CN-121973701-A - Rearview mirror control system, method and medium based on large language model

Abstract

The application discloses a rearview mirror control system, method and medium based on a large language model. The method comprises the steps of obtaining driver information through a vehicle-mounted sensor module, sensing driving environment, obtaining adjustment input data, generating a rearview mirror adjustment instruction through a large language model module according to the adjustment input data, analyzing the rearview mirror adjustment instruction by a vehicle-mounted system module and controlling a rearview mirror driving system to execute corresponding actions, and receiving control signals sent by the vehicle-mounted system module by the rearview mirror driving module to adjust a rearview mirror. According to the application, the driver information and the environment information are integrated through the large language model, the corresponding adjustment instruction is generated in an inference mode, the vehicle-machine system analyzes the instruction and then controls the rearview mirror to execute corresponding actions through the CAN signal, and the driving experience and the safety of the driver are improved.

Inventors

• LI PENG
• QU LEI
• WANG JINKUI

Assignees

• 北京汽车股份有限公司

Dates

Publication Date

20260505

Application Date

20260306

Claims (10)

1. 1. A rearview mirror control system based on a large language model, comprising: The vehicle-mounted sensor module is used for acquiring adjustment input data; The large language model module generates a rearview mirror adjustment instruction according to the adjustment input data; The vehicle-mounted system module is used for analyzing the rearview mirror adjustment instruction and controlling a rearview mirror driving system to execute corresponding actions; and the rearview mirror driving module is used for receiving the control signal sent by the vehicle machine system module and adjusting the position and the angle of the rearview mirror.
2. 2. The large language model based rearview mirror control system of claim 1, wherein said on-board sensor module comprises a seat position sensor, a driver identification module, a door status detection sensor, a grade detection sensor.
3. 3. The large language model based rearview mirror control system of claim 1, wherein the adjustment input data comprises driver height, seat position, door status and current driving grade, road curvature.
4. 4. A large language model based rearview mirror control method using the large language model based rearview mirror control system as claimed in any one of claims 1-3, comprising: The method comprises the steps of obtaining driver information, sensing driving environment and obtaining adjustment input data through a vehicle-mounted sensor module; Generating a rearview mirror adjustment instruction through a large language model module according to the adjustment input data; The vehicle-mounted system module analyzes the rearview mirror adjustment instruction and controls the rearview mirror driving system to execute corresponding actions; And the rearview mirror driving module receives the control signal sent by the vehicle machine system module and adjusts the rearview mirror.
5. 5. The large language model based rearview mirror control method of claim 4, wherein said adjustment input data comprises driver height, seat position, door status and current driving grade, road curvature.
6. 6. The large language model based rearview mirror control method of claim 5, wherein said rearview mirror adjustment instructions comprise adjusting angle, position.
7. 7. The large language model based rearview mirror control method of claim 6, wherein generating rearview mirror adjustment instructions via a large language model module based on the adjustment input data comprises: and determining whether data which is the same as or similar to the adjustment input data exists in the historical data according to the adjustment input data, if so, extracting the corresponding rearview mirror adjustment instruction, and if not, carrying out reasoning analysis by combining the input data by a large voice model to generate the corresponding rearview mirror adjustment instruction.
8. 8. The large language model based rearview mirror control method as claimed in claim 4, wherein the large language model module recognizes that the rearview mirror adjustment instruction is directly generated after a user gets on a vehicle, or The large language model module generates the rearview mirror adjustment instruction based on the user voice trigger.
9. 9. The large language model based rearview mirror control method of claim 4, further comprising: after the rearview mirror is adjusted, the visual field effect of the user is monitored through the vehicle-mounted sensor, and if the visual field effect is unsatisfactory, the rearview mirror is adjusted again through a voice command.
10. 10. A computer readable storage medium, characterized in that the computer readable storage medium stores a computer program which, when executed by a processor, implements the large language model based rearview mirror control method as claimed in any one of claims 4-9.

Description

Rearview mirror control system, method and medium based on large language model Technical Field The invention relates to the field of automobile control, in particular to a rearview mirror control system, method and medium based on a large language model. Background With the continuous progress of vehicle technology, vehicle-mounted intelligent systems have become an important component of modern automobiles. Most of the existing rearview mirror adjusting methods are traditional physical control methods, and a driver needs to manually adjust the rearview mirror through a button or a knob. However, conventional rearview mirror adjustment methods have some disadvantages: 1. the manual operation is complicated, and the driver needs to manually adjust the position of the rearview mirror, and particularly when the position is switched among different drivers or passengers, the problem of inconvenient adjustment exists. 2. The prior system cannot automatically adjust the rearview mirror according to the personalized requirements of drivers, heights, seat positions and other parameters, and cannot provide more accurate and comfortable visual angles. 3. The existing system cannot adapt to environmental changes in real time, and cannot take the influence of the environmental changes in the driving process into consideration, such as different roads and different visual field requirements under weather conditions. 4. In the prior art, the adjustment of the rearview mirror is always a passive process, and cannot be adjusted in real time according to the individual requirements of drivers or driving environments, especially in a vehicle with multiple drivers, the rearview mirror needs to be manually adjusted again each time the drivers switch. Therefore, how to utilize modern artificial intelligence technology, especially a Large Language Model (LLM), and combine with vehicle-mounted sensor information to realize automatic, active and intelligent rearview mirror control becomes a great demand for improving comfort and safety of drivers, and it is necessary to develop a rearview mirror control system, method and medium based on the large language model. The information disclosed in the background section of the invention is only for enhancement of understanding of the general background of the invention and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person skilled in the art. Disclosure of Invention The invention provides a rearview mirror control system, a rearview mirror control method and a rearview mirror control medium based on a large language model, which can automatically calculate and adjust the angle of a rearview mirror by combining the height, the seat position, the personal habit and the real-time driving environment (such as gradient and the like) of a driver, so as to realize the intelligent and personalized adjustment of the rearview mirror. The driver information and the environment information are integrated through the large language model, the corresponding adjustment instruction is generated in an inference mode, the vehicle-machine system analyzes the instruction and then controls the rearview mirror to execute corresponding actions through the CAN signal, and driving experience and safety of the driver are improved. In a first aspect, embodiments of the present disclosure provide a rearview mirror control system based on a large language model, including: The vehicle-mounted sensor module is used for acquiring adjustment input data; The large language model module generates a rearview mirror adjustment instruction according to the adjustment input data; The vehicle-mounted system module is used for analyzing the rearview mirror adjustment instruction and controlling a rearview mirror driving system to execute corresponding actions; and the rearview mirror driving module is used for receiving the control signal sent by the vehicle machine system module and adjusting the position and the angle of the rearview mirror. Preferably, the vehicle-mounted sensor module comprises a seat position sensor, a driver identity recognition module, a vehicle door state detection sensor and a gradient detection sensor. Preferably, the adjustment input data includes the height of the driver, the seat position, the door status, and the current driving gradient, the road curvature. In a second aspect, an embodiment of the present disclosure further provides a rearview mirror control method based on a large language model, including: The method comprises the steps of obtaining driver information, sensing driving environment and obtaining adjustment input data through a vehicle-mounted sensor module; Generating a rearview mirror adjustment instruction through a large language model module according to the adjustment input data; The vehicle-mounted system module analyzes the rearview mirror adjustment instruction and controls the rearvie