CN-122019866-A - Method and device for associating scene of vehicle with audio, vehicle and storage medium

CN122019866ACN 122019866 ACN122019866 ACN 122019866ACN-122019866-A

Abstract

The application relates to a method, a device, a vehicle and a storage medium for matching and associating a scene of a vehicle with audio, wherein the method for matching and associating the scene of the vehicle with the audio can firstly determine a current audio preference analysis result and a scene mode of the vehicle according to multi-source data, then determine a current user portrait according to the current audio preference analysis result and a historical audio preference analysis result in a memory bank, accurately represent the current user preference according to the current user portrait, and then determine matched recommended audio according to the current user portrait and the scene mode, so that the recommended audio can meet the user preference and adapt to the current scene mode of the vehicle, and the accuracy of the recommended audio and the user experience of the user are improved.

Inventors

CHEN YING
LIU ZHIYU
ZHANG YUAN
ZHANG YUANMOU
Nie Yamei

Assignees

重庆蓝电汽车科技有限公司

Dates

Publication Date: 20260512
Application Date: 20251204

Claims (13)

1. A method of associating a scene of a vehicle with audio, the method comprising: acquiring multi-source data; determining a current audio preference analysis result and a scene mode of the vehicle according to the multi-source data; determining a current user portrait according to the current audio preference analysis result and the historical audio preference analysis result in the memory; And determining matched recommended audio according to the current user portrait and the scene mode.
2. The method of claim 1, wherein obtaining multi-source data comprises: Acquiring multi-source original data at each interval for a preset duration, and/or acquiring the multi-source original data when a preset trigger event is detected; and carrying out data preprocessing on the multi-source original data to obtain the multi-source data, wherein the data preprocessing comprises at least one of data cleaning, data deduplication and format unification.
3. The method of claim 1, wherein determining the current audio preference analysis result from the multi-source data comprises: determining preliminary audio preference information according to music application data in the multi-source data; extracting dominant expression data from voice data in the multi-source data; and determining the current audio preference analysis result according to the preliminary audio preference information and the explicit expression data.
4. A method according to claim 3, wherein determining the current audio preference analysis result from the preliminary audio preference information and the explicit expression data comprises: Acquiring target preference analysis weights under the condition that the explicit expression data contains audio preference characteristics, wherein the target preference analysis weights contain first weight coefficients corresponding to the preliminary audio preference information and second weight coefficients corresponding to the audio preference characteristics; Determining the current audio preference analysis result according to the preliminary audio preference information, the first weight coefficient, the audio preference feature and the second weight coefficient; and under the condition that the explicit expression data does not contain the audio preference characteristics, determining the current audio preference analysis result according to the preliminary audio preference information.
5. The method of claim 4, wherein obtaining target preference analysis weights comprises: acquiring the confidence coefficient of the audio preference feature; acquiring a preset preference mapping relation, wherein the preference mapping relation is a mapping relation between confidence coefficient and preference analysis weight; and determining target preference analysis weight according to the confidence coefficient and the preference mapping relation, wherein the higher the confidence coefficient is, the smaller the first weight coefficient is and the larger the second weight coefficient is.
6. The method of claim 1, wherein determining a scene mode of a vehicle from the multi-source data comprises: extracting driver and passenger state information, vehicle state information and environment perception data from the multi-source data; Determining a target scene mode with highest matching degree from preset scene modes according to the driver and passenger state information, the vehicle state information and the environment perception data; and taking the target scene mode as the scene mode of the current vehicle.
7. The method of claim 1, wherein determining the current user representation based on the current audio preference analysis result and the historical audio preference analysis result in the memory bank comprises: Acquiring a historical audio preference analysis result in a memory bank; distributing time weight coefficients to the current audio preference analysis result and the historical audio preference analysis result according to time, wherein the earlier the time corresponding to the analysis result is, the smaller the distributed time weight coefficient is; and determining the current user portrait according to the current audio preference analysis result, the historical audio preference analysis result and the time weight coefficient.
8. The method of claim 7, wherein each of the current audio preference analysis result and the historical audio preference analysis result includes an audio preference feature and a corresponding preference, wherein determining the current user representation based on the current audio preference analysis result, the historical audio preference analysis result, and the time weighting factor comprises: For each audio preference feature, acquiring a time weight coefficient corresponding to an analysis result containing the audio preference feature and the preference degree of the audio preference feature in the corresponding analysis result, and taking the sum of products of the time weight coefficients and the corresponding preference degree as a preference feature weighted calculation value of the audio preference feature; And sequencing all the preference feature weighted calculation values, and determining the current user portrait according to the audio preference features corresponding to the N preference feature weighted calculation values sequenced in the front, wherein N is greater than 1.
9. The method of claim 1, wherein determining matching recommended audio from the current user representation and the scene mode comprises: Determining a target audio type according to the scene mode and a preset mapping relation, wherein the mapping relation is the mapping relation between the scene mode and the audio type; Determining an audio list corresponding to the target audio type; determining matching recommended audio from the audio list according to the current user portrait; Or alternatively Inputting the current user representation and the scene mode into a pre-trained artificial intelligence model; and acquiring recommended audio output by the artificial intelligent model.
10. The method of claim 1, wherein after determining the matching recommended audio from the current user representation and the scene mode, the method further comprises: Acquiring recommendation reasons corresponding to the recommendation audio; Displaying the recommended audio and the recommended reason; acquiring feedback information of the user on the recommended audio, and redetermining a latest scene mode and a latest current user portrait; and re-determining matched recommended audio based on the feedback information, the latest current user portrait and the latest scene mode.
11. A scene and audio matching association device for a vehicle, the device comprising: The acquisition module is used for acquiring multi-source data; The first determining module is used for determining the current audio preference analysis result and the scene mode of the vehicle according to the multi-source data; The second determining module is used for determining the current user portrait according to the current audio preference analysis result and the historical audio preference analysis result in the memory bank; and the matching module is used for determining matched recommended audio according to the current user portrait and the scene mode.
12. The vehicle is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus; a memory for storing a computer program; a processor for implementing the scene and audio matching association method of a vehicle according to any one of claims 1 to 10 when executing a program stored on a memory.
13. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements a scene and audio matching association method of a vehicle according to any of claims 1-10.

Description

Method and device for associating scene of vehicle with audio, vehicle and storage medium Technical Field The application relates to the technical field of vehicle-mounted audio matching recommendation, in particular to a method and a device for associating scene and audio matching of a vehicle, the vehicle and a storage medium. Background Currently, a vehicle-mounted information entertainment system has a music playing function generally, and some preliminary personalized recommendation schemes are presented, but the current recommendation schemes generally rely on historical behavior data of a single music application of a user to conduct recommendation, or refer to the current time to conduct recommendation (such as recommending and playing soft and relaxed music in a working period), and cannot provide a personalized audio experience which is truly accurate and accords with the current scene of a vehicle for the user. Disclosure of Invention The application provides a method, a device, a vehicle and a storage medium for matching and associating a scene and audio of a vehicle, which are used for solving the technical problem of how to enable recommended audio to meet user preference and adapt to the scene of the vehicle. In a first aspect, the present application provides a method for associating a scene of a vehicle with audio matching, the method comprising: acquiring multi-source data; determining a current audio preference analysis result and a scene mode of the vehicle according to the multi-source data; determining a current user portrait according to the current audio preference analysis result and the historical audio preference analysis result in the memory; And determining matched recommended audio according to the current user portrait and the scene mode. Optionally, acquiring the multi-source data includes: Acquiring multi-source original data at each interval for a preset duration, and/or acquiring the multi-source original data when a preset trigger event is detected; and carrying out data preprocessing on the multi-source original data to obtain the multi-source data, wherein the data preprocessing comprises at least one of data cleaning, data deduplication and format unification. Optionally, determining the current audio preference analysis result according to the multi-source data includes: determining preliminary audio preference information according to music application data in the multi-source data; extracting dominant expression data from voice data in the multi-source data; and determining the current audio preference analysis result according to the preliminary audio preference information and the explicit expression data. Optionally, determining the current audio preference analysis result according to the preliminary audio preference information and the explicit expression data includes: Acquiring target preference analysis weights under the condition that the explicit expression data contains audio preference characteristics, wherein the target preference analysis weights contain first weight coefficients corresponding to the preliminary audio preference information and second weight coefficients corresponding to the audio preference characteristics; Determining the current audio preference analysis result according to the preliminary audio preference information, the first weight coefficient, the audio preference feature and the second weight coefficient; and under the condition that the explicit expression data does not contain the audio preference characteristics, determining the current audio preference analysis result according to the preliminary audio preference information. Optionally, obtaining the target preference analysis weight includes: acquiring the confidence coefficient of the audio preference feature; acquiring a preset preference mapping relation, wherein the preference mapping relation is a mapping relation between confidence coefficient and preference analysis weight; and determining target preference analysis weight according to the confidence coefficient and the preference mapping relation, wherein the higher the confidence coefficient is, the smaller the first weight coefficient is and the larger the second weight coefficient is. Optionally, determining a scene mode of the vehicle according to the multi-source data includes: extracting driver and passenger state information, vehicle state information and environment perception data from the multi-source data; Determining a target scene mode with highest matching degree from preset scene modes according to the driver and passenger state information, the vehicle state information and the environment perception data; and taking the target scene mode as the scene mode of the current vehicle. Optionally, determining the current user portrait based on the current audio preference analysis result and the historical audio preference analysis result in the memory bank includes: Acquiring a historical audio prefere