Self-help hearing aid fitting system for hearing detection

Abstract

The application relates to the technical field of self-service hearing aid fitting, and discloses a self-service hearing aid fitting system for hearing detection, which comprises a user interaction module, a sound signal generation module, a user response detection module, a hearing evaluation module, a parameter calculation module, a hearing aid configuration module and a data storage module. A user can input personal information on a mobile device and initiate a hearing detection request. The system generates a personalized hearing detection instruction through image recognition and data analysis. The sound signal generation module generates a sound signal according to the hearing detection instruction and transmits the sound signal to the user's ear. The user response detection module evaluates the user's hearing threshold and hearing loss level in combination with a key response and a physiological signal response, and calculates hearing aid fitting parameters accordingly. Through integrated and self-service system design, multi-dimensional information collection and personalized parameter configuration, the application effectively improves the convenience, accuracy and personalization level of hearing aid fitting.

Description

Technical Field

[0001] This invention relates to the field of self-service hearing aid fitting technology, and particularly to a self-service hearing aid fitting system for hearing testing. Background Technology

[0002] Traditional hearing aid fitting mainly relies on professionals to perform the procedure at medical institutions or professional fitting centers. Users need to have their hearing assessed by professionals using a series of hearing testing devices and manually adjust the parameters of the hearing aid. This traditional method has many inconveniences, such as users needing to spend a lot of time and energy going to professional institutions, and possibly being unable to accurately express their feelings due to nervousness or unfamiliarity with the environment, which affects the accuracy of hearing tests.

[0003] Most existing hearing testing methods rely solely on subjective user feedback, such as button responses. This method is easily affected by subjective factors, especially when users cannot express themselves accurately or their subjective feedback is inaccurate, which can easily lead to inaccurate test results.

[0004] Traditional hearing aid fitting systems typically cannot obtain user responses from multiple physiological dimensions and generate personalized hearing test instructions, thus failing to meet users' self-service fitting needs. Most existing hearing aid fitting systems adopt universal hearing test procedures and parameter configuration methods, which cannot be accurately adjusted according to individual user differences, making it difficult to meet the personalized needs of different users.

[0005] With the continuous advancement of technology, people have placed higher demands on the convenience and personalization of hearing aid fitting. Users hope to be able to conduct hearing tests and configure hearing aids anytime and anywhere without relying on professionals and complex equipment. At the same time, in order to improve the accuracy of hearing tests, a system that can comprehensively consider the user's physiological response is needed to achieve more accurate hearing assessment and hearing aid parameter adjustment. Summary of the Invention

[0006] This invention provides a self-service hearing aid fitting system for hearing testing to solve existing technical problems.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] Self-service hearing aid fitting systems for hearing tests include:

[0009] User interaction module: Used to receive personal information input by the user, generate hearing test instructions, and provide operation guidance and prompts to the user via voice.

[0010] Sound signal generation module: used to generate sound signals according to hearing test instructions and transmit the sound signals to the user's ear;

[0011] User response detection module: used to detect the user's response to sound signals, including key press responses and physiological signal responses;

[0012] Hearing assessment module: Based on the user's key press response and physiological signal response, it assesses the user's hearing status and obtains the user's hearing threshold and degree of hearing loss;

[0013] Parameter calculation module: Calculates hearing aid fitting parameters based on the user's hearing threshold and degree of hearing loss;

[0014] Hearing aid configuration module: Configures the hearing aid according to the hearing aid fitting parameters;

[0015] Data storage module: Used to store hearing aid fitting parameters, user's personal information, hearing threshold and hearing loss level, and perform data encryption processing, while providing users with a visual query function.

[0016] Furthermore, the user interaction module is deployed on the user's mobile device and includes an input interface, an image recognition unit, a data processing unit, and a voice prompt unit;

[0017] The input interface is used to receive the user's personal information and hearing test request. The personal information includes age, gender, ear photos, and medical history.

[0018] The image recognition unit is used to analyze the shape of the ear based on the ear photograph using image recognition technology, and to extract and generate ear structural features;

[0019] The data processing unit is used to integrate the user's age, gender, medical history and ear structure characteristics, and generate hearing test instructions through a personalized analysis method based on support vector machines;

[0020] The voice prompt unit issues voice prompts to the user based on the hearing test instructions, guiding the user to complete the hearing test operation.

[0021] Furthermore, the sound signal generation module is deployed on the hearing aid and includes a command receiving unit, a sound signal generation unit, and a sound signal transmission unit;

[0022] The instruction receiving unit receives hearing detection instructions from the user interaction module via wireless data transmission.

[0023] The sound signal generation unit is used to generate a sound signal according to the hearing test instruction and through a digital signal processing algorithm. The sound signal includes a pure tone signal, a modulated signal, and a noise signal.

[0024] The sound signal transmission unit is used to transmit sound signals to the user's ear through a hearing aid-specific earphone.

[0025] Furthermore, the user response detection module includes a key response detection unit and a physiological signal response detection unit;

[0026] The key response detection unit is deployed on the user's mobile device. After the sound signal is emitted, it asks the user in text form via the touch screen whether they heard the sound, the pitch of the sound, the loudness of the sound, and the direction of the sound source. It also provides the user with visual key interaction and generates key response based on the user's interaction with the visual key.

[0027] The physiological signal response detection unit includes an electroencephalogram (EEG) detection unit, an eye-tracking unit, and a skin conductance detection unit.

[0028] The EEG detection unit includes an EEG sensor and an EEG signal processing component. The EEG sensor is used to detect the user's brainwave activity after the sound signal is emitted. The EEG signal processing component is used to analyze the brainwave activity through event-related potential analysis and generate an EEG signal response.

[0029] The eye-tracking unit includes an eye-tracking device and an eye-tracking signal processing component. The eye-tracking device is used to detect changes in the user's eye movements after the sound signal is emitted. The changes in eye movements include changes in fixation point, changes in saccades, and changes in pupil diameter. The eye-tracking signal processing component is used to analyze the changes in eye movements using a neural network-based analysis algorithm and generate an eye-tracking signal response.

[0030] The skin conductance detection unit includes a skin conductance sensor and a skin conductance signal processing component. The skin conductance sensor is used to detect changes in the user's skin conductance after a sound signal is emitted. The skin conductance signal processing component is used to analyze the changes in skin conductance using a skin conductance analysis method and generate a skin conductance signal response.

[0031] The physiological signal responses include electroencephalogram (EEG) signal responses, eye-tracking signal responses, and skin conductance signal responses.

[0032] Furthermore, the hearing assessment module is deployed on the user's mobile device and includes a data preprocessing unit, a feature extraction unit, a hearing threshold calculation unit, and a hearing loss degree assessment unit;

[0033] The data preprocessing unit is used to receive key responses and physiological signal responses from the user response detection module via wireless data transmission, and to perform data cleaning, time alignment and standardization to obtain preprocessed response data.

[0034] The feature extraction unit is used to extract features from the preprocessed response data using the principal component analysis (PCA) algorithm to obtain comprehensive response features.

[0035] The hearing threshold calculation unit is used to analyze the comprehensive response characteristics through a linear regression algorithm to calculate the user's hearing threshold.

[0036] The hearing loss assessment unit is used to classify the user's hearing loss level based on the hearing threshold and in conjunction with internationally accepted hearing loss classification standards, and to determine the user's hearing loss level.

[0037] Furthermore, the parameter calculation module is deployed on the user's mobile device and includes a gain calculation unit, a frequency compensation calculation unit, a noise detection unit, and a noise suppression parameter calculation unit;

[0038] The gain calculation unit is used to calculate a fixed gain based on the hearing threshold, calculate a nonlinear gain based on the hearing loss level, and output a gain value.

[0039] The frequency compensation calculation unit is used to generate frequency compensation values ​​for sound signals of different frequencies based on the hearing threshold and the degree of hearing loss using a nonlinear frequency compensation algorithm.

[0040] The noise detection unit independently detects environmental noise using an environmental noise sensor to obtain environmental noise data;

[0041] The noise suppression parameter calculation unit is used to calculate noise suppression parameters based on the environmental noise data using the adaptive noise suppression algorithm LMS.

[0042] The parameter calculation module fuses the gain value, frequency compensation value, and noise suppression parameter to generate hearing aid fitting parameters.

[0043] Furthermore, the hearing aid configuration module is deployed on the hearing aid and includes a communication interface unit and a parameter writing unit;

[0044] The communication interface unit is used to receive hearing aid fitting parameters from the parameter calculation module through wireless communication technology, and to perform data integrity verification on the hearing aid fitting parameters using a hash verification algorithm. If the verification fails, a write rejection instruction is generated; if the verification passes, a write instruction and a trusted parameter set are generated.

[0045] The parameter writing unit is used to make a writing judgment based on the result of data integrity verification. If a writing instruction is received, the hearing aid is configured with parameters through a trusted parameter set. If a write rejection instruction is received, the last valid configuration is used.

[0046] Furthermore, the data storage module is deployed on the user's mobile device and includes a database unit, a data encryption unit, and a data query unit;

[0047] The database unit is used to store hearing aid fitting parameters, user's personal information, hearing threshold, and hearing loss level;

[0048] The data encryption unit uses the RSA encryption algorithm to encrypt the data stored in the database unit and sets user access permissions;

[0049] The data query unit is used to provide a visual query interface, supporting users and professionals to query the data stored in the database unit.

[0050] The beneficial effects of the technical solution provided by this invention include at least the following:

[0051] This invention, through its integrated and self-service design, enables users to complete hearing tests and hearing aid configurations independently on their mobile devices. Users do not need to go to professional institutions; they can simply enter their personal information and initiate a hearing test request at home or any convenient location via their mobile device. The system can then automatically generate hearing test instructions and complete the test. This design greatly improves the convenience of hearing aid fitting, saves users time and energy, and reduces reliance on professionals and equipment.

[0052] This invention acquires the user's response to sound signals from multiple physiological dimensions, including physiological signals such as electroencephalogram (EEG), eye tracking, and electrodermal activity. This multimodal response detection method overcomes the limitations of traditional single-response methods and can more comprehensively and accurately assess the user's hearing status. By comprehensively analyzing physiological signal responses and key responses, the system can more accurately determine whether the user has heard the sound and the degree of sound perception, thereby improving the accuracy of hearing assessment.

[0053] This invention generates more personalized hearing test instructions based on the user's personal information, such as age, gender, ear photos, and medical history. It fully considers individual differences among users, can more accurately assess the user's hearing status, and provides a more accurate basis for hearing aid parameter calculation.

[0054] This invention achieves a comprehensive improvement in the user experience and actual effectiveness of hearing aid fitting through core innovations such as integrated self-service design, multi-physiological dimension detection, and personalized hearing test instructions. Users can more conveniently complete hearing tests and self-configure hearing aids through this system, without being limited by professional institutions or time and location. This innovative fitting system can significantly optimize the fitting accuracy and user experience of hearing aids, effectively enhancing user satisfaction and trust in hearing aids, and promoting the widespread application of hearing aids, providing hearing-impaired individuals with convenient, efficient, and personalized hearing health solutions. Attached Figure Description

[0055] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0056] Figure 1 This is a system structure diagram provided for an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.

[0058] Please refer to Figure 1 , Figure 1 This is a system structure diagram provided for an embodiment of the present invention.

[0059] The self-service hearing aid fitting system for hearing testing in this embodiment includes:

[0060] I. User Interaction Module: This module receives personal information input by the user, generates hearing test instructions, and provides operation guidance and prompts to the user via voice.

[0061] The user interaction module is deployed on the user's mobile device and includes an input interface, an image recognition unit, a data processing unit, and a voice prompt unit.

[0062] The input interface is used to receive users' personal information and hearing test requests. Personal information includes age, gender, ear photos, and medical history.

[0063] The image recognition unit is used to analyze the shape of the ear based on the ear photograph using image recognition technology, and to extract and generate ear structural features;

[0064] The data processing unit is used to generate hearing test instructions based on the user's age, gender, medical history, and ear structure characteristics using a personalized analysis method based on support vector machines.

[0065] The voice prompt unit issues voice prompts to the user based on the hearing test instructions generated by the data processing unit, guiding the user to complete the hearing test operation.

[0066] It should be noted that the specific implementation steps of the personalized analysis method based on support vector machines are as follows:

[0067] The RBF kernel is selected as the kernel function of the support vector machine to construct the support vector machine model. The support vector machine model is trained using the user's age, gender, medical history and ear structure features. The parameters of the support vector machine model (such as the penalty parameter C and the γ parameter of the RBF kernel) are optimized by cross-validation. The trained support vector machine model is run to output one or more hearing test instructions (such as sound frequency range, sound intensity and test time).

[0068] II. Sound Signal Generation Module: Used to generate sound signals according to hearing test instructions and transmit the sound signals to the user's ear;

[0069] The sound signal generation module is deployed on the hearing aid and includes a command receiving unit, a sound signal generation unit, and a sound signal transmission unit;

[0070] The instruction receiving unit is used to receive hearing detection instructions from the user interaction module via wireless data transmission.

[0071] The sound signal generation unit is used to generate sound signals according to hearing test instructions through digital signal processing (DSP) algorithms. The sound signals include pure tone signals, modulated signals, and noise signals.

[0072] The sound signal transmission unit is used to transmit sound signals to the user's ear through a hearing aid-specific earphone.

[0073] It should be noted that the specific implementation method for generating sound signals using digital signal processing (DSP) algorithms is as follows:

[0074] Pure tone signal generation: A sine wave signal of the target frequency is generated using a digital oscillator. The amplitude of the generated sine wave signal is adjusted according to the sound intensity parameters in the hearing test instructions. The continuous sine wave signal is sampled and quantized, and then converted into a digital signal.

[0075] Modulation signal generation: Create a high-frequency carrier signal and a low-frequency modulation signal. Superimpose the low-frequency modulation signal onto the high-frequency carrier signal through amplitude modulation (AM) or frequency modulation (FM) to generate a modulated signal. Sample and quantize the modulated signal and convert it into a digital signal.

[0076] Noise signal generation: Based on the hearing test instructions, select to generate white noise or pink noise, and use a random number generator to generate a random noise signal (for white noise, the generated random number sequence has a uniform power spectral density; for pink noise, the generated random number sequence has a power spectral density that is the reciprocal of the frequency). According to the sound intensity parameters in the hearing test instructions, adjust the amplitude of the generated noise signal, sample and quantize the adjusted noise signal, and convert it into a digital signal.

[0077] III. User Response Detection Module: Used to detect the user's response to sound signals, including key press responses and physiological signal responses;

[0078] The user response detection module includes a key response detection unit and a physiological signal response detection unit;

[0079] The key response detection unit is deployed on the user's mobile device. After the sound signal is emitted, it asks the user in text form via the touch screen whether they heard the sound, the pitch of the sound, the loudness of the sound, and the direction of the sound source. It also provides the user with visual key interaction and generates key response based on the user's interaction with the visual key.

[0080] The physiological signal response detection unit includes an electroencephalogram (EEG) detection unit, an eye-tracking unit, and a skin conductance detection unit.

[0081] The brainwave detection unit includes a brainwave sensor and a brainwave signal processing component. The brainwave sensor is used to detect the user's brainwave activity after the sound signal is emitted, and the brainwave signal processing component is used to analyze brainwave activity through event-related potential (ERP) analysis and generate brainwave signal response.

[0082] The eye-tracking unit includes an eye-tracking device and an eye-tracking signal processing component. The eye-tracking device is used to detect changes in the user's eye movements after the sound signal is emitted. These changes include changes in fixation point, saccades, and pupil diameter. The eye-tracking signal processing component is used to analyze these changes in eye movements using a neural network-based analysis algorithm and generate an eye-tracking signal response.

[0083] The skin conductance detection unit includes a skin conductance sensor and a skin conductance signal processing component. The skin conductance sensor is used to detect changes in the user's skin conductance after the sound signal is emitted, and the skin conductance signal processing component is used to analyze the changes in skin conductance through the skin conductance (GSR) analysis method and generate skin conductance signal response.

[0084] Physiological signal responses include electroencephalogram (EEG) signal responses, eye-tracking signal responses, and skin conductance signal responses.

[0085] It should be noted that event-related potentials (ERPs) are brain electrical activities associated with specific stimuli (such as sound signals), reflecting the brain's processing of a specific event (such as hearing a sound). ERP signals typically appear within tens to hundreds of milliseconds after the stimulus occurs. The specific detection process is as follows:

[0086] Signal acquisition: Brainwave sensors (such as multi-channel electroencephalograms) are used to acquire brainwave data when a user hears a sound signal. Brainwave sensors are usually placed in specific locations on the scalp to better capture the electrical activity of the cerebral cortex.

[0087] Signal preprocessing: The acquired EEG data is preprocessed, including filtering (removing noise and interference signals), artifact removal (removing artifacts such as eye movements and muscle activity), and baseline correction.

[0088] ERP extraction: ERP signals are extracted from preprocessed EEG data using time-locked analysis.

[0089] Feature extraction: Extract key features from ERP signals, such as peak amplitude, latency (the time from stimulus occurrence to peak appearance), and waveform morphology;

[0090] Analysis and Response Generation: Based on the extracted key features, analyze whether the user responds to the sound signal (for example, if the peak amplitude reaches a certain threshold, it means the user heard the sound; if the latency is within the normal range, it means the user's reaction speed to the sound is normal), and generate EEG signal responses based on these analysis results.

[0091] Eye-tracking technology infers a user's attention and cognitive state by detecting eye movements. The detection process is as follows:

[0092] Signal acquisition: Eye-tracking devices (such as eye trackers) are used to collect eye movement data when a user hears a sound signal. These devices typically track the position and movement of the eyes by shining infrared light into the eyes and detecting changes in the reflected light.

[0093] Signal preprocessing: Preprocessing the acquired eye-tracking data, including noise reduction, smoothing, and data correction;

[0094] Feature extraction: Extract key features from eye-tracking data, such as fixation point changes (whether the eye's fixation position moves), saccade changes (rapid eye movements), and pupil diameter changes (pupil dilation or constriction).

[0095] Neural network analysis: This method uses neural network-based algorithms to analyze extracted key features. The neural network can learn the relationship between eye movement features and the user's response to sound signals through training.

[0096] Analysis and Response Generation: Based on the analysis results of the neural network, determine whether the user responds to the sound signal (for example, if the gaze point changes significantly or the pupil diameter dilates, it indicates that the user may have heard the sound), and generate an eye-tracking signal response based on the analysis results.

[0097] Galvanic Skin Response (GSR) is a physiological indicator that reflects changes in the electrical conductivity of the skin. When a user is stimulated (such as by hearing a sound), the activity of the sweat glands in the skin increases, leading to an increase in skin conductivity. The detection process is as follows:

[0098] Signal acquisition: Using a skin conductance sensor (such as a skin electrode) to collect data on the skin conductance of a user when they hear a sound signal. Skin conductance sensors are usually placed on the fingers or wrist.

[0099] Signal preprocessing: The collected skin conductivity data is preprocessed, including noise reduction, smoothing, and data correction;

[0100] Feature extraction: Extract key features from skin conductivity data, such as the magnitude and rate of change of skin conductivity;

[0101] Analysis and Response Generation: Based on the extracted key features, determine whether the user responds to the sound signal (for example, if the skin conductivity increases significantly, it indicates that the user may have heard the sound), and generate the skin conductivity signal response based on the analysis results.

[0102] IV. Hearing Assessment Module: Based on button response and physiological signal response, the module assesses the user's hearing to obtain the user's hearing threshold and degree of hearing loss.

[0103] The hearing assessment module is deployed on the user's mobile device and includes a data preprocessing unit, a feature extraction unit, a hearing threshold calculation unit, and a hearing loss assessment unit.

[0104] The data preprocessing unit is used to receive key responses and physiological signal responses from the response detection module via wireless data transmission, and to perform data cleaning, time alignment and standardization to obtain preprocessed response data.

[0105] The feature extraction unit is used to extract features from the preprocessed response data using the principal component analysis (PCA) algorithm to obtain the comprehensive response features;

[0106] The hearing threshold calculation unit is used to analyze the comprehensive response characteristics through a linear regression algorithm to calculate the user's hearing threshold.

[0107] The hearing loss assessment unit is used to classify a user's hearing loss level into different grades based on hearing thresholds and internationally recognized hearing loss classification standards, thereby determining the user's hearing loss level.

[0108] It should be noted that Principal Component Analysis (PCA) is a statistical method used to reduce the dimensionality of multidimensional data to a few principal components while preserving as much variance information as possible. PCA transforms the original data into a new coordinate system through linear transformation, so that the variance of the data is mainly concentrated on a few principal components in the new coordinate system. In hearing assessment, PCA is used to extract key features from the user's key press responses and physiological signal responses, reduce data dimensionality, remove noise and redundant information, and improve the efficiency and accuracy of subsequent analysis. The specific implementation steps are as follows:

[0109] Data reception and preprocessing: Receive key response and physiological signal response data from the response detection module via wireless data transmission, and perform data cleaning, time alignment and standardization.

[0110] Constructing the covariance matrix: Calculate the covariance matrix of the preprocessed data (the covariance matrix reflects the correlation between features);

[0111] Calculate eigenvalues ​​and eigenvectors: Perform eigenvalue decomposition on the covariance matrix to obtain eigenvalues ​​and corresponding eigenvectors (eigenvalues ​​represent the magnitude of the variance of each principal component, and eigenvectors represent the direction of the principal components);

[0112] Principal component selection: Principal components with a cumulative variance contribution rate of 85% to 95% are typically selected;

[0113] Projecting to Principal Component Space: Projecting the original principal component data onto the selected principal component space yields the dimensionality-reduced comprehensive response features.

[0114] Linear regression is a statistical method used to establish a linear relationship between a dependent variable (such as hearing threshold) and an independent variable (such as comprehensive response characteristics). By fitting a straight line, it minimizes the error between the predicted and actual values. In hearing assessment, linear regression is used to predict a user's hearing threshold based on comprehensive response characteristics. The hearing threshold is the minimum sound intensity a user can hear and is a key indicator for assessing the degree of hearing loss. The specific implementation steps are as follows:

[0115] Input independent variables: i.e., the comprehensive response features extracted using PCA;

[0116] Define the dependent variable: the expected output hearing threshold;

[0117] Model selection: Select the linear regression model, which assumes a linear relationship between the dependent and independent variables;

[0118] Model Fitting: The least squares method is used to fit the linear regression model, with the goal of minimizing the squared error between the predicted and actual values;

[0119] Model evaluation: Evaluate the model's performance using methods such as cross-validation to ensure that the model has good generalization ability;

[0120] Predicting hearing thresholds: Using a trained linear regression model, the user's hearing threshold is predicted based on comprehensive response characteristics;

[0121] Interpretation of results: Based on the predicted hearing threshold, assess the user's hearing status (e.g., the higher the hearing threshold, the more sound intensity the user needs to hear, and the more severe the hearing loss).

[0122] V. Parameter Calculation Module: Calculates hearing aid fitting parameters based on the user's hearing threshold and degree of hearing loss;

[0123] The parameter calculation module is deployed on the user's mobile device and includes a gain calculation unit, a frequency compensation calculation unit, a noise detection unit, and a noise suppression parameter calculation unit.

[0124] The gain calculation unit is used to calculate a fixed gain based on hearing thresholds and a nonlinear gain based on the degree of hearing loss, thereby obtaining the gain value.

[0125] The frequency compensation calculation unit is used to generate frequency compensation values ​​for sound signals of different frequencies based on hearing threshold and hearing loss level using a nonlinear frequency compensation algorithm.

[0126] The noise detection unit independently detects ambient noise through an ambient noise sensor to obtain ambient noise data;

[0127] The noise suppression parameter calculation unit is used to calculate noise suppression parameters based on environmental noise data using the adaptive noise suppression algorithm LMS.

[0128] The parameter calculation module fuses the gain value, frequency compensation value, and noise suppression parameters to generate hearing aid fitting parameters.

[0129] It should be noted that nonlinear frequency compensation algorithm is a technique for compensating for sound signals of different frequencies. Based on the user's hearing threshold and degree of hearing loss, it adjusts the gain of sound signals of different frequencies to varying degrees to improve the user's auditory experience. In hearing aids, nonlinear frequency compensation algorithm is used to optimize the frequency response of sound signals, enabling users to hear sounds of different frequencies more clearly. The specific implementation steps are as follows:

[0130] Hearing threshold analysis: Based on the user's hearing threshold and degree of hearing loss, determine the frequency range that needs compensation (for example, if the user has significant hearing loss at high frequencies (such as above 4000Hz), then more compensation is needed for high-frequency signals).

[0131] Frequency compensation curve design: Design a non-linear frequency compensation curve that adjusts the gain at different frequencies according to the user's hearing loss. Typically, the compensation curve is segmented according to the degree of hearing loss, for example:

[0132] Mild hearing loss (26-40dB), with relatively low gain;

[0133] Moderate hearing loss (41-55dB), with moderate gain;

[0134] Severe hearing loss (56-70dB), with relatively high gain;

[0135] A specific implementation example is as follows:

[0136] Assume the user's hearing threshold is as follows:

[0137] 250Hz: 20dB;

[0138] 500Hz: 30dB;

[0139] 1000Hz: 40dB;

[0140] 2000Hz: 50dB;

[0141] 4000Hz: 60dB;

[0142] Based on these data, the designed nonlinear frequency compensation curve is as follows:

[0143] 250Hz: Gain 10dB;

[0144] 500Hz: Gain 15dB;

[0145] 1000Hz: Gain 20dB;

[0146] 2000Hz: Gain 25dB;

[0147] 4000Hz: Gain 30dB.

[0148] Design multiple bandpass filters to process audio signals in different frequency ranges, and adjust the gain of the audio signal in each frequency range according to the nonlinear frequency compensation curve.

[0149] An ambient noise sensor is a device that can detect the level of ambient noise. It typically uses a microphone array to capture sound signals in the environment and convert them into electrical signals. In hearing aids, ambient noise sensors are used to monitor the noise level of the user's environment in real time in order to adjust the hearing aid's operating mode in subsequent steps and improve the user's hearing comfort.

[0150] The Least Mean Squares (LMS) adaptive noise suppression algorithm is an adaptive filter algorithm based on the minimum mean square error. It minimizes the error between the noise signal and the desired signal by continuously adjusting the weights of the filter, thereby achieving noise suppression. In hearing aids, the LMS algorithm is used to dynamically adjust the noise suppression parameters according to the ambient noise level to improve the user's hearing comfort and speech recognition ability.

[0151] VI. Hearing Aid Configuration Module: Configures the hearing aid according to the hearing aid fitting parameters;

[0152] The hearing aid configuration module is deployed on the hearing aid and includes a communication interface unit and a parameter writing unit;

[0153] The communication interface unit is used to receive hearing aid fitting parameters from the parameter calculation module through wireless communication technology, and to verify the data integrity of the hearing aid fitting parameters through a hash verification algorithm to obtain the verified hearing aid fitting parameters.

[0154] The parameter writing unit is used to write the verified hearing aid adaptation parameters into the hearing aid configuration file to configure the hearing aid parameters.

[0155] It should be noted that a hash verification algorithm is a one-way encryption algorithm that converts input data of arbitrary length into a fixed-length output (called a hash value or digest). Commonly used hash functions for hash verification algorithms include MD5, SHA-1, and SHA-256. Its application in the hearing aid configuration module is as follows:

[0156] The hearing aid fitting parameters are combined into a data block, and a hash function is used to perform a hash operation on the data block to generate a fixed-length hash value. The hash value and the hearing aid fitting parameters are then sent to the hearing aid configuration module via wireless communication technology.

[0157] VII. Data storage module: Used to store hearing aid fitting parameters, user's personal information, hearing threshold and hearing loss level, and to perform data encryption processing, while providing users with a visual query function;

[0158] The data storage module is deployed on the user's mobile device and includes a database unit, a data encryption unit, and a data query unit;

[0159] The database unit is used to store hearing aid fitting parameters, user personal information, hearing thresholds, and hearing loss levels;

[0160] The data encryption unit is used to encrypt the data stored in the data storage module using the RSA encryption algorithm and to set user access permissions;

[0161] The data query unit provides a visual query interface, enabling users and professionals to query data stored in the data storage module.

[0162] It should be noted that the RSA encryption algorithm is an asymmetric encryption algorithm that uses a pair of keys for encryption and decryption. This pair of keys includes a public key for encrypting data and a private key for decrypting data. The public key can be distributed publicly, while the private key must be kept secret.

[0163] In the data storage module, all sensitive data (such as users' personal information, hearing thresholds, hearing loss levels, and hearing aid fitting parameters) are encrypted using the RSA encryption algorithm before storage. The private key is strictly kept by the data storage module's security system to ensure that only authorized users or systems can access it.

[0164] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Moreover, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code.

[0165] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0166] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0167] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element.

[0168] Finally, it should be noted that the above description represents a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make various improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including both the preferred embodiments and all changes and modifications falling within the scope of the embodiments of the present invention.

Claims

1. A self-service hearing aid fitting system for hearing detection, characterized in that, Comprise: User interaction module: for receiving user input personal information, generating hearing detection instructions, and providing operation guidance and prompts to users through voice; Sound signal generation module: for generating sound signals according to hearing detection instructions, and transmitting sound signals to user's ear; User response detection module: for detecting user's response to sound signals, including key response and physiological signal response, the physiological signal response includes brain wave signal response, eye tracking signal response and skin electric signal response; Hearing evaluation module: based on user's key response and physiological signal response, the hearing condition is evaluated, the hearing threshold and the hearing loss degree level of the user are obtained; Parameter calculation module: according to the hearing threshold and the hearing loss degree level of the user, the hearing aid fitting parameters are calculated; Hearing aid configuration module: according to the hearing aid fitting parameters, the hearing aid is configured; Data storage module: for storing hearing aid fitting parameters, user's personal information, hearing threshold and hearing loss degree level and carrying out data encryption processing, at the same time, visual query function is provided to user; The user interaction module is deployed on the user mobile device, containing input interface, image recognition unit, data processing unit and voice prompt unit; The input interface is used for receiving user's personal information and hearing detection request, the personal information includes age, gender, ear photo and medical history; The image recognition unit is used for analyzing ear shape through image recognition technology according to ear photo, extracting and generating ear structure characteristics; The data processing unit is used for integrating user's age, gender, medical history and ear structure characteristics, and generating hearing detection instructions through support vector machine based personalized analysis method; The voice prompt unit issues voice prompt to user according to hearing detection instructions, guiding user to complete hearing detection operation; The hearing evaluation module is deployed on the user mobile device, including data preprocessing unit, feature extraction unit, hearing threshold calculation unit and hearing loss degree evaluation unit; The data preprocessing unit is used for receiving key response and physiological signal response from user response detection module through wireless data transmission mode, and carrying out data cleaning, time alignment and standardization processing, obtaining preprocessing response data; The feature extraction unit is used for extracting comprehensive response characteristics through principal component analysis algorithm PCA according to preprocessing response data; The hearing threshold calculation unit is used for analyzing the comprehensive response characteristics through linear regression algorithm, calculating the hearing threshold of the user; The hearing loss degree evaluation unit is used for grading the hearing loss degree of the user according to the hearing threshold, combining with the international general hearing loss classification standard, determining the hearing loss degree level of the user; The parameter calculation module is deployed on the user mobile device, containing gain calculation unit, frequency compensation calculation unit, noise detection unit and noise suppression parameter calculation unit; The gain calculation unit is used for calculating fixed gain based on the hearing threshold, calculating nonlinear gain through the hearing loss degree level, and outputting gain value; The frequency compensation calculation unit is configured to generate frequency compensation values of different frequency sound signals based on the hearing threshold and the hearing loss degree level through a nonlinear frequency compensation algorithm. The noise detection unit independently detects environmental noise through an environmental noise sensor to obtain environmental noise data. The noise suppression parameter calculation unit is configured to calculate noise suppression parameters based on the environmental noise data through an adaptive noise suppression algorithm LMS. The parameter calculation module fuses the gain value, the frequency compensation value, and the noise suppression parameter, and generates a hearing aid fitting parameter.

2. The self-service hearing aid fitting system for hearing detection according to claim 1, wherein: The sound signal generation module is arranged on the hearing aid and includes an instruction receiving unit, a sound signal generation unit, and a sound signal transmission unit. The instruction receiving unit receives a hearing detection instruction from the user interaction module through a wireless data transmission method. The sound signal generation unit is configured to generate sound signals, including pure tone signals, modulated signals, and noise signals, through a digital signal processing algorithm according to the hearing detection instruction. The sound signal transmission unit is configured to transmit the sound signals to the user's ear through a hearing aid special earphone.

3. The self-service hearing aid fitting system for hearing detection according to claim 1, wherein: The user response detection module includes a key response detection unit and a physiological signal response detection unit. The key response detection unit is arranged on the user's mobile device. After the sound signal is emitted, the user is asked whether he / she hears the sound, the tone of the sound, the loudness of the sound, and the source direction of the sound in a text manner through a touch screen, and the user is provided with visual key interaction. The key response is generated according to the interaction result of the user and the visual key. The physiological signal response detection unit includes an electroencephalogram detection unit, an eye movement tracking unit, and a skin electricity detection unit. The electroencephalogram detection unit includes an electroencephalogram sensor and an electroencephalogram signal processing assembly. The electroencephalogram sensor is configured to detect the electroencephalogram activity of the user after the sound signal is emitted. The electroencephalogram signal processing assembly is configured to analyze the electroencephalogram activity through an event-related potential analysis method and generate an electroencephalogram signal response. The eye movement tracking unit includes an eye movement tracking device and an eye movement signal processing assembly. The eye movement tracking device is configured to detect the eye movement changes of the user after the sound signal is emitted. The eye movement changes include fixation point changes, saccade changes, and pupil diameter changes. The eye movement signal processing assembly is configured to analyze the eye movement changes through a neural network-based analysis algorithm and generate an eye movement tracking signal response. The skin electricity detection unit includes a skin electricity sensor and a skin electricity signal processing assembly. The skin electricity sensor is configured to detect the skin electricity changes of the user after the sound signal is emitted. The skin electricity signal processing assembly is configured to analyze the skin electricity changes through a skin electricity conductivity analysis method and generate a skin electricity signal response.

4. The self-service hearing aid fitting system for hearing detection according to claim 1, wherein: The hearing aid configuration module is deployed on the hearing aid and includes a communication interface unit and a parameter writing unit; The communication interface unit is configured to receive the hearing aid fitting parameters from the parameter calculation module through wireless communication technology, and perform data integrity verification on the hearing aid fitting parameters using a hash verification algorithm. If the verification fails, a write rejection instruction is generated. If the verification is passed, a write instruction and a trusted parameter set are generated. The parameter writing unit is configured to make a write judgment according to the result of the data integrity verification. If the write instruction is received, the hearing aid is configured with the parameters through the trusted parameter set. If the write rejection instruction is received, the last valid configuration is used.

5. The self-service hearing aid fitting system for hearing detection according to claim 1, wherein: The data storage module is deployed on the user's mobile device and includes a database unit, a data encryption unit, and a data query unit; The database unit is configured to store hearing aid fitting parameters, personal information of the user, hearing threshold, and hearing loss level; The data encryption unit is configured to encrypt the data stored in the database unit using the RSA encryption algorithm and set user access permissions; The data query unit is configured to provide a visual query interface to support the user and professionals to query the data stored in the database unit.

Images