CN-121993007-A - Vehicle window adjusting method, vehicle, storage medium and program product

CN121993007ACN 121993007 ACN121993007 ACN 121993007ACN-121993007-A

Abstract

One or more embodiments of the present disclosure provide a method for adjusting a vehicle window, a vehicle, a storage medium, and a program product, where the method is applied to a server, and the server is in communication connection with the vehicle, and includes obtaining environment sensing information and occupant information of a target vehicle, where the environment sensing information is provided based on a vehicle-mounted sensing system of the target vehicle, and the occupant information is used to characterize a user representation of an occupant associated with the target vehicle, inputting the environment sensing information and the occupant information into a natural language processing model to obtain an analysis result of a current driving environment and a vehicle window adjustment preference of the occupant, and generating and issuing a vehicle window adjustment instruction matched with the current driving environment and the vehicle window adjustment preference according to the analysis result of the natural language processing model, so as to trigger the target vehicle to adjust the vehicle window, thereby achieving intelligent and personalized vehicle window control, and significantly improving convenience in a driving process and a degree of fit of a cabin experience.

Inventors

KUANG HUAHUI
LI MING
DING JIANZE
YANG SHUO
TIAN CAN
LIU YUNPENG
ZHANG XINDA
XU SHENG
LI YAN

Assignees

浙江吉利控股集团有限公司
吉利汽车研究院（宁波）有限公司

Dates

Publication Date: 20260508
Application Date: 20260106

Claims (14)

1. The car window adjusting method is applied to a server, the server is in communication connection with a car, the server is deployed with a natural language processing model, and the method comprises the following steps: Acquiring environment perception information and passenger information of a target vehicle, wherein the environment perception information is provided based on a vehicle-mounted perception system of the target vehicle, and the passenger information is used for representing a user portrait of a passenger associated with the target vehicle; Inputting the environment perception information and the passenger information into a natural language processing model to obtain an analysis result aiming at the current driving environment and the window regulation preference of the passenger; And generating and issuing a window adjusting instruction matched with the current driving environment and the window adjusting preference according to the analysis result of the natural language processing model so as to trigger the target vehicle to adjust the window.
2. The method of claim 1, wherein the occupant information includes feature data for constructing the user representation, the feature data including at least any one of: long-term behavior habit information, physiological characteristic parameter information and subjective preference configuration information.
3. The method of claim 1, wherein the context awareness information is generated by the on-board awareness system upon satisfaction of at least one of the following types of trigger conditions: geographic location, vehicle driving conditions, external environmental conditions, occupant compartment behavior, or vehicle power conditions.
4. The method of claim 3, wherein the context awareness information is generated by the vehicle-mounted awareness system upon satisfaction of a target trigger condition of a geographic location type, the target trigger condition comprising: And determining that the target vehicle reaches a preset geographic area according to the relative relation between the position information of the target vehicle and at least one interest point of a preset type.
5. The method of claim 4, wherein determining that the target vehicle arrives at a predetermined geographic area based on a relative relationship between the location information of the target vehicle and at least one predetermined type of point of interest comprises: Receiving the position information uploaded by the target vehicle, calculating the distance between the target vehicle and the at least one interest point of the preset type according to the position information, determining that the target vehicle arrives at the geographic area when the distance is smaller than a first preset threshold value, or And determining that the target vehicle reaches the geographic area by the target vehicle under the condition that the distance is smaller than a second preset threshold value.
6. The method of claim 1, wherein the generating and issuing window adjustment instructions that match the current driving environment and the window adjustment preferences of the occupant comprises: acquiring window state information of the target vehicle and passenger operation history information aiming at a window; Judging whether the target vehicle meets the occupant leading condition in the latest judging time according to the vehicle window state information and the occupant operation history information; And under the condition that the judgment result is yes, prohibiting the generation and/or the issuing of the car window adjusting instruction.
7. The method of claim 6, wherein the occupant-dominant conditions comprise at least any of: The current opening of at least one window in the target vehicle is in a preset numerical value interval; and in the latest judging time period, the frequency of the window adjusting operation triggered by the user is higher than a preset minimum frequency threshold value.
8. The method according to claim 1, wherein after the window adjustment command is issued, the method further comprises: Acquiring window state information of the target vehicle, and judging whether a corresponding window reaches a target state consistent with the window adjusting instruction within a preset response time according to the window state information; And under the condition that the judgment result is yes, prohibiting generation and/or issuing of a new window adjusting instruction in a preset prohibition time.
9. The method of claim 1, wherein the inputting the context awareness information and the occupant information into a natural language processing model to obtain an analysis result of a current driving environment comprises: Acquiring vehicle running information of the target vehicle; and inputting the environment sensing information, the passenger information and the vehicle running information into a natural language processing model together so as to acquire an analysis result of the current driving environment.
10. The method according to claim 1, wherein the method further comprises: acquiring at least one group of associated data of the target vehicle, wherein the associated data comprises historical environment sensing information, historical vehicle running information, historical passenger information and passenger operation historical information executed by passengers for vehicle windows at corresponding historical moments; Training the natural language processing model based on at least one set of the associated data to obtain a new natural language processing model.
11. The method according to any one of claims 1 to 10, wherein the context awareness information includes in-vehicle environment awareness information and in-vehicle environment awareness information, wherein: the external environment perception information is used for representing the external driving environment of the vehicle and comprises at least one of visual environment information, auditory environment information, road surface environment information and atmospheric environment information; The in-vehicle environmental perception information is used for representing the internal state of the vehicle cockpit and comprises at least one of in-cabin visual information and in-cabin auditory information.
12. A vehicle comprising a processor, a memory for storing processor executable instructions, wherein the processor is configured to implement the steps of the method of any one of claims 1-11 by executing the executable instructions.
13. A computer readable storage medium having stored thereon computer instructions which, when executed by a processor, implement the steps of the method of any of claims 1-11.
14. A computer program product comprising computer programs/instructions which, when executed by a processor, implement the steps of the method according to any of claims 1-11.

Description

Vehicle window adjusting method, vehicle, storage medium and program product Technical Field One or more embodiments of the present disclosure relate to the field of vehicle control, and more particularly, to a method for adjusting a window of a vehicle, a storage medium, and a program product. Background In conventional vehicle designs, opening or closing of the windows of the vehicle is primarily dependent upon manual operation or voice commands by the occupant. The reasons for its regulation are usually directly served by simple immediate demands, such as ventilation or communication with the outside. With the intelligent development of automobiles, users put forward higher requirements on cabin experience, and the automobiles are expected to be more actively and more carefully adapted to complex and changeable driving environments and personalized passenger states, so that operation distraction in the driving process is reduced, and comfortableness and convenience are improved. In the related art, some vehicles are equipped with a single condition-triggered automatic window function, such as automatic closing when rain is detected, in addition to basic manual control. However, such measures face fundamental limitations in realizing higher-order intellectualization, namely, based on control logic of preset rules, it is difficult to formally define and cover all complex driving scenes formed by interleaving multi-dimensional information such as geographic positions, weather, noise, in-vehicle atmosphere and the like, and more importantly, it is impossible to understand that the complex intention and context underlying the personalized habits and long-term preferences of passengers are associated, so that the system response is stiff, and comprehensive judgment and personalized decision cannot be performed like a human. Disclosure of Invention In view of this, one or more embodiments of the present disclosure provide the following technical solutions: according to a first aspect of one or more embodiments of the present specification, there is provided a method of adjusting a vehicle window, applied to a server, the server being communicatively connected to a vehicle, the method comprising: Acquiring environment perception information and passenger information of a target vehicle, wherein the environment perception information is provided based on a vehicle-mounted perception system of the target vehicle, and the passenger information is used for representing a user portrait of a passenger associated with the target vehicle; Inputting the environment perception information and the passenger information into a natural language processing model to obtain an analysis result aiming at the current driving environment and the window regulation preference of the passenger; And generating and issuing a window adjusting instruction matched with the current driving environment and the window adjusting preference according to the analysis result of the natural language processing model so as to trigger the target vehicle to adjust the window. According to a second aspect of one or more embodiments of the present specification, a vehicle is proposed, comprising a processor, a memory for storing processor executable instructions, wherein the processor implements the steps of the method of the first aspect by executing the executable instructions. According to a third aspect of the present description there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of the first aspect. According to a fourth aspect of the present description, a computer program product comprises a computer program/instruction which, when executed by a processor, implements the steps of the method of the first aspect. According to the embodiment, the scheme of the specification comprehensively analyzes the environment sensing information provided by the vehicle-mounted sensing system and the passenger information representing the self portrait of the passenger through the natural language processing model deployed on the server, so that deep fusion understanding of complex driving scenes and individual requirements of the passenger is realized. Therefore, the limitation of preset rules is broken through, window adjusting instructions matched with the current environment and the intention of passengers are autonomously generated, the problem that the response is stiff due to the fact that the traditional scheme cannot understand context association is solved, intelligent and personalized window control similar to human judgment is finally achieved, and convenience in the driving process and the fitting degree of cabin experience are remarkably improved. Drawings FIG. 1 is a schematic architecture diagram of an adjustment system for a vehicle window shown in the disclosed embodiments of the present specification; FIG. 2 is a flow chart of a meth