Hearing aid multi-environment mode switching adaptation method

Abstract

The invention relates to the field of hearing aids, in particular to a hearing aid multi-environment mode switching adaptation method, and the overall framework comprises the following components: a data acquisition module, an environment recognition module, a mode switching module, a parameter optimization module, a user feedback module, an environment recognition algorithm and a mode switching strategy. The mode switching strategy is the key to ensure that the hearing aid can provide appropriate hearing output in different environments, the hearing experience of a user in a complex environment can be improved by optimizing multi-environment mode switching of the hearing aid, so that the user satisfaction is improved, the hearing aid can automatically adapt to different environments in multiple environments, and the user experience is improved. The hearing aid has the advantages that the hearing burden of a user is relieved, the risk of hearing loss is reduced, the hearing aid is well applied in multiple environments, hearing impaired people can be better integrated into the society, the life quality of the hearing impaired people is improved, the performance of the hearing aid in complex environments is improved, and a better hearing aid solution is provided for the hearing impaired people.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of hearing aids, in particular to a hearing aid multi-environment mode switching adaptation method. BACKGROUND

[0002] A hearing aid is a tool, device, apparatus, and instrument used by hearing-impaired individuals to compensate for the defects caused by hearing impairment and to improve their communication abilities. A hearing aid consists of a microphone, an amplifier, a receiver, and a power source. When wearing a hearing aid, the relationship between the electro-acoustic characteristics of the hearing aid and the hearing characteristics and needs of the patient should be considered to select a suitable product for the patient. After wearing a hearing aid, it is best to adapt to various background sounds in a quiet environment and try to distinguish each sound.

[0003] Traditional hearing aid environment adaptation methods mainly rely on manual adjustment or pre-set fixed programs to adapt to different hearing environments. These methods adjust through manual adjustment, pre-set programs, or feedback suppression. Although traditional methods can help users adapt to different environments to some extent, they still face the following challenges and problems during multi-environment mode switching. Hearing aids need to quickly adjust parameters during environment switching, but traditional methods often respond slowly and cannot adapt to environmental changes in real time. The judgment of the environment and the adjustment of the parameters are often not accurate enough to meet the individual needs of users in complex environments. Traditional methods usually require user intervention, increasing the user's operational burden and limiting the practicality of hearing aids. Therefore, it is necessary to propose a hearing aid multi-environment mode switching adaptation method. SUMMARY

[0004] To solve the problems in the prior art, the present application provides a hearing aid multi-environment mode switching adaptation method.

[0005] The technical solution adopted by the present application to solve its technical problems is a hearing aid multi-environment mode switching adaptation method, which has the following components in its overall framework: It includes a data acquisition module, an environment recognition module, a mode switching module, a parameter optimization module, a user feedback module, an environment recognition algorithm, and a mode switching strategy. The mode switching strategy is the key to ensuring that the hearing aid can provide appropriate auditory output in different environments, including: Real-time monitoring: Real-time monitoring of environmental changes and user feedback ensures that the hearing aid can quickly respond to environmental changes. Dynamic adjustment: Based on the environment recognition results and user feedback, dynamically adjust the amplification factor, frequency response, noise suppression, and other parameters of the hearing aid. Smooth transition: During mode switching, use gradual adjustment to avoid parameter mutations that may cause discomfort to the user. Personalized settings: considering the personalized needs of users, allowing users to customize the parameters and conditions of mode switching; The data collection module is responsible for collecting sound data and environmental information during the use of the hearing aid.

[0006] The environment recognition module processes and analyzes the collected data to identify the current environment type, which is used to establish a database model later.

[0007] The mode switching module automatically adjusts the working mode of the hearing aid according to the environment recognition result, to adapt to different environments.

[0008] The parameter optimization module optimizes the parameters of the hearing aid in real time, and adjusts them according to the external collected data at any time, to achieve the best hearing effect.

[0009] The user feedback module further optimizes the algorithm and strategy by receiving user feedback on the current hearing effect, so as to understand user habits and facilitate mode switching.

[0010] The environment recognition algorithm is the core of the multi-environment mode switching adaptation method, and its accuracy directly affects the effect of mode switching, including: Sound feature extraction: by analyzing the frequency spectrum, energy, entropy and other features of sound signals, it provides basic data for environment recognition; Machine learning algorithm: using support vector machine, random forest, neural network and other machine learning algorithms to classify sound features and identify different environment types; Deep learning algorithm: using convolutional neural network and recurrent neural network deep learning algorithm to improve the accuracy and robustness of environment recognition, and improve the adaptability of hearing aid multi-environment mode switching.

[0011] A method for using a hearing aid multi-environment mode switching adaptation method, including the following steps: S1: First, collect sound data in different environments, including quiet environment, noisy environment, music environment, etc. These data will be used to train the environment recognition algorithm and optimize the mode switching strategy; use the collected environmental data to train the environment recognition algorithm, which can be achieved through machine learning or deep learning algorithm to improve the accuracy and robustness of the algorithm; S2: According to the output of the environment recognition algorithm and user preferences, design appropriate mode switching strategy, which includes determining the switching time, switching speed and switching mode; according to the mode switching strategy, automatically adjust the parameters of the hearing aid, such as amplification, frequency response, noise suppression, to adapt to the needs of different environments; S3: Collect user feedback on the performance of the hearing aid, including the accuracy of environmental recognition, the speed of mode switching, and user satisfaction; integrate the multi-environment mode switching adaptation method into the hearing aid system and test it to verify its performance and reliability in actual application; based on the performance evaluation results and user feedback, continuously optimize and improve the multi-environment mode switching adaptation method to improve its performance and user experience in different environments; S4: Implement the multi-environment mode switching adaptation method to improve the performance of the hearing aid in different environments and provide a better hearing experience, while considering factors such as environmental data, algorithm training, strategy design, parameter adjustment, user feedback, and system integration to ensure the practicality and effectiveness of the method The beneficial effects of the present application are: The hearing aid multi-environment mode switching adaptation method described in the present application can improve the user's hearing experience in complex environments by optimizing the multi-environment mode switching of the hearing aid, thereby improving user satisfaction. In multiple environments, the hearing aid can automatically adapt to different environments, reducing the user's hearing burden and reducing the risk of hearing loss. The good application of the hearing aid in multiple environments helps hearing-impaired people better integrate into society and improves their quality of life. The performance of the hearing aid in complex environments is improved, providing better hearing assistance solutions for hearing-impaired people and helping them better adapt to social life. DETAILED DESCRIPTION

[0012] In order to make the technical means, creative features, purposes and effects realized by the present application easy to understand, the present application is further described below in conjunction with specific embodiments.

[0013] The hearing aid multi-environment mode switching adaptation method described in the present application has the following components in the overall framework: It includes: data acquisition module, environment recognition module, mode switching module, parameter optimization module, user feedback module, environment recognition algorithm and mode switching strategy; The mode switching strategy is the key to ensuring that the hearing aid can provide appropriate auditory output in different environments, including: Real-time monitoring: Real-time monitoring of environmental changes and user feedback to ensure that the hearing aid can quickly respond to environmental changes; Dynamic adjustment: dynamically adjust the amplification factor, frequency response, noise suppression, and other parameters of the hearing aid according to the environment recognition results and user feedback; Smooth transition: In the mode switching process, use gradual adjustment to avoid sudden changes in parameters that cause discomfort to the user; Personalized settings: Consider the user's individual needs and allow the user to customize the parameters and conditions of mode switching; Mode switching strategy is a key factor to ensure that the hearing aid provides the best auditory output in different hearing environments. This paper studies the mode switching strategy from three aspects: user preference analysis, mode switching threshold setting, and switching strategy optimization. User preference analysis (1) User preference analysis is the basis for designing the mode switching strategy. By analyzing the user's auditory needs and usage habits in different environments, important evidence can be provided for the switching strategy. (2) Data collection: Through questionnaires, user interviews, behavior data analysis and other methods, the user's auditory preferences in different environments are collected. (3) Preference modeling: Use statistical analysis and data mining techniques to build a user preference model to capture the user's auditory needs in different environments. (4) Personalized adjustment: According to the user preference model, customize personalized mode switching parameters for each user to better meet their individual needs. Mode switching threshold setting The mode switching threshold determines when to trigger mode switching. Reasonable threshold setting can ensure that the switching timing is both timely and accurate. (1) Environmental feature threshold: Based on the output of the environment recognition algorithm, set the threshold corresponding to different environmental features to trigger mode switching. (2) User feedback threshold: According to the user's feedback on the current auditory effect, set the user satisfaction threshold to trigger switching. (3) Dynamic threshold adjustment: According to the user's usage habits and environmental changes, dynamically adjust the switching threshold to improve the adaptability and accuracy of switching. Switching strategy optimization In order to improve the efficiency and user experience of mode switching, the switching strategy needs to be optimized. (1) Smooth switching: Use gradual switching to avoid sudden parameter changes that may cause discomfort to the user. (2) Predictive switching: By analyzing user behavior and environmental change trends, predict the environment the user may enter and switch modes in advance. (3) Adaptive switching: Combine environmental recognition results and user preferences to achieve adaptive mode switching, ensuring that the switching timing and mode match the user's needs. (4) Feedback mechanism: Establish an effective user feedback mechanism to collect user feedback on the switching strategy for continuous optimization of the strategy. Through the above research, a more intelligent and personalized mode switching strategy can be designed, which not only automatically adapts to the user's transition from one environment to another, but also provides the best auditory support according to the user's specific needs, thereby significantly improving the overall performance of the hearing aid and user satisfaction.

[0014] The data collection module is responsible for collecting sound data and environmental information during the use of the hearing aid.

[0015] The environment recognition module processes and analyzes the collected data to identify the current environment type, which is used to establish a database model later.

[0016] The mode switching module automatically adjusts the working mode of the hearing aid according to the environment recognition result to adapt to different environments.

[0017] The parameter optimization module optimizes the parameters of the hearing aid in real time, adjusting them according to external data collection to achieve the best hearing effect.

[0018] The user feedback module further optimizes the algorithm and strategy by receiving user feedback on the current hearing effect, so as to understand user habits and facilitate mode switching.

[0019] The environment recognition algorithm is the core of the multi-environment mode switching adaptation method, and its accuracy directly affects the effect of mode switching, including: Sound feature extraction: by analyzing the frequency spectrum, energy, entropy, and other features of sound signals, it provides basic data for environment recognition; Machine learning algorithm: using support vector machines, random forests, neural networks, and other machine learning algorithms to classify sound features and identify different environment types; Deep learning algorithm: using convolutional neural networks and recurrent neural networks deep learning algorithms to improve the accuracy and robustness of environment recognition and enhance the adaptability of hearing aid multi-environment mode switching.

[0020] The environment recognition algorithm is a key technology in the multi-environment mode switching adaptation method, and the following are three main aspects of environment recognition algorithm research: Acoustic feature extraction Acoustic feature extraction is the first step in environment recognition, which involves converting the original sound signal into a feature vector that can represent the characteristics of the environment, Mel-frequency cepstral coefficients (MFCC) is a widely used acoustic feature extraction method that simulates human auditory perception to convert sound signals into frequency features on a Mel scale; Spectral features include mean, variance, kurtosis, skewness, and other statistical quantities of the spectrum, which can reflect the energy distribution and spectral shape of the sound signal; Time-domain features: such as energy, zero-crossing rate, and average amplitude of sound signals, which can reflect the time-domain characteristics of sound signals.

[0021] Feature selection and optimization Acoustic feature vectors typically contain a large number of feature dimensions, some of which may not contribute much to environmental recognition or even introduce noise, so feature selection and optimization are key steps to improve the performance of recognition algorithms: Feature selection: Through methods such as correlation analysis and recursive feature elimination (RFE), select the features that contribute most to environmental classification; Feature dimension reduction: Use methods such as principal component analysis and linear discriminant analysis to reduce feature dimensions and improve algorithm efficiency and recognition performance; Feature fusion: Combine different types of acoustic features through feature fusion technology to improve the accuracy and robustness of environmental recognition.

[0022] Recognition algorithm implementation and evaluation After acoustic feature extraction and optimization, appropriate recognition algorithms are needed to classify the environment. The following is the implementation and evaluation process of the recognition algorithm: Algorithm implementation: According to the research objectives and data characteristics, select appropriate machine learning or deep learning algorithms such as SVM, decision tree, random forest, CNN, RNN, etc. to implement environmental recognition; Model training: Use the labeled training data set to train the recognition model, optimize the model parameters, and improve the recognition accuracy; Performance evaluation: Evaluate the performance of the recognition algorithm through cross-validation, confusion matrix, accuracy, recall, F1 score, etc. Model tuning: According to the evaluation results, adjust and optimize the recognition model to improve its performance and reliability in practical applications. The environmental recognition algorithm can more accurately identify different hearing environments, providing reliable data support for the mode switching of hearing aids, thereby optimizing the user's hearing experience.

[0023] System implementation and testing is a key step to verify the effectiveness of the multi-environment mode switching adaptation method. Through the analysis of hardware design, software architecture, and test results; System hardware design The hardware design of the system needs to consider the portability, power consumption and cost of the hearing aid. The following are some key hardware design elements: Hearing aid modules: (1) Including microphones, amplifiers, speakers, batteries, etc., responsible for sound collection, amplification and output; (2) Signal processing module: Use digital signal processors or application-specific integrated circuits to implement acoustic feature extraction and environmental recognition algorithms; (3) Mode switching module: According to the environmental recognition results, automatically adjust the parameters of the hearing aid to adapt to different environments; (4) Wireless communication module: Through Bluetooth, Wi-Fi, and other wireless communication technologies, the hearing aid can connect with external devices and transmit data.

[0024] System software architecture The software architecture of the system needs to ensure the coordination between modules, achieving efficient environment recognition and mode switching: (1) Driver program: responsible for the initialization and control of hardware modules, ensuring the normal operation of hardware devices; (2) Environment recognition module: realizes the extraction of acoustic features and environment recognition algorithms, providing data support for mode switching; (3) Mode switching module: automatically adjusts the parameters of the hearing aid according to the environment recognition results and user preferences; (4) User interface: provides a friendly user interface for easy personalized settings and feedback.

[0025] Test plan and result analysis In order to verify the effectiveness and reliability of the system, a series of tests need to be conducted, and the test plan and result analysis are as follows: (1) Test environment: test in various hearing environments, including quiet environment, noisy environment, music environment, etc.; (2) Test users: recruit users with different hearing levels to participate in the test to evaluate the applicability of the system and user satisfaction; (3) Test indicators: including environment recognition accuracy, mode switching speed, user satisfaction, etc.; (4) Result analysis: statistically analyze the test data to evaluate the performance and reliability of the system, and provide basis for further optimization of the system.

[0026] Through system implementation and testing, the effectiveness and reliability of the multi-environment mode switching adaptation method can be verified, providing scientific basis for the practical application of hearing aids. At the same time, the test results can also provide important reference for further optimization and improvement of the system; The setting of experimental scenarios needs to simulate various hearing environments that users may encounter in the real world, to ensure the practicality and reliability of the experimental results: Environment selection: select representative environments such as library (quiet environment), restaurant (noisy environment), and park (natural environment); Environment simulation: simulate real-world sound scenarios by playing recorded environmental sounds through a sound system in the laboratory; User participation: invite hearing-impaired individuals to participate in the experiment to ensure that the experimental scenarios are consistent with their actual use scenarios.

[0027] Experimental data collection and processing is the core of experimental verification, which directly affects the accuracy and effectiveness of experimental results: Data collection: Collect sound data in experimental scenarios using hearing aids and record users' subjective evaluation of hearing aid performance; Data synchronization: Ensure the synchronous collection of sound data, environmental information and user feedback for subsequent analysis; Data processing: Clean, label and preprocess the collected data to provide a clean and accurate dataset for subsequent analysis.

[0028] Experimental results analysis and discussion Performance evaluation: Evaluate the performance of the environment recognition algorithm using accuracy, recall, F1 score and other indicators; Switching effect analysis: Analyze the switching speed, switching accuracy and user satisfaction of the mode switching strategy in different environments; Statistical test: Use appropriate statistical methods such as t-test, analysis of variance (ANOVA) to verify the significance of experimental results.

[0029] Specific use: First, collect sound data in different environments, including quiet, noisy, music, etc. These data will be used to train the environment recognition algorithm and optimize the mode switching strategy; Use the collected environmental data to train the environment recognition algorithm, which can be achieved through machine learning or deep learning algorithms to improve the accuracy and robustness of the algorithm; According to the output of the environment recognition algorithm and user preferences, design appropriate mode switching strategies, including determining switching time, switching speed and switching method; According to the mode switching strategy, automatically adjust the parameters of the hearing aid, such as amplification, frequency response, noise suppression, to adapt to the needs of different environments; Collect user feedback on hearing aid performance, including accuracy of environment recognition, mode switching speed and user satisfaction; Integrate the multi-environment mode switching adaptation method into the hearing aid system and test it to verify its performance and reliability in actual application; According to the performance evaluation results and user feedback, continuously optimize and improve the multi-environment mode switching adaptation method to improve its performance and user experience in different environments; Implement multi-environment mode switching adaptation method to improve the performance of hearing aids in different environments and provide better hearing experience. At the same time, we need to consider environmental data, algorithm training, strategy design, parameter adjustment, user feedback and system integration to ensure the practicality and effectiveness of the method.

[0030] The above shows and describes the basic principles, main features and advantages of the present application. Those skilled in the art should understand that the present application is not limited to the above embodiments, and the above embodiments and descriptions in the specification are only to illustrate the principles of the present application. Without departing from the spirit and scope of the present application, various changes and improvements can be made to the present application, and these changes and improvements all fall within the scope of the present application. The scope of protection of the present application is defined by the appended claims and their equivalents.

Claims

1. A method for switching and adapting to multiple environmental modes in a hearing aid, characterized in that, The overall framework includes the following components: It includes: a data acquisition module, an environment recognition module, a mode switching module, a parameter optimization module, a user feedback module, an environment recognition algorithm, and a mode switching strategy; The mode switching strategy is key to ensuring that the hearing aid can provide appropriate auditory output in different environments, including: Real-time monitoring: Real-time monitoring of environmental changes and user feedback to ensure that the hearing aid can respond quickly to environmental changes; Dynamic adjustment: Based on environmental recognition results and user feedback, dynamically adjust parameters such as the amplification, frequency response, and noise suppression of the hearing aid; Smooth transition: During mode switching, a gradual adjustment is used to avoid sudden parameter changes that may cause discomfort to the user; Personalized settings: To cater to users' individual needs, the system allows users to customize the parameters and conditions for mode switching.

2. The hearing aid multi-environment mode switching adaptation method according to claim 1, characterized in that: The data acquisition module is responsible for collecting sound data and environmental information during the use of the hearing aid.

3. The hearing aid multi-environment mode switching adaptation method according to claim 1, characterized in that: The environment identification module processes and analyzes the collected data to identify the current environment type, which is used to build a database model later.

4. The hearing aid multi-environment mode switching adaptation method according to claim 1, characterized in that: The mode switching module automatically adjusts the hearing aid's working mode based on the environment recognition results to adapt to different environments.

5. The hearing aid multi-environment mode switching adaptation method according to claim 1, characterized in that: The parameter optimization module optimizes the hearing aid parameters in real time and adjusts them according to externally collected data to achieve the best hearing effect.

6. The hearing aid multi-environment mode switching adaptation method according to claim 1, characterized in that: The user feedback module receives user feedback on the current auditory effect and further optimizes the algorithm and strategy, thereby working with intelligent machine learning algorithms to understand user habits and facilitate mode switching.

7. The hearing aid multi-environment mode switching adaptation method according to claim 1, characterized in that: The environment recognition algorithm is the core of the multi-environment mode switching adaptation method, and its accuracy directly affects the mode switching effect, including: Sound feature extraction: By analyzing the characteristics of sound signals such as spectrum, energy, and entropy, basic data is provided for environmental identification; Machine learning algorithms: Using machine learning algorithms such as support vector machines, random forests, and neural networks to classify sound features and identify different environmental types; Deep learning algorithms: Convolutional neural networks and recurrent neural networks are used to improve the accuracy and robustness of environmental recognition and enhance the adaptability of hearing aids to switch between multiple environmental modes.

8. A method of using the hearing aid multi-environment mode switching adaptation method as described in any one of claims 1-7, characterized in that: Includes the following steps: Step 1: First, it is necessary to collect sound data in different environments, including quiet environments, noisy environments, and music environments. This data will be used to train the environment recognition algorithm and optimize the mode switching strategy. The collected environment data is used to train the environment recognition algorithm, which can be achieved through machine learning or deep learning algorithms to improve the accuracy and robustness of the algorithm. The second step is to design a suitable mode switching strategy based on the output of the environmental recognition algorithm and user preferences. This includes determining the switching timing, switching speed, and switching method. Based on the mode switching strategy, the parameters of the hearing aid, such as amplification, frequency response, and noise suppression, are automatically adjusted to adapt to the needs of different environments. Step 3: Collect user feedback on hearing aid performance, including evaluations of environmental recognition accuracy, mode switching speed, and user satisfaction; integrate the multi-environment mode switching adaptation method into the hearing aid system and test it to verify its performance and reliability in practical applications. Based on performance evaluation results and user feedback, we continuously optimize and improve the multi-environment mode switching adaptation method to enhance its performance and user experience in different environments. Step 4: Implement a multi-environment mode switching adaptation method to improve the performance of hearing aids in different environments and provide a better auditory experience. At the same time, it is necessary to comprehensively consider factors such as environmental data, algorithm training, strategy design, parameter adjustment, user feedback and system integration to ensure the practicality and effectiveness of the method.