Assistance system and assistance method for vehicle
By introducing a large language model and communication with the interface module into the vehicle assistance system, the problem of interpretation errors in the vehicle voice control system was solved, resulting in more accurate voice control and user response, thus improving driving safety and user satisfaction.
CN122374816APending Publication Date: 2026-07-10BAYERISCHE MOTOREN WERKE AG
0 Cites 0 Cited by
Patent Information
- Application Number
- CN202480078088.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Priority Date
- 2024-01-30
- Filing Date
- 2024-10-17
- Publication Date
- 2026-07-10
AI Technical Summary
Technical Problem
Existing vehicle voice control systems are prone to errors in interpreting commands, leading to user dissatisfaction and potentially affecting driving safety, and they also fail to understand user explanations.
Method used
The system uses a large language model to communicate with the interface module of the vehicle assistance system. It converts voice user input into commands adapted to vehicle functions through configuration information and generates user responses, thereby reducing error transmission.
Benefits of technology
It improves the accuracy of voice control for vehicle functions, reduces erroneous transmission of user commands, and enhances driving safety and user experience.
✦ Generated by Eureka AI based on patent content.
Abstract
The disclosure relates to an assistance system (100) for a vehicle (10), comprising:-at least one processor module (110), which is designed to manipulate a vehicle function and / or to inquire information of the vehicle function on the basis of a predetermined instruction input; -a user interface module (120) arranged to receive a voice user input (BEN); and-an interface module (130) which is designed to communicate with the at least one processor module (110) and with the large language model (LLM), the interface module (130) being designed to: provide the large language model (LLM) with first configuration information (KFG1) regarding a predetermined instruction input for a vehicle function; -providing the voice user input (BEN) or information about the voice user input (BEN) to the large language model (LLM); and-receiving a result (KNV) of the conversion of the voice user input (BEN) from the large language model (LLM) on the basis of the first configuration information (KFG1) and providing it at least partially to the at least one processor module (110) in order to manipulate the vehicle function and / or to query the information of the vehicle function correspondingly.
Need to check novelty before this filing date? Find Prior Art