A method and system for operation and maintenance data mining and compliance inspection

Abstract

The present application provides an operation and maintenance data mining and compliance inspection method and system, the method comprising: obtaining operation and maintenance data information, calculating and obtaining unstructured data in the operation and maintenance data information according to the operation and maintenance data information; Perform word segmentation processing on the unstructured data, and convert the text model obtained after word segmentation processing into a digital vector model; obtain an operation and maintenance data processing model through machine learning algorithm training according to the digital vector model; according to the operation and maintenance The data processing model performs clustering processing on the digital vector model and / or obtains key elements of the digital vector model; performs clustering processing on the digital vector model according to the structured data in the operation and maintenance data information and / or Or obtain the key element points of the digital vector model to obtain structured operation and maintenance data, and obtain the inspection result of the operation and maintenance data according to the structured operation and maintenance data.

Description

Technical field [0001] The present invention relates to data management, and more particularly denote a data mining operation and maintenance and inspection method and system compliance. Background technique [0002] In the current data management, with the continued expansion of business scope as well as new applications come on stream, the maintenance department is facing shortage of manpower, production and compliance pressures aggravate the problem. Which in data management, production operation and maintenance activities will generate a lot of data operation and maintenance alarm events. Which is in the form of structured or semi-structured. Even if a similar warning, due to the difference in content can not be directly consolidated statistics; the same time, event content using natural language, semantic rules can not be identified through a simple refining. This gave the operation and maintenance behavior analysis to bring trouble; because of the massive operation and main...

AI Technical Summary

Problems solved by technology

Even for similar alarms, they cannot be directly merged and counted due to the difference in content; at the same time, the event content described in natural language cannot be identified by simply extracting semantic rules

This has brought troubles to the analysis of operation and maintenance behavior; due to the existence of massive operation and maintenance behavior data, security compliance inspections are mostly conducted by spot checks, and it is difficult to achieve full coverage

Even if you choose spot checks, you will often be troubled by the same type of alarms or events in different forms, which consumes a lot of labor and time costs

At the same time, the existing traditional data maintenance methods also have the following problems: 1. The existing problems cannot be exposed in time due to the low efficiency of manual processing; 2. The original data is not intuitive enough, and front-line personnel and even management personnel cannot directly grasp key information from the original detailed records and trends, cannot be referenced and associated analysis, and the form is not dynamic enough, so the data availability rate is low; 3. The hidden dangers of the system are not known in advance; As a key focus item, monitoring and incidents are also included in the scope of production compliance inspection. Since each team generates a large number of monitoring alarms and events every day, compliance inspection is extremely labor-intensive, and resources are limited. The inspection work cannot cover 100% of monitoring alarms and event records, and there are inspection omissions; at the same time, simple manual statistics and walk-through inspections cannot form a comprehensive and systematic correlation analysis, and the accuracy rate cannot be fully guaranteed

Since the number of K cannot be known in advance, it takes a lot of work to adjust the K parameters

[0006] 3. Custom semantic rules cannot adapt to all scenarios

Images