Entity Relation Mining via Graph Sorting and Temporal Interpolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for mining entity relations in enterprise business contexts suffer from low accuracy and inability to analyze large volumes of data effectively.
Innovation Solution
An entity relation mining method that involves acquiring and processing enterprise text information using a graph sorting algorithm for key entity extraction, calculating relation weights through temporal order interpolation, and identifying standard entity relations based on preset conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual tracking and analysis methods are used for entity relation mining, then the process is simple to implement, but the accuracy of entity relation extraction is low and the ability to analyze large volumes of data is insufficient
Solution Approach 1:
The patent replaces manual mechanical analysis with automated computational methods including graph sorting algorithms, temporal order interpolation algorithms, and weight calculation mechanisms. This substitution enables high-accuracy entity relation extraction from large volumes of enterprise text information without manual intervention, resolving the contradiction between simplicity and accuracy.
Solution Approach 2:
The patent introduces multiple parameters including relation weights, temporal order parameters, and graph sorting parameters to enhance the precision of entity relation mining. By changing and optimizing these parameters through automated algorithms, the system achieves high extraction accuracy while maintaining operational simplicity for users.
2Productivity
If automated algorithms are used to improve entity relation mining accuracy, then the analysis capability is enhanced, but the system complexity increases
Solution Approach 1:
The patent segments the entity relation mining process into distinct modular stages: graph sorting algorithm execution, key entity extraction, temporal order interpolation, and weight calculation. Each module performs a specific function independently, which enhances overall data analysis capability while managing system complexity through clear separation of concerns and modular design.
3Measurement precision
If multiple processing steps including graph sorting and temporal order interpolation are implemented, then entity relation mining accuracy is improved, but the processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary graph sorting and key entity extraction before the main weight calculation process. By pre-processing the text information to identify and rank key entities upfront, the system reduces the computational burden during subsequent temporal order interpolation and weight calculation stages, thereby improving accuracy while mitigating time loss.
Data Source
AI summary
The present invention relates to artificial intelligence and discloses an entity relation mining method, including steps of acquiring enterprise text information, and extracting an enterprise relation instance in the enterprise text information; performing key entity extraction on the enterprise relation instance to obtain a key entity set; identifying an entity relation between key entities in the key entity set and a first relation weight corresponding to the entity relation, and performing weight calculation on the enterprise text information after deletion of the entity relation instance to obtain a second relation weight; and, using an entity relation having the first relation weight or the second relation weight satisfying a preset reference condition as a standard entity relation. The present invention further provides an entity relation mining apparatus, an electronic device and a storage medium. The present invention can improve the accuracy of entity relation mining.