CN-121997211-A - Data processing method, apparatus, electronic device, computer readable storage medium, and computer program product

Abstract

The application provides a data processing method, a data processing device, an electronic device, a computer readable storage medium and a computer program product; the method comprises the steps of obtaining environment data and vehicle running data recorded under the condition of abnormal automatic driving function, analyzing the environment data and the vehicle running data through an abnormal analysis model, and outputting abnormal reasons and/or driving risks of the automatic driving function. The application can improve the efficiency and accuracy of the analysis of the abnormal functions of the automatic driving.

Inventors

• LIU CHUANG
• GAO YANG
• XUE CHANGLIANG
• CHEN JIANCHENG

Assignees

• 北京罗克维尔斯科技有限公司

Dates

Publication Date

20260508

Application Date

20241107

Claims (12)

1. 1. A method of data processing, the method comprising: acquiring environmental data and vehicle running data recorded under the condition of abnormal automatic driving function; and analyzing the environmental data and the vehicle running data through an anomaly analysis model, and outputting the anomaly reasons and/or driving risks of the automatic driving function.
2. 2. The method according to claim 1, wherein analyzing the environmental data and the vehicle running data by an anomaly analysis model, outputting an anomaly cause and/or a driving risk of an automatic driving function, comprises: Performing environmental analysis on the environmental data through the anomaly analysis model to determine target environmental analysis data; and analyzing the target environment analysis data and the vehicle running data, and outputting the abnormality reason and/or the driving risk.
3. 3. The method of claim 2, wherein the performing environmental analysis on the environmental data to determine target environmental analysis data comprises: performing dynamic object detection and/or static object detection on the environment data, and determining at least one dynamic object data and/or at least one static object data; And analyzing according to the at least one dynamic object data and/or the at least one static object data, and determining the target environment analysis data.
4. 4. The method of claim 2, wherein the anomaly cause comprises an anomaly of at least one function module corresponding to a target environment category, the target environment category being an environment category corresponding to the target environment analysis data.
5. 5. The method according to claim 2, wherein the driving risk comprises an accident risk and/or a user subjective risk corresponding to a target environment category, and the user subjective risk is determined based on an automatic driving instruction and a user operation instruction in the vehicle driving data.
6. 6. The method according to any one of claims 1-5, further comprising: determining a target area with abnormal automatic driving function, and determining an automatic driving function correction strategy according to the abnormal reason and/or the driving risk; broadcasting the automatic driving function correction strategy in the target area so that the vehicle in the target area updates the automatic driving function of the vehicle according to the received automatic driving function correction strategy.
7. 7. A model training method, comprising: Training an initial anomaly analysis model by using a training sample set to obtain the anomaly analysis model; the training sample set comprises a plurality of training samples, each training sample comprises sample environment data, vehicle driving sample data and labeling information recorded under the condition of abnormal automatic driving functions, and the labeling information comprises abnormal cause true values and/or driving risk true values corresponding to each training sample.
8. 8. The method of claim 7, wherein the truth of the cause of the anomaly in the training sample set comprises anomalies in at least one functional module corresponding to at least one environmental category, the truth of the driving risk in the training sample set comprises at least one driving risk corresponding to at least one environmental category, and the at least one driving risk comprises at least one of an accident risk and a subjective risk of a user.
9. 9. A data processing apparatus, the apparatus comprising: the acquisition module is used for acquiring the environmental data and the vehicle running data recorded under the condition of abnormal automatic driving function; And the determining module is used for analyzing the environment data and the vehicle running data through an anomaly analysis model and outputting the anomaly reasons and/or driving risks of the automatic driving function.
10. 10. An electronic device, the electronic device comprising: a memory for storing computer executable instructions; a processor for implementing the method of any one of claims 1 to 6 or the method of claim 7 or claim 8 when executing computer executable instructions stored in said memory.
11. 11. A computer readable storage medium storing computer executable instructions, wherein the computer executable instructions or computer program when executed by a processor implement the method of any one of claims 1 to 6 or the method of claim 7 or claim 8.
12. 12. A computer program product comprising computer-executable instructions, characterized in that the computer-executable instructions or computer program, when executed by a processor, implement the method of any one of claims 1 to 6 or the method of claim 7 or claim 8.

Description

Data processing method, apparatus, electronic device, computer readable storage medium, and computer program product Technical Field The present application relates to artificial intelligence technology, and in particular, to a data processing method, apparatus, electronic device, computer readable storage medium, and computer program product. Background Currently, in a real driving scene, the automatic driving cannot be performed in a sufficient scene and working conditions, and usually, the reason for the abnormal automatic driving function is determined by manually analyzing related data when the automatic driving is abnormal. The method is low in efficiency and is easily subjectively influenced by people, so that the efficiency and accuracy of abnormality analysis of the automatic driving function are reduced. Disclosure of Invention The embodiment of the application provides a data processing method, a data processing device, electronic equipment, a computer readable storage medium and a computer program product, which can improve the accuracy and efficiency of automatic driving abnormality analysis. The technical scheme of the embodiment of the application is realized as follows: the embodiment of the application provides a data processing method, which comprises the following steps: acquiring environmental data and vehicle running data recorded under the condition of abnormal automatic driving function; and analyzing the environmental data and the vehicle running data through the anomaly analysis model, and outputting the anomaly reasons and/or driving risks of the automatic driving function. The embodiment of the application provides a model training method, which comprises the following steps: Training an initial anomaly analysis model by using a training sample set to obtain the anomaly analysis model; the training sample set comprises a plurality of training samples, each training sample comprises sample environment data, vehicle driving sample data and labeling information recorded under the condition of abnormal automatic driving functions, and the labeling information comprises abnormal cause true values and/or driving risk true values corresponding to each training sample. An embodiment of the present application provides a data processing apparatus, including: the acquisition module is used for acquiring the environmental data and the vehicle running data recorded under the condition of abnormal automatic driving function; And the determining module is used for analyzing the environmental data and the vehicle running data through the anomaly analysis model and outputting the anomaly reasons and/or driving risks of the automatic driving function. Optionally, the determining module is further configured to perform environmental analysis on the environmental data through the anomaly analysis model to determine target environmental analysis data, and analyze the vehicle driving data based on the target environmental analysis data, and output the anomaly cause and/or the driving risk. Optionally, the determining module is further configured to perform dynamic object detection and/or static object detection on the environmental data, determine at least one dynamic object data and/or at least one static object data, and analyze according to the at least one dynamic object data and/or the at least one static object data to determine the target environmental analysis data. Optionally, the abnormal reasons comprise the abnormality of at least one functional module corresponding to a target environment category, and the target environment category is an environment category corresponding to the target environment analysis data. Optionally, the driving risk comprises accident risk corresponding to the target environment category and/or user subjective risk, and the user subjective risk is determined based on an automatic driving instruction and a user operation instruction in the vehicle driving data. Optionally, the data processing device further comprises a correction module, wherein the correction module is used for acquiring a manual analysis result aiming at the environmental data and the vehicle driving data, and correcting the abnormal reason and/or driving risk according to the manual analysis result. Optionally, the data processing device further comprises a broadcasting module, wherein the determining module is further used for determining a target area with abnormal automatic driving functions and determining an automatic driving function correction strategy according to the abnormal reasons and/or the driving risks, and the broadcasting module is used for broadcasting the automatic driving function correction strategy in the target area so that the vehicles in the target area update the automatic driving functions of the vehicles according to the received automatic driving function correction strategy. The embodiment of the application provides a model training device, which comprises: the t