN112383870B (en) | Adaptive hearing parameter fitting method and device | |
| CN107995360A (en) | Call handling method and Related product | |
| CN110060696B (en) | Sound mixing method and device, terminal and readable storage medium | |
| CN111901737A (en) | Hearing aid parameter self-adaption method based on intelligent terminal | |
| CN113542960A (en) | Audio signal processing method, system, device, electronic equipment and storage medium | |
| CN113421583B (en) | Noise reduction method, storage medium, chip and electronic device | |
| CN117480554A (en) | Voice enhancement method and related equipment | |
| CN113038337B (en) | Audio playing method, wireless earphone and computer readable storage medium | |
| CN113613123B (en) | Audio data processing method and device, earphone and storage medium | |
| CN116249062B (en) | Hearing-aid equipment state intelligent quality inspection method, system and medium | |
| CN103796145B (en) | Auditory sense threshold value determining method and device and hearing aid | |
| WO2023197474A1 (en) | Method for determining parameter corresponding to earphone mode, and earphone, terminal and system | |
| US11457320B2 (en) | Selectively collecting and storing sensor data of a hearing system | |
| CN111800700B (en) | Method and device for prompting object in environment, earphone equipment and storage medium | |
| CN114598970A (en) | Audio processing method and device, electronic equipment and storage medium | |
| CN114175684A (en) | Audio training | |
| US11902745B2 (en) | System of processing devices to perform an algorithm | |
| WO2023193686A1 (en) | Monitoring method and apparatus for hearing assistance device | |
| EP4303873A1 (en) | Personalized bandwidth extension |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |