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

A security analysis and automatic evaluation method based on indicator threshold and semantic parsing

A security analysis and automatic evaluation technology, applied in semantic analysis, natural language data processing, data processing applications, etc., can solve problems such as low data utilization, high dependence on expert experience, and insufficient automation of analysis methods

Active Publication Date: 2022-07-26
THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Existing document review methods have increasingly obvious deficiencies such as excessive reliance on expert experience, insufficient information mining, low data utilization, and insufficient automation of analysis 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
  • A security analysis and automatic evaluation method based on indicator threshold and semantic parsing
  • A security analysis and automatic evaluation method based on indicator threshold and semantic parsing
  • A security analysis and automatic evaluation method based on indicator threshold and semantic parsing

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0034] 1. Construction of security indicator entities

[0035] The security indicator entity library is the basis of semantic analysis. The richer and more accurate the indicators contained in the entity library, the higher the accuracy of word segmentation algorithm segmentation. According to the accident causation theory of different safety activities and safety matters, combined with the evaluation requirements such as safety regulations, technical requirements, and judgment basis, the present invention constructs an index entity database by grading and classification through the analytic hierarchy process, and defines the safety index entities and attributes. Process such as figure 2 shown, the specific steps are as follows:

[0036] a) Select documents such as safety regulations and standards, technical requirements, judgment basis, review outline, and safety analysis report as the corpus for determining the indicator entities;

[0037] b) From the corpus, according to...

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 discloses a security analysis and automatic evaluation method based on index threshold and semantic analysis. First, extract semantic relationships from unstructured security analysis reports, regulations and standards, and other security analysis original corpora to build a standardized security knowledge base; at the same time, build security indicator entity sets according to dimensions such as activities and events, and classify and hierarchically divide security Indicator set; based on the semantic similarity calculation method, it can identify and extract security indicator entities and threshold attributes from corpora such as regulations, standards, technical requirements, and judgment basis, and can identify and extract security indicator entities and monitoring data attributes from security analysis reports; Semantic parsing results can automatically benchmark and determine the satisfaction of safety indicators, and can review and verify the initial judgment results of indicators in combination with expert experience. This method meets the needs of users for fast, accurate and intelligent safety analysis and automatic evaluation of different activities and events, and can effectively improve the efficiency and accuracy of safety evaluation.

Description

technical field [0001] The invention belongs to the field of safety supervision, and in particular relates to a safety analysis and automatic evaluation method based on index thresholds and semantic analysis, which is suitable for safety evaluation of certain types of task activities or task matters. Background technique [0002] For task activities or tasks in the field of safety supervision, in the safety assessment work that has been carried out, the method of document review is usually adopted, and the review experts compare relevant safety laws, regulations and technical standards, and combine expert experience to find safety problems, and through on-site witnesses With on-site measurement and other methods to further verify related problems, with more and more safety assessment task input and the accumulation and updating of safety assessment related materials and data resources, how to establish more scientific and effective analysis and evaluation capabilities to solv...

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 Patents(China)
IPC IPC(8): G06F40/30G06F40/295G06F40/289G06F40/211G06Q10/06G06Q50/18G06Q50/26
CPCG06F40/30G06F40/295G06F40/289G06F40/211G06Q10/06393G06Q50/18G06Q50/265
Inventor 赵梅宦国杨陈奡张翠侠郭珍苏兆安宿晓丹张永伟汤杰谢俊杰
Owner THE 28TH RES INST OF CHINA ELECTRONICS TECH GROUP CORP
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