# US 2022/0286796 A1 · Fitting agent and method of determining hearing device parameters

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2022/0286796 A1
- Document ID: US20220286796A1
- Status: Published application
- Kind: A1
- Application number: 17/673,134
- Filed: 2022-02-16
- Published: 2022-09-08
- Earliest claimed: 2021-02-26
- Assignees: GN Hearing A/S
- Applicants: GN Hearing A/S
- Inventors: Tanya IGNATENKO; Kirill KONDRASHOV
- Web page: https://patentgrep.com/patent/US20220286796A1

## CPC

- H04R 25/70: {Adaptation of deaf aid to hearing loss, e.g. initial electronic fitting}
- H04R 29/001: {for loudspeakers (H04R29/007 takes precedence)}
- H04R 29/008: {Visual indication of individual signal levels (visual indication of stereophonic sound image H04S7/40)}
- H04R 2225/55: Communication between hearing aids and external devices via a network for data exchange
- H04R: LOUDSPEAKERS, MICROPHONES, GRAMOPHONE PICK-UPS OR LIKE ACOUSTIC ELECTROMECHANICAL TRANSDUCERS; ELECTRIC HEARING AIDS; PUBLIC ADDRESS SYSTEMS (producing sounds with frequency not determined by supply frequency G10K)

## Abstract

A fitting agent for a hearing device and related method is disclosed, wherein the fitting agent is configured to initialize a user model comprising a user preference function; obtain a primary test setting for the hearing device; obtain a secondary test setting for the hearing device; present the primary test setting and the secondary test setting to a user; detect a user input of a preferred test setting indicative of a preference for either the primary test setting or the secondary test setting; and update the user model based on hearing device parameters of the preferred test setting, wherein to obtain the secondary test setting comprises: obtain a candidate set of candidate test settings; determine an uncertainty parameter for each candidate test setting; and select the secondary test setting from the candidate set of candidate test settings based on the uncertainty parameters of the candidate test settings.

## Claims

### Claim 1

An apparatus comprising:
an output interface configured to provide a primary test setting and a secondary test setting for presentation to a user;
an input interface configured to obtain a user input indicative of a preference for either the primary test setting or the secondary test setting as a preferred test setting;
a processing unit configured to update a user model based on a hearing device parameter associated with the preferred test setting, the user model comprising a user preference function and user response distribution;
wherein the processing unit is configured to obtain the secondary test setting by:
obtaining a set of candidate test settings;
determining uncertainty parameters respectively for the candidate test settings; and
selecting one of the candidate test settings as the secondary test setting based on one or more of the uncertainty parameters of the candidate test settings.

### Claim 2 (depends on 1)

The apparatus according to claim 1, wherein the processing unit is configured to determine the uncertainty parameters respectively for the candidate test settings by applying a predictor for each of the candidate test settings.

### Claim 3 (depends on 2)

The apparatus according to claim 2, wherein the predictor for each of the candidate test settings is a weighted distribution function.

### Claim 4 (depends on 1)

The apparatus according to claim 1, wherein the processing unit is configured to select the one of the candidate test settings having the largest uncertainty parameter as the secondary test setting.

### Claim 5 (depends on 1)

The apparatus according to claim 1, wherein the processing unit is configured to obtain the set of candidate test settings by sampling a posterior distribution.

### Claim 6 (depends on 1)

The apparatus according to claim 1, wherein the processing unit is configured to determine whether a stopping criterion is satisfied; and
after a determination that the stopping criterion is satisfied, updating the hearing device based on the updated user model.

### Claim 7 (depends on 6)

The apparatus according to claim 6, wherein the stopping criterion is based on a normalized weighted information divergence.

### Claim 8 (depends on 7)

The apparatus according to claim 7, wherein the normalized weighted information divergence comprises a Kullback-Leibler (KL) divergence.

### Claim 9 (depends on 1)

The apparatus according to claim 1, wherein the processing unit is configured to update a predictor based on the hearing device parameter associated with the preferred test setting.

### Claim 10 (depends on 1)

The apparatus according to claim 1, wherein the set of candidate test settings comprises at least five candidate test settings.

### Claim 11 (depends on 1)

The apparatus according to claim 1, wherein the user model is based on a first assumption and a second assumption, wherein the first assumption is that the user preference function is a unimodal preference function, and the second assumption is that the user can be uncertain about preference.

### Claim 12 (depends on 1)

The apparatus according to claim 1, wherein the user preference function ƒ(ø) is given by:
ƒ(x;θ,Λ)=−((x−θ)TΛ(x−θ))s,
where x is an M-dimensional vector in a hypercube └0,1┘M that represents M hearing device parameters of the hearing device, θ is a maximizing argument of ƒ, Λ is a positive definite M×M scaling matrix characterizing user sensitivity to hearing device parameter changes, wherein M is an integer, and s is a real-valued exponent in a range from 0.01 to 0.99.

### Claim 13

A method comprising:
obtaining a user model comprising a user preference function;
obtaining a primary test setting for a hearing device;
obtaining a secondary test setting for the hearing device;
outputting the primary test setting and the secondary test setting for presentation to a user;
obtaining a user input of indicative of a preference for either the primary test setting or the secondary test setting as a preferred test setting; and
updating the user model based on a hearing device parameter associated with the preferred test setting;
wherein the act of obtaining the secondary test setting comprises:
obtaining a set of candidate test settings;
determining uncertainty parameters respectively for the candidate test settings; and
selecting one of the candidate test settings as the secondary test setting based on one or more of the uncertainty parameters of the candidate test settings.

### Claim 14 (depends on 13)

A fitting agent configured to perform the method of claim 13.

### Claim 15 (depends on 1)

The apparatus according to claim 1, wherein the apparatus comprises an electronic device, a server device, the hearing device, or any combination of the foregoing.
