Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Method for detecting abnormal data of automobile maintenance record library

A technology for car maintenance and abnormal data, which is applied in the fields of electrical digital data processing, error detection/correction, natural language data processing, etc. It can solve problems such as weak data matching, low detection accuracy, and no corresponding relationship, and achieve quality The effect of improving management level and enhancing precision

Pending Publication Date: 2021-11-26
RES INST OF HIGHWAY MINIST OF TRANSPORT
View PDF0 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The existing method has weak data matching and low detection accuracy, and there is no corresponding relationship between the three data fields of fault description, maintenance items, and maintenance parts
The reason is that the existing method builds an abnormal data detection algorithm based on the traditional idea of ​​exhaustive matching, but it cannot exhaustively describe all the description results of each field in more than 10,000 parts of the entire car; The description language is not standardized and unified, so some abnormal data uploaded to the automobile maintenance record database cannot be accurately identified by existing methods

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Method for detecting abnormal data of automobile maintenance record library
  • Method for detecting abnormal data of automobile maintenance record library
  • Method for detecting abnormal data of automobile maintenance record library

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The invention provides a method for detecting abnormal data in the automobile maintenance record library, which has been practically applied in the data detection work of the ministerial-level automobile maintenance electronic health file system, and solves the problem that the original system can only identify the existence of null values ​​or incorrect data types. Abnormal conditions of matching, but for data with no null value and correct data type, it is impossible to judge whether it is normal or abnormal.

[0048] For data with correct and complete data types, the abnormal manifestations are as follows: First, the data of a single field is abnormal, which mainly appears in the fault description field. The standard content consists of the name of the auto part and its working status description, and the actual data content only contains a certain part. Or only contains the working status, this kind of abnormality is that the language description is not standardized;...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to a method for detecting abnormal data of an automobile maintenance record library. The method comprises the steps of performing preprocessing and feature extraction on the data of the automobile maintenance record library; reconstructing the data by using an automatic encoder for suppressing the depth; obtaining weight vectors and bias vectors of all layers with reconstruction loss and accuracy meeting expected requirements through deep training, and constructing a discrimination standard on the basis of the weight vectors and the bias vectors to carry out normal feature labeling on normal data; and performing abnormal feature labeling on the abnormal data so as to complete the detection of the abnormal data. According to the invention, through regularization suppression of the loss function, a detection algorithm for the abnormal data of the automobile maintenance record library is established, and the accuracy of abnormal data identification and the quality of data in the library can be effectively improved.

Description

technical field [0001] The invention relates to the technical field of data detection, in particular to a method for detecting abnormal data in an automobile maintenance record store. Background technique [0002] The data of the automobile maintenance record database includes 5 data fields of repair mileage, driving time, fault description, maintenance items and maintenance parts. The automobile maintenance record database is the data basis for the operation of the automobile maintenance electronic health record system. The electronic health record system for automobile maintenance establishes links between industry management departments, maintenance companies and vehicle owners, and is of great value in the two levels of post-market channels and maintenance big data. Build a data analysis and big data service system through systematic data resources and advantages to provide services for car owners, maintenance companies, industry management departments and related indust...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G06F11/34G06K9/62G06F40/284
CPCG06F11/3409G06F40/284G06F18/24G06F18/214
Inventor 周刚陈方华耿心蔡凤田
Owner RES INST OF HIGHWAY MINIST OF TRANSPORT
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products