KR20220037630A - Hearing aid suitable system using artificial intelligence - Google Patents

Abstract

A hearing aid fitting system according to an embodiment of the present invention includes a server and a subject device. The server can provide, to the subject device, test data for fitting a hearing aid in response to a hearing aid fitting request from the subject device, can train a subject's cognitive change model based on response information obtained while a hearing aid fitting test is conducted, can input response information to a pre-learned cognitive change model to calculate a result value of quantifying the degree of change in the subject's hearing ability, and can reset a hearing aid setting value in response to the result value.

Description

Hearing aid suitable system using artificial intelligence

The present invention relates to a hearing aid fitting system using artificial intelligence.

Recently, the number of patients with hearing loss in Korea has increased by about 1.4 times, and annual medical expenses due to hearing loss diseases are also steadily increasing. Among hearing loss patients, the number of registered deaf patients is also increasing rapidly, and among newly registered persons with disabilities in 2019, hearing impairment accounts for the largest share with 39.3%.

Although the number of patients with hearing loss is increasing, the current system for assisting people with hearing loss is insufficient. Specifically, people with hearing loss correct their hearing ability by using hearing aids, such as hearing aids, and these hearing aids require periodic appropriate management according to the characteristics and living environment of the hearing loss, but in order to fit and manage the hearing aid, the patient It is understood that there is no system with empirical data of each individual.

Accordingly, there is a need for a service to periodically check the suitability of the hearing aids used by the hearing-impaired and to support them to frequently refit their hearing aids in response to changes in their hearing function.

An object of the present invention is to predict a change in hearing state corresponding to the elapse of a hearing aid wearing period of a person with hearing loss by utilizing an artificial intelligence-based analysis function, and to help a person with hearing loss receive an appropriate hearing aid suitability test in response thereto.

Another object of the present invention is to support hearing aid fitting more conveniently.

A hearing aid fitting system according to an embodiment of the present invention includes a server and a target device, wherein the server provides hearing aid fitting test data to the target device in response to a hearing aid fitting request from the target device, and performs a hearing aid fitting test A cognitive change model of the subject is learned based on the response information obtained while performing In response, the hearing aid setting value may be reset.

The present invention can help a person with hearing loss to receive an appropriate hearing aid suitability test by predicting a change in the hearing state corresponding to the elapse of a hearing aid wearing period of a person with hearing loss by utilizing an artificial intelligence-based analysis function.

Also, the present invention can support hearing aid fitting more conveniently.

1 is a diagram showing the configuration of a system according to an embodiment of the present invention.
2 is a diagram illustrating the configuration of a server according to an embodiment of the present invention.
3 is a diagram illustrating the configuration of an artificial intelligence analysis unit according to an embodiment of the present invention.
4 is a diagram illustrating the configuration of a suitable model setting unit according to an embodiment of the present invention.
5 is a diagram illustrating a sequence of a hearing aid fitting operation using artificial intelligence according to an embodiment of the present invention.
6 is a diagram for explaining the concept of an artificial intelligence model according to an embodiment of the present invention.

Advantages and features of the present invention and methods of achieving them will become apparent with reference to the embodiments described below in detail in conjunction with the accompanying drawings. However, the present invention is not limited to the embodiments disclosed below, but may be implemented in various different forms, and only the present embodiments allow the disclosure of the present invention to be complete, and those of ordinary skill in the art to which the present invention pertains. It is provided to fully understand the scope of the present invention to those skilled in the art, and the present invention is only defined by the scope of the claims.

The terminology used herein is for the purpose of describing the embodiments and is not intended to limit the present invention. In this specification, the singular also includes the plural unless specifically stated otherwise in the phrase. As used herein, “comprises” and/or “comprising” does not exclude the presence or addition of one or more other components in addition to the stated components. Like reference numerals refer to like elements throughout, and "and/or" includes each and every combination of one or more of the recited elements. Although "first", "second", etc. are used to describe various elements, these elements are not limited by these terms, of course. These terms are only used to distinguish one component from another. Accordingly, it goes without saying that the first component mentioned below may be the second component within the spirit of the present invention.

Unless otherwise defined, all terms (including technical and scientific terms) used herein will have the meaning commonly understood by those of ordinary skill in the art to which this invention belongs. In addition, terms defined in a commonly used dictionary are not to be interpreted ideally or excessively unless specifically defined explicitly.

As used herein, the term “unit” or “module” refers to a hardware component such as software, FPGA, or ASIC, and “unit” or “module” performs certain roles. However, “part” or “module” is not meant to be limited to software or hardware. A “unit” or “module” may be configured to reside on an addressable storage medium or to reproduce one or more processors. Thus, as an example, “part” or “module” refers to components such as software components, object-oriented software components, class components and task components, processes, functions, properties, Includes procedures, subroutines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. Components and functionality provided within “parts” or “modules” may be combined into a smaller number of components and “parts” or “modules” or as additional components and “parts” or “modules”. can be further separated.

Spatially relative terms "below", "beneath", "lower", "above", "upper", etc. It can be used to easily describe the correlation between a component and other components. Spatially relative terms should be understood as terms including different directions of components during use or operation in addition to the directions shown in the drawings. For example, when a component shown in the drawing is turned over, a component described as “beneath” or “beneath” of another component may be placed “above” of the other component. can Accordingly, the exemplary term “below” may include both directions below and above. Components may also be oriented in other orientations, and thus spatially relative terms may be interpreted according to orientation.

In this specification, a computer refers to all types of hardware devices including at least one processor, and may be understood as encompassing software configurations operating in the corresponding hardware device according to embodiments. For example, a computer may be understood to include, but is not limited to, smart phones, tablet PCs, desktops, notebooks, and user clients and applications running on each device.

In addition, in the present specification, the term 'subject' means a subject to perform a hearing test and hearing aid fitting, and at the same time may mean a user of an electronic device and a system according to an embodiment of the present invention.

Hereinafter, a hearing aid fitting system using artificial intelligence according to an embodiment of the present invention will be described with reference to FIGS. 1 to 4 .

First, FIG. 1 is a diagram showing the configuration of a system according to an embodiment of the present invention.

As shown in FIG. 1 , the hearing aid fitting system using artificial intelligence according to an embodiment of the present invention may include a server 100, a target device 200, and an organ-side device 300 .

And according to an embodiment, the server 100 receives a hearing aid suitability operation (eg, a hearing aid suitability test) from the subject device 200, and in response, the server 100 provides data for the hearing aid suitability test to the subject device 200 side can do.

In addition, the server 100 may obtain basic information of the subject from the subject device 200, where the basic information is hearing-related information including the age of the subject, the cause of the hearing loss, the degree of hearing loss, the type of hearing loss, and the period of wearing the hearing aid. can mean

In addition, the basic information may include information on the physical state of the subject related to the hearing aid fit. Accordingly, the server 100 may conduct a predetermined questionnaire to the subject in order to obtain basic information required for hearing aid fitting, and may obtain basic information related to a physical condition through a response corresponding to the questionnaire. For example, 'Have you had otitis media recently?' A questionnaire related to physical characteristics related to wearing a hearing aid, such as a hearing aid, may be attempted, and a response of the subject may be obtained in response thereto. These physical characteristics may be considered to determine whether attention needs to be paid when resetting the hearing aid setting value by estimating the state of the eardrum. Also, basic information related to physical characteristics may be considered to determine whether the material, shape, etc. of the hearing aid insertion part are changed when the hearing aid is refitted. In addition, basic information related to physical characteristics may be considered to determine whether a subject is capable of remotely performing hearing aid refitting or whether a visit to an institution is required for treatment.

In addition, the basic information may include information about a setting state of a hearing aid currently worn by the subject. Hearing aid settings can be set including items such as noise cancellation threshold, low volume (eg, first-stage sound) gain, low-pitched threshold, loud (eg, second-level sound) gain, loudness threshold, and sound compression ratio. can Since it is composed of such various items, it is virtually difficult for the subject to directly recognize and input the setting values of the hearing aid he is wearing. Accordingly, in order to obtain information on the setting state of the hearing aid among the basic information, the server 100 may retrieve the corresponding information from the organ that stores the result of the most recent hearing aid fitting by the corresponding subject. That is, the server 100 may obtain associated organ information from the subject device 200, and may retrieve recent hearing aid suitability setting value information of the subject from the associated organ inputted from the subject.

It may be assumed that the server 100 according to an embodiment of the present invention is associated with an institution that sets a hearing aid setting value. Accordingly, at the time of initial hearing aid setup, the subject may be given a preset membership number by the organization that has set up the hearing aid, and may access the server 100 through the assigned member number. In this case, when the subject accesses the server 100 through the assigned member number, the subject directly fills in the basic information related to the subject's physical characteristics and the response to the questionnaire, but the hearing aid setting value information or hearing loss related information is pre-entered from the institution It can be inferred that it may have been

The server 100 may select the contents of the hearing aid suitability test based on the basic information of the subject obtained from the subject device 200, for example, may select a level or difficulty of the test, the theme of the content for the test, and the like.

Also, the server 100 may acquire response information obtained from the target device 200 as a test operation for hearing aid fitting is performed. In this case, the response information may refer to information (eg, text information, or voice recording information, selection information, etc.) that the subject responds to in response to the fitness test provided by the server 100 during the hearing aid suitability operation.

The server 100 may perform artificial intelligence learning based on response information obtained from the target device 200 to generate a cognitive change model for each individual target. In addition, the server 100 may perform a hearing aid refit by performing a hearing aid suitability test suitable for the subject based on the artificial intelligence analysis result through the generated individual cognitive change model.

The server 100 may generate a cognitive change model trained according to each subject according to various embodiments, and after generating a cognitive change model for each subject characteristic, a method of selecting a cognitive change model corresponding to a characteristic of a subject can also be used.

The server 100 may transmit, to the organ-side device 300, a result value related to a cognitive change model generated based on test result information of a subject and response information obtained through an auditory test. The institution may refer to an institution that manages hearing characteristic information and hearing aid setting information of a subject, such as a hearing loss clinic.

The target device 200 may be implemented through various types of electronic devices capable of communication and data storage. For example, the target device 200 may be a smartphone, a tablet personal computer, a mobile phone, a video phone, an e-book reader, or a desktop personal computer. , laptop personal computer, netbook computer, workstation, server, personal digital assistant (PDA), portable multimedia player (PMP), MP3 player, mobile medical device, camera, Alternatively, it may include at least one of a wearable device. According to various embodiments, the wearable device may be an accessory type (eg, a watch, ring, bracelet, anklet, necklace, eyeglass, contact lens, or head-mounted-device (HMD)), a fabric or an integrated garment (HMD). It may include at least one of: electronic clothing), body attachable (eg skin pad or tattoo), or bioimplantable (eg implantable circuit).

In addition, although not shown in detail in the drawings, the subject device 200 may include various configurations for providing the subject device with data for a conformance test received from the server 100 . For example, the target device 200 includes a communication unit for communicating with the server 100, a storage unit for storing conformance test data provided from the server 100, and a display unit displaying visual content among conformance test data provided from the server 100 , an input unit that receives text input, selection information input, etc. from the subject among response information corresponding to the conformance test operation, an audio processing unit that receives the subject's voice information among the response information and outputs auditory content among the data for the conformance test, the subject It may be configured to include a sensor unit for acquiring information required to determine the concentration of the test.

Specifically, the display unit may include a panel, a hologram device, or a projector. The panel may be implemented, for example, to be flexible, transparent, or wearable. The panel may be composed of a touch panel and one module. The holographic device may display a three-dimensional image in the air using interference of light. A projector can display an image by projecting light onto a screen. The screen may be located inside or outside the electronic device, for example. According to an embodiment, the display unit may further include a control circuit for controlling the panel, the hologram device, or the projector.

The input unit may include, for example, a touch panel, a pen sensor, a key, or an ultrasonic input device. At least one of a method, a pressure sensitive method, an infrared method, and an ultrasonic method may be used.In addition, the touch panel may further include a control circuit. The touch panel further includes a tactile layer, so that the user can provide a tactile response.

The audio processing unit may interactively convert a sound and an electrical signal, for example. At least some components of the audio processing unit may be included in the input/output interface. The audio processing unit may process sound information input or output through, for example, a speaker, a receiver, an earphone, or a microphone.

The sensor unit may, for example, measure a physical quantity or sense an operating state of an electronic device, and convert the measured or sensed information into an electrical signal. The sensor unit may include, for example, a gesture sensor, a gyro sensor, a barometric pressure sensor, a magnetic sensor, an acceleration sensor, a grip sensor, a proximity sensor, a color sensor (eg, an RGB (red, green, blue) sensor), a biometric sensor, an on / It may include at least one of a humidity sensor, an illuminance sensor, and an ultra violet (UV) sensor. Additionally or alternatively, the sensor unit, for example, an olfactory sensor (E-nose sensor), an electromyography sensor (EMG sensor), an electroencephalogram sensor (EEG sensor), an electrocardiogram sensor (ECG sensor), an IR (infrared) a sensor, an iris sensor and/or a fingerprint sensor. The sensor unit may further include a control circuit for controlling at least one or more sensors included therein. In some embodiments, the electronic device may further include a processor configured to control the sensor unit, as part of the processor or separately, to control the sensor unit while the processor is in a sleep state.

According to various embodiments of the present disclosure, the sensor unit of the target device 200 may perform a sensing operation to detect a user's movement, a change in the external environment, a change in the user's emotion, and the like while the conformance test is in progress. Information on movement, emotional change, and environmental change detected through the sensor unit during the conformance test may be used to determine the concentration of the conformance test and to determine the reliability of response information obtained during the conformance test operation.

Previously, the operation performed through the server 100 was briefly described, but for a more detailed description, reference will be made to FIGS. 2 to 3 .

2 is a diagram illustrating the configuration of a server according to an embodiment of the present invention.

2, the server 100 according to an embodiment of the present invention includes a communication unit 110, a storage unit 120, a subject basic information obtaining unit 131, a conformance test performing unit 132, a response information obtaining unit 133, an artificial intelligence analysis unit 134, It may be configured to include a hearing aid suitability setting unit 135 and a suitable model setting unit 136 .

The communication unit 110 may use a network for data transmission/reception between the user device and the server, and the type of the network is not particularly limited. The network may be, for example, an IP (Internet Protocol) network that provides a large-capacity data transmission/reception service through Internet Protocol (IP) or an All IP network that integrates different IP networks. In addition, the network includes a wired network, a Wibro (Wireless Broadband) network, a mobile communication network including WCDMA, a High Speed Downlink Packet Access (HSDPA) network, and a Long Term Evolution (LTE) network including a mobile communication network, LTE advanced (LTE-A) ), a mobile communication network including 5G (Five Generation), a satellite communication network, and a Wi-Fi network, or a combination of at least one or more of them.

The communication unit 110 according to an embodiment of the present invention may communicate with the target device 200 and the organ-side device 300 . In detail, the communication unit 110 may receive basic information related to the subject's hearing ability, response information during a fitness test of the subject, and the like, from the subject device 200 . In addition, the communication unit 110 may transmit a result value obtained by performing an artificial intelligence-based analysis by the server 100 to the device 300 of the institution based on subject-related information.

The storage unit 120 may include, for example, an internal memory or an external memory. The internal memory includes, for example, a volatile memory (eg, dynamic RAM (DRAM), static RAM (SRAM), or synchronous dynamic RAM (SDRAM), etc.), non-volatile memory (eg, OTPROM (one time programmable ROM), programmable ROM (PROM), erasable and programmable ROM (EPROM), electrically erasable and programmable ROM (EEPROM), mask ROM, flash ROM, flash memory (such as NAND flash or NOR flash), hard drive, or a solid state drive (SSD).

External memory is a flash drive, for example, CF (compact flash), SD (secure digital), Micro-SD (micro secure digital), Mini-SD (mini secure digital), XD (extreme digital), It may further include a multi-media card (MMC) or a memory stick. The external memory may be functionally and/or physically connected to the electronic device through various interfaces.

The storage unit 120 according to an embodiment of the present invention may store algorithms and data required for artificial intelligence analysis.

Also, the storage unit 120 may store basic information for each subject and response information of the subject obtained from the subject device 200 . In addition, the storage unit 120 may store a setting value according to the hearing aid refit of the subject calculated through the artificial intelligence model.

The subject basic information obtaining unit 131 may perform an operation of obtaining, from the subject device 200, characteristic information related to hearing loss of a person with hearing loss who is a subject suitable for a hearing aid.

According to an embodiment, the subject basic information obtaining unit 131 may request the subject's basic information in the step of the target device 200 logging in to an application or web supported by the server 100 or requesting hearing aid refit in an online environment. Accordingly, the target device 200 may transmit the requested basic information of the target to the server 100 side.

The subject basic information obtaining unit 131 may obtain various types of basic information from the subject device 200, and the basic information may include the subject's age group, the cause of hearing loss, the degree of hearing loss, the type of hearing loss, the hearing aid wearing period, etc. . The obtained basic information of the subject may be used to select data for the initial fitness test. For example, a subject's degree of hearing loss may be utilized to select a stage or level of initial hearing aid fit test material.

The subject basic information obtaining unit 131 may obtain information on the subject's physical state related to hearing aid fitting. Accordingly, the subject basic information obtaining unit 131 may conduct a predetermined survey to the subject in order to obtain basic information required for hearing aid fit, and obtain basic information related to the physical condition through a response corresponding to the survey. can For example, 'Have you had otitis media recently?' A questionnaire related to physical characteristics related to wearing a hearing aid, such as a hearing aid, may be attempted, and a response of the subject may be obtained in response thereto. These physical characteristics may be considered to determine whether attention needs to be paid when resetting the hearing aid setting value by estimating the state of the eardrum. Also, basic information related to physical characteristics may be considered to determine whether the material, shape, etc. of the hearing aid insertion part are changed when the hearing aid is refitted. In addition, basic information related to physical characteristics may be considered to determine whether a subject is capable of remotely performing hearing aid refitting or whether a visit to an institution is required for treatment.

In addition, the basic information may include information about a setting state of a hearing aid currently worn by the subject. Hearing aid settings can be set including items such as noise cancellation threshold, low volume (eg, first-stage sound) gain, low-pitched threshold, loud (eg, second-level sound) gain, loudness threshold, and sound compression ratio. can

The conformance test performing unit 132 may provide data for a conformance test to the subject device when a hearing aid conformance test is requested from the subject device 200, but may provide test data in response to the subject's auditory characteristics. As described above, the suitability test performing unit 132 selects and provides a type of data for a hearing aid suitability test in response to items related to auditory characteristics (eg, degree of hearing loss, cause of hearing loss, etc.) among the acquired basic information of the subject. can do.

The operation of the conformance test performing unit 132 selecting data for the conformance test based on the auditory characteristics included in the basic information may be performed in an initial conformance test step.

The conformance test performing unit 132 may also determine whether the subject's previous conformance test history exists. If the subject's previous conformance test history exists, the conformance test performing unit 132 is configured to perform conformance test data according to the subject's subsequent test step information obtained through an artificial intelligence model learned based on the response information obtained during the previous test operation. can be selected.

According to various embodiments of the present disclosure, the conformance test performing unit 132 may differentiate a method for selecting characteristic values (eg, test difficulty, test duration, etc.) of conformance test data according to the presence or absence of a conformance test history of the subject. In the case of a subject who does not have a previous conformance test history, the feature value selection of the initial conformance test data may be performed based on only the auditory feature information included in the basic information. On the other hand, in the case of a subject having a previous conformance test history, a cognitive change model corresponding to the subject's characteristics will exist, so that a conformance test characteristic value may be selected according to a value calculated through the corresponding cognitive change model. For example, if the test difficulty of the 2nd, 4th, and 6th stages of a specific subject has been sequentially performed in the hearing aid fit stage, and the current stage suitability test characteristic value calculated according to the cognitive change model is stage 8, the fit test Accordingly, the performing unit 132 may provide the test data of step 8 to the subject. When test data having a specific characteristic value is provided to the subject through this process, the server 100 may later calculate a hearing aid setting value optimized for the subject through a predetermined detailed fitting process based on the result of the provided test.

The response information obtaining unit 133 may obtain response information of the subject obtained from the subject device while a conformance test operation is performed. In this case, the response information may include recording information, text information, and selection information (correct answer check information for a problem) input by the subject in response to data provided during the conformance test.

The response information obtaining unit 133 may classify the response information input by the subject for each item according to the attribute, and calculate a result of the conformance test. For example, the response information acquisition unit 133 may classify the acquired response information of the subject into recording data, text data, selection data, and the like. In addition, the response information obtaining unit 133 may evaluate the overall test result, test participation rate, concentration, etc. of the subject by comparing the obtained subject's response information with the provided conformity test data.

Also, the response information acquisition unit 133 may acquire response information corresponding to the degree of elapse of the subjects' fitness test and hearing aid wearing period (eg, the number of test cycles, the number of months elapsed from the hearing aid wearing date, etc.).

The artificial intelligence analysis unit 134 may diagnose the state of the subject's hearing ability based on the artificial intelligence algorithm, and may predict the possibility of a change level of the auditory function in the future.

The configuration of the artificial intelligence analysis unit 134 will be described in more detail with reference to FIG. 3 below.

In addition, the hearing aid suitability setting unit 135 selects a cognitive change model corresponding to the auditory characteristic of a subject from among the artificial intelligence models (cognitive change model) learned by the artificial intelligence analysis unit 134, and responds to the selected cognitive change model By completing detailed fitting obtained by inputting information, it is possible to calculate a setting value to be finally applied to the subject's hearing aid.

Specifically, the hearing aid suitability setting unit 135 according to an embodiment may first check the hearing aid setting value of the subject before refitting. The main setting value items of the hearing aid worn by the subject are, for example, noise reduction threshold, low volume (eg, first-stage sound) gain, low-pitched sound threshold, loud (second-level sound) gain, loud sound threshold, sound compression ratio, etc. It may be composed of

In addition, the hearing aid suitability setting unit 135 includes a result value analyzed by the artificial intelligence analysis unit 134 (eg, a result value analyzed by inputting response information to the cognitive change model, item information in which the rate of change of cognitive ability value is greater than or equal to the reference value) and the subject's test By combining the result values (eg, test scores for each question, etc.), the hearing aid settings can be adjusted and reset in detail.

In addition, the fitting model setting unit 136 is configured to observe the subject's response after the hearing aid is fitted, and to provide feedback on the hearing aid fitting operation in response to the subject's response.

Specifically, the fitted model setting unit 136 may include an effect data collecting unit 136a and a fitted model correcting unit 136b.

A more detailed description of the configuration of the suitable model setting unit 136 will be described with reference to FIG. 4 .

Hereinafter, the description of the artificial intelligence analysis unit 134 will be described in detail with reference to FIG. 3 .

3 is a diagram illustrating the configuration of an artificial intelligence analysis unit according to an embodiment of the present invention.

3 , the artificial intelligence analysis unit 134 may include a data selection unit 134a, a model training unit 134b, and an analysis execution unit 134c.

First, the data selection unit 134a may select the subject's response information and the subject's basic information obtained from the subject device during the conformance test for each item to be input to AI learning.

The data selector 134a may perform a pre-processing operation of the input data before performing the AI model learning. At this time, for the pre-processing, the obtained response information may be classified by input items. For example, the data selector 134a may classify the obtained response information for each subject, and classify the response information obtained from a plurality of subjects according to the hearing aid suitability test order. Alternatively, the data selector 134a may classify response information obtained from a plurality of subjects by hearing aid wearing period, for example, into response information of subjects who have been 6 months old and response information of subjects who have worn hearing aids for more than a year.

The model training unit 134b may generate a cognitive change model of the subject based on artificial intelligence. The model training unit 134b may train a cognitive change model using a Recurrent Neural Network (RNN) called a recurrent neural network according to an embodiment of the present invention.

The RNN is known as a neural network that has strength in processing ordered data, such as natural language processing or speech recognition, unlike other neural networks that process state-fixed data. Accordingly, when it is desired to guess the next information from the previous information, a prediction program can be generated using the RNN.

The basic structure of the RNN will be described with reference to FIG. 6 .

6 is a diagram for explaining the concept of an artificial intelligence model according to an embodiment of the present invention.

Referring to FIG. 6 , a single neural network represented by 'A' is called a 'cell', and the RNN creates a deep neural network by overlapping several such cells. As a result, the RNN uses the results learned in the previous step for learning in the next step. According to the RNN structure, it has a memory layer called a 'hidden state'. can And in RNN, whenever new input data is input, the neural network modifies the memory, and after processing all input data, the memory left in the neural network becomes information summarizing the entire sequence.

According to the computational process in RNN, when the first input data is input, the first memory is created, and when the second input data comes in, a new memory is created by referring to the existing memory and the new input data. Each memory becomes information that summarizes the input data up to that point. The RNN generates an output based on this summarized information.

The model training unit 134b may train a cognitive change model of subjects based on the RNN-type artificial neural network. Due to the characteristics of the RNN, it is necessary for the model training unit 134b to input the data to be trained in stages in the process of learning the RNN-type cognitive change model. In this case, according to an embodiment, the model training unit 134b may sequentially input learning data in response to a temporal element related to hearing loss of a subject to learn. In addition, a plurality of such cognitive change models may be generated according to learning content or learning field.

More specifically, for example, the model training unit 134b may train the subjects' cognitive change model for a specific question. At this time, when the first learning data is input, the answer completion value is input during the first fitness test for the specific question, As the second learning data, the learning operation can be performed by inputting the answer completeness value in the second suitability test for the same question.

In this way, the model training unit 134b may generate a cognitive change model capable of predicting an answer completeness value for a corresponding question of an arbitrary subject who has performed the n-th fitness test. And through the cognitive change model generated in this way, an answer completeness value for a specific question of an arbitrary subject scheduled for the n-th fitness test may be predicted.

The above example is only described to explain the learning and utilization of the cognitive change model, and the fact that the cognitive change model is designed for arbitrary questions and that the answer completeness value for a specific question is input as learning data is sufficient Items that can be configured differently.

Instead of items, multiple cognitive change models may be generated according to attributes such as the age of the subject and the cause of the subject's hearing loss. In addition, the order of sequentially input learning data may be set according to a period of time elapsed from the wearing time of the hearing aid device or a period elapsed from the start date of treatment for hearing loss, etc. as well as the suitability test cycle.

The analysis performing unit 134c selects a model corresponding to the characteristics of the subject to be analyzed from among previously generated cognitive change models, and inputs response information corresponding to the subject to be analyzed to the selected model to detect a change in the subject's auditory state in the future predictable.

For example, the analysis performing unit 134c may calculate a change in the subject's hearing state as a specific value such as a numerical value in the future, and the calculated result value may mean the degree of adjustment of the subject's hearing aid setting value. . And accordingly, the result value can be used to determine the characteristic values of the test data (eg, the theme of the data for the conformance test, the difficulty of the test data, the main test type, etc.) when the subject performs the conformity test to be performed later. there is.

Hereinafter, the suitable model setting unit 136 will be described in more detail with reference to FIG. 4 .

4 is a diagram illustrating the configuration of a suitable model setting unit according to an embodiment of the present invention.

As shown in FIG. 4 , the fitted model setting unit 136 according to an embodiment of the present invention may include an effect data collecting unit 136a and a fitted model correcting unit 136b.

The fit model setting unit 136 may acquire information on use after hearing aid fitting is completed in response to a hearing aid fitting request of the subject, and evaluate the appropriateness of the hearing aid fitting operation based on this.

To this end, the effect data collection unit 136a may collect evaluation information on the hearing aid suitability of the subject for a preset period after the hearing aid fitting operation. To this end, the effect data collection unit 136a may provide a push notification requesting evaluation of the suitability of the setting value applied when the hearing aid is fitted according to a preset period for a reference period to the target device 200 . In addition, the subject can evaluate the suitability of the hearing aid by accessing the hearing aid fitting app or web supported by the server 100 through the notification. In this way, the effect data collection unit 136a may collect data required to evaluate the degree of completion of hearing aid fitting from a subject who has completed hearing aid fitting.

According to various embodiments of the present disclosure, the effect data collection unit 136a may check the problem situation of the hearing aid fitting operation in the previous stage when a subject requesting to fit the hearing aid again within the reference period occurs, and collect case information recognized as the problem situation. It can be used to calculate the completeness of fit.

The effect data collection unit 136a may acquire hearing aid setting value change information of subjects whose hearing aid suitability operation is re-requested within a reference period or to whom complaints have been received.

The fitting model corrector 136b may set a hearing aid fitting model based primarily on the subject's test response information and artificial intelligence analysis result value. In addition, the hearing aid fitting model may be corrected by correcting a value for an item in which an error is confirmed based on the effect data collected by the effect data collection unit 136a.

The hearing aid fitting model generated by the fitting model corrector 136b may be used to determine and evaluate the reliability of the hearing aid fitting result.

5 is a diagram illustrating a sequence of a hearing aid fitting operation using artificial intelligence according to an embodiment of the present invention.

As shown in FIG. 5 , the server 100 of the hearing aid fitting system of the present invention may first perform operation 505 of acquiring basic information about a subject.

Thereafter, the server 100 may perform operation 510 of performing a hearing aid suitability test according to a hearing aid suitability request from the target device 200 side. The suitability test may include items that allow the subject to determine whether the corrected hearing through the currently worn hearing aid is good, whether adjustment of a specific hearing aid setting value is required, and the like.

The server 100 may then perform operation 515 of obtaining response information corresponding to the conformance test from the subject while performing the conformance test.

In addition, the server 100 may perform operation 520 of performing artificial intelligence analysis based on the obtained response information.

Specifically, the AI analysis operation may perform an operation for analyzing the degree of change in the subject's hearing ability, which is changed according to the subject's suitability test order, the period of wearing a hearing aid, and the like. In order to effectively analyze such sequence data, the server 100 may utilize a recurrent neural network (RNN) for artificial intelligence analysis.

Thereafter, the server may perform operation 525 of refitting the hearing aid in response to the artificial intelligence analysis result and correcting the fitted model.

In addition, the server 100 performs artificial intelligence analysis by inputting the response information obtained from a specific subject to the artificial intelligence model based on the recurrent neural network in the step 525, and as a result of the analysis, data characteristic value information for subsequent tests suitable for the subject, corresponding It may include an operation of transmitting a result value, such as an estimate of the subject's future auditory ability change, to the organ-side device 300 . In this case, the organ-side device 300 means an institution that periodically diagnoses the subject's hearing ability status and supports the periodic fit of the hearing aid, such as a hearing loss clinic. Guidance regarding a hearing aid refit schedule and whether or not to change a hearing aid in the future may be provided to the subject.

In short, the hearing aid fitting system according to an embodiment of the present invention includes a server and a target device, and the server provides hearing aid fitting test data to the target device in response to a hearing aid fitting request from the target device, The subject's cognitive change model is learned based on the response information obtained during the hearing aid fit test, and the response information is input to the previously learned cognitive change model to quantify the subject's hearing ability change. , the hearing aid setting value may be reset in response to the result value.

And the server obtains basic information of the subject requesting hearing aid fit from the subject device, including the age of the subject, the cause of hearing loss, the degree of hearing loss, the type of hearing loss, and the period of wearing the hearing aid as the basic information. It may include a basic information obtaining unit, a response information obtaining unit which obtains response information of the subject obtained from the subject device while the conformance test is performed, and obtains response information in response to the degree of lapse of the conformity test order and the hearing aid wearing period there is.

In this case, the subject basic information acquisition unit may acquire basic information on physical characteristics related to wearing the hearing aid in order to determine the necessity of changing the hearing aid and the need for visiting treatment when the hearing aid is refitted.

And the server performs artificial intelligence learning based on the subject's response information obtained from the subject device to generate a cognitive change model for each auditory characteristic, and input the subject's response information to the cognitive change model created as a result of the learning. It may include an artificial intelligence analysis unit for predicting a change in the subject's auditory characteristics through performing artificial intelligence analysis, wherein the artificial paper analysis unit learns artificial intelligence based on the subject's response information and the subject's basic information obtained from the subject device A data selection unit that selects each item to be input to the program, a model training unit that trains a cognitive change model of subjects based on an artificial neural network of the RNN method, and sequentially inputs learning data according to the flow of a subject's hearing loss-related temporal elements to learn and an analysis performing unit that selects a model corresponding to the characteristics of the subject to be analyzed among the previously generated cognitive change models, and predicts the change in the subject's auditory state in the future by inputting response information corresponding to the subject to be analyzed to the selected model may be included.

And the server includes a model setting unit for evaluating the suitability of the hearing aid fit by acquiring the use information after the hearing aid fit of the subject is completed, wherein the fit model setting unit provides information on the hearing aid fit of the subjects for a preset period after the hearing aid fitting is completed A hearing aid fitting effect data collection unit that collects evaluation information and acquires information on changing the hearing aid setting values of subjects who have undergone hearing aid refit within the reference period, and sets up a hearing aid fit model based on the subject’s test response information and artificial intelligence analysis results However, based on the effect data collected by the effect data collection unit, a suitable model correction unit for correcting the hearing aid suitable model by correcting a value for an item in which an error is confirmed may be included.

Although the present invention has been described in detail with reference to the above-described examples, those skilled in the art can make modifications, changes, and modifications to the examples without departing from the scope of the present invention. In short, in order to achieve the intended effect of the present invention, it is not necessary to separately include all the functional blocks shown in the drawings or follow all the orders shown in the drawings. Note that it may fall within the scope.

100 : server
110: communication department
120: storage
131: subject basic information acquisition unit
132: conformance test execution unit
133: response information acquisition unit
134: artificial intelligence analysis unit
134a: data selection unit
134b: Model Training Department
134c: analysis execution unit
135: hearing aid suitable setting unit
136: suitable model setting unit
136a: effect data collection unit
136b: fit model correction unit

Claims (9)

In a system comprising a server and a target device,
the server is
A hearing aid fitting test data is provided to the target device in response to a hearing aid fitting request from the target device, and a cognitive change model of the target is trained based on the response information obtained while the hearing aid fitting test is performed. A hearing aid fitting system that inputs response information into the cognitive change model, calculates a result value quantifying the degree of change in the subject's hearing ability, and resets a hearing aid setting value in response to the result value. The method of claim 1,
the server is
A subject basic information acquisition unit that acquires basic information of a subject requesting hearing aid fit from the subject device, including the subject's age group, cause of hearing loss, degree of hearing loss, type of hearing loss, and duration of wearing a hearing aid as the basic information ;
A response information acquisition unit that acquires response information of a subject obtained from the subject device while a conformance test is performed, and obtains response information in response to a degree of lapse of a conformity test order and a hearing aid wearing period; characterized in that it comprises a; Hearing Aid Fit System. 3. The method of claim 2,
The subject basic information acquisition unit
A hearing aid fitting system comprising: acquiring basic information on physical characteristics related to wearing a hearing aid in order to determine the necessity of changing the hearing aid and the need for visit treatment when the hearing aid is refitted. The method of claim 1,
the server is
Based on the subject's response information obtained from the subject device, artificial intelligence learning is performed to generate a cognitive change model for each auditory characteristic, and artificial intelligence analysis is performed by inputting the subject's response information to the cognitive change model created as a result of the learning. Hearing aid fitting system comprising: an artificial intelligence analysis unit that predicts a change in the subject's auditory characteristics through performing. 5. The method of claim 4,
The artificial paper analysis unit
a data selection unit that selects the subject's response information and the subject's basic information obtained from the subject device for each item to be input to AI learning;
a model training unit for learning a cognitive change model of subjects based on an RNN-type artificial neural network, and sequentially inputting learning data according to the flow of a subject's hearing loss-related temporal elements; and
an analysis performing unit that selects a model corresponding to the characteristics of the subject to be analyzed among the previously generated cognitive change models, and predicts a change in the subject's auditory state in the future by inputting response information corresponding to the subject to be analyzed to the selected model; Hearing aid fitting system comprising a. The method of claim 1,
the server is
A model setting unit for evaluating the adequacy of hearing aid fitting by acquiring information on use after the subject's hearing aid fitting is completed,
The suitable model setting unit
a hearing aid suitability effect data collection unit that collects evaluation information on the hearing aid suitability of subjects for a preset period after hearing aid fit is completed, and acquires information on changing hearing aid settings of subjects who have undergone hearing aid refit within a reference period; and
A hearing aid fitting model is set based on the subject's test response information and artificial intelligence analysis result value, but the hearing aid fitting model is established by correcting the values for items whose errors are confirmed based on the effect data collected by the effect data collection unit. Hearing aid fitting system comprising: a fitting model correcting unit for correcting. A system comprising a server, a subject device, and an organ-side device,
the server is
A hearing aid fitting test data is provided to the target device in response to a hearing aid fitting request from the target device, and a cognitive change model of the target is trained based on the response information obtained while the hearing aid fitting test is performed. By inputting response information to the cognitive change model, a result value obtained by quantifying the degree of change in the subject's hearing ability is calculated, and the hearing aid setting value is reset in response to the result value,
Hearing aid fitting system, characterized in that the result value is transmitted to the organ-side device. In response to the hearing aid suitability request from the subject device, the hearing aid fit test data is provided to the subject device, the subject's cognitive change model is trained based on the response information obtained during the hearing aid fit test, and the previously learned A hearing aid suitable server, characterized in that by inputting response information into the cognitive change model, calculating a result value obtained by quantifying the degree of change in the subject's hearing ability, and resetting the hearing aid setting value in response to the result value. A hearing aid fitting test data is provided to the target device in response to a hearing aid fitting request from the target device, and the subject's cognitive change model is trained based on the response information obtained while the hearing aid fitting test is performed. By inputting the response information to the cognitive change model, the result value of the degree of change in the subject's hearing ability is calculated numerically, the hearing aid setting value is reset in response to the result value, and the result value is transmitted to the organ-side device that manages the subject. Hearing aid-compatible server, characterized in that it delivers.

Images