Engineering project self-adaptive review method, device and equipment and storage medium
CN121599602APending Publication Date: 2026-03-03STATE GRID JIANGSU ECONOMIC RES INST
View PDF 0 Cites 0 Cited by
Patent Information
- Application Number
- CN202511516500.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-10-23
- Publication Date
- 2026-03-03
AI Technical Summary
Technical Problem
Existing project review systems rely on static rules and expert experience, leading to missed key information, misjudgments of compliance, and an inability to intelligently handle complex scenarios, thus limiting review efficiency and quality.
Method used
Construct a review knowledge graph, combine deterministic rule review of structured data, anomaly detection, and semantic analysis of unstructured text to generate intelligent review reports.
Benefits of technology
It enables intelligent and comprehensive review of project documents, improving efficiency and quality while reducing reliance on human experience.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure CN121599602A_ABST
Abstract
The invention provides an engineering project self-adaptive review method and device, equipment and a storage medium, which are used for improving the review efficiency and quality of an engineering project file and reducing the dependence of engineering project review on artificial experience. The method comprises the following steps: extracting contents needing to be examined in a project file to be examined, wherein the contents needing to be examined comprise structured data and unstructured texts; querying a corresponding review standard in a review knowledge graph according to the structured data, and reviewing first data with the corresponding review standard in the structured data according to the corresponding review standard to obtain a first review result, the review knowledge graph being constructed based on standard terms of different projects; performing abnormal data detection on second data which does not have a corresponding review standard in the structured data to obtain a second review result; and performing semantic review on the unstructured text to identify missing terms and fuzzy description terms in the unstructured text to obtain a third review result.
Need to check novelty before this filing date? Find Prior Art