Audio data processing method of hearing aid device in noisy environment and related device

Abstract

The application provides an audio data processing method of a hearing aid device in a noisy environment and a related device. The method is applied to a hearing aid device, which includes an audio processing module. The method comprises the following steps: obtaining a preset user frequency response gain curve; obtaining background sound data of a current environment; determining to-be-output audio data according to the user frequency response gain curve; analyzing the background sound data and the to-be-output audio data to obtain an analysis result; determining an adjustment strategy for the to-be-output audio data according to the analysis result; adjusting the to-be-output audio data according to the adjustment strategy, and outputting the adjusted to-be-output audio data. In this way, the safety of environmental perception of a hearing-impaired user is ensured, the listening clarity of target audio in a complex scene is improved, and the hearing aid compensation accuracy and the listening adaptability to different hearing-impaired users are improved by implementing a targeted audio adjustment strategy.

Description

Technical Field

[0001] This application relates to the field of hearing aid technology, and in particular to a method and related apparatus for processing audio data of hearing aids in noisy environments. Background Technology

[0002] Hearing aids are devices used to generate personalized frequency response gain curves based on the user's hearing loss, and to compensate for the gain of specific audio, such as music, to be played by the hearing aid through these personalized frequency response gain curves.

[0003] Currently, most existing hearing aids employ a one-size-fits-all approach of either full-band noise reduction or volume amplification, failing to differentiate the listening value and urgency of different sounds. This leads to either excessive amplification of the target audio while blocking crucial information such as environmental warnings and effective conversations, threatening the user's environmental safety, or excessive retention of ambient sounds causing the target audio to be masked, thus failing to meet the user's core listening needs. Furthermore, the use of a uniform volume adjustment rule, without differentiated adaptation based on the user's hearing loss level, fails to cater to the different listening needs of users with severe, moderate, and mild hearing loss. This results in severely hearing-impaired users being unable to clearly hear core audio, while mildly hearing-impaired users experience severely insufficient listening comfort, making it difficult to meet individual user needs. Summary of the Invention

[0004] In view of this, this application provides an audio data processing method and related apparatus for hearing aids in noisy environments, aiming to analyze the degree of interference of background noise with the output audio by combining the user's frequency response gain curve and implement targeted audio adjustment strategies. While ensuring the user's environmental perception safety, it improves the clarity of target audio reception, the accuracy of hearing aid compensation, and the personalized listening adaptation for different hearing-impaired users in complex scenarios.

[0005] In a first aspect, embodiments of this application provide an audio data processing method for a hearing aid device in a noisy environment, applied to a hearing aid device, the hearing aid device including an audio processing module; the method includes: Acquire a preset user frequency response gain curve, which is audio configuration information based on the user's personalized hearing loss and the effective listening volume at continuous frequency points for gain compensation; and acquire background sound data of the current environment. The audio data to be output is determined based on the user's frequency response gain curve. The background sound data and the audio data to be output are analyzed to obtain analysis results. The analysis results are used to characterize the degree of mutual interference between the background sound data and the audio data to be output, as well as the sound reception value for the user. Based on the analysis results, determine the adjustment strategy for the audio data to be output; Adjust the audio data to be output according to the adjustment strategy, and output the adjusted audio data to be output.

[0006] In one possible embodiment, the analysis of the background sound data and the audio data to be output to obtain the analysis results includes: acquiring a first volume value of the background sound data at each frequency point and a second volume value of the audio data to be output at each frequency point; comparing the volume difference between the first volume value and the second volume value at the same or adjacent frequency points; if the volume difference is less than a preset conflict threshold, the mutual interference level is determined to be high; if the volume difference is greater than the preset conflict threshold, the mutual interference level is determined to be low; identifying the sound source type of the background sound data and the audio data to be output respectively; and determining a first reception value of the background sound data and a second reception value of the audio data to be output based on the sound source type of the background sound data and the audio data to be output.

[0007] In one possible embodiment, determining the adjustment strategy for the audio data to be output based on the analysis result includes: if the analysis result indicates that the mutual interference level is high, and the first reception value of the background sound data is less than the second reception value of the audio data to be output, then the adjustment strategy for the audio data to be output is determined to be: increasing the second volume value of the audio data to be output at the frequency point conflicting with the background sound data; if the analysis result indicates that the mutual interference level is high, and the first reception value is greater than the second reception value, then the adjustment strategy for the audio data to be output is determined to be: decreasing the second volume value of the audio data to be output at the frequency point conflicting with the background sound data. The second volume value at the conflicting frequency point of the background sound data; if the analysis result indicates that the mutual interference level is high, and the first reception value is equal to the second reception value, then the adjustment strategy for the audio data to be output is determined as follows: according to the user's hearing loss level, the first volume value and the second volume value are allocated at the conflicting frequency point according to the volume allocation ratio, and the total volume of the first volume value and the second volume value is less than the upper limit of the effective listening volume of the user's frequency response gain curve at the conflicting frequency point; if the analysis result indicates that the mutual interference level is low, then the adjustment strategy for the audio data to be output is determined as follows: maintain the original configuration information of the audio data to be output.

[0008] In one possible embodiment, allocating the first volume value and the second volume value at the conflicting frequency point according to the user's hearing loss level includes: configuring the volume allocation ratio of the audio data to be output and the background sound data at the conflicting frequency point according to the user's hearing loss level, wherein the higher the user's hearing loss level, the higher the proportion of the audio data to be output in the volume allocation ratio; and adjusting the first volume value and the second volume value according to the volume allocation ratio.

[0009] In one possible embodiment, determining the first reception value of the background sound data and the second reception value of the audio data to be output based on the sound source types of the background sound data and the audio data to be output includes: acquiring the sound source types of the background sound data and the audio data to be output, wherein the sound source types include at least one of the following: warning sound sources, dialogue sound sources, media sound sources, and ambient background sound sources; determining the first reception value and the second reception value according to a preset sound source priority relationship, wherein the sound source priority relationship characterizes the relationship between different sound source types and the reception value, and the reception value reflects the urgency of the sound data to the user, wherein the reception value of the warning sound source is higher than that of the dialogue sound source, the reception value of the dialogue sound source is higher than that of the media sound source, and the reception value of the media sound source is higher than that of the ambient background sound source.

[0010] In one possible embodiment, after the adjusted audio data to be output, the method further includes: collecting the user's listening feedback data, the listening feedback data including: volume adjustment commands actively triggered by the user, and adjustment operation records within a preset duration; adjusting one or more of the preset conflict threshold, the volume allocation ratio, and the sound source priority relationship based on the listening feedback data; and updating the analysis results based on the adjusted parameters.

[0011] In one possible embodiment, obtaining the preset user frequency response gain curve includes: obtaining the user's hearing status parameters, the hearing status parameters including hearing loss values ​​at the continuous frequency points; and generating a frequency response gain curve matching the user through a preset neural network model based on the hearing status parameters, the user frequency response gain curve including the effective listening volume range of the user at each frequency point of the continuous frequency points, and a safe volume threshold.

[0012] Secondly, embodiments of this application provide an audio data processing device for a hearing aid in a noisy environment, applied to a hearing aid, the hearing aid including an audio processing module; the device includes: an acquisition unit, a determination unit, an analysis unit, an adjustment unit, and an output unit; wherein, the acquisition unit is used to acquire a preset user frequency response gain curve, the user frequency response gain curve being audio configuration information based on the user's personalized hearing loss and effective listening volume at continuous frequency points for gain compensation; and to acquire background sound data of the current environment; the determination unit is used to determine the audio data to be output according to the user frequency response gain curve; the analysis unit is used to analyze the background sound data and the audio data to be output to obtain an analysis result, the analysis result being used to characterize the mutual interference degree of the background sound data and the audio data to be output, and the reception value for the user; the adjustment unit is used to determine an adjustment strategy for the audio data to be output according to the analysis result; the output unit is used to adjust the audio data to be output according to the adjustment strategy and output the adjusted audio data to be output.

[0013] Thirdly, embodiments of this application provide an electronic device including a processor, a memory, the memory being used to store one or more programs and configured to be executed by the processor, the programs including instructions for performing the steps in the first aspect of embodiments of this application.

[0014] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program for electronic data interchange, wherein the computer program causes a computer to perform some or all of the steps described in the first aspect of embodiments of this application.

[0015] Fifthly, embodiments of this application provide a computer program product, wherein the computer program product includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps described in the first aspect of embodiments of this application. The computer program product may be a software installation package.

[0016] As can be seen, the audio data processing method and related apparatus for hearing aids in noisy environments provided in this application, whereby the method is applied to a hearing aid including an audio processing module, includes: acquiring a preset user frequency response gain curve, which is audio configuration information based on the effective listening volume at continuous frequency points for gain compensation of the user's personalized hearing loss; acquiring background sound data of the current environment; determining the audio data to be output based on the user frequency response gain curve; analyzing the background sound data and the audio data to be output to obtain analysis results, which characterize the mutual interference degree between the background sound data and the audio data to be output, as well as their reception value for the user; determining an adjustment strategy for the audio data to be output based on the analysis results; adjusting the audio data to be output according to the adjustment strategy; and outputting the adjusted audio data to be output. Thus, by combining the user frequency response gain curve, analyzing the interference degree of background sound with the audio data to be output, and implementing targeted audio adjustment strategies, the clarity of target audio reception in complex scenarios is improved, and the accuracy of hearing aid compensation and the listening adaptability for different hearing-impaired users are enhanced, while ensuring the environmental perception safety of hearing-impaired users. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 This is a schematic diagram of the structure of a hearing aid device provided in an embodiment of this application; Figure 2 This is a schematic flowchart of an audio data processing method for a hearing aid device in a noisy environment, provided in an embodiment of this application. Figure 3 This is a flowchart illustrating a method for determining an audio adjustment strategy, as provided in an embodiment of this application. Figure 4 This is a schematic diagram of a process for dynamically updating analysis results provided in an embodiment of this application; Figure 5 This is a block diagram of the functional units of an audio data processing device for a hearing aid in a noisy environment, as provided in an embodiment of this application. Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0019] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present application, and not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present application.

[0020] The terms "first," "second," etc., in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or apparatus that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or apparatuses.

[0021] It should be understood that the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article indicates that the preceding and following related objects have an "or" relationship.

[0022] In this application's embodiments, "multiple" refers to two or more. In this application's embodiments, "connection" refers to various connection methods, such as direct or indirect connections, to achieve communication between devices; this application's embodiments do not impose any limitations on this.

[0023] In this document, the term "embodiment" means that a particular feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places throughout the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described herein can be combined with other embodiments.

[0024] The following describes the relevant content, concepts, meanings, technical issues, technical solutions, and beneficial effects involved in the embodiments of this application.

[0025] Hearing aids are devices used to generate personalized frequency response gain curves based on the user's hearing loss. These curves compensate for the gain of specific audio, such as music, to be played. Currently, most existing hearing aids use a one-size-fits-all approach of full-band noise reduction or volume amplification, failing to differentiate the listening value and urgency of different sounds. This leads to either excessive amplification of the target audio while blocking crucial information such as environmental warnings and conversations, threatening the user's perceived safety, or excessive retention of ambient sounds, masking the target audio and failing to meet the user's core listening needs. Furthermore, the use of uniform volume adjustment rules, without differentiated adaptation based on the user's hearing loss level, fails to cater to the different listening needs of users with severe, moderate, and mild hearing loss. This results in severely hearing-impaired users being unable to hear core audio clearly, while mildly hearing-impaired users experience significant listening comfort issues, making it difficult to meet individual user needs.

[0026] To address the aforementioned issues, this application provides an audio data processing method and related apparatus for hearing aids in noisy environments. By combining the user's personalized hearing loss characteristics, the method aims to determine the interference of ambient background noise and implement targeted audio adjustment strategies. This ensures the user's environmental perception safety while improving the clarity of target audio reception, the accuracy of hearing aid compensation, and the personalized listening adaptation for different hearing loss users in complex scenarios.

[0027] Specifically, please refer to Figure 1 , Figure 1 This is a schematic diagram of the structure of a hearing aid device provided in an embodiment of this application. Figure 1 As shown, the hearing aid device 100 is used to implement the audio data processing method of the hearing aid device in a noisy environment provided by the present invention.

[0028] The hearing aid device 100 includes, but is not limited to, the following functional components, which are connected via an internal bus or a dedicated audio data link to form a complete signal acquisition, processing, and output channel: an audio acquisition module 110, an audio processing module 120, and a storage unit 130. Specifically, the hearing aid device 100 can be a hearing aid speaker.

[0029] The audio acquisition module 110 is configured to acquire background sound data of the current environment. This module can be an omnidirectional or directional microphone array integrated on the hearing aid's housing, used to pick up ambient sounds around the user in real time, including but not limited to background noise, other people's voices, and warning sounds. The audio acquisition module 110 converts the acquired analog audio signals into digital audio signals and transmits them to the audio processing module 120 via an internal audio data link. The storage unit 130 is configured to store a preset user frequency response gain curve. This user frequency response gain curve is audio configuration information based on the user's personalized hearing loss and effective listening volume at continuous frequency points (such as the range of 125Hz to 8000Hz) for gain compensation. The storage unit 130 can be a non-volatile memory (such as Flash or EEPROM) used to persistently store the user's hearing status parameters and the corresponding frequency response gain curve data, which can be accessed by the audio processing module 120 when the device is started or when the user switches hearing modes.

[0030] The audio processing module 120 is the central decision-making and execution core of the hearing aid device 100. It can be a high-performance digital signal processor (DSP) or an embedded neural network processor (NPU), equipped with an independent algorithm firmware area and high-speed cache. The storage unit 130 is a non-volatile memory (such as Flash or EEPROM) that establishes bidirectional communication with the audio processing module 120 through a data bus. It is used to store the user's personalized hearing loss profile and historical strategy library.

[0031] Specifically, the audio processing module 120 is configured to perform the following steps: read a preset user frequency response gain curve from the storage unit 130, which defines the effective listening volume range and safe volume limit for the user at each frequency point. Based on the user frequency response gain curve, perform gain compensation on the audio data to be output input from the audio acquisition module 110, ensuring that the output volume at each frequency point falls within the user's effective listening volume range. Receive background sound data and audio data to be output sent by the audio acquisition module 110, and obtain the first and second volume values ​​at each frequency point; determine the degree of mutual interference by comparing the volume differences at the same or adjacent frequency points; simultaneously, identify the sound source type of the two signals and determine the first and second reception values ​​according to a preset sound source priority relationship; and generate an adjustment strategy for the audio data to be output based on the comparison results of the mutual interference degree and reception value. When the mutual interference level is high and the reception value differs, bias is achieved by increasing or decreasing the volume of the audio to be output at the conflicting frequency. When the mutual interference level is high and the reception value is equal, the first and second volume values ​​are adjusted according to the user's hearing loss level and the volume distribution ratio at the conflicting frequency, ensuring that the total superimposed volume does not exceed the upper limit of the effective listening volume of the user's frequency response gain curve at that frequency. According to the determined adjustment strategy, the gain coefficient of the audio data to be output at each conflicting frequency is independently adjusted through the built-in equalizer or dynamic range compressor, and the adjusted audio data to be output is output to the user through the audio output unit 140 (such as a speaker, headphone jack, or wireless audio transmitter module).

[0032] The hearing aid device 100 in this embodiment further includes an audio output unit 140, which is the sound output unit of the hearing aid device 100 and can be a high-fidelity balanced armature or dynamic coil speaker (Receiver), and is connected to the output terminal of the audio processing module 120 via a power amplifier.

[0033] In other possible embodiments, the hearing aid device 100 further includes an interface module that establishes a communication connection with at least one portable terminal. Specifically, the portable terminal includes, but is not limited to, smartphones, smartwatches, tablets, or other wearable devices with microphone acquisition capabilities that maintain near-field communication (such as Bluetooth, Wi-Fi, NFMI) with the hearing aid device 100. When the user initiates an audio output task, the hearing aid device 100 sends an auxiliary acquisition command to the paired portable terminal through the communication interface unit. The portable terminal responds to the command, activates its audio acquisition module to synchronously acquire ambient sound data around the user, and transmits the acquired audio stream or preprocessed feature data back to the hearing aid device 100 in real time. The portable terminal is typically worn on the user's wrist, clothing, or placed on a table, and its acquisition angle differs from that of the hearing aid device 100, thus supplementing the acquisition of background sound information in the blind spots of the hearing aid device 100.

[0034] The following is combined with Figure 2 This application describes an audio data processing method for a hearing aid device in a noisy environment. Figure 2 This is a schematic flowchart illustrating an audio data processing method for a hearing aid device in a noisy environment, as provided in an embodiment of this application. The method in this embodiment is applied to, for example... Figure 1 The hearing aid device 100 shown is described, and the method includes the following steps: Step S210: Obtain the preset user frequency response gain curve; and obtain the background sound data of the current environment.

[0035] The user frequency response gain curve is audio configuration information that compensates for gain at effective listening volumes across continuous frequency points based on the user's individual hearing loss. Effective listening volume refers to the volume range at which a user can clearly hear a sound signal without discomfort at a certain frequency point. This range includes a lower limit (minimum audible volume) and an upper limit (maximum comfortable volume or safety threshold). Beyond this range, the user may not be able to hear clearly or may experience harshness.

[0036] Specifically, the curve obtains the user's hearing loss values ​​at standard frequency points such as 250Hz, 500Hz, 750Hz, 1000Hz, and 1500Hz through pure tone hearing threshold testing, and generates a continuous curve covering the range of frequencies audible to the human ear through interpolation or neural network models.

[0037] The hearing aid uses a built-in microphone array to collect background sound data of the current environment in real time. This data includes various sound signals in the environment, such as steady-state noise, transient noise, and other people's voices.

[0038] Step S220: Determine the audio data to be output based on the user's frequency response gain curve.

[0039] The audio data to be output refers to the sound signal that the hearing aid will play to the user. Its source can be an external audio source device, such as a mobile phone, TV, or computer, which transmits audio streams via Bluetooth, Wi-Fi, or wired means, or it can be an audio file stored locally on the device.

[0040] Specifically, based on the user's frequency response gain curve, initial gain compensation is performed on the original audio data to be output. The hearing aid device decomposes the original audio signal in the frequency domain. For each frequency point, if the original volume is lower than the effective listening volume lower limit of that frequency point, the gain is increased; if the original volume is higher than the effective listening volume upper limit, the gain is attenuated to ensure that the output volume falls within the range that the user can listen comfortably.

[0041] Step S230: Analyze the background sound data and the audio data to be output to obtain the analysis results.

[0042] The analysis results characterize the degree of mutual interference between background sound data and the audio data to be output, as well as their reception value for the user. The analysis of mutual interference involves performing frequency domain transformations on both the background sound data and the audio data to be output, obtaining their respective volume values ​​at each frequency point. By comparing the volume differences at the same or adjacent frequency points, it is determined whether there is a volume conflict. If the volume difference is small, it indicates that the loudness of the two signals at that frequency point is similar, resulting in a high degree of mutual interference; if the volume difference is large, the degree of mutual interference is low. The analysis of reception value involves identifying the sound source type, such as using a pre-trained neural network model to determine whether the background sound is environmental noise, other people's voices, or warning sounds, and determining whether the audio to be output is "music," "call voice," or "broadcast content." Based on preset priority rules, such as warning sounds having higher priority than call voices, and call voices having higher priority than music, each signal is assigned a reception value score, which reflects the importance or urgency of the sound to the user.

[0043] Step S240: Determine the adjustment strategy for the audio data to be output based on the analysis results.

[0044] Specifically, the decision-making logic is as follows: If the mutual interference level is high and the reception value of the background sound is lower than that of the audio to be output, then the adjustment strategy is determined as follows: increase the volume of the audio to be output at the conflicting frequency point to make it more prominent relative to the background sound.

[0045] If the level of mutual interference is high, and the reception value of the background sound is higher than that of the audio to be output, then the adjustment strategy is determined as follows: reduce the volume of the audio to be output at the conflicting frequency point to avoid interfering with the more important background sound.

[0046] If the mutual interference level is high and the reception value of both is equal, then it is necessary to further combine the user's hearing characteristics to achieve a balanced allocation.

[0047] If the mutual interference level is low, no adjustment is needed; maintain the original configuration information of the audio to be output.

[0048] Step S250: Adjust the audio data to be output according to the adjustment strategy, and output the adjusted audio data to be output.

[0049] The fine-tuning of the output audio data is achieved through an equalizer or dynamic range compressor in a digital signal processor. The gain adjustment is only applied to conflicting frequencies and does not affect the normal output of other frequencies.

[0050] As can be seen, the audio data processing method and related apparatus for hearing aids in noisy environments provided in this application, whereby the method is applied to a hearing aid including an audio processing module, includes: acquiring a preset user frequency response gain curve, which is audio configuration information based on the effective listening volume at continuous frequency points for gain compensation of the user's personalized hearing loss; acquiring background sound data of the current environment; determining the audio data to be output based on the user frequency response gain curve; analyzing the background sound data and the audio data to be output to obtain analysis results, which characterize the mutual interference degree between the background sound data and the audio data to be output, as well as their reception value for the user; determining an adjustment strategy for the audio data to be output based on the analysis results; adjusting the audio data to be output according to the adjustment strategy; and outputting the adjusted audio data to be output. Thus, by combining the user frequency response gain curve, analyzing the interference degree of background sound with the audio data to be output, and implementing targeted audio adjustment strategies, the clarity of target audio reception in complex scenarios is improved, and the accuracy of hearing aid compensation and the listening adaptability for different hearing-impaired users are enhanced, while ensuring the environmental perception safety of hearing-impaired users.

[0051] In one possible embodiment, the background sound data and the audio data to be output are analyzed to obtain analysis results, including: acquiring the first volume value of the background sound data at each frequency point and the second volume value of the audio data to be output at each frequency point; comparing the volume difference between the first volume value and the second volume value at the same or adjacent frequency points; if the volume difference is less than a preset conflict threshold, the mutual interference level is determined to be high; if the volume difference is greater than the preset conflict threshold, the mutual interference level is determined to be low; identifying the sound source type of the background sound data and the audio data to be output respectively; and determining the first reception value of the background sound data and the second reception value of the audio data to be output based on the sound source type of the background sound data and the audio data to be output.

[0052] Here, "frequency point" does not refer to a single frequency value, but rather to the center frequency or frequency band interval of several frequency bands after frequency domain transformation. For example, in hearing aids, the audible range of the human ear is often divided into 32, 64, or more frequency bands with equal proportions or equal loudness intervals, each corresponding to a center frequency. For each frequency band, the average or maximum energy of all frequency components within that band is calculated as the volume value of that frequency point.

[0053] The preset conflict threshold refers to a pre-defined upper limit for the volume difference, used to determine whether the loudness of two audio signals at the same or adjacent frequency points is close enough to produce an auditory masking effect. This threshold can be dynamically set according to the user's hearing characteristics or the level of ambient background noise, with a typical range of 3dB to 10dB. If the difference is less than this threshold, it means that the loudness of the two signals at that frequency point is comparable, and they are prone to mutual interference, making it impossible for the user to clearly distinguish either sound; if the difference is greater than this threshold, the loudness difference is large, and the lower loudness will be naturally masked by the higher loudness, resulting in a lower degree of interference.

[0054] Specifically, to further differentiate the importance of the two audio signals to the user, the audio processing module performs sound source type identification on the input audio signals. This identification process can be implemented through a pre-trained neural network model. The model input is the time-frequency characteristics of the audio signal, such as Mel-frequency cepstral coefficients (MFCC) and spectral centroid, and the output is the probability distribution of the sound source category to which the audio segment belongs. Sound source types include, but are not limited to, the following four categories: Warning sound sources: such as car horns, fire alarms, doorbells, alarm clocks, etc., which are usually urgent and of high importance; Conversation sound sources: such as other people's voices, telephone calls, voice messages, etc., which contain linguistic information and are of medium to high importance to the user; Media sound sources: such as music, TV programs, podcasts, etc., mainly used for entertainment or information acquisition, and of medium importance; Environmental background sound sources: such as air conditioner noise, wind noise, clinking of tableware, etc., which have no specific semantic content and are of low importance.

[0055] As can be seen, in this embodiment, by extracting the frequency domain volume values ​​of the background sound data and the audio data to be output, and comparing the volume difference of the same or adjacent frequency points with a preset conflict threshold, the degree of mutual interference is quantitatively determined. Simultaneously, through sound source type identification and preset priority ranking, each of the two sound data streams is assigned a reception value score reflecting its importance. In this way, the mutual interference relationship between multiple sound signals in a noisy environment is accurately quantified, and the importance and urgency of each sound stream are objectively assessed, providing a reliable decision-making basis for subsequent adjustment strategies.

[0056] Specifically, please refer to Figure 3 , Figure 3 This is a flowchart illustrating a method for determining an audio adjustment strategy, as provided in an embodiment of this application. Figure 3 As shown, the adjustment strategy for the audio data to be output is determined based on the analysis results, including the following steps: S301, determine the degree of mutual interference represented by the analysis results; if the degree of mutual interference is high, proceed to step S302; if the degree of mutual interference is low, proceed to step S306.

[0057] S302, compare the first recording value of the background sound data with the second recording value of the audio data to be output; if the first recording value is less than the second recording value, proceed to step S303; if the first recording value is greater than the second recording value, proceed to step S304; if the first recording value is equal to the second recording value, proceed to step S305.

[0058] S303, the adjustment strategy for the audio data to be output is determined as follows: increase the second volume value of the audio data to be output at the frequency point that conflicts with the background sound data.

[0059] Specifically, when the system determines that the mutual interference level at a certain frequency is high, and the reception value of the background sound data is lower than that of the audio data to be output, it indicates that the loudness of the two signals is similar at that frequency, causing mutual interference. However, the audio to be output is more important to the user, for example, when the user is listening to an important voice call or their favorite music. In this case, the adjustment strategy is to increase the second volume value of the audio data to be output at the conflicting frequency, making it significantly louder than the background sound, thereby overcoming the masking effect and allowing the user to clearly distinguish the content of the audio to be output. Specifically, increasing the volume does not simply boost the gain of the entire audio to be output; instead, it uses the equalizer in the digital signal processor to only boost the gain of the identified conflicting frequency.

[0060] S304, the adjustment strategy for the audio data to be output is determined as follows: lower the second volume value of the audio data to be output at the frequency point that conflicts with the background sound data.

[0061] Specifically, when the system determines that the mutual interference level at a certain frequency is high, and the reception value of the background sound data is higher than that of the audio data to be output, it indicates that the loudness of the two signals is similar at that frequency, causing mutual interference. However, the background sound is more important to the user, such as warning sounds like car horns or doorbells, or important voices from others. In this case, the adjustment strategy is to lower the second volume value of the audio data to be output at the conflicting frequency, making it significantly lower in loudness than the background sound, thus preventing the audio data to be output from interfering with the user's perception of important environmental sounds. Specifically, lowering the volume is achieved by attenuating the gain only at the conflicting frequency through the equalizer. The attenuation can be set so that the volume of the background sound, after being superimposed, is still significantly higher than that of the audio data to be output, for example, setting a target difference of more than 5dB. It should be understood that the reduction should not be excessive, lest the audio data to be output become completely indistinguishable, affecting the user's basic user experience.

[0062] S305, the adjustment strategy for the audio data to be output is determined as follows: based on the user's hearing loss level, the first volume value and the second volume value are allocated at the conflicting frequency points according to the volume distribution ratio.

[0063] Among them, the total volume of the first volume value and the second volume value is less than the upper limit of the effective listening volume of the user's frequency response gain curve at the conflict frequency point.

[0064] Specifically, the degree of hearing loss can be categorized into mild, moderate, and severe hearing loss. Different levels correspond to different volume distribution biases, based on the user's varying sensitivity to different frequencies. For example, users with severe hearing loss are more reliant on sound signals and therefore tend to allocate a higher volume percentage to the audio being output when there is a conflict; users with mild hearing loss, on the other hand, tend to retain the perception of ambient sound to maintain contextual awareness. The effective listening volume limit refers to the maximum volume value that a user can comfortably listen to at a given frequency, as defined in the user's frequency response gain curve. This value is set based on the user's individual hearing loss and auditory tolerance and is a condition for ensuring auditory safety.

[0065] Specifically, in one possible embodiment, according to the user's hearing loss level, a first volume value and a second volume value are allocated on the conflicting frequency point according to a volume allocation ratio, including: configuring the volume allocation ratio of the audio data to be output and the background sound data on the conflicting frequency point according to the user's hearing loss level, wherein the higher the user's hearing loss level, the higher the proportion of the audio data to be output in the volume allocation ratio; and adjusting the first volume value and the second volume value according to the volume allocation ratio.

[0066] The volume allocation ratio refers to the target proportion of the output audio and background sound in the output loudness at the conflict frequency point, reflecting the system's bias towards one signal over the other in terms of loudness. For example, setting the output audio to account for 55% and the background sound for 45% does not mean that the arithmetic ratio of the two volumes is 55:45. Rather, it means that by adjusting their respective gain values, the loudness of the output audio is slightly higher than that of the background sound, while keeping the total volume constant after superposition, thus achieving an auditory bias. Specifically, the volume allocation ratio relationship is as follows, and the specific values ​​can be optimized based on clinical data: Mild hearing loss: The output audio accounts for 45%, and the background sound accounts for 55%, which is biased towards ambient sound and maintains contextual awareness; Moderate hearing loss: The output audio accounts for 55%, and the background sound accounts for 45%, slightly biased towards the output audio; Severe hearing loss: The output audio accounts for 65%, while the background sound accounts for 35%, showing a significant bias towards the output audio.

[0067] For example, a user is using a hearing aid in a meeting room. The background sound data includes colleagues talking in hushed tones (2000Hz, 70dB SPL), while the output audio is a telephone conversation (2000Hz, 72dB SPL). The mutual interference level is high. The sound source type identification results show that both are conversational sound sources with medium reception value, and the first reception value equals the second reception value. The device queries the user's hearing loss level. Assuming the user has moderate hearing loss, the system's preset volume allocation ratio for moderate hearing loss is 55% for the output audio and 45% for the background sound. The device calculates that the current total superimposed volume is approximately 74.5 dB SPL, which does not exceed the user's effective listening volume limit of 85 dB SPL at this frequency. Therefore, it adjusts the volume according to the allocation ratio: the gain of the audio to be output is increased to 74 dB SPL, and the gain of the background sound is attenuated to 68 dB SPL, so that the total volume after superposition is controlled within a safe range. At the same time, the audio to be output has a slight advantage in loudness, so that the user can hear the phone call first, while still being able to perceive the conversation of colleagues.

[0068] The adjustment of the first and second volume values ​​is accomplished through the gain control unit in the digital signal processor. For the audio data to be output, a target gain value is applied at the conflicting frequency; for the background sound data, an independent gain value is also applied at the conflicting frequency. The gain adjustments of the two signals are independent of each other and do not affect each other, ensuring that fine-tuning is performed only at the conflicting frequency, while other frequencies remain unchanged. The adjustment process uses a gradual gain change, such as a change of no more than 0.5dB per frame, to avoid auditory discomfort caused by sudden volume changes.

[0069] As can be seen, in this embodiment, by using the user's hearing loss level as the core basis for the volume allocation ratio, a dynamic allocation mechanism is established where the higher the degree of hearing loss, the higher the proportion of the output audio. During the adjustment process, the total volume is constrained to not exceed the effective listening volume limit defined by the user's frequency response gain curve. Thus, the differentiated configuration of the volume allocation ratio at conflicting frequency points makes the adjustment strategy more closely match the user's personalized auditory needs, ensuring that the total volume after any adjustment does not exceed the user's hearing tolerance range, avoiding potential auditory discomfort or damage due to excessive volume, and guaranteeing safety.

[0070] S306, The adjustment strategy for the audio data to be output is determined to be: maintain the original configuration information of the audio data to be output.

[0071] When the system determines that the mutual interference level at a certain frequency is low, it means that the volume difference between the two signals at that frequency is large enough that the louder signal naturally masks the weaker one, and will not cause substantial interference to the user's auditory perception. In this case, no adjustments need to be made to the output audio; simply maintain its original configuration information.

[0072] As can be seen, in this embodiment, by constructing an adjustment strategy based on the comparison of mutual interference level and reception value, the system maintains its original state when the mutual interference level is low to avoid excessive intervention. When the mutual interference level is high, it prioritizes the side with higher reception value based on the reception value comparison result. Furthermore, when the values ​​are equal, a volume allocation ratio mechanism driven by hearing loss level is introduced. In this way, the adaptability of the hearing aid device in complex environments is improved, ensuring both the clarity of the output audio and the necessary environmental sound perception, thereby enhancing user safety and listening comfort.

[0073] In one possible embodiment, determining a first reception value of the background sound data and a second reception value of the audio data to be output, based on the sound source types of the background sound data and the audio data to be output, includes: acquiring the sound source types of the background sound data and the audio data to be output, wherein the sound source types include at least one of the following: warning sound sources, dialogue sound sources, media sound sources, and ambient background sound sources; and determining the first reception value and the second reception value according to a preset sound source priority relationship, wherein the sound source priority relationship characterizes the relationship between different sound source types and reception value, and the reception value reflects the urgency of the sound data to the user, wherein the reception value of warning sound sources is higher than that of dialogue sound sources, the reception value of dialogue sound sources is higher than that of media sound sources, and the reception value of media sound sources is higher than that of ambient background sound sources.

[0074] Specifically, warning sound sources refer to sound sources used to convey emergency and safety-related information, such as car horns, fire alarms, doorbells, alarm clocks, reversing warning sounds, and smoke detectors. These sounds are usually sudden, loud, and provide clear warnings, making them crucial for user safety. Conversational sound sources include sound sources containing spoken communication, such as face-to-face conversations, telephone calls, voice messages, radio news broadcasts, and television dialogues. These sounds carry semantic information and are highly valuable for users' social interaction and information acquisition. Media sound sources refer to sound sources used for entertainment or information consumption, such as music, podcasts, audiobooks, background music from television programs, and game sound effects. While these sounds have some value, they usually do not contain emergency information and have a lower priority than conversational sound sources. Environmental background sound sources refer to environmental noise without specific semantic content, such as air conditioner noise, fan noise, rain noise, wind noise, traffic noise, and the sound of tableware clattering. These sounds primarily provide contextual awareness but do not carry specific information and have the lowest priority.

[0075] For example, when a user uses an in-vehicle hearing aid, the device collects background sound data in real time: at one moment, the background sound data includes the siren of an ambulance passing by, and the sound source type recognition model outputs a warning sound source with a confidence level of 95%; at another moment, the background sound data includes greetings from a friend nearby, and the recognition result is a conversation sound source with a confidence level of 88%; the device receives music played by a mobile device via Bluetooth, and the recognition result of the audio data to be output is a media sound source with a confidence level of 92%; the background sound data also includes continuous wind noise, and the recognition result is an environmental background sound source with a confidence level of 85%.

[0076] Radio reception value is a quantitative indicator of the importance or urgency of sound data to a user. In this embodiment, radio reception value can be represented as a level (e.g., high, medium, low, very low) or a numerical value (e.g., 0-10 points) to facilitate comparison in the decision-making logic. The assignment of radio reception value follows the sound source priority relationship, and the specific mapping relationship is shown in Table 1: Table 1

[0077] Furthermore, the sound reception value in this embodiment is not static. Although the priority relationship of sound sources is fixed, the system can fine-tune the sound reception value within the same sound source type according to the specific context. For example, face-to-face conversations and telephone calls, which belong to the dialogue category, can be assigned different value scores based on the user's historical behavior, such as the user answering the phone more often; fire alarms and doorbells, which belong to the warning category, can be set with different values ​​according to the difference in urgency, such as 10 points for fire alarms and 9 points for doorbells.

[0078] As can be seen, in this embodiment, by classifying sound sources into four categories—warning, dialogue, media, and environmental background—and establishing clear sound source priority relationships, each sound signal is assigned a quantified reception value, providing a bias basis for subsequent adjustment strategy decisions. This enhances the user's safety perception in complex sound fields, ensures the clarity of voice communication, and improves the user experience of using hearing aids.

[0079] Specifically, please refer to Figure 4 , Figure 4 This is a schematic diagram of a process for dynamically updating analysis results provided in an embodiment of this application, such as... Figure 4 As shown, after outputting the adjusted audio data to be output, the method also includes the following steps: S401 collects user listening feedback data.

[0080] The listening feedback data includes: user-triggered volume adjustment commands and adjustment operation records within a preset time period. Specifically, user-triggered volume adjustment commands refer to user-initiated interventions in device volume during listening. These include: Overall volume adjustment: Users can actively increase or decrease the overall output volume using the device's volume buttons or the application's slider. Frequency band volume adjustment: If the device supports fine-tuning, users can select specific frequency bands, such as high or low frequencies, through the application to increase or decrease volume, reflecting the user's sensitivity preferences for specific frequency ranges. Mode switching: Users can actively switch listening modes, such as "music mode," "conversation mode," and "outdoor mode," indirectly expressing their volume allocation preferences for different scenarios. Adjustment operation records within a preset time period refer to the user's operation history automatically recorded by the system within a set time window, such as the past 7 days, the past 30 days, or the past 100 playback sessions. This record includes not only the specific adjustment instructions but also contextual information about when the adjustment occurred, such as: the time of occurrence, the specific time when the adjustment operation took place, which can be used to analyze user preference differences at different times; the scene identifier, contextual parameters such as the type of background sound and the degree of mutual interference identified by the system when the adjustment occurred; the adjustment magnitude, the incremental or decremental value adjusted by the user, reflecting the user's tolerance for deviations in the current output; and the adjustment frequency, the number of times the user initiates adjustments per unit of time, reflecting the user's degree of dissatisfaction with the current strategy.

[0081] S402 adjusts one or more of the preset conflict threshold, volume distribution ratio, and sound source priority relationship based on listening feedback data.

[0082] For example, based on the scenario example of this embodiment, the system detects that the user frequently manually increases the volume in an outdoor environment, averaging twice a day, and the adjustments occur within 12 seconds after the system automatically adjusts the volume, indicating that the user believes the gain adjustment by the system is insufficient. Accordingly, the system lowers the preset conflict threshold from 5dB to 3dB, causing more frequency points to be judged as having high levels of mutual interference, thereby triggering a more aggressive gain adjustment to meet the user's need for clarity.

[0083] S403, update the analysis results based on the adjusted parameters.

[0084] As can be seen, in this embodiment, by collecting user listening feedback data, including active volume adjustment commands and adjustment operation records within a preset time period, one or more of the preset conflict threshold, volume allocation ratio, and sound source priority relationship are dynamically adjusted, and the analysis results are updated based on the adjusted parameters, forming a complete adaptive optimization mechanism. In this way, by continuously learning user operation behavior, the system parameters can match the user's personalized optimal configuration, improving the ease of use and intelligence level of the hearing aid.

[0085] In one possible embodiment, the method further includes: obtaining a preset user frequency response gain curve, including: obtaining the user's hearing status parameters, the hearing status parameters including hearing loss values ​​at continuous frequency points; and generating a matching user frequency response gain curve based on the hearing status parameters using a preset neural network model, the user frequency response gain curve including the effective listening volume range of the user at each frequency point in the continuous frequency points, and a safe volume threshold.

[0086] Specifically, users can provide hearing status parameters to hearing aids in the following ways: After completing a hearing test at a hearing institution, users receive a hearing test report; users can scan the QR code in the report via an application or manually enter their hearing loss value to synchronize the data to the hearing aid. The user's hearing status parameters are pre-stored in a cloud server, and the hearing aid automatically downloads them after the user logs in with their account.

[0087] The pre-defined deep learning model converts discrete hearing loss parameters into continuous frequency response gain curves. The model's structure includes: an input layer that receives the user's hearing loss value vector at standard frequencies, with the input dimension corresponding to the number of test frequencies (e.g., 11 frequencies); a hidden layer composed of multiple fully connected or convolutional layers that learns the nonlinear mapping between hearing loss data and frequency response gain; and an output layer that outputs gain compensation values ​​at continuous frequencies, with the output dimension adjustable based on the device's supported frequency resolution (e.g., 32, 64, or more frequencies).

[0088] Input the aforementioned hearing state parameters into the neural network model. The model outputs the following frequency response gain curves and corresponding parameters, as detailed in Table 2: Table 2

[0089] In the low-frequency range of 125Hz-1000Hz, hearing loss is relatively mild, the target gain is relatively small (18dB-33dB), the effective listening volume range is approximately 30dB dynamic range, and the safety threshold is relatively high (85dB-93dB). In the high-frequency range of 4000Hz-8000Hz, hearing loss is severe, the target gain is relatively large (62dB-72dB), the effective listening volume range narrows, the dynamic range is approximately 12dB-15dB, and the safety threshold is relatively lower (88dB-92dB). This reflects that users with severe hearing loss have a decreased tolerance for volume and require more precise volume control.

[0090] As can be seen, in this embodiment, by acquiring the user's hearing loss parameters at continuous frequency points and using a preset neural network model for inference, a personalized frequency response gain curve is generated that includes the effective listening volume range and safe volume threshold for each frequency point. This allows for the generation of a smooth and reasonable frequency response gain curve, making the compensation more closely match the user's actual hearing needs.

[0091] This application embodiment can divide the electronic device into functional units according to the above method example. For example, each function can be divided into a separate functional unit, or two or more functions can be integrated into one processing unit. The integrated unit can be implemented in hardware or as a software functional unit. It should be noted that the unit division in this application embodiment is illustrative and only represents one logical functional division. In actual implementation, there may be other division methods.

[0092] and Figure 2 The implementation is consistent with the previous one; please refer to [link / reference]. Figure 5 , Figure 5 This is a functional unit block diagram of an audio data processing device for a hearing aid in a noisy environment, provided in an embodiment of this application. The audio data processing device 500 for a hearing aid in a noisy environment is applied to, for example... Figure 1 The hearing aid device 100 shown includes an audio data processing device 500 for use in noisy environments, comprising: an acquisition unit 510, a determination unit 520, an analysis unit 530, an adjustment unit 540, and an output unit 550. The acquisition unit 510 acquires a preset user frequency response gain curve, which is audio configuration information based on the user's personalized hearing loss and effective listening volume at continuous frequency points for gain compensation; and acquires background sound data of the current environment. The determination unit 520 determines the audio data to be output based on the user frequency response gain curve. The analysis unit 530 analyzes the background sound data and the audio data to be output to obtain analysis results, which characterize the degree of mutual interference between the background sound data and the audio data to be output, as well as their reception value for the user. The adjustment unit 540 determines an adjustment strategy for the audio data to be output based on the analysis results. The output unit 550 adjusts the audio data to be output according to the adjustment strategy and outputs the adjusted audio data.

[0093] In one possible embodiment, the background sound data and the audio data to be output are analyzed to obtain analysis results. Specifically, the analysis unit 530 is used to: acquire the first volume value of the background sound data at each frequency point and the second volume value of the audio data to be output at each frequency point; compare the volume difference between the first volume value and the second volume value at the same or adjacent frequency points; if the volume difference is less than a preset conflict threshold, the mutual interference level is determined to be high; if the volume difference is greater than the preset conflict threshold, the mutual interference level is determined to be low; identify the sound source type of the background sound data and the audio data to be output respectively; and determine the first reception value of the background sound data and the second reception value of the audio data to be output based on the sound source type of the background sound data and the audio data to be output.

[0094] In one possible embodiment, the adjustment strategy for the audio data to be output is determined based on the analysis results. Specifically, the adjustment unit 540 is used to: if the analysis result indicates a high level of mutual interference and the first reception value of the background sound data is less than the second reception value of the audio data to be output, then the adjustment strategy for the audio data to be output is determined as follows: increase the second volume value of the audio data to be output at the frequency point conflicting with the background sound data; if the analysis result indicates a high level of mutual interference and the first reception value is greater than the second reception value, then the adjustment strategy for the audio data to be output is determined as follows: decrease the second volume value of the audio data to be output at the frequency point conflicting with the background sound data; if the analysis result indicates a high level of mutual interference and the first reception value is equal to the second reception value, then the adjustment strategy for the audio data to be output is determined as follows: allocate the first volume value and the second volume value at the conflicting frequency point according to the user's hearing loss level and the total volume of the first volume value and the second volume value is less than the upper limit of the effective listening volume of the user's frequency response gain curve at the conflicting frequency point; if the analysis result indicates a low level of mutual interference, then the adjustment strategy for the audio data to be output is determined as follows: maintain the original configuration information of the audio data to be output.

[0095] In one possible embodiment, based on the user's hearing loss level, a first volume value and a second volume value are allocated on the conflicting frequency points according to a volume allocation ratio. The adjustment unit 540 is specifically used to: configure the volume allocation ratio of the audio data to be output and the background sound data on the conflicting frequency points according to the user's hearing loss level, wherein the higher the user's hearing loss level, the higher the proportion of the audio data to be output in the volume allocation ratio; and adjust the first volume value and the second volume value according to the volume allocation ratio.

[0096] In one possible embodiment, the analysis unit 530 determines a first reception value of the background sound data and a second reception value of the audio data to be output based on the sound source types of the background sound data and the audio data to be output. Specifically, the analysis unit 530 is used to: acquire the sound source types of the background sound data and the audio data to be output, wherein the sound source types include at least one of the following: warning sound sources, dialogue sound sources, media sound sources, and ambient background sound sources; and determine the first reception value and the second reception value according to a preset sound source priority relationship, wherein the sound source priority relationship characterizes the relationship between different sound source types and reception value, and the reception value reflects the urgency of the sound data to the user, wherein the reception value of warning sound sources is higher than that of dialogue sound sources, the reception value of dialogue sound sources is higher than that of media sound sources, and the reception value of media sound sources is higher than that of ambient background sound sources.

[0097] In one possible embodiment, after outputting the adjusted audio data to be output, the output unit 550 is further configured to: collect user listening feedback data, including: volume adjustment commands actively triggered by the user, and adjustment operation records within a preset duration; adjust one or more of the preset conflict threshold, volume allocation ratio, and sound source priority relationship based on the listening feedback data; and update the analysis results based on the adjusted parameters.

[0098] In one possible embodiment, a preset user frequency response gain curve is obtained. The acquisition unit 510 is specifically used to: acquire the user's hearing status parameters, which include hearing loss values ​​at continuous frequency points; and generate a matching user frequency response gain curve based on the hearing status parameters through a preset neural network model. The user frequency response gain curve includes the effective listening volume range of the user at each frequency point in the continuous frequency points, as well as a safe volume threshold.

[0099] It is understood that since the method embodiments and the device embodiments are different presentations of the same technical concept, the content of the method embodiment section in this application should be adapted to the device embodiment section in a synchronous manner, and will not be repeated here.

[0100] Figure 6 This is a structural block diagram of an electronic device provided in an embodiment of this application. For example... Figure 6 As shown, electronic device 600 may include one or more components: a processor 601 and a memory 602 coupled to the processor 601, wherein the memory 602 may store one or more computer programs, which may be configured to implement the methods described in the examples above when executed by one or more processors 601. Electronic device 600 may be as follows: Figure 1 The hearing aid device 100 shown is shown.

[0101] Processor 601 may include one or more processing cores. Processor 601 connects to various parts within the electronic device 600 using various interfaces and lines, and performs various functions and processes data of the electronic device 600 by running or executing instructions, programs, code sets, or instruction sets stored in memory 602, and by calling data stored in memory 602. Optionally, processor 601 may be implemented using at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), or Programmable Logic Array (PLA). Processor 601 may integrate one or a combination of several of the following: Central Processing Unit (CPU), Graphics Processing Unit (GPU), and modem. It is understood that the aforementioned modem may also not be integrated into processor 601, but may be implemented separately through a communication chip.

[0102] The memory 602 may include random access memory (RAM) or read-only memory (ROM). The memory 602 can be used to store instructions, programs, code, code sets, or instruction sets. The memory 602 may include a program storage area and a data storage area. The program storage area may store instructions for implementing an operating system, instructions for implementing at least one function (such as touch functionality, sound playback functionality, image playback functionality, etc.), and instructions for implementing the various method examples described above. The data storage area may also store data created during the use of the electronic device 600.

[0103] It is understood that the electronic device 600 may include more or fewer structural elements than those shown in the above block diagram, such as a power module, physical buttons, WiFi (Wireless Fidelity) module, speaker, Bluetooth module, sensor, etc., without limitation.

[0104] This application also provides a computer storage medium storing a computer program / instructions thereon, which, when executed by a processor, implements some or all of the steps of any of the methods described in the above method embodiments.

[0105] This application also provides a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program operable to cause a computer to perform some or all of the steps of any of the methods described in the above method embodiments.

[0106] It should be understood that in the various embodiments of this application, the order of the above-mentioned processes does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0107] In the several embodiments provided in this application, it should be understood that the disclosed methods, apparatuses, and systems can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for example, the division of units is merely a logical functional division, and there may be other division methods in actual implementation; for example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0108] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0109] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can be physically comprised separately, or two or more units can be integrated into one unit. The integrated unit described above can be implemented in hardware or in the form of hardware plus software functional units.

[0110] The integrated units implemented as software functional units described above can be stored in a computer-readable storage medium. These software functional units, stored in a storage medium, include several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute partial steps of the methods of the various embodiments of the present invention. The aforementioned storage medium includes: a USB flash drive, a portable hard drive, a magnetic disk, an optical disk, volatile memory, or non-volatile memory. The non-volatile memory can be read-only memory (ROM), programmable read-only memory (PROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), or flash memory. The volatile memory can be random access memory (RAM), which is used as an external cache. By way of example, but not limitation, many forms of random access memory (RAM) are available, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous linked DRAM (SLDRAM), and direct rambus RAM (DR RAM), etc., which are various media capable of storing program code.

[0111] While the present invention has been disclosed above, it is not limited thereto. Any person skilled in the art can easily conceive of variations or substitutions without departing from the spirit and scope of the present invention, and various modifications and alterations can be made, including combinations of the different functions and implementation steps described above, as well as software and hardware implementation methods, all of which are within the protection scope of the present invention.

Claims

1. A method for processing audio data of a hearing aid in a noisy environment, characterized in that, Applied to a hearing aid device, the hearing aid device including an audio processing module; the method includes: Acquire a preset user frequency response gain curve, which is audio configuration information based on the user's personalized hearing loss and the effective listening volume at continuous frequency points for gain compensation; and acquire background sound data of the current environment. The audio data to be output is determined based on the user's frequency response gain curve. The background sound data and the audio data to be output are analyzed to obtain analysis results, including: acquiring the first volume value of the background sound data at each frequency point and the second volume value of the audio data to be output at each frequency point; comparing the volume difference between the first volume value and the second volume value at the same or adjacent frequency points; if the volume difference is less than a preset conflict threshold, the mutual interference level between the background sound data and the audio data to be output is determined to be high; if the volume difference is greater than the preset conflict threshold, the mutual interference level is determined to be low; and sound source type identification is performed on the background sound data and the audio data to be output, respectively. The sound source type includes at least one of the following: warning sound source, dialogue sound source, media sound source, and ambient background sound source; according to a preset sound source priority relationship, the first reception value of the background sound data and the second reception value of the audio data to be output are determined, wherein the sound source priority relationship represents the relationship between different sound source types and the reception value, and the reception value reflects the urgency of the sound data to the user, wherein the reception value of the warning sound source is higher than that of the dialogue sound source, the reception value of the dialogue sound source is higher than that of the media sound source, and the reception value of the media sound source is higher than that of the ambient background sound source; If the analysis result indicates that the mutual interference level is high, and the first reception value of the background sound data is less than the second reception value of the audio data to be output, then the adjustment strategy for the audio data to be output is determined to be: increasing the second volume value of the audio data to be output at the frequency point that conflicts with the background sound data; if the analysis result indicates that the mutual interference level is high, and the first reception value is greater than the second reception value, then the adjustment strategy for the audio data to be output is determined to be: decreasing the second volume value of the audio data to be output at the frequency point that conflicts with the background sound data; if the analysis result indicates that the mutual interference level is high, and the first reception value is greater than the second reception value, then the adjustment strategy for the audio data to be output is determined to be: decreasing the second volume value of the audio data to be output at the frequency point that conflicts with the background sound data; if the analysis result indicates that the mutual interference level is high, and the first reception value is less than the second reception value of the background sound data .... If the reception value is equal to the second reception value, then the adjustment strategy for the audio data to be output is determined as follows: based on the user's hearing loss level, the first volume value and the second volume value are allocated at the conflicting frequency point according to the volume distribution ratio, and the total volume of the first volume value and the second volume value is less than the upper limit of the effective listening volume of the user's frequency response gain curve at the conflicting frequency point; if the analysis result is that the mutual interference level is low, then the adjustment strategy for the audio data to be output is determined as follows: maintain the original configuration information of the audio data to be output; adjust the audio data to be output according to the adjustment strategy, and output the adjusted audio data to be output.

2. The method according to claim 1, characterized in that, The step of allocating the first volume value and the second volume value at the conflicting frequency point according to the user's hearing loss level and volume distribution ratio includes: Based on the user's hearing loss level, configure the volume distribution ratio of the audio data to be output and the background sound data at the conflict frequency point, wherein the higher the user's hearing loss level, the higher the proportion of the audio data to be output in the volume distribution ratio; adjust the first volume value and the second volume value according to the volume distribution ratio.

3. The method according to claim 2, characterized in that, After the adjusted audio data to be output, the method further includes: Collect the user's listening feedback data, which includes: volume adjustment commands actively triggered by the user, and adjustment operation records within a preset time period; Based on the listening feedback data, one or more of the following can be adjusted: the preset conflict threshold, the volume allocation ratio, and the sound source priority relationship. The analysis results are updated based on the adjusted parameters.

4. The method according to claim 1, characterized in that, The process of obtaining the preset user frequency response gain curve includes: The user's hearing status parameters are obtained, including hearing loss values ​​at the continuous frequency points; Based on the hearing state parameters, a frequency response gain curve matching the user is generated through a preset neural network model. The user frequency response gain curve includes the effective listening volume range of the user at each frequency point of the continuous frequency points, as well as the safe volume threshold.

5. An audio data processing device for hearing aids in noisy environments, characterized in that, This device is applied to hearing aids, which include an audio processing module; the device includes: an acquisition unit, a determination unit, an analysis unit, an adjustment unit, and an output unit; wherein, The acquisition unit is used to acquire a preset user frequency response gain curve, which is audio configuration information based on the user's personalized hearing loss and the effective listening volume at continuous frequency points for gain compensation; and to acquire background sound data of the current environment. The determining unit is used to determine the audio data to be output based on the user frequency response gain curve; The analysis unit is used to analyze the background sound data and the audio data to be output, and obtain analysis results, including: acquiring the first volume value of the background sound data at each frequency point and the second volume value of the audio data to be output at each frequency point; comparing the volume difference between the first volume value and the second volume value at the same or adjacent frequency points; if the volume difference is less than a preset conflict threshold, the mutual interference level between the background sound data and the audio data to be output is determined to be high; if the volume difference is greater than the preset conflict threshold, the mutual interference level is determined to be low; and performing sound source type identification on the background sound data and the audio data to be output respectively. The sound source types include at least one of the following: warning sound sources, dialogue sound sources, media sound sources, and ambient background sound sources; according to a preset sound source priority relationship, the first reception value of the background sound data and the second reception value of the audio data to be output are determined, wherein the sound source priority relationship characterizes the relationship between different sound source types and the reception value, and the reception value reflects the urgency of the sound data to the user, wherein the reception value of the warning sound source is higher than that of the dialogue sound source, the reception value of the dialogue sound source is higher than that of the media sound source, and the reception value of the media sound source is higher than that of the ambient background sound source; The adjustment unit is configured to: if the analysis result indicates a high level of mutual interference and the first reception value of the background sound data is less than the second reception value of the audio data to be output, then determine the adjustment strategy for the audio data to be output as follows: increase the second volume value of the audio data to be output at the frequency point conflicting with the background sound data; if the analysis result indicates a high level of mutual interference and the first reception value is greater than the second reception value, then determine the adjustment strategy for the audio data to be output as follows: decrease the second volume value of the audio data to be output at the frequency point conflicting with the background sound data; if the analysis result indicates a high level of mutual interference and the first reception value is equal to the second reception value, then determine the adjustment strategy for the audio data to be output as follows: allocate the first volume value and the second volume value at the conflicting frequency point according to the user's hearing loss level, and the total volume of the first volume value and the second volume value is less than the upper limit of the effective listening volume of the user's frequency response gain curve at the conflicting frequency point; if the analysis result indicates a low level of mutual interference, then determine the adjustment strategy for the audio data to be output as follows: maintain the original configuration information of the audio data to be output. The output unit is used to adjust the audio data to be output according to the adjustment strategy and output the adjusted audio data to be output.

6. An electronic device, characterized in that, It includes a processor and a memory, the memory being used to store one or more programs and configured to be executed by the processor, the programs including instructions for performing the steps of the method as described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, A computer program for storing electronic data interchange is provided, wherein the computer program causes a computer to perform the method as described in any one of claims 1-4.

Images