Abnormal data screening method
A technology of abnormal data and screening methods, which is applied in neural learning methods, electrical digital data processing, digital data information retrieval, etc., can solve problems such as poor abnormal detection effect, and achieve the effect of reducing deviation, reducing variance and deviation
Pending Publication Date: 2021-10-19
上海梯之星信息科技有限公司
View PDF5 Cites 2 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0004] The purpose of the present invention is to provide a method for screening abnormal data to solve the problem of poor abnormal detection effect
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 moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment approach
[0073] Combine figure 1 with figure 2 As shown, in accordance with an embodiment of the present invention, an abnormal data screening method of the present invention includes the following steps:
[0074] S1. Collect target data; where the target data includes: target history data and target real-time data;
[0075] S2. Preprocessing the target data and conducts feature extraction;
[0076] S3. As a training set, training is based on the parallel integrated abnormality detection model based on local characteristics;
[0077] S4. Using training completion of parallel integrated abnormal detection model to infer the target real-time data, filtering out the abnormal data of the target.
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
Login to view more Abstract
The invention relates to an abnormal data screening method. The abnormal data screening method comprises the following steps: S1, collecting target data, wherein the target data comprises target historical data and target real-time data; S2, preprocessing the target data, and performing feature extraction; S3, training a parallel integrated anomaly detection model based on local features by taking the target historical data as a training set; and S4, deducing the target real-time data by using the trained parallel integrated anomaly detection model, and screening out the abnormal data of the target. According to the method, the relationship between local data is utilized, the basic model is screened, mutual counteraction between the basic classifier with a good effect and the basic classifier with a poor effect is avoided, and the local data features are better utilized.
Description
Technical field [0001] The present invention relates to an abnormal data screening method, and more particularly to an abnormal data screening method. Background technique [0002] Existing abnormal detection is no oversight algorithm, and this traditional abnormal detection integrated algorithm has two problems. 1. Because the integrated algorithm is combined by multiple detectors, after the final training is completed, there may be a good model, and there may be a model of effectiveness. Because there is no label, these models cannot be filtered, which can only be used All of the basic classifiers, the effect, the effect of the effect, the effect is poor, and the relationship between local data is more conducive to detecting anomalous value. The integrated algorithm is often in the whole situation. Consider problems, there is no relationship between data local. [0003] With the increase in modern high-rise buildings, elevators become important transportation tools. There is a ...
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
Login to view more Patent Type & Authority Applications(China)
IPC IPC(8): G06F16/9035G06N3/08
CPCG06F16/9035G06N3/08
Inventor 李壮朱帅贾春华刘峰蔡巍伟
Owner 上海梯之星信息科技有限公司
Who we serve
- R&D Engineer
- R&D Manager
- IP Professional
Why Eureka
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Social media
Try Eureka
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap