CN-121979767-A - Vehicle diagnosis method, device, vehicle and storage medium

CN121979767ACN 121979767 ACN121979767 ACN 121979767ACN-121979767-A

Abstract

The application relates to the technical field of vehicles, in particular to a vehicle diagnosis method, a vehicle diagnosis device, a vehicle and a storage medium, wherein the method comprises the steps of judging whether a dotting signal of the vehicle is received or not; and carrying out fault analysis according to the heterogeneous data to obtain a fault analysis result, packaging the fault analysis result and the original data to obtain diagnostic data, and uploading the diagnostic data to a preset terminal. Therefore, the problems that the defects are easy to miss, the data are difficult to be associated in a scattered way and the process is tedious and low in efficiency due to the fact that the defects are recorded manually are solved, and the defect reproduction rate and the recording efficiency can be improved.

Inventors

YAO ZHIHONG
Hu Zhaoquan
ZHAO XINCHUN
LI CHUNBO

Assignees

奇瑞汽车股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260112

Claims (10)

1. A method of diagnosing a vehicle, comprising the steps of: judging whether a dotting signal of the vehicle is received or not; if the dotting signal is received, acquiring heterogeneous data of the vehicle based on the dotting signal, and packaging the heterogeneous data based on a time stamp of the dotting signal to obtain original data; and carrying out fault analysis according to the heterogeneous data to obtain a fault analysis result, packaging the fault analysis result and the original data to obtain diagnosis data, and uploading the diagnosis data to a preset terminal.
2. The method of claim 1, wherein the disparate data comprises at least one of communication data, log data, video data, and audio data, performing a failure analysis based on the disparate data to obtain the failure analysis result comprises: performing voice recognition on the audio data to obtain text description, and performing semantic analysis on the text description based on a preset rule engine to obtain fault information, wherein the fault information comprises the current fault type; and determining at least one piece of data to be analyzed from the heterogeneous data according to the current fault type, and performing fault diagnosis according to the at least one piece of data to be analyzed to obtain a fault analysis result.
3. The method according to claim 2, wherein determining at least one data to be analyzed from the heterogeneous data according to the current fault type, and performing fault diagnosis according to the at least one data to be analyzed to obtain the fault analysis result, comprises: when the fault type is a vehicle control type fault, determining that the data to be analyzed is communication data, and inputting the communication data into a preset fault analysis model to obtain a fault analysis result; and when the fault type is a system software type fault, determining that the data to be analyzed is log data, and determining the fault analysis result based on a preset fault mode rule base according to the log data.
4. The method according to claim 1, comprising, after performing a failure analysis based on the heterogeneous data to obtain a failure analysis result: Processing the fault analysis result to obtain fault characteristics, storing the fault characteristics into a preset knowledge base, and judging whether any type of fault sample in the preset knowledge base exceeds a preset sample threshold value; if any type of fault sample in the preset knowledge base exceeds a preset sample threshold, generating an abnormality reminding instruction, and carrying out abnormality reminding based on the abnormality reminding instruction.
5. The method of claim 1, wherein the acquiring heterogeneous data of the vehicle based on the dotting signal comprises: Determining a time stamp of the dotting signal, and determining a first time range to a fourth time range based on the time stamp; And acquiring communication data in the first time range, log data in the second time range, video data in the third time range and audio data in the fourth time range to obtain the heterogeneous data.
6. A diagnostic device for a vehicle, comprising: The judging module is used for judging whether a dotting signal of the vehicle is received or not; The acquisition module is used for acquiring heterogeneous data of the vehicle based on the dotting signal under the condition that the dotting signal is received, and packaging the heterogeneous data based on the timestamp of the dotting signal to obtain original data; the diagnosis module is used for carrying out fault analysis according to the heterogeneous data to obtain a fault analysis result, packaging the fault analysis result and the original data to obtain diagnosis data, and uploading the diagnosis data to a preset terminal.
7. The apparatus of claim 6, wherein the disparate data comprises at least one of communication data, log data, video data, and audio data, the diagnostic module comprises: the recognition unit is used for carrying out voice recognition on the audio data to obtain text description, carrying out semantic analysis on the text description based on a preset rule engine to obtain fault information, wherein the fault information comprises the current fault type; and the generating unit is used for determining at least one piece of data to be analyzed from the heterogeneous data according to the current fault type, and carrying out fault diagnosis according to the at least one piece of data to be analyzed to obtain a fault analysis result.
8. The apparatus of claim 7, wherein the generating unit comprises: The first determining subunit is used for determining that the data to be analyzed is communication data when the fault type is a vehicle control type fault, and inputting the communication data into a preset fault analysis model to obtain a fault analysis result; And the second determining subunit is used for determining that the data to be analyzed is log data when the fault type is a system software type fault, and determining the fault analysis result based on a preset fault mode rule base according to the log data.
9. A vehicle comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor executing the program to implement the method of diagnosing a vehicle according to any one of claims 1-5.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the program is executed by a processor for implementing a diagnostic method of a vehicle according to any one of claims 1-5.

Description

Vehicle diagnosis method, device, vehicle and storage medium Technical Field The present application relates to the field of vehicle technologies, and in particular, to a vehicle diagnosis method and apparatus, a vehicle, and a storage medium. Background In the dynamic road test process of the whole vehicle, testers frequently encounter sporadic and transient functional anomalies such as unresponsive voice instructions, failure of vehicle window control, blocking of a central control interface and the like, the problems are difficult to reproduce, multi-system collaboration is involved, if complete contexts cannot be accurately captured when the problems occur, the difficulty of subsequent reproduction and root cause positioning is greatly increased, and the quality verification efficiency and research and development iteration period of the whole vehicle software are seriously influenced. The related art has the defects that (1) the road test problem record depends on manual notes and key information is easy to miss, (2) bus data, host logs and video pictures are stored in a scattered mode and are difficult to analyze in a post-association mode, (3) the defect submitting process is complicated, manual data integration is needed, and the efficiency is low, so that an intelligent vehicle testing method capable of replacing manual records and realizing high-precision automatic diagnosis and reporting is needed. Disclosure of Invention The application provides a vehicle diagnosis method, a vehicle diagnosis device, a vehicle and a storage medium, which are used for solving the problems that the road test defects are easy to miss, the data are difficult to be associated in a scattered way, the flow is tedious and the efficiency is low by means of manual recording, and can improve the defect reproduction rate and the recording efficiency. An embodiment of a first aspect of the present application provides a diagnostic method for a vehicle, including the steps of: judging whether a dotting signal of the vehicle is received or not; if the dotting signal is received, acquiring heterogeneous data of the vehicle based on the dotting signal, and packaging the heterogeneous data based on a time stamp of the dotting signal to obtain original data; and carrying out fault analysis according to the heterogeneous data to obtain a fault analysis result, packaging the fault analysis result and the original data to obtain diagnosis data, and uploading the diagnosis data to a preset terminal. Optionally, in some embodiments, the heterogeneous data includes at least one of communication data, log data, video data, and audio data, and performing fault analysis according to the heterogeneous data to obtain a fault analysis result includes: performing voice recognition on the audio data to obtain text description, and performing semantic analysis on the text description based on a preset rule engine to obtain fault information, wherein the fault information comprises the current fault type; and determining at least one piece of data to be analyzed from the heterogeneous data according to the current fault type, and performing fault diagnosis according to the at least one piece of data to be analyzed to obtain a fault analysis result. Optionally, in some embodiments, the determining at least one data to be analyzed from the heterogeneous data according to the current fault type, and performing fault diagnosis according to the at least one data to be analyzed to obtain the fault analysis result includes: when the fault type is a vehicle control type fault, determining that the data to be analyzed is communication data, and inputting the communication data into a preset fault analysis model to obtain a fault analysis result; and when the fault type is a system software type fault, determining that the data to be analyzed is log data, and determining the fault analysis result based on a preset fault mode rule base according to the log data. Optionally, in some embodiments, after performing fault analysis according to the heterogeneous data to obtain a fault analysis result, the method includes: Processing the fault analysis result to obtain fault characteristics, storing the fault characteristics into a preset knowledge base, and judging whether any type of fault sample in the preset knowledge base exceeds a preset sample threshold value; if any type of fault sample in the preset knowledge base exceeds a preset sample threshold, generating an abnormality reminding instruction, and carrying out abnormality reminding based on the abnormality reminding instruction. Optionally, in some embodiments, the acquiring heterogeneous data of the vehicle based on the dotting signal includes: Determining a time stamp of the dotting signal, and determining a first time range to a fourth time range based on the time stamp; And acquiring communication data in the first time range, log data in the second time range, video data in the third time range an