Assistance system and assistance method for a vehicle

Abstract

This disclosure relates to an assistance system (100) for a vehicle (10), comprising: - at least one processor module (110) configured to operate vehicle functions and / or query information about vehicle functions based on predetermined command inputs; - a user interface module (120) configured to receive voice user input (BEN); and - an interface module (130) configured to communicate with the at least one processor module (110) and a large language model (LLM), wherein the interface module (130) is configured to: - provide the large language model (LLM) with first configuration information (KFG1) regarding predetermined command inputs for vehicle functions; - provide the large language model (LLM) with voice user input (BEN) or information about voice user input (BEN); and - receive from the large language model (LLM) a conversion result (KNV) of the voice user input (BEN) based on the first configuration information (KFG1) and provide it at least partially to the at least one processor module (110) to correspondingly operate vehicle functions and / or query information about vehicle functions.

Description

Technical Field

[0001] This disclosure relates to an assistance system for a vehicle, a vehicle having such an assistance system, an assistance method for a vehicle, and a storage medium for performing the assistance method. This disclosure particularly relates to the use of a large language model for interaction with a vehicle. Background Technology

[0002] In modern vehicles, various vehicle functions, such as heating, entertainment systems, power windows, and navigation, can be operated via voice control. However, this voice control is specifically developed for automobiles and therefore has limited performance. Errors frequently occur, particularly when interpreting commands. Users cannot explain these errors to the system because the system cannot understand them. This can lead to user dissatisfaction and discourage the use of voice control. For example, the lack of voice control in manually driven vehicles can negatively impact road safety, as voice control is less likely to distract the driver from driving tasks compared to using touchscreens or similar controls. Summary of the Invention

[0003] The objective of this disclosure is to provide an assistance system for a vehicle, a vehicle having such an assistance system, an assistance method for a vehicle, and a storage medium for performing the assistance method, all of which enable the transmission of user commands to the vehicle with reduced errors. Particularly, the objective of this disclosure is to provide an improved voice control system for a vehicle.

[0004] This task is solved by the technical solution in the independent claim. Advantageous embodiments are given in the dependent claims.

[0005] According to one aspect of this disclosure, an assistance system for vehicles, particularly motor vehicles, is proposed. The assistance system includes: at least one processor module configured to operate vehicle functions and / or query information about vehicle functions based on predetermined command inputs; a user interface module configured to receive voice user input; and an interface module configured to communicate with the at least one processor module and a large language model.

[0006] The interface module is configured to:

[0007] - Provide the large language model with initial configuration information about the predetermined instruction inputs for vehicle functions;

[0008] - Provide large language models with voice user input or information about voice user input; and

[0009] - Receive the conversion results of the voice user input based on the first configuration information from the large language model and provide them at least in part to the processor module so as to control vehicle functions and / or query information of vehicle functions accordingly.

[0010] According to the present invention, an interface is provided that mediates between a user and a vehicle function capable only of processing specific command inputs. For this purpose, the interface communicates with a large language model (provided, for example, in the form of a chatbot). The interface first informs the large language model of configuration information regarding the predetermined command input. Subsequently, the interface sends the voice user input (e.g., "The music is too loud") to the large language model, which converts the voice user input into a format adapted to the vehicle function (e.g., "Turn down the radio volume") based on the configuration information. Optionally, the large language model can also generate a response for the user based on the configuration information (e.g., "Volume adjusted").

[0011] As a result, improved voice control of vehicle functions is achieved due to reduced errors in the transmission of user commands to the vehicle. Furthermore, new and / or other large language models can be integrated at any time based on the interface according to the invention.

[0012] User interface modules and / or interface modules may include software components / algorithms configured to execute on at least one processor and thereby perform the functions of the respective modules.

[0013] Large language models are machine learning models from the field of generative artificial intelligence and are generally used to generate text-based content. They are based on neural networks using a Transformer architecture and employ deep learning algorithms. An example of such a large language model is ChatGPT.

[0014] Preferably, the large language model has no prior knowledge and acquires knowledge about the assistive system solely through the first configuration information. In particular, the large language model can be developed and trained without prior knowledge about the rest of the assistive system and can acquire knowledge about the assistive system solely through the first configuration information.

[0015] Preferably, the large language model is configured for text-based communication. The interface module can be configured to provide first configuration information about a predetermined command input in text form, and to provide first voice user input or information about the voice user input in text form. Furthermore, the interface module can receive the conversion results of the voice user input in text form from the large language model.

[0016] Preferably, the vehicle functions include or involve one or more of the following functions:

[0017] - Entertainment systems (such as radio); and / or

[0018] - Air conditioning systems (e.g., heating, cooling, ventilation, seat heating, etc.); and / or

[0019] - Window regulators, especially power window regulators; and / or

[0020] - Navigation system.

[0021] The at least one processor module can be configured to control at least one vehicle function based on a predetermined command input. For example, upon receiving a corresponding command, the at least one processor module can adjust the radio volume or open a car window.

[0022] The at least one processor module can be configured to query information for at least one vehicle function based on a predetermined instruction input. For example, upon receiving a corresponding instruction, the at least one processor module can request the current vehicle location.

[0023] As used within the scope of this disclosure, the term "predefined instruction input" refers to a limited number of predefined expressions that can be processed / recognized by a processor module or vehicle function for execution. In particular, the term "predefined instruction input" refers to a natural language request that can be processed / recognized by the vehicle or a speech recognition system implemented directly in the vehicle.

[0024] Preferably, the at least one processor module includes, or is an electronic controller. The controller is an electronic module that performs a range of different functions within the vehicle and operates according to the so-called "EVA" (Input-Process-Output) principle: it receives signals from sensors and operating elements, evaluates these signals, and manipulates actuators that are responsible for translating the controller's signals into specific actions. Controllers are typically networked via a data bus and can therefore communicate with each other.

[0025] Preferably, the interface module is configured to transmit first configuration information regarding predetermined command inputs for vehicle functions to the large language model during the communication initialization between the assistance system and the large language model. In particular, the interface can be configured to operate using the configuration information before transmitting voice user input to the large language model.

[0026] Preferably, the interface module further includes second configuration information for providing the large language model with user responses regarding the control of vehicle functions and / or queried information to be output by the user interface module; and for receiving user responses based on the second configuration information from the large language model and providing them, at least partially, to the user interface module for output to the user. This allows feedback to be given to the user regarding the control of vehicle functions and / or queried information. For example, for the command "navigation," the user response "the navigation map will be displayed" can be output. In another example, for the command "radio," the user response "the radio will be turned on" can be output.

[0027] Preferably, the interface module is configured to provide the large language model substantially simultaneously or at the same time with first configuration information regarding predetermined command inputs for vehicle functions and second configuration information regarding user responses to be output by the user interface module, for example during the communication initialization between the assistance system and the large language model.

[0028] The user interface module may include at least one input device for receiving voice user input, and optionally at least one output device for outputting user responses. Preferably, the user interface module is fixedly installed in a vehicle.

[0029] The at least one input device may include a voice input device for receiving voice user input, and optionally include a touch-sensitive input device, such as a touchpad or touch panel and / or a tactile input device, such as a switch (such as a push switch and / or a rotary switch) or other mechanically operable button elements.

[0030] The at least one output device may include at least one speaker and / or at least one display device to output a user response. The at least one display device may include a display, particularly an LCD display, a plasma display, or an OLED display. Alternatively or supplementarily, the at least one display device may include a projection device configured to display information directly within the driver's field of vision, particularly projecting it onto the windshield.

[0031] Preferably, the interface module is configured to transmit a standard message to the large language model when the received conversion result of the voice user input does not correspond to a predetermined instruction input or cannot be processed / recognized by the processor module. This allows the large language model to receive feedback regarding the received erroneous conversion result.

[0032] Preferably, the standard message relates to first configuration information regarding the predetermined instruction input and / or explanatory user output regarding the received conversion result, which needs to be output by the user interface module. That is, when the large language model sends an instruction that the processor module or onboard computer cannot process, the processor module or onboard computer can respond via a standard message. The standard message may, for example, describe that the instruction cannot be processed and that an explanation needs to be given to the user. Subsequently, the large language model can generate an explanation, which is output to the user through the user interface module (e.g., "The instruction is not understood. Please try again").

[0033] Preferably, the auxiliary system is configured to communicate with the large language model based on data protection settings. Therefore, the auxiliary system can determine which information is transmitted to the large language model and which is not.

[0034] Preferably, the data protection settings can be preset or configured by the user. For example, the user can configure in the onboard computer which information should be provided to the large language model to protect privacy. Such data protection settings can also be configured upon first use of the instruction.

[0035] Preferably, the interface module is web-based. For example, the interface module can use a web URL, to which the auxiliary system (such as a vehicle's onboard computer) can send a request and receive a response. This integration method enables rapid integration of any new large language models emerging in the market.

[0036] Preferably, the interface module is implemented as an application, particularly on a user's mobile terminal device or vehicle component (e.g., a controller or head unit). In other words, the user can install an App that provides the interface according to the invention. The term "mobile terminal device" specifically includes smartphones, but also other mobile phones or handsets, personal digital assistants (PDAs), tablets, laptops, smartwatches, smart glasses, and all existing and future electronic devices equipped with communication technologies.

[0037] Preferably, the large language model is implemented in a central unit (e.g., a server or backend) and / or based on the cloud.

[0038] Preferably, the vehicle, and especially the auxiliary system, includes a communication module. The vehicle's communication module can be configured to communicate via a mobile network. The mobile network can be, for example, an LTE network or a 5G network. Therefore, the vehicle can communicate with a large language model (or a central unit and / or the cloud) via the mobile network to achieve the functions according to the invention.

[0039] Preferably, the large language model is a chatbot. A chatbot is a text-based dialogue system that allows communication with technical systems. Chatbots are configured for text input and text output, enabling communication in natural language.

[0040] According to another independent aspect of this disclosure, a vehicle, particularly a motor vehicle, is proposed. The vehicle includes an auxiliary system according to embodiments of this disclosure.

[0041] The term "vehicle" includes cars, trucks, transport vehicles, buses, RVs, motorcycles, etc., used for transporting people and goods. In particular, the term includes motor vehicles used for the transport of people.

[0042] According to another independent aspect of this disclosure, an assistance method for vehicles, particularly motor vehicles, is proposed. The assistance method includes: transmitting first configuration information regarding predetermined command inputs for vehicle functions to a large language model via an interface module, wherein the predetermined command inputs provide information on the ability to control and / or query vehicle functions; receiving voice user input via a user interface module; transmitting the voice user input or information about the voice user input to the large language model via the interface module; receiving a conversion result of the voice user input based on the first configuration information from the large language model via the interface module; and using the conversion result of the voice user input received from the large language model to control at least one vehicle function and / or query information about at least one vehicle function.

[0043] The auxiliary method described herein can realize all aspects of the auxiliary system described in this paper.

[0044] According to another independent aspect of this disclosure, a software (SW) program is proposed. This software program can be configured to execute on one or more processors and thereby perform the auxiliary methods described herein.

[0045] According to another independent aspect of this disclosure, a storage medium is proposed. This storage medium may include a software program configured to execute on one or more processors and thereby perform the auxiliary methods described herein.

[0046] According to another independent aspect of this disclosure, software having program code is proposed. This software is configured to execute the auxiliary method when it is running on one or more software-controlled devices.

[0047] According to another independent aspect of this disclosure, an assistance system for a vehicle is provided. The assistance system includes one or more processors; and at least one memory connected to the one or more processors and including instructions executable by the one or more processors to perform the assistance methods described herein.

[0048] According to another independent aspect of this disclosure, a chatbot system is proposed. The chatbot system includes one or more processors; and at least one memory connected to the one or more processors and including instructions executable by the one or more processors to receive (first) configuration information from a vehicle's assistance system regarding predetermined instruction inputs for vehicle functions; receive voice user input or information regarding the voice user input from the vehicle's assistance system; and generate a conversion result of the voice user input based on the (first) configuration information and transmit it to the vehicle's assistance system.

[0049] A processor or processor module is a programmable computing unit, that is, a machine or electronic circuit that controls other components and advances algorithms (processes) based on received instructions. Attached Figure Description

[0050] Embodiments of this disclosure are illustrated in the accompanying drawings and described in detail below. The drawings are as follows:

[0051] Figure 1 A vehicle with an auxiliary system according to an embodiment of the present disclosure is illustrated schematically;

[0052] Figure 2 An auxiliary system according to an embodiment of the present disclosure is illustrated schematically; and

[0053] Figure 3 A flowchart illustrating an auxiliary method according to an embodiment of the present disclosure is shown. Detailed Implementation

[0054] In the following text, unless otherwise stated, the same reference numerals are used for elements that have the same function.

[0055] Figure 1 A vehicle 10 having an auxiliary system 100 according to an embodiment of the present disclosure is shown schematically. Figure 2 An auxiliary system 100 according to an embodiment of the present disclosure is illustrated schematically.

[0056] The assistance system 100 includes at least one processor module 110 configured to input and control vehicle functions and / or query information about vehicle functions based on predetermined instructions; and a user interface module 120 configured to receive voice input from vehicle users, particularly drivers.

[0057] In some embodiments, vehicle functions that can be controlled by the at least one processor module 120 via predetermined instruction input may include, but are not limited to, entertainment systems (e.g., radios), air conditioning systems (e.g., heating, cooling, ventilation, seat heating, etc.), power window regulators, and / or navigation systems. For example, upon receiving a corresponding instruction, the at least one processor module 110 may adjust the radio volume or open a window. In another example, upon receiving a corresponding instruction, the at least one processor module 110 may request the current vehicle location.

[0058] As used within the scope of this disclosure, the term "predefined instruction input" refers to a limited number of predefined expressions that can be processed / recognized by a processor module or vehicle function for execution. In particular, the term "predefined instruction input" refers to a natural language request that can be processed / recognized by the vehicle or a speech recognition system implemented directly in the vehicle.

[0059] The user interface module 120 may include at least one input device 122 for receiving voice input from a vehicle user and optionally at least one output device 124 for outputting a user response. Preferably, the user interface module 120 is fixedly installed in the vehicle 10.

[0060] The auxiliary system 100 also includes an interface module 130 configured to communicate with the at least one processor module 110 and the large language model LLM, and optionally with the user interface module 120. The interface module 130 is specifically configured to communicate with the large language model LLM regarding voice user input to generate instruction input that can be processed by the at least one processor module 110. The large language model LLM may be implemented in a central unit 20 (e.g., a server or backend) and / or based on the cloud.

[0061] Communication between the interface module 130, the at least one processor module 110, and the user interface module 120 can be performed via the corresponding data bus of the vehicle 10.

[0062] Communication between interface module 130 and the Large Language Model (LLM) can be achieved via communication connection 1, which may use a mobile network, for example. The mobile network could be an LTE network or a 5G network. In some embodiments, vehicle 10 may include a communication module with a SIM unit. This communication module may be configured to communicate with central unit 20 via a mobile network. Thus, vehicle 10 can communicate with the large language model (or central unit 20) via a mobile network to achieve the functions according to the invention.

[0063] Interface module 130 is configured to communicate with a large language model (LLM) regarding speech user input to generate instruction input that can be processed by the at least one processor module 110. For this purpose, interface module 130 may be configured to:

[0064] —Provide the large language model LLM with first configuration information KFG1 about the predetermined instruction inputs for vehicle functions;

[0065] —Provide the Large Language Model (LLM) with information about the user's speech input BEN or information about the user's speech input BEN; and

[0066] — Receive the conversion result KNV of the voice user input BEN based on the first configuration information KFG1 from the large language model LLM and provide it at least partially to the at least one processor module 110 so as to correspondingly control vehicle functions and / or query vehicle function information.

[0067] Therefore, the interface module 130 acts as an intermediary between the onboard computer, which can only process specific command inputs, and the user. Specifically, the interface module 130 first informs the Large Language Model (LLM) of the configuration information regarding the predetermined command input. Then, the interface module 130 sends the voice user input (e.g., "The music is too loud") to the LLM, which converts the voice user input (BEN) into a format adapted to vehicle functions (e.g., "Turn down the radio volume") based on the configuration information (KFG1). Optionally, the LLM can also generate a response for the user based on the configuration information (e.g., "Volume adjusted").

[0068] In some implementations, the interface module 130 is configured to transmit first configuration information KFG1 regarding predetermined command inputs for vehicle functions to the large language model LLM during communication initialization between the assistance system 100 and the large language model LLM. Specifically, the interface can be configured to operate using this configuration information prior to transmitting the voice user input BEN to the large language model LLM.

[0069] Optionally, the interface module 130 may also be configured to provide the Large Language Model (LLM) with second configuration information KFG2 regarding user responses to vehicle function controls and / or queried information that needs to be output by the user interface module 120; and to receive user responses based on the second configuration information KFG2 from the LLM and provide them, at least partially, to the user interface module 120 for output to the user. This allows feedback to be given to the user regarding vehicle function controls and / or queried information. For example, for the command "navigation," the user response "navigation map will be displayed" can be output. In another example, for the command "radio," the user response "radio will be turned on" can be output.

[0070] Interface module 130 can be configured to provide first configuration information KFG1 about the input of predetermined instructions for vehicle functions and second configuration information KFG2 about the user response to be output by user interface module 120 substantially simultaneously or at the same time, for example during the communication initialization between the assistance system 100 and the large language model LLM.

[0071] Preferably, the Large Language Model (LLM) is a chatbot. A chatbot is a text-based dialogue system that allows communication with technical systems. Chatbots are configured for text input and text output, enabling communication in natural language.

[0072] Exemplary first configuration information KFG1 and second configuration information KFG2 can be output to the large language model LLM in text form, with the following content:

[0073] "Now I want you to act as an interface for the vehicle's onboard computer. If I send a message that starts with #, please treat it as a user request and respond in the format shown in the next two lines:"

[0074] Instruction: Vehicle Instruction

[0075] Response: User Response

[0076] In this context, vehicle commands are instructions sent to the vehicle, and user responses are text that should be displayed to the user. The vehicle supports the following commands: "Navigation" and "Radio." Navigation is used to display a map, and Radio is used to turn on the radio.

[0077] These configurations can also be flexibly adjusted by transmitting further configuration information KFG1 and KFG2 to the Large Language Model (LLM) via interface module 130, for example:

[0078] The vehicle's onboard computer now also supports the command "turn off the radio," which is used to turn off the radio.

[0079] If the user interface module 120 receives the voice user input "# turn on the radio", then the voice user input is transmitted by the interface module 130 to the Large Language Model (LLM). The LLM returns the corresponding conversion result KNV, which is the predefined command input and the user response to be output.

[0080] Vehicle instructions: Radio

[0081] User response: The radio will turn on.

[0082] In some implementations, the interface module 130 may be configured to transmit a standard message to the Large Language Model (LLM) when the received conversion result KNV of the voice user input does not correspond to the predetermined instruction input BEN or cannot be processed / recognized by the processor module 110. This allows the LLM to receive feedback regarding the received erroneous conversion result.

[0083] The standard message may include first configuration information KFG1 regarding the predetermined instruction input, and / or interpretive user output regarding the received conversion result KNV, which needs to be output by the user interface module 120. That is, when the Large Language Model (LLM) sends an instruction that the processor module 110 or the onboard computer cannot process, the processor module 110 or the onboard computer can respond via a standard message. The standard message may, for example, describe that the instruction cannot be processed and that an explanation needs to be given to the user. Subsequently, the LLM can generate an explanation, which is output to the user through the user interface module 120 (e.g., "The instruction is not understood. Please try again").

[0084] In some implementations, the assistance system 100 is configured to communicate with the Large Language Model (LLM) according to data protection settings. Therefore, the assistance system 100 can determine which information is transmitted to the LLM and which is not. The data protection settings can be preset or configured by the user. For example, the user can configure in the onboard computer which information should be provided to the LLM to protect privacy. Such data protection settings can also be configured upon first use.

[0085] In some implementations, interface module 130 is web-based. For example, interface module 130 can use a web URL, to which the auxiliary system 100 (e.g., the onboard computer of vehicle 10) can send requests and receive responses. This integration method enables rapid integration of any new large language models emerging in the market.

[0086] In other embodiments, the interface module 130 is implemented as an application, particularly on a user's mobile terminal device or vehicle component (e.g., a controller or head unit). In other words, a user can install an app that provides an interface according to the present invention.

[0087] Figure 3 A flowchart of an auxiliary method 300 according to an embodiment of the present disclosure is shown schematically. The auxiliary method 300 can be implemented by corresponding software, which can be executed by a processor (e.g., CPU).

[0088] The auxiliary method 300 includes: in block 310, transmitting first configuration information about predetermined command inputs for vehicle functions to a large language model via an interface module, wherein the predetermined command inputs provide information on the ability to control and / or query vehicle functions; in block 320, receiving voice user input via a user interface module; in block 330, transmitting the voice user input or information about the voice user input to the large language model via the interface module; in block 340, receiving a conversion result of the voice user input based on the first configuration information from the large language model via the interface module; and in block 350, using the conversion result of the voice user input received from the large language model to control at least one vehicle function and / or query information about at least one vehicle function.

[0089] According to the present invention, an interface is provided that mediates between a user and a vehicle function capable only of processing specific command inputs. For this purpose, the interface communicates with a large language model (provided, for example, in the form of a chatbot). The interface first informs the large language model of configuration information regarding the predetermined command input. Subsequently, the interface sends the voice user input (e.g., "The music is too loud") to the large language model, which converts the voice user input into a format adapted to the vehicle function (e.g., "Turn down the radio volume") based on the configuration information. Optionally, the large language model can also generate a response for the user based on the configuration information (e.g., "Volume adjusted").

[0090] As a result, improved voice control of vehicle functions is achieved due to reduced errors in the transmission of user commands to the vehicle. Furthermore, new and / or other large language models can be integrated at any time based on the interface according to the invention.

[0091] Although the invention has been described and explained in more detail through preferred embodiments, it is not limited to the disclosed examples, and other modifications can be derived by those skilled in the art without departing from the scope of protection of the invention. Therefore, it is clear that many possible modifications exist. It is also clear that the exemplary embodiments mentioned are merely illustrative and should not be construed in any way as limiting the scope of protection, application possibilities, or configuration of the invention. Rather, the foregoing description and accompanying drawings enable those skilled in the art to specifically implement the exemplary embodiments, wherein various changes can be made by those skilled in the art (e.g., regarding the function or arrangement of the various elements mentioned in one exemplary embodiment) upon understanding the disclosed inventive concept, without departing from the scope of protection defined by the claims and their legal equivalents, such as the further interpretations in the specification.

Claims

1. An auxiliary system (100) for a vehicle (10), comprising: At least one processor module (110) is configured to control vehicle functions and / or query information about vehicle functions based on predetermined instruction inputs; User interface module (120), the user interface module is configured to receive voice user input (BEN). as well as An interface module (130) is configured to communicate with the at least one processor module (110) and the Large Language Model (LLM), wherein the interface module (130) is configured to: —Provide the Large Language Model (LLM) with first configuration information (KFG1) about the predetermined instruction inputs for vehicle functions; —Provide the speech user input (BEN) or information about the speech user input (BEN) to the Large Language Model (LLM); as well as — Receive the conversion result (KNV) of the voice user input (BEN) based on the first configuration information (KFG1) from the large language model (LLM) and provide it at least partially to the at least one processor module (110) so as to correspondingly control vehicle functions and / or query information of vehicle functions.

2. The auxiliary system (100) according to claim 1, wherein, The interface module (130) is also configured to: Provide the Large Language Model (LLM) with second configuration information (KFG2) regarding user responses to vehicle function controls and / or queried information that need to be output by the user interface module (120); and The system receives user responses based on the second configuration information (KFG2) from the Large Language Model (LLM) and provides them at least in part to the user interface module (120) for output to the user.

3. The auxiliary system (100) according to claim 1 or 2, wherein, The interface module (130) is configured to transmit a standard message to the Large Language Model (LLM) when the received conversion result (KNV) of the voice user input (BEN) does not correspond to the predetermined instruction input. The standard message relates to first configuration information (KFG1) about the predetermined instruction input and / or interpretive user output about the received conversion result (KNV) that needs to be output by the user interface module (120).

4. The auxiliary system (100) according to any one of claims 1 to 3, wherein, The auxiliary system (100) is configured to communicate with the Large Language Model (LLM) according to data protection settings, in particular the data protection settings can be predefined by the user.

5. The auxiliary system (100) according to any one of claims 1 to 4, wherein, The interface module (130) is web-based, or the interface module (130) is implemented as an application, particularly on a user's mobile terminal device or vehicle component.

6. The auxiliary system (100) according to any one of claims 1 to 5, wherein, The large language model (LLM) is implemented in the central unit (20) and / or on the cloud.

7. The auxiliary system (100) according to any one of claims 1 to 6, wherein, The large language model (LLM) has no prior knowledge and obtains knowledge about the auxiliary system through the first configuration information (KFG1).

8. A vehicle (10), particularly a motor vehicle, said vehicle including an auxiliary system (100) according to any one of claims 1 to 7.

9. An auxiliary method (300) for a vehicle (10), comprising: The interface module (130) transmits (310) first configuration information (KFG1) about predetermined instruction inputs for vehicle functions to the large language model (LLM), wherein the predetermined instruction inputs enable the vehicle functions to be operated and / or information that enables the vehicle functions to be queried. The user interface module (120) receives (320) voice user input (BNE); The interface module (130) transmits (330) the voice user input (BEN) or information about the voice user input (BEN) to the large language model (LLM). The interface module (130) receives (340) the conversion result (KNV) of the voice user input (BEN) based on the first configuration information (KFG1) from the Large Language Model (LLM); and The conversion result (KNV) of the voice user input (BEN) received from the Large Language Model (LLM) is used to manipulate (350) at least one vehicle function and / or query information of at least one vehicle function.

10. A storage medium, including a software program configured to execute on one or more processors and thereby perform the auxiliary method (300) according to claim 9.

11. A chatbot system (20) comprising one or more processors and at least one memory, the memory being connected to the one or more processors and including instructions executable by the one or more processors, such that: Receive configuration information (KFG1) about predetermined command inputs for vehicle functions from the vehicle’s (100) auxiliary system (100). Receive voice user input (BEN) or information about voice user input (BEN) from the vehicle's (100) assistance system; and An auxiliary system (100) generates a conversion result (KNV) of the voice user input (BEN) based on the configuration information (KFG1) and transmits it to the vehicle (10).

Images