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

Abnormal data feature extraction method, device and equipment and storage medium

An abnormal data and feature extraction technology, applied in the field of big data processing, can solve the problems of inability to find abnormal data, large workload, low accuracy, etc., to eliminate subjective factors and reduce workload.

Inactive Publication Date: 2020-06-26
NEUSOFT REACH AUTOMOBILE TECH (SHENYANG) CO LTD
View PDF5 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] In the prior art, the exception tree method is often used to identify the abnormal data in the battery data, that is, to use the artificially accumulated knowledge to generate rules to screen out the abnormal data. The workload is heavy and the accuracy is low, and the manually formulated rules can only filter out The abnormal data known by people based on knowledge cannot discover the unknown abnormal data

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
  • Abnormal data feature extraction method, device and equipment and storage medium
  • Abnormal data feature extraction method, device and equipment and storage medium
  • Abnormal data feature extraction method, device and equipment and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] After research, the applicant found that when using the abnormal tree method to identify abnormalities in battery data, misjudgments and missed judgments often occur, and the accuracy is low, and the rules are manually formulated. Because there are many factors considered, a large number of Detailed rules take a long time and require a lot of work. After misjudgment, missed judgment, etc., it needs to be corrected manually, which adds a lot of extra workload. More importantly, artificially formulated rules can only filter out abnormal data judged by people based on knowledge, that is, abnormal data that people have discovered, while unknown abnormal data that people have not discovered cannot be predicted. For example, in general, the probe temperature profile shows aggregation, and only when abnormal, it shows emission. However, this rule often leads to misjudgment in winter. Through experiments, the applicant found that if the battery is charged, the battery will be ...

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 embodiment of the invention discloses an abnormal data feature extraction method, device and equipment, and a storage medium. The method comprises the steps: obtaining vehicle battery data; constructing a neural network model according to the characteristics of time sequence and high dimension of the vehicle battery data; and extracting a feature vector of the vehicle battery data according tothe neural network model. According to the technical scheme provided by the invention, the neural network model is constructed according to the characteristics of the vehicle battery data, the feature vectors of the data can be automatically extracted from a large number of vehicle battery data by adopting the model structure, a large number of detailed rules do not need to be manually made, theworkload is reduced, and abnormal data determined according to the feature vectors automatically extracted by the model is more accurate.

Description

technical field [0001] The invention relates to the field of big data processing, in particular to a method, device, equipment and storage medium for extracting abnormal data features. Background technique [0002] With the country's great attention and strong support, the development of my country's new energy vehicle industry has entered a growth period from the incubation period. The latest production and sales data released by the China Association of Automobile Manufacturers shows that as of September, the production and sales of new energy vehicles have completed 888,000 units and 872,000 units respectively. million vehicles, an increase of 20.9% and 20.8% respectively over the same period of the previous year. [0003] The huge production and sales of new energy vehicles in my country have also brought many safety issues. As of August 18, 2019, the New Energy Vehicle National Big Data Alliance released the "New Energy Vehicle National Supervision Platform Big Data Safe...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G07C5/08G06N3/04G06N3/08B60L3/00
CPCG07C5/0808G06N3/088B60L3/0046G06N3/044G06N3/045
Inventor 李鹏飞
Owner NEUSOFT REACH AUTOMOBILE TECH (SHENYANG) CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com