Hearing test method, device and storage medium

Abstract

The present application discloses a hearing test method, device and storage medium, and relates to the technical field of hearing aids, wherein the hearing test method comprises: obtaining first facial feature data of a user before playing a test sound, and obtaining second facial feature data of the user after playing the test sound; processing the first facial feature data and the second facial feature data to determine facial change data of the user; processing the facial change data based on a pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the test sound; adjusting the volume amplification degree of the hearing aid according to the degree of hearing loss; the present application aims to solve the technical problem that some elderly users cannot provide feedback on whether they hear the test sound due to limited hand function.

Description

Technical Field

[0001] The present application relates to the technical field of hearing aids, and in particular to a hearing test method, device and storage medium. Background Art

[0002] The main function of a hearing aid is to enhance the sound so that the elderly with hearing loss can better hear the sounds of the surrounding environment, including daily sounds such as family conversations, phone ringing, and TV sounds, thereby effectively improving their hearing condition.

[0003] Since different elderly people have different degrees of hearing loss, when they first use hearing aids, they will first perform an audiometric test to adjust the working mode of the hearing aids. The existing test method is that when the elderly hear the audiometric sound while using the hearing aid, they press a feedback button electrically connected to the hearing aid to give feedback on the event that they heard the audiometric sound. However, due to limited hand functions, some elderly users find it difficult to promptly give feedback on whether they heard the audiometric sound by pressing buttons or other hand movements during self-audiometry, resulting in deviations in test results. Summary of the invention

[0004] The main purpose of this application is to provide a hearing test method, device and storage medium, aiming to solve the technical problem that some elderly users are unable to provide feedback on whether they hear the test sound due to limited hand function.

[0005] To achieve the above objectives, the present application proposes a hearing test method, the method comprising:

[0006] Before playing the test sound, obtaining first facial feature data of the user, and after playing the test sound, obtaining second facial feature data of the user;

[0007] Processing the first facial feature data and the second facial feature data to determine facial change data of the user;

[0008] Processing the facial change data based on a pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the test tone;

[0009] The volume amplification level of the hearing aid is adjusted according to the degree of hearing loss.

[0010] In one embodiment, the processing the first facial feature data and the second facial feature data to determine the facial change data of the user includes:

[0011] Extracting a plurality of different first facial key features based on the first facial feature data, and proposing a plurality of different second facial key features based on the second facial feature data;

[0012] The plurality of first facial key features are compared with the plurality of second facial key features one by one to determine the degree of difference between the second facial key features and the first facial key features.

[0013] In one embodiment, the first key facial feature or the second key facial feature includes eye size, mouth size, or mouth corner angle.

[0014] In one embodiment, the processing of the facial change data based on a pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the audiometric sound comprises:

[0015] When the degree of difference of at least one of the second key facial features is less than a first preset value, determining that the user does not hear the test tone;

[0016] When the degree of difference of at least one of the second key facial features is greater than a first preset value, determining that the user hears the test tone;

[0017] When the degree of difference of at least one of the second key facial features is greater than a first preset value and less than a second preset value, determining that the degree of hearing loss is moderate hearing loss;

[0018] When the degree of difference of at least one of the second key facial features is greater than a second preset value and less than a third preset value, determining that the degree of hearing loss is mild hearing loss;

[0019] When the degree of difference of at least one of the second facial key features is greater than a third preset value, it is determined that the user's hearing is at a normal level.

[0020] In one embodiment, the processing the first facial feature data and the second facial feature data to determine the facial change data of the user includes:

[0021] Extracting a plurality of different first facial key features based on the first facial feature data, and proposing a plurality of different second facial key features based on the second facial feature data;

[0022] Processing a plurality of different positional relationships of the first key facial features and a plurality of different positional relationships of the second key facial features to determine a head rotation angle of the user;

[0023] The first key facial feature or the second key facial feature includes the tip of the nose, the corners of the eyes, the corners of the mouth and the chin.

[0024] In one embodiment, the processing of the positional relationship of the plurality of different first facial key features with the positional relationship of the plurality of different first facial key features to determine the head rotation angle of the user includes:

[0025] Performing a difference operation on the positional relationship of the plurality of first facial key features and the positional relationship of the plurality of second facial key features in a one-to-one correspondence;

[0026] The user's head rotation angle is determined based on the results of multiple difference operations.

[0027] In one embodiment, the processing of the facial change data based on a pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the audiometric sound comprises:

[0028] When the user's head rotation angle is greater than a first preset angle and less than a second preset angle, determining that the hearing loss degree is moderate hearing loss;

[0029] When the user's head rotation angle is greater than the second preset angle and less than the third preset angle, determining that the hearing loss degree is mild hearing loss;

[0030] When the rotation angle of the user's head is greater than the third preset angle, it is determined that the user's hearing is at a normal level.

[0031] In one embodiment, the extracting a plurality of different first facial key features based on the first facial feature data and proposing a plurality of different second facial key features based on the second facial feature data comprises:

[0032] When the plurality of different first key facial features do not include the facial features and the plurality of different second key facial features all include the facial features, it is determined that the user's hearing is at a normal level.

[0033] In addition, to achieve the above-mentioned purpose, the present application also proposes a hearing test device, which includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the hearing test method described above; a communication module for establishing a communication connection with a hearing aid; and an image acquisition module for acquiring facial feature data of a user.

[0034] In addition, to achieve the above objectives, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the hearing test method described above are implemented.

[0035] One or more technical solutions proposed in this application have at least the following technical effects:

[0036] Before playing the test tone, the user's first facial feature data is obtained, and after playing the test tone, the user's second facial feature data is obtained; the first facial feature data and the second facial feature data are processed to determine the user's facial change data; the facial change data is processed based on a pre-trained hearing assessment model to determine the user's hearing loss degree when hearing the test tone; and the volume amplification degree of the hearing aid is adjusted according to the degree of hearing loss. With such a configuration, the hearing test method of the present application assesses the user's hearing loss degree by capturing and analyzing the changes in the user's facial features before and after hearing the test tone, and adjusts the volume amplification degree of the hearing aid accordingly. For elderly users with limited hand function, no hand movement is required to provide feedback on the event of hearing the test tone, thereby avoiding feedback difficulties caused by limited hand function and improving the accuracy and convenience of the test. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0038] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0039] Figure 1 A flowchart of an embodiment of a hearing test method of the present application is provided;

[0040] Figure 2 A flowchart diagram of another embodiment of the hearing test method of the present application;

[0041] Figure 3 A flowchart diagram of another embodiment of the hearing test method of the present application is provided;

[0042] Figure 4 A flowchart diagram of another embodiment of the hearing test method of the present application is provided.

[0043] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0044] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0045] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0046] The main function of a hearing aid is to enhance the sound so that the elderly with hearing loss can better hear the sounds of the surrounding environment, including daily sounds such as family conversations, phone ringing, and TV sounds, thereby effectively improving their hearing condition.

[0047] Since different elderly people have different degrees of hearing loss, when they first use hearing aids, they will first perform an audiometric test to adjust the working mode of the hearing aids. The existing test method is that when the elderly hear the audiometric sound while using the hearing aid, they press a feedback button electrically connected to the hearing aid to give feedback on the event that they heard the audiometric sound. However, due to limited hand functions, some elderly users find it difficult to promptly give feedback on whether they heard the audiometric sound by pressing buttons or other hand movements during self-audiometry, resulting in deviations in test results.

[0048] To this end, the present application provides a hearing test device, a control device and a storage medium, aiming to solve the technical problem that some elderly users are unable to provide feedback on whether they hear the audiometric sound due to limited hand function.

[0049] refer to Figure 1 In one embodiment of the present application, a hearing test method includes:

[0050] Step S100: before playing the test sound, obtaining the first facial feature data of the user, and after playing the test sound, obtaining the second facial feature data of the user;

[0051] It should be noted that the facial features of elderly users will change accordingly according to the content of the test tone when they hear the test tone. For example, elderly users are relatively calm before hearing pleasant content, and the angle of the corners of their mouths is close to 180 degrees (first facial feature data). After hearing pleasant content, they may feel happy and smile, and the angle of the corners of their mouths bend upward when smiling (second facial data feature); or before hearing unpleasant or incomprehensible content, the eyes of elderly users are normal size (first facial data feature), and after hearing unpleasant or incomprehensible content, they may widen their eyes due to surprise or nervousness (second facial data feature). For another example, before hearing the test tone, the elderly user may lower his head or face forward (first facial data feature), and after hearing the test tone, he may turn his head or neck left or right or up and down due to the source direction of the test tone (second facial data feature).

[0052] Step S200: Processing the first facial feature data and the second facial feature data to determine facial change data of the user;

[0053] It should be noted that by comparing the facial feature data before and after playing the test sound, the user's facial change data can be calculated. The facial change data may include the change range of facial features such as the change range of the mouth corner angle, the change range of the eye size, the change range of the mouth corner opening or closing, or the change range of the eyebrow size.

[0054] Optionally, step S200 can be implemented by a method based on image difference, directly operating on the image containing the first facial feature data and the second facial feature data. Subtract the pixel values ​​at the same position of the two images to obtain a difference image. The pixel values ​​in the difference image reflect the degree of change of the face at the corresponding position. For example, if the pixel value of a certain area changes greatly, it means that the facial features of the area have changed greatly. Alternatively, step S200 can use a deep learning model such as a convolutional neural network (CNN) to input the first facial feature data and the second facial feature data (which can be in image form or in vector form after feature extraction) into a pre-trained neural network model, and the neural network model outputs facial change data by extracting the change information of the facial features.

[0055] Step S300: Processing the facial change data based on a pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the test tone;

[0056] It should be noted that the training steps of the hearing assessment model include: collecting a large amount of hearing test data, the hearing test data should contain facial change data (such as facial expressions, muscle tension, etc.) of users with different hearing levels and the corresponding hearing test results, and preprocessing the hearing test data, including data cleaning, feature extraction and standardization steps to ensure the quality and consistency of the data. Subsequently, the hearing assessment model is trained based on the preprocessed hearing test data so that the hearing assessment model can accurately assess the degree of hearing loss of elderly users based on facial change data. For example, when hearing-impaired users try to understand the test sound, they often unconsciously increase the tension of facial muscles, such as frowning their foreheads and drooping corners of their mouths. As hearing recovers, these tense expressions will gradually decrease. The hearing assessment model can indirectly assess the degree of hearing loss of elderly users by analyzing changes in the user's facial expressions. For another example, when a hearing-impaired user hears a sound, if the hearing is normal, the head will naturally turn to the direction of the sound source. However, hearing-impaired elderly users may not be able to accurately judge the location of the sound source, resulting in reduced or inaccurate head turning movements. The hearing assessment model can assess the degree of hearing loss of elderly users by analyzing the frequency and amplitude of their head turning movements.

[0057] It should be noted that, when it is determined based on the facial change data that the facial features of the elderly user remain basically unchanged before and after the test tone is played, it is determined that the elderly user did not hear the test tone, that is, when the hearing loss level is severe or above, the volume amplification level of the hearing aid is directly adjusted to increase a fixed amplification volume value, and the test is re-performed until it is determined that the elderly user hears the test tone.

[0058] Step S400: adjusting the volume amplification level of the hearing aid according to the hearing loss level.

[0059] It should be noted that after processing the facial change data, the hearing assessment model will output a specific hearing loss index, which reflects the improvement in the user's hearing after wearing the hearing aid and hearing the test tone. The hearing aid will automatically adjust the volume amplification level according to the hearing loss index. If the user's hearing loss is low, the volume amplification level of the hearing aid can be reduced accordingly; conversely, if the hearing loss is high, the volume amplification level needs to be increased.

[0060] It is understandable that the device for playing the test tone and obtaining the facial feature data can be implemented by a mobile terminal such as a mobile phone or a tablet, and the hearing test method of the present application can be installed in a mobile phone or a tablet as an application. Most mobile phones and tablets are equipped with a front camera. Before and after playing the test tone, the application starts the front camera to obtain the user's facial images before and after playing the test tone, and extracts the first facial feature data and the second facial feature data based on the facial images before and after playing the test tone. Mobile phones and tablets can select the corresponding test tone to play through the pre-installed application. The application processes the first facial feature data and the second facial feature data to identify the change data of the facial features of the elderly user after hearing the test tone. According to the change data, the application can determine the elderly user's reaction to the test tone, such as whether to smile, frown or turn the head, etc., and determine the user's hearing loss degree according to the change of facial features. The mobile phone or tablet establishes a wireless communication connection with the hearing aid via Bluetooth or WIFI, so that the application adjusts the volume amplification of the hearing aid through the wireless communication connection according to the degree of hearing loss. Among them, the application can collect recordings of the elderly users' relatives or friends as test sounds. In actual applications, the application can play the recordings at a preset volume. When the elderly users hear the voices of their relatives or friends, the degree of facial changes will be more obvious, which is helpful to assess the degree of hearing loss of the elderly users.

[0061] Specifically, one or more technical solutions proposed in this application have at least the following technical effects:

[0062] Before playing the test tone, the user's first facial feature data is obtained, and after playing the test tone, the user's second facial feature data is obtained; the first facial feature data and the second facial feature data are processed to determine the user's facial change data; the facial change data is processed based on a pre-trained hearing assessment model to determine the user's hearing loss degree; and the volume amplification level of the hearing aid is adjusted according to the hearing loss degree. With such a configuration, the hearing test method of the present application assesses the user's hearing loss degree by capturing and analyzing the changes in the user's facial features before and after hearing the test tone, and adjusts the volume amplification level of the hearing aid accordingly. For elderly users with limited hand function, no hand movement is required to provide feedback on the event of hearing the test tone, thereby avoiding feedback difficulties caused by limited hand function and improving the accuracy and convenience of the test.

[0063] refer to Figure 2 In one embodiment of the present application, the processing of the first facial feature data and the second facial feature data to determine the facial change data of the user includes:

[0064] Step S210: extracting a plurality of different first facial key features based on the first facial feature data, and proposing a plurality of different second facial key features based on the second facial feature data;

[0065] It should be noted that since facial muscle tension is usually continuous and subtle, it is difficult to quantify it through specific values ​​or indicators, especially in dynamic situations, and existing measurement technologies find it difficult to accurately capture these changes. However, the eye size, mouth size, and mouth corner angles are relatively fixed in position on the face and relatively stable in shape, so they are easier to measure accurately. Through image processing techniques such as edge detection and contour extraction, the measurement values ​​of eye size, mouth size, and mouth corner angles can be accurately obtained. Therefore, assessing the user's hearing loss level based on changes in eye size, mouth size, and mouth corner angles has higher reliability and accuracy.

[0066] Step S211: compare the first facial key features at multiple locations with the second facial key features at multiple locations one by one to determine the degree of difference between the second facial key features and the first facial key features.

[0067] It should be noted that the degree of difference is the change of facial features such as eye size, mouth size and mouth corner angle before and after the test tone is played. For example, the content of the test tone is pleasant content. Before the test tone is played, the elderly user is relatively calm, and the angle of the mouth corner is usually close to the horizontal state (for example, 180 degrees). After the test tone is played, the elderly user feels happy and smiles after hearing the pleasant content. When smiling, the angle of the mouth corner rises (for example, 150 degrees). The degree of difference is the difference between the angle of the mouth corner before and after the test tone is played (for example, the difference of 30 degrees is obtained by subtracting the angle of 150 degrees from the angle of 180 degrees, and the difference of 30 degrees is about 50% of the degree of difference). For another example, before and after the test tone is played, the degree of opening and closing of the eyelids of the elderly user (such as the distance between the upper and lower eyelids) or the diameter of the pupil is measured respectively, and the degree of opening and closing of the eyelids or the diameter of the pupil before and after the test tone is played is subtracted to determine the degree of difference in eye size before and after the test tone is played. For another example, before and after the test tone is played, the width or height of the elderly user's lips in a naturally closed state is measured, and the difference between the width or height of the lips before and after the test tone is played is taken to determine the degree of difference in mouth size before and after the test tone is played. The test tone contains specific emotional content (such as happiness, sadness, surprise, etc.) or specific language information, so that the elderly user's facial features change accordingly after hearing the test tone.

[0068] In this embodiment, the processing of the facial change data based on the pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the test tone includes:

[0069] When the degree of difference of at least one of the second key facial features is less than a first preset value, determining that the user does not hear the test tone;

[0070] When the degree of difference of at least one of the second key facial features is greater than a first preset value, determining that the user hears the test tone;

[0071] When the degree of difference of at least one of the second key facial features is greater than a first preset value and less than a second preset value, determining that the degree of hearing loss is moderate hearing loss;

[0072] When the degree of difference of at least one of the second key facial features is greater than a second preset value and less than a third preset value, determining that the degree of hearing loss is mild hearing loss;

[0073] When the degree of difference of at least one of the second facial key features is greater than a third preset value, it is determined that the user's hearing is at a normal level.

[0074] It should be noted that the hearing assessment model has been trained with a large amount of data and can identify the association between key facial features (such as mouth movement, eye opening and closing degree, eyebrow height, etc.) and hearing recovery status. The first preset value, the second preset value, and the third preset value are thresholds set according to historical data, which are used to distinguish different degrees of hearing loss. For example, in the case where the elderly user does not hear the test tone after wearing the hearing aid, multiple facial features of the elderly user remain basically unchanged before and after the test tone is played, so that the difference in the degree of mouth opening before and after the test tone is played is less than the first preset value (5%). In the case where the hearing loss degree of the elderly user after wearing the hearing aid is moderate hearing loss (hearing level between 41 and 60 decibels), the elderly user usually only opens his mouth slightly after hearing the test tone, and hardly makes an obvious reaction, so that the difference in the degree of mouth opening before and after the test tone is played is greater than the first preset value (such as 5%), but less than the second preset value (such as 20%). When the hearing loss of an elderly user after wearing a hearing aid is mild (hearing level between 26 and 40 decibels), after hearing the test tone, the elderly user opens his mouth more obviously than at a lower level, but still not fully, and the difference in the degree of mouth opening is greater than the second preset value (20%), but less than the third preset value (e.g., 50%). When the hearing of an elderly user after wearing a hearing aid is normal, after hearing the test tone, the elderly user opens his mouth obviously in response, which is similar to the response of a normal hearing person when hearing the same sound, and the difference in the degree of mouth opening is greater than the third preset value (50%).

[0075] It is understandable that setting "at least one" as the judgment standard can simplify the process of hearing assessment. Different elderly users may have different facial reactions after hearing sound stimulation. Some elderly users may show obvious changes in a specific facial area (such as wide eyes, wide mouth, etc.), but not much change in other areas. Therefore, the use of the "at least one" standard can more flexibly reflect this individual difference and avoid ignoring individual significant facial changes due to strict requirements for multiple features.

[0076] refer to Figure 3 In one embodiment of the present application, the processing of the first facial feature data and the second facial feature data to determine the facial change data of the user includes:

[0077] Step S220: extracting a plurality of different first facial key features based on the first facial feature data, and proposing a plurality of different second facial key features based on the second facial feature data;

[0078] Step S221: Processing the positional relationship of the first facial key features at different locations and the positional relationship of the second facial key features at different locations to determine the head rotation angle of the user;

[0079] The first key facial feature or the second key facial feature includes the tip of the nose, the corners of the eyes, the corners of the mouth and the chin.

[0080] It should be noted that when the test tone is played on the right or left side of the elderly user, the elderly user will turn his head to the source direction of the test tone after hearing the test tone. Therefore, the degree of hearing loss of the elderly user can be determined based on the head rotation angle of the elderly user. For multiple different first facial key features, a positional relationship model between them can be established. For example, the distance vector from the tip of the nose to the corner of the eye, the distance vector from the tip of the nose to the corner of the mouth, the distance vector from the corner of the mouth to the chin, and the angle relationship between these vectors are calculated. The same operation is performed for the second facial key feature. The head rotation angle is determined by comparing the difference between the positional relationship of the first facial key feature and the positional relationship of the second facial key feature. For example, if the distance vector from the tip of the nose to the corner of the eye has an obvious change in direction before and after the test tone is played, the head rotation angle of the elderly user in the horizontal direction can be calculated based on processing the direction change through geometric transformation or machine learning algorithm.

[0081] refer to Figure 4 In this embodiment, the processing of the positional relationship of the plurality of different first facial key features with the positional relationship of the plurality of different first facial key features to determine the user's head rotation angle includes:

[0082] Step S2210: performing a difference operation on the positional relationship of the plurality of first facial key features and the positional relationship of the plurality of second facial key features in a one-to-one correspondence;

[0083] Step S2221: Determine the user's head rotation angle based on the results of multiple difference operations.

[0084] It should be noted that for each pair of corresponding key facial features (for example, the nose tip in multiple first key facial features and the nose tip in multiple second key facial features), the difference in positional relationship between them is calculated. This can be achieved through vector subtraction, that is, calculating the difference between the position vector of the second key facial feature point and the position vector of the first key facial feature point. The difference vector represents the position change of the key facial feature in two different states. By analyzing the direction and size of multiple difference vectors, the head rotation angle and direction of the elderly user are determined. For example, if multiple difference vectors all point to the same direction and are similar in size, then this may indicate that the user's head has rotated in that direction.

[0085] In this embodiment, the processing of the facial change data based on the pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the test tone includes:

[0086] When the user's head rotation angle is less than a first preset angle, determining that the user does not hear the test sound;

[0087] When the user's head rotation angle is greater than a first preset angle, determining that the user hears the test sound;

[0088] When the user's head rotation angle is greater than a first preset angle and less than a second preset angle, determining that the hearing loss degree is moderate hearing loss;

[0089] When the user's head rotation angle is greater than the second preset angle and less than the third preset angle, determining that the hearing loss degree is a mild hearing degree;

[0090] When the rotation angle of the user's head is greater than the third preset angle, it is determined that the user's hearing is at a normal level.

[0091] It should be noted that the hearing assessment model has been trained with a large amount of data and can identify the association between the head rotation angle and the hearing recovery state. The first preset value, the second preset value, and the third preset value are thresholds set according to historical data, which are used to distinguish different degrees of hearing loss. For example, when the elderly user does not hear the test sound, the elderly user's head will basically not turn, that is, the angle of head rotation is less than the first preset angle (assuming that 15 degrees is the upper limit of the first preset angle). When the test sound comes from the left side of the elderly user, if the elderly user's sensitivity to sound is still low after wearing the hearing aid, and the hearing has not yet recovered, the elderly user's head rotation after hearing the sound is only slightly turned, and the rotation angle is less than 30 degrees (assuming that 30 degrees is the lower limit of the second preset angle, and 15 degrees is the upper limit of the first preset angle). According to the hearing assessment model, the hearing loss degree of the elderly user is assessed as moderate hearing loss (hearing level between 41 and 60 decibels). If the elderly user's sensitivity to sound recovers slightly after wearing the hearing aid, but has not returned to the normal level, then after hearing the test tone, the head will turn more obviously, and the rotation angle is about 45 degrees (assuming that 45 degrees is the upper limit of the second preset angle, and 60 degrees is the lower limit of the third preset angle). According to the hearing assessment model, the hearing loss of the elderly user is assessed as mild hearing loss (hearing level between 26 and 40 decibels). If the elderly user's sensitivity to sound returns to normal after wearing the hearing aid, then after hearing the test tone, the head will be accurately turned to the source direction of the test tone, and the rotation angle is greater than the third preset angle (for example, 60 degrees). According to the hearing assessment model, the elderly's hearing is at a normal level.

[0092] It should be noted that, in the above steps, the device for acquiring facial feature data and the device for playing the test sound are independent devices. For example, the facial feature data of the elderly user is acquired through a mobile phone in front of the elderly user, so that the mobile phone can obtain the head rotation angle of the elderly user before and after the test sound is played. The test sound is played on the left side of the elderly user through a speaker, and a wireless communication connection is established between the speaker and the mobile phone, so that the mobile phone controls the speaker to play the corresponding test sound through a pre-installed application.

[0093] In one embodiment of the present application, the extracting a plurality of different first facial key features based on the first facial feature data and proposing a plurality of different second facial key features based on the second facial feature data comprises:

[0094] When the plurality of different first key facial features do not include the facial features and the plurality of different second key facial features all include the facial features, it is determined that the user's hearing is at a normal level.

[0095] In this embodiment, when the mobile phone or tablet plays a test tone on the left side, right side or top of the elderly user, before playing the test tone, the mobile phone and tablet can only capture the side face image of the elderly user, and cannot capture the complete facial features. If the elderly user's hearing returns to normal level after wearing a hearing aid, then after hearing the test tone, the mobile phone or tablet can capture the complete facial features of the elderly user. In this way, it can be directly determined to what extent the elderly user's hearing level has returned to normal level after wearing a hearing aid.

[0096] The present application provides a hearing test device, which includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the hearing test method in the above-mentioned embodiment 1; a communication module, used to establish a communication connection with a hearing aid; and an image acquisition module, used to acquire facial feature data of a user.

[0097] The hearing test device provided by the present application adopts the hearing test method in the above embodiment, which can solve the technical problem that some elderly users cannot give feedback on whether they hear the audiometric sound due to limited hand function. Compared with the prior art, the beneficial effects of the hearing test device provided by the present application are the same as the beneficial effects of the hearing test method provided by the above embodiment, and other technical features in the hearing test device are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0098] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0099] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the hearing test method in the above-mentioned embodiment.

[0100] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM: Random Access Memory), a read-only memory (ROM: Read Only Memory), an erasable programmable read-only memory (EPROM: Erasable Programmable Read Only Memory or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM: CD-Read Only Memory), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program, which may be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency: Radio Frequency), etc., or any suitable combination of the above.

[0101] The readable storage medium provided in the present application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned hearing test method, and can solve the technical problem that some elderly users cannot provide feedback on whether they hear the audiometric sound due to limited hand functions. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in the present application are the same as the beneficial effects of the hearing test method provided in the above-mentioned embodiment, and will not be elaborated here.

[0102] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A hearing test method, characterized in that: The method comprises: Before playing the test sound, obtaining first facial feature data of the user, and after playing the test sound, obtaining second facial feature data of the user; Processing the first facial feature data and the second facial feature data to determine facial change data of the user; Processing the facial change data based on a pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the test tone; adjusting the volume amplification level of the hearing aid according to the degree of hearing loss; The processing of the first facial feature data and the second facial feature data to determine the facial change data of the user comprises: Extracting a plurality of different first facial key features based on the first facial feature data, and proposing a plurality of different second facial key features based on the second facial feature data; Processing a plurality of different positional relationships of the first key facial features and a plurality of different positional relationships of the second key facial features to determine a head rotation angle of the user; Wherein, the first key facial feature or the second key facial feature comprises the tip of the nose, the corners of the eyes, the corners of the mouth and the chin; The processing of the positional relationship of the plurality of different first facial key features with the positional relationship of the plurality of different first facial key features to determine the head rotation angle of the user includes: Performing a difference operation on the positional relationship of the plurality of first facial key features and the positional relationship of the plurality of second facial key features in a one-to-one correspondence; Determine the user's head rotation angle based on the results of multiple difference operations; The processing of the facial change data based on the pre-trained hearing assessment model to determine the degree of hearing loss of the user when hearing the test tone includes: When the user's head rotation angle is less than a first preset angle, determining that the user does not hear the test sound; When the user's head rotation angle is greater than a first preset angle, determining that the user hears the test sound; When the user's head rotation angle is greater than a first preset angle and less than a second preset angle, determining that the hearing loss degree is moderate hearing loss; When the user's head rotation angle is greater than the second preset angle and less than the third preset angle, determining that the hearing loss degree is mild hearing loss; When the rotation angle of the user's head is greater than a third preset angle, determining that the user's hearing is at a normal level; Among them, the positional relationship between multiple first facial key features and the positional relationship between multiple second facial key features include: the distance vector from the tip of the nose to the corner of the eye, the distance vector from the tip of the nose to the corner of the mouth, and the distance vector from the corner of the mouth to the chin.

2. The hearing test method according to claim 1, characterized in that: The extracting of a plurality of different first facial key features based on the first facial feature data and proposing a plurality of different second facial key features based on the second facial feature data comprises: When the plurality of different first key facial features do not include the facial features and the plurality of different second key facial features all include the facial features, it is determined that the user's hearing is at a normal level.

3. A hearing test device, characterized in that: The hearing test device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the hearing test method according to any one of claims 1 to 2; a communication module for establishing a communication connection with a hearing aid; and an image acquisition module for acquiring facial feature data of a user.

4. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the hearing test method according to any one of claims 1 to 2 are implemented.

Images