Unlock instant, AI-driven research and patent intelligence for your innovation.

Abnormality and drift detection for constrained repository using domain index

A repository and abnormal technology, applied in the information field, can solve problems such as the inability to apply original data

Pending Publication Date: 2022-05-03
IBM CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Often, these methods cannot be applied to raw 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
  • Abnormality and drift detection for constrained repository using domain index
  • Abnormality and drift detection for constrained repository using domain index
  • Abnormality and drift detection for constrained repository using domain index

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0017] Existing anomaly and drift detection techniques do not provide an explanation when anomalies are detected away from, for example, the expected value region and its distance from the actual value. There is no intuitive explanation of how to calculate the expected value. Existing techniques also tend to require transformation or encoding of input data and / or fail to take into account the user's domain.

[0018] Many use cases of anomaly and drift detection can benefit from providing intuitive natural language explanations alongside detected anomalies. Additionally, existing anomaly and drift detection techniques focus on time-series datasets for anomaly detection, and thus do not consider unusual outliers and / or drifting data points in non-temporal datasets.

[0019] As described herein, embodiments of the invention include providing interpretable anomaly detection of data sets. For example, an intelligent data engineering platform may be provided that automatically det...

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

A computer-implemented method comprising: obtaining a data set and information indicative of a domain of the data set (600); obtaining constraints from a domain-indexed constraint repository based at least in part on the data set and the information (602), where the domain-indexed constraint repository includes a knowledge graph having a plurality of nodes, where each node includes an attribute associated with at least one of the plurality of domains and a constraint corresponding to the attribute; detecting an anomaly in the dataset based on whether a portion of the dataset violates the retrieved constraint (604); generating an interpretation corresponding to each of the anomalies, the interpretation describing an attribute corresponding to the violated constraint (606); and outputting an indication of the anomaly and a corresponding interpretation (608).

Description

technical field [0001] This application relates generally to information technology, and more specifically to anomaly and drift detection. Background technique [0002] Anomaly detection involves identifying irregularities in data, and typically relies on statistical or machine learning-based methods applied to numerical or encoded data. Often, these methods cannot be applied to raw data. [0003] Anomaly detection is used in a variety of applications such as intrusion detection, fraud detection, fault detection, system health monitoring, event detection in sensor networks, and detection of ecosystem disturbances. Contents of the invention [0004] In one embodiment of the invention, techniques are provided for domain-aware explainable anomaly and drift detection on multivariate raw data using a constraint repository. An exemplary computer-implemented method includes the steps of: obtaining (i) a data set and (ii) information indicative of a domain of the data set; One ...

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): G06F11/36
CPCG06N5/022G06N20/00G06N5/01G06F16/2365G06F16/9027G06N5/02G06F16/215
Inventor S.汉斯S.Z.H.夏克R.阿南塔纳拉亚南D.萨哈A.阿加瓦尔G.辛格P.K.洛希亚M.A.比德S.梅塔
Owner IBM CORP