Methods for operating a hearing system

Abstract

The invention relates to a method for operating a hearing system (2), comprising a hearing aid (4) and a remote interaction unit (6) with a user interface (44) for inputting a hearing system-related user request (56, 56a, 56b), a linguistic data processing unit (36) coupled to the user interface (44), a data cloud (40) coupled to the linguistic data processing unit (36) with a database (42) in which answers (68, 68a, 68b) for the user request (56, 56a, 56b) are stored, wherein, upon input of a hearing aid-related user request (56, 56a, 56b), the content of the user request (56, 56a, 56b) is analyzed by means of the linguistic data processing unit (36) and a request (66, 66a, 66b) is sent to the data cloud (40). (40) based on the query (66, 66a, 66b) an answer (68, 68a, 68b) is selected from the database (42), the answer (68, 68a, 68b) is sent to the linguistic data processing (36),The linguistic data processing (36) generates an output (70, 70a, 70b) based on the response (68, 68a, 68b) and sends it to the remote interaction unit (6), and the output (70, 70a, 70b) is displayed by the remote interaction unit (6).

Description

[0001] The invention relates to a method for operating a hearing system comprising a hearing aid and a remote interaction unit. The invention further relates to a hearing system for implementing the method.

[0002] The term “hearing system” or “hearing device” refers to a single device or a group of devices and, where applicable, non-physical functional units, which, when in operation, provide (hearing) functions to a person using the hearing system (hereinafter referred to as the “(hearing system) user” or “(hearing system) user”). In the simplest case, the hearing system can consist of a single hearing aid. Alternatively, the hearing system can comprise two hearing aids working together to supply the user’s two ears. In this case, it is referred to as a “binaural hearing system” or “binaural hearing aid.” The hearing system can also include external components, for example, an additional device such as an ear coupling, telephone interface, hearing aid accessory, a smartphone, or a smartphone app.

[0003] A hearing aid is generally defined as an electronic device that supports the hearing of a person wearing the hearing aid. In particular, the invention relates to a hearing aid designed to fully or partially compensate for the hearing loss of a hearing-impaired user. Such a hearing aid is also referred to as a "hearing aid" (HA). There are also hearing aids designed to protect or improve the hearing of users with normal hearing, for example, to enable improved speech understanding in complex listening situations. Such devices are also referred to as "personal sound amplification products" (PSAPs for short). Finally, the term "hearing aid" as used here also includes headphones worn on or in the ear (wired or wireless, with or without active noise cancellation), headsets, etc., as well as implantable hearing aids such as cochlear implants.

[0004] Hearing aids in general, and hearing aid devices in particular, are usually designed to be worn on the user's head, particularly in or on one ear, particularly as behind-the-ear (BTE) or in-the-ear (ITE) devices. Due to their internal structure, hearing aids typically have at least one output transducer that converts an input audio signal into a signal perceivable by the user as sound, and then outputs the latter to the user.

[0005] In most cases, the output transducer is designed as an electro-acoustic transducer that converts the (electrical) output audio signal into airborne sound, which is then emitted into the user's ear canal. In a hearing aid worn behind the ear, the output transducer, also known as the "receiver," is usually integrated outside the ear in a hearing aid housing. In this case, the sound emitted by the output transducer is guided into the user's ear canal via a sound tube. Alternatively, the output transducer can be located in the ear canal, and thus outside the housing worn behind the ear. Such hearing aids are also referred to as "Receiver In Channel" devices.Hearing aids worn in the ear, which are so small that they do not protrude beyond the ear canal, are also called CIC devices (after the English term “Completely in Canal”).

[0006] In other designs, the output transducer can also be an electromechanical transducer that converts the output audio signal into structure-borne sound (vibrations), which is then transmitted, for example, to the user's skull. There are also implantable hearing aids, particularly cochlear implants, and hearing aids whose output transducers directly stimulate the user's auditory nerve.

[0007] In addition to the output transducer, a hearing aid often has at least one (acousto-electrical) input transducer. During operation of the hearing aid, the or each input transducer picks up airborne sound from the hearing aid's environment and converts this airborne sound into an input audio signal (i.e., an electrical signal that conveys information about the ambient sound). This input audio signal - also referred to as the "picked up sound signal" - is regularly output to the user in its original or processed form, e.g., to implement a so-called transparency mode in headphones, for active noise cancellation, or - e.g., in a hearing aid - to achieve improved noise perception for the user.

[0008] In addition, a hearing aid often has a signal processing unit (signal processor). The signal processing unit processes the or each input audio signal (i.e., modifies its sound information). The signal processing unit then outputs a correspondingly processed audio signal (also referred to as the "output audio signal" or "modified sound signal") to the output transducer and / or to an external device.

[0009] Hearing aid users face various challenges when using their hearing systems. Typical challenges include (temporary) hearing aid malfunction, often due to dirt and sweat; difficulties setting up and maintaining a smartphone connection to the hearing aid, for example, for streaming music and making phone calls; dissatisfaction with the amplified sound characteristics and usability of the hearing aid itself or a connected ear coupling or charger.

[0010] The hearing aid acoustician is often the first point of contact for solving problems of this kind, but they can only be contacted to a limited extent. In particular, the hearing aid acoustician may not be available when the problem occurs.

[0011] Digital self-learning solutions as part of a smartphone app for hearing aids or on websites are always available, but the right solution for the actual problem is difficult to find when it is typically contained in FAQ lists or a menu navigation.

[0012] Recent advances in generative text processing and linguistic data processing have created the possibility of a human-like dialogue between the hearing aid wearer and an "always-on" AI. However, commercially available chatbots lack specific information for resolving hearing aid problems, thus limiting the quality of advice provided to the hearing aid user. Furthermore, the user's problems are often very specific to the actual hearing aid worn and also depend on how the system (i.e., hearing aid, ear coupling, app, phone interface, accessories) was previously fitted or used, thus limiting the usefulness of existing chatbots for finding solutions to hearing aid problems.

[0013] The invention is based on the object of providing a particularly suitable method for operating a hearing system. In particular, solutions for hearing system-specific problems are to be provided as simply, reliably, and always available as possible. The invention is further based on the object of providing a particularly suitable hearing aid for implementing the method.

[0014] With regard to the method, the problem is solved according to the invention with the features of claim 1 and with regard to the hearing system with the features of claim 8. Advantageous embodiments and further developments are the subject of the dependent claims (subclaims).

[0015] The advantages and embodiments described with regard to the method can also be applied to the hearing system, and vice versa. Where method steps are described below, advantageous embodiments for the hearing system result, in particular, from the fact that the hearing system is designed to perform one or more of these method steps.

[0016] The invention relates to a method for operating a hearing system. The hearing system comprises at least one hearing aid and a remote interaction unit with a user interface. The user interface is provided and configured for inputting a hearing system-related user query.

[0017] In the preferred application, the hearing aid of the hearing system is a hearing aid designed for hearing impaired people. However, the invention is also fundamentally applicable to a hearing system with a "personal sound amplification device." The hearing aid is available in one of the designs mentioned above, in particular as a BTE, RIC, ITE, or CIC device. The hearing instrument can also be an implantable or vibrotactile hearing aid.

[0018] The hearing aid is designed to receive sound signals from the environment and transmit them to the user. The hearing aid has a hearing aid housing, which houses, for example, an input transducer, a signal processing device, and an output transducer. The housing is designed so that it can be worn by the user on the head and near the ear, e.g., in the ear, on the ear, or behind the ear.

[0019] The hearing aid has at least one acoustoelectrical input transducer, in particular a microphone, which is part of the receiving unit of the hearing system. During operation of the hearing aid, the input transducer receives sound signals (noises, tones, speech, etc.) from the environment and converts them into an electrical input signal (acoustic data). The output transducer, in particular an electroacoustic one, is designed, for example, as a (miniature) loudspeaker to generate an acoustic output signal based on an audio signal generated by the signal processing device.

[0020] The remote interaction unit can be integrated or implemented in a peripheral device separate from the hearing aid, e.g., a smartphone or tablet computer. Preferably, the remote interaction unit is designed in the form of a (hearing aid) app associated with and interacting with the hearing aid. The app is installed on a smartphone or other mobile device as intended. In this case, the smartphone or mobile device itself is usually not part of the hearing system, but is used by it merely as an external resource.

[0021] The hearing system has linguistic data processing coupled to the user interface. The user interface is, for example, a function of the remote interaction unit or the app. For example, the user interface is designed as a digital assistant. In particular, the user interface or the digital assistant is designed as a chat or chat window in which the hearing system user can enter inputs, particularly in text form, for example, using an on-screen keyboard in combination with a (smartphone) touchscreen.

[0022] A “chat” is understood here and below to mean, in particular, a text-based interaction between a hearing system user and the linguistic data processing system, in which communication takes place in natural language.

[0023] The user interface preferably includes a chat window, i.e., a graphical element within the software application or app that serves to display user interaction in the chat. The chat window is, in particular, the interface through which the hearing aid user interacts with the linguistic data processing system.

[0024] The user query is, in particular, a chat input, i.e., textual or linguistic information entered by the hearing system user into the chat window or user interface. This (chat) input can be written in natural language and serves to transmit a query or message to the linguistic data processing system. The chat input can contain questions, instructions, or general communication elements that are interpreted and processed by the linguistic data processing system to generate appropriate responses or actions. The user query is, for example, a problem description by the hearing system user regarding a problem they are having with the hearing system. The user query can also be a question about a specific function of the hearing system.

[0025] Natural Language Processing (NLP) is understood here and below to mean, in particular, the application of computer algorithms and techniques for analyzing and processing natural language to extract, understand, or generate semantic, syntactic, and pragmatic information from textual or linguistic data sources. This includes the use of generative artificial intelligence (AI), large language models (LLM), and other linguistic processing systems to efficiently and accurately perform tasks such as text classification, automated text generation, sentiment analysis, language understanding, and similar tasks.

[0026] Linguistic data processing is trained using common AI and NLP training methods. A typical example is the training of an LLM such as GPT-3, which uses a vast amount of text data from the internet as a training corpus. The model adjusts its weights and parameters to learn probabilities for the occurrence of words and word combinations. This method enables the model to respond to complex natural language inputs by generating context-appropriate and meaningful responses or text generation.

[0027] The linguistic data processing is integrated into a network connected to the remote interaction unit, for example, as software or algorithms on a server or in a data cloud. However, it is also conceivable that the linguistic data processing is integrated into a local computer device, for example, also in the remote interaction unit, so that no network or internet connection to a remote server or data cloud is necessary.

[0028] The hearing system also has a data cloud coupled with linguistic data processing with a database in which answers to the user query are stored.

[0029] A data cloud (also referred to as a cloud or computing cloud) is understood here and below to be a model that provides, on demand – usually via the internet and device-independently – shared computing resources as a service, such as servers, data storage, or applications. The provision and use of these computing resources is defined and usually occurs via a programming interface or, for users, via a website or a program (e.g., an app).

[0030] The linguistic data processing unit is preferably linked to the data cloud or database via an application programming interface (API). The linguistic data processing unit sends a query to the database via the application programming interface, and the database responds by sending an answer or solution back to the linguistic data processing unit via the application programming interface. The query can also be, for example, a (direct) database access by the linguistic data processing unit.

[0031] A "database" is understood here and below to mean, in particular, an organized and structured collection of electronic information that is stored and manageable in digital form. This information can include various types of data, such as text, numbers, graphics, or multimedia, and is designed to be efficiently retrieved, searched, and updated. In this process, the database serves as a central storage location for information that the hearing system or linguistic processing system accesses to provide answers or solutions to user queries.

[0032] The database is structured as a comprehensive hearing system topic repository, containing a multitude of answers or solutions to hearing aid-specific user queries. The database includes a generic repository of text and media, structured to cover the full range of solutions, depending on the query and different hearing aid configurations.

[0033] For example, the database contains at least twenty different topics, in particular at least forty topics, for example fifty topics, which are grouped into topic areas in a repository. For example, the repository contains six topic areas: Hearing Aid, Charger, Accessories, Data Connection, App Use, and Sound.

[0034] For example, answers to questions on the topic of "hearing aids" include battery runtime, beeps or whistling in hearing aids, cleaning hearing aids, inserting and removing hearing aids, turning hearing aids on and off, using a telecoil, a lost hearing aid, a malfunctioning hearing aid, recommended actions if a hearing aid gets wet, and hearing aid controls. Preferably, answers are provided for different hearing aid types or designs.

[0035] For example, answers to questions on the topic of "charger" include questions about a charger's LED display, a power plug, a power bank, wireless charging (e.g., via Qi), drying and cleaning, a charger that isn't charging, a defective or lost charger, or insufficient charging by the charger. Preferably, answers are provided for different charger types or designs.

[0036] For example, the topic "Accessories" contains answers about various additional devices that are paired or can be paired with the hearing aid. For example, there are answers about using streaming devices, such as a television (e.g., StreamlineTV), pairing the hearing aid with streaming devices, using a communication system, such as a telecoil (e.g., StreamLine Mic), pairing with a communication system, or a hearing aid control element, such as a remote control (e.g., miniPocket).

[0037] For example, the topic "data connection" contains answers about the wireless connectivity of the hearing aid and / or the remote interaction unit, such as LoRa, Bluetooth, WiFi, UWB, WLAN, magnetic induction (e.g., T-Coil), or the cellular network. Regarding a Bluetooth connection of the hearing aid, answers are provided about pairing, connection difficulties / problems, hands-free streaming, operating system-dependent streaming (e.g., Android streaming), or streaming configuration.

[0038] For example, the topic "App Usage" contains answers about a remote interaction unit implemented as an app or about app-controlled adjustment of hearing aid settings and parameters. For example, answers are provided about adjusting the hearing aid's sound balance, volume adjustment, directional adjustment, general app usage, changing a program, checking battery status, stored user health data, (tinnitus) masking, the user interface, app functions, or pairing the app with external devices (e.g., a smartwatch).

[0039] The topic area "Sound" relates to hearing aid settings or the fitting of the hearing aid. Responses are provided which are intended to bring about changes in the hearing aid settings linked to a sound-related problem / need, and which can be applied (directly) to the hearing aid (via a write connection) by the user interface or the remote interaction unit in order to resolve sound-related problems or requests. For example, the topic area stores for several different hearing aid types and / or remote interaction units whether, and if so, which settings can be influenced or changed by a remote interaction unit to resolve the query or problem. The responses are therefore primarily setting changes based on the identification of the sound sub-topic through dialogue with the hearing system user.

[0040] Here and in the following, an “answer” or “solution” is understood to mean in particular the result or output of the database in order to respond to a query.

[0041] According to the process, when a hearing aid-related user query is entered via the user interface, the content of the user query is first analyzed using linguistic data processing and a query is sent to the data cloud. The input or user query thus serves as a prompt for linguistic data processing, which then generates the query for the data cloud or database.

[0042] A "prompt" is understood here and below to mean, in particular, a text-based input or request for input that serves to stimulate linguistic processing to provide specific information, answers, or generated content, in particular to provide the (database) query. A prompt can be in the form of a sentence, a question, a request, or a text fragment and is used to retrieve an answer from the database. A prompt is processed, for example, by analyzing the content, followed by algorithmic query generation by the linguistic processing.

[0043] The data cloud then selects one of the stored responses from the database based on the query. If no response from the database can be assigned to the query, an error message such as "user query not understood" or "answer for user query not found" is selected as the response. The selected response is sent to the linguistic data processing unit, which generates an output based on the response and sends it to the remote interaction unit or user interface. Finally, the output is output by the remote interaction unit. This realizes a particularly suitable method for operating the hearing system.

[0044] The data cloud or database provides a hearing system-specific repository to a standard linguistic data processing engine, acting as a text-generating AI, which preferably covers the widest possible range of problems and questions of the hearing system user. The linguistic data processing engine uses this information as input to provide qualified answers or to optimize a dialogue between a chatbot and the hearing system user in order to solve the problem or answer a question. In particular, the linguistic data processing engine manages the dialogue with the hearing system user via the user interface and includes a classification of the user query. Based on the user query, the linguistic data processing engine requests the currently required database entry for the identified problem, which is then output to the hearing system user.

[0045] In an advantageous embodiment, a current hearing system configuration is determined during the user query input and transmitted to the data cloud. Preferably, the data cloud selects a response from the database based on the hearing system configuration and the query. This allows a hearing system-specific response to be selected for the query or the user query.

[0046] A “hearing system configuration” is understood here and below to mean in particular a configuration or setting of the hearing system or at least one hearing system component (hearing aid, remote interaction unit, optional additional devices, etc.).

[0047] For this purpose, the database contains, for example, a repository of hearing aid capabilities, remote input unit capabilities or smartphone / tablet capabilities, remote input unit configuration (e.g., connection / pairing type), use of additional devices (e.g., charger type, streamer), and hearing aid fit settings (e.g., ear coupling, hearing program).

[0048] The database thus preferably has a generic answer or solution repository, in particular with the subject areas of hearing aid, charger, accessories, data connection, and app usage, and a hearing system-specific answer or solution repository, in particular with the subject areas of hearing aid capabilities, remote input unit capabilities or smartphone / tablet capabilities, configuration of the remote input unit, use of additional devices, and fit adjustment of the hearing aid.

[0049] The generic repository, for example, consists of text and media and is structured to cover the full range of solutions, depending on the problem, but also on different hearing aid configurations. The actual hearing aid configuration (hearing aid type and corresponding capabilities, fitting configuration, accessory configuration, app configuration, phone type) is passed on by the remote interaction unit or to the data cloud, which can then provide a hearing aid-specific solution repository for linguistic data processing.

[0050] The hearing aid configuration can, for example, be part of the user request or a linked input prompt of the user interface. The hearing aid configuration is preferably determined or read by the remote interaction unit. In one conceivable embodiment, the hearing aid is or will be signal-linked to the remote interaction unit (e.g., via Bluetooth), with the remote interaction unit sending a status request to the hearing aid, and the hearing aid transmitting a current hearing aid configuration to the remote interaction unit.

[0051] The signal coupling between the hearing aid and the remote interaction unit is preferably wireless. A wireless communication connection, such as a radio link, is thus established between the components. For this purpose, the hearing aid and the electronic device have corresponding transceivers for data and signal exchange. The transceiver can be, for example, a radio frequency transceiver (e.g., LoRa, Bluetooth, Wi-Fi, UWB, WLAN). A transceiver for signal transmission via magnetic induction (e.g., T-coil, etc.) or via the mobile network is also conceivable.

[0052] In an advantageous embodiment, a current remote interaction unit configuration (e.g., an app version, a smartphone operating system, remote interaction unit settings, etc.) is recorded using the remote interaction unit. The transmitted hearing aid configuration and the recorded remote interaction unit configuration are transmitted to the data cloud as a hearing system configuration.

[0053] An additional or further aspect of the invention provides that text data and / or media data are transmitted as a response. In other words, text data and / or media data are stored in the database as a response.

[0054] The conjunction “and / or” is to be understood here and in the following in such a way that the features linked by this conjunction can be formed both together and as alternatives to one another.

[0055] "Text data" refers, for example, to information on a topic or subject area in text form that is stored in the database. The text data can be output from the database as a response or part of the response. The text data can be passed on to the user interface by the linguistic data processing essentially unchanged. Alternatively, the linguistic data processing can also analyze or process the text data and, based on this, generate a text output for the remote interaction unit or for the user interface.

[0056] "Media data" here and below refers in particular to digital information or content, which may be available in various media formats, such as images, videos, audio recordings, PDF documents, or other multimedia files. This media data serves to represent visual, auditory, or audiovisual information and is stored in the database to be available as a response or part of the response to user requests. This allows the information or explanations for the response to be output in visual, auditory, or other multimedia form. The media data selected as a response or part of the response preferably represents the most accurate, relevant, and understandable response to the user request.

[0057] The repository therefore preferably consists of text and media. If the linguistic processing is multimedia-capable, it can utilize all types of solution repositories, i.e., text and media. If the linguistic processing is not capable of processing and / or utilizing media, the classification of the linguistic processing can be used, for example, to provide the hearing aid user with other media that are appropriate for the problem identified by the hearing aid user. For example, the output is forwarded to another image in the remote interaction unit or user interface based on the problem identified.

[0058] In one possible training approach, the linguistic processing engine is trained using feedback on the output provided via the user interface. For example, part of the output might include a textual question asking whether the output was able to solve a problem described in the user query or whether it was helpful. This feedback is used to train the linguistic processing engine. This allows the linguistic processing engine to be trained based on conversations and dialogues with the hearing aid user, prioritizing the parts of the database that, from the hearing aid user's perspective, contribute most to solving or answering their query.

[0059] The hearing system according to the invention is intended for carrying out a method described above, and is suitable and configured for this purpose. The hearing system comprises a hearing aid, a remote interaction unit with a user interface, a linguistic data processing unit, and a data cloud with a database. The linguistic data processing unit is an interface between the remote interaction unit (or user interface) and the data cloud (or database), which converts user queries into (database) queries and the (database) responses into corresponding (user interface) outputs. This creates a particularly suitable hearing system.

[0060] In particular, this provides a hearing system that allows a hearing system user to receive automatic responses to user queries virtually around the clock. Through database access, linguistic data processing can generate hearing system-specific responses for a chatbot, enabling reliable and rapid resolution of hearing system problems. In other words, conversational AI is provided by the personalized hearing aid texts and media stored in the database, enabling the hearing system user's problems to be resolved in a human-like dialogue.

[0061] Exemplary embodiments of the invention are explained in more detail below with reference to a drawing. In schematic and simplified representations, the drawings show: Fig. 1 a hearing system comprising a hearing aid and a remote interaction unit as well as linguistic data processing and a data cloud, Fig. 2 shows a block diagram of a method for operating the hearing system according to a first embodiment, and Fig. 3 a block diagram of a method for operating the hearing system according to a second embodiment.

[0062] Corresponding parts and sizes are always provided with the same reference symbols in all figures.

[0063] In the Fig. Figure 1 shows a simplified schematic representation of a hearing system 2 comprising a hearing aid 4 and a remote interaction unit 6. In the illustrated embodiment, the hearing aid 4 is, for example, a BTE hearing aid.

[0064] The hearing aid 4 comprises a (hearing aid) housing 8 to be worn behind the ear of a hearing-impaired user. The housing contains two input transducers 10 in the form of microphones, a signal processing unit 12 with a digital signal processor (e.g., in the form of an ASIC) and / or a microcontroller, an output transducer 14 in the form of a receiver, and a battery 16. The hearing aid 4 further comprises a transceiver 18, particularly for wireless data exchange, for example, based on the Bluetooth standard.

[0065] During operation of the hearing aid 4, ambient sound from the surroundings of the hearing aid 4 is recorded by the input transducer 10 and output to the signal processing unit 12 as an audio signal 20 (i.e., as an electrical signal carrying the sound information). The signal processing unit 12 processes the audio signal 20 (filtered, amplified, attenuated, etc.). For this purpose, the signal processing unit 12 comprises a variety of signal processing functions, including an amplifier that amplifies the audio signal 20 frequency-dependently to compensate for the user's hearing impairment.

[0066] The signal processing unit 12 outputs a modified audio signal 22 resulting from this signal processing to the output transducer 14. This in turn converts the modified audio signal 22 into sound. This sound (modified compared to the recorded ambient sound) is first transmitted by the output transducer 14 through a sound channel 24 to a tip 26 of the housing 8, and from there through a sound tube (not explicitly shown) to an earpiece that can be inserted or is inserted into the user's ear.

[0067] The signal processing unit 12 is supplied with electrical energy 28 from the battery 16.

[0068] The remote interaction unit 6 is implemented in the illustrated embodiment as software in the form of an app that is installed on a smartphone 30. The smartphone 30 is preferably a smartphone of the hearing aid user. The smartphone 30 itself is not a component of the hearing system 2 and is used by the latter merely as a resource. Specifically, the remote interaction unit 6 uses the memory space and computing power of the smartphone 30 to carry out a method, described in more detail below, for operating the hearing system 2 or the hearing aid 4. Furthermore, the remote interaction unit 6 uses a Bluetooth transceiver (not shown in more detail) of the smartphone 30 for wireless communication, i.e., for exchanging data with the hearing aid 4 via a Fig. 1 indicated wireless signal or communication connection 32 (Bluetooth connection) with the transceiver 18. The communication connection 32 is established by pairing the smartphone 30 or the remote interaction unit 6 with the hearing aid 4.

[0069] The remote interaction unit 6 is further connected to a linguistic data processing unit 36 ​​via a further wireless or wired (data) communication connection 34, for example, based on the IEEE 802.11 standard (WLAN) or a mobile communications standard, e.g., LTE. The linguistic data processing unit 36 ​​has, for example, a cloud infrastructure. For this purpose, the functions of the linguistic data processing unit 36 ​​are hosted, for example, on one or more servers and accessible via the Internet.

[0070] The linguistic data processing unit 36 ​​is connected via a wireless or wired (data) communication link 38 to a data cloud 40 located on the Internet, in which a database 42 is installed. The database 42 can also be a server coupled to the data cloud 40. The linguistic data processing unit 36 ​​has an unspecified application programming interface (API).

[0071] The dialogue or chatbot is managed by the linguistic data processing unit 36 ​​via the communication connection 32, with queries regarding hearing system-specific topics being sent to the database 42 via the communication connection 38.

[0072] The remote interaction unit 6 is optionally coupled or can be coupled directly to the data cloud 40 via a communication connection 43.

[0073] For data exchange with the linguistic data processing 36 and / or with the database 42, the remote interaction unit 6 accesses a WLAN or mobile radio interface of the smartphone 30 (also not explicitly shown).

[0074] Below is a procedure for operating the hearing system 2 using the Fig. 2 is explained in more detail.

[0075] The remote interaction unit 6 has a user interface 44 for interacting with a hearing system user. The user interface 44 is embodied, for example, as an assistance function (digital assistant), in particular in the form of a chat or chat window. The smartphone 30 has a touch-sensitive display 46 as a touchscreen, so that the hearing system user can enter text inputs using an on-screen keyboard 48 of the user interface 44 as an input means.

[0076] In this embodiment, the user interface 44 has, for example, three input lines 50, 52, 54. The hearing system user can enter hearing system-specific inputs in the input lines 50, 52, 54. For example, a type or device number of the hearing aid 4 can be entered in the input line 50, a smartphone type in the input line 52, and a pairing type, i.e., the type of communication connection 32, in the input line 54.

[0077] When the hearing system user 32 enters a user request 56 into the user interface 44 or into the chat window using the on-screen keyboard 48, a chatbot responds using the linguistic data processing 36, wherein the linguistic data processing 36 accesses the database 42.

[0078] The text or chat input of the user request 56 is transmitted via the communication connection 32 to an (API) endpoint of the linguistic data processing unit 36. The linguistic data processing unit 36 ​​processes the user request 56 or a corresponding prompt using an LLM, accessing the database 42 of the data cloud 40 via the programming interface. According to the method, a hearing system-specific answer or solution repository 58 is made available to the linguistic data processing unit 36.

[0079] The data cloud 40 or database 42 has a general, non-hearing system-specific solution repository 60. The solution repository 60 has, for example, fifty topics, which are divided into five topic areas (hearing aid, charger, accessories, data connection / pairing, and app usage). The topics are stored, for example, in one or more tables as text or text data 62.

[0080] To provide the hearing system-specific solution repository 58, the information from the input lines 50, 52, 54 is transmitted to the data cloud 40 as a hearing system configuration 64. Based on the transmitted hearing system configurations 64, the data cloud 40 determines those entries in the solution repository 60 that apply to the hearing system 2 and thus generates the hearing system-specific solution repository 58. In other words, the solution repository 58 is selected from the solution repository 60 based on the information from the hearing system configuration 64.

[0081] In the course of processing the user query 56, the linguistic data processing unit 36 ​​generates a (database) query 66, which is sent to the data cloud 40 via the communication connection 38. The data cloud 40 generates the solution repository 58, from which a solution or answer 68 is selected based on the query 66 and sent to the linguistic data processing unit 36.

[0082] The linguistic data processing 36 processes the user request 56 using the transmitted response 68 and generates an output 70. The output 70 is sent to the remote interaction unit 6, where it is forwarded to the hearing system user by the chatbot as a chat output (chat response) 72 in the chat window of the user interface 44.

[0083] Below is a further development of the procedure described above based on the Fig. 3 is explained in more detail.

[0084] In this exemplary embodiment, the user interface 44 does not have input lines 50, 52, 54. During an input into the user interface 44, the remote interaction unit 6 determines or records the hearing system configuration 64 and transmits it to the data cloud 40 via the communication connection 43. To this end, the remote interaction unit 6 determines or records the hearing aid configuration of the hearing aid 4 via the signal communication connection 32. As part of the hearing aid configuration, for example, the hearing aid type or the hearing aid type and the fitting configuration or settings of the hearing aid 4 are transmitted. Furthermore, the remote interaction unit 6 records or determines, for example, the smartphone configuration, an app configuration, and a pairing configuration. These individual or component configurations are combined to form the hearing system configuration 64.

[0085] The data cloud 40 or database 42, for example, has a repository 74 regarding the hearing aid capabilities, the remote input unit capabilities or smartphone / tablet capabilities, a configuration of the remote input unit (e.g., connection / pairing type), the use of additional devices (e.g., charger type, streamer), and the hearing aid fit setting (e.g., ear coupling, hearing program). Based on the hearing system configuration 64, the information relevant to the hearing system 2 is determined from the repository 74.

[0086] In this embodiment, the general solution repository 60 includes, in addition to text data 62, media data in the form of image data 76, video data 78, and document data (e.g., instructions, user manuals, brochures, etc.) 80. The document data 80 is, for example, PDF data.

[0087] In a specific embodiment, the hearing system 2 comprises, for example, a binaural hearing aid 4 with two individual devices. The individual devices are embodied, for example, as ITE devices. If one of the individual devices is not functioning, the hearing system user can enter a user request 56a into the user interface 44. For example, the hearing system user enters "my left hearing aid has not been working since this morning."

[0088] With the input, the remote interaction unit 6 records or determines the hearing system configuration 2 and transmits it via the communication connection 43. The user request 56a is sent to the linguistic data processing 36, which sends a corresponding request 66a to the data cloud 40.

[0089] Based on the hearing system configuration 64 and the repository 74, the data cloud determines information 82 about hearing system 2. For example, based on the hearing aid configuration, it is determined that hearing aid 4 or its individual devices are rechargeable ITE devices with Bluetooth that support directional microphones and hands-free calling, and are compatible with an ITE charger. Furthermore, based on the smartphone configuration, it is determined that the smartphone operating system supports an ASHA wireless protocol (ASHA: Audio Streaming for Hearing Aids). Furthermore, based on the fitting configuration, it can be determined that hearing aid 4 is equipped with domes, Own Voice Processing (OVP), and an additional program for noisy environments.

[0090] Based on this information, the solution repository 60 is filtered, and those text data 62 and media data 76, 78, 80 that match the hearing system 2 are selected for the solution repository 58. A response 68a is selected from the solution repository 58, which consists, for example, of text data 62a, an image file 76a, and a video file 78a. The chat output 72a resulting from the output 70a is, for example, a text that reads "Please check your ITE for a buildup of cerumen. Watch the following video and image," as well as an image from the image file 76a displayed therewith and a video from the video file 78a.

[0091] In the illustrated embodiment, the chat output 72a does not solve the hearing system user's problem, and the user enters a second user request 56b, which is, for example, "I did that, everything is fine, but it still doesn't work." Subsequently, a second request 68b is generated, and a new response 68b is selected from the solution repository 58. The response 68b comprises, for example, text data 62b and another image file 76b, which are sent as output 70b to the chatbot, which subsequently outputs a chat output 72b with a text similar to "Please place your ITE in the charger for 20 seconds and check the LED..." and a corresponding image of an ITE in a charger.

[0092] Preferably, two feedback buttons 84 are generated and displayed as part of the chat output 72b, which can be activated by the hearing system user via the (touch) display. For example, one of the feedback buttons 84 is linked to positive feedback ("thumbs up", "answer helped", ...) and the other to negative feedback ("thumbs down", "answer didn't help", ...). When one of the feedback buttons 84 is activated, a corresponding feedback 86 is generated, based on which the linguistic data processing 36 is trained through fine-tuning or personalization 88 so that it can better support the hearing system user in the future. The fine-tuning 88 is therefore a training for the linguistic data processing 36.

[0093] In an additional or alternative embodiment, the solution repository 60 further comprises setting data 90. The setting data 90 contains information about whether and which hearing aid settings can be set for different hearing systems 2. The setting data 90 further contains information about which of these hearing aid settings are relevant for the respective user request 56, 56a, 56b, as well as the specific settings and changes for implementing a suitable hearing aid setting or hearing aid configuration. The setting data 90 may also contain information about how these hearing aid settings can be set, for example, if this cannot be set automatically by the remote interaction unit 6.

[0094] The solution repository 58 preferably contains only those setting data 90 that can be transmitted to the hearing aid 4 via the communication connection 32 for adjusting the hearing aid 4. This allows the chatbot to make changes to the hearing aid settings directly or indirectly (i.e., through actions by the user) during the dialogue with the hearing system user.

[0095] In this case, it is conceivable, for example, for the chatbot to access a setting or assistance function of the remote interaction unit 6, by means of which the settings on the coupled hearing aid 4 are changed. It is also conceivable for the chatbot to access or refer to further software, in particular another smartphone app, which is installed on the smartphone 30 in addition to the remote interaction unit 6, in order to transmit the setting data 90 to the hearing aid 4 or to change the hearing aid settings (directly or indirectly). For example, the chatbot can explain how the hearing aid settings can be adjusted using the remote interaction unit 6 or using a smartphone app running separately from the remote interaction unit 6. For the latter, the hearing system configuration 64 includes, for example, information about which other apps are installed on the smartphone 30.

[0096] For example, in the case of a user query such as "background noise is too loud," the chatbot initially outputs text data from the settings data 90 as a chat output, and then asks the user whether a hearing care provider has stored different hearing programs for the hearing aid 4, for example, which can be selected via the remote interaction unit 6 (or a separate app). If the user denies this through a further user query, and the hearing aid 4 has a directional microphone function (directional focus), a chat output is generated based on the settings data 90, for example, explaining how the directivity or directional characteristic can be temporarily changed or adjusted.If the user subsequently requests that the settings be permanently applied to his hearing aid 4, the setting data 90 can be used as a chat output, for example, to output instructions with a text / image reference to an assistance function of the remote interaction unit 6, by means of which the settings can be permanently adjusted.

[0097] The claimed invention is not limited to the exemplary embodiments described above. Rather, other variants of the invention can also be derived therefrom by those skilled in the art within the scope of the disclosed claims without departing from the subject matter of the claimed invention. In particular, all individual features described in connection with the various exemplary embodiments can also be combined in other ways within the scope of the disclosed claims without departing from the subject matter of the claimed invention. List of reference symbols 2 hearing system 4 Hearing aid 6 Remote interaction unit 8 housings 10 input converters 12 Signal processing unit 14 output converters 16 Battery 18 transceivers 20, 22 Audio signal 24 sound channels 26 lace 28 Energy 30 smartphones 32, 34 Communication connection 36 linguistic data processing 38 Communication connection 40 Data Cloud 42 Database 43 Communication connection 44 User interface 46 Display 48 On-screen keyboard 50, 52, 54 input line 56, 56a, 56b User request 58 Solution Repository 60 Solution Repository 62, 62a, 62b Text data 64 Hearing system configuration 66, 66a, 66b Inquiry 68, 68a, 68b Answer 70, 70a, 70b edition 72, 72a, 72b Chat output 74 Repository 76, 76a, 76b Image data 78, 78a Video data 80 document data 82 information 84 feedback buttons 86 Feedback 88 Fine-tuning 90 setting data

Claims

[1] Method for operating a hearing system (2), comprising - a hearing aid (4) and a remote interaction unit (6) with a user interface (44) for inputting a hearing system-related user request (56, 56a, 56b), - a linguistic data processing unit (36) coupled to the user interface (44), - a data cloud (40) coupled to the linguistic data processing (36) with a database (42) in which answers (68, 68a, 68b) for the user query (56, 56a, 56b) are stored, - wherein upon input of a hearing aid-related user request (56, 56a, 56b) a) a content of the user request (56, 56a, 56b) is analyzed by means of the linguistic data processing (36) and a request (66, 66a, 66b) is sent to the data cloud (40), b) the data cloud (40) selects an answer (68, 68a, 68b) from the database (42) based on the request (66, 66a, 66b), c) the answer (68, 68a, 68b) is sent to the linguistic data processing (36), d) the linguistic data processing unit (36) generates an output (70, 70a, 70b) based on the response (68, 68a, 68b) and sends it to the remote interaction unit (6), and e) the output (70, 70a, 70b) is output by the remote interaction unit (6). [2] Method according to claim 1, characterized by that in the course of entering the user request (56, 56a, 56b) a current hearing system configuration (64) is determined and transmitted to the data cloud (40). [3] Method according to claim 2, characterized by that a response (68, 68a, 68b) is selected from the database (42) by the data cloud (40) based on the hearing system configuration (64) and the request (66, 66a, 66b). [4] Method according to claim 2 or 3, wherein the hearing aid (4) is signal-coupled to the remote interaction unit (6), characterized bythat a current hearing aid configuration is transmitted from the hearing aid (4) to the remote interaction unit (6). [5] Method according to claim 4, characterized by that a current remote interaction unit configuration is recorded by means of the remote interaction unit (6), and wherein the hearing aid configuration and the remote interaction unit configuration are transmitted to the data cloud (40) as a hearing system configuration (2). [6] Method according to one of claims 1 to 5, characterized by that text data (62, 62a, 62b) and media data (76, 76a, 76b, 78, 78a, 80) are transmitted as a response (68, 68a, 68b). [7] Method according to one of claims 1 to 6, characterized by that the linguistic data processing (36) is trained on the output (70, 70a, 70b) with feedback (86) input via the user interface (44). [8] Hearing system for carrying out a method according to one of claims 1 to 7, comprising a hearing aid (4) and a remote interaction unit (6) with a user interface (44) for inputting a hearing system-related user query (56, 56a, 56b), a linguistic data processing unit (36) coupled to the user interface (44), and a data cloud (40) coupled to the linguistic data processing unit (36) with a database (42) in which answers (68, 68a, 68b) for the user query (56, 56a, 56b) are stored.

Images