Article Vector Space Association for Trend Report Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional technologies face challenges in using knowledge graphs to find associations between new articles and existing articles, leading to a decrease in user experience due to inaccuracies in generating trend reports.
Innovation Solution
An article processing method that determines a target article vector and a reference article vector set, using a knowledge graph to find associations between the target article and existing articles, and generates an accurate trend report by calculating distances in the article vector space to identify associated articles.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional knowledge graph methods are used to find associations between articles, then the system can process articles, but the association accuracy decreases leading to poor user experience
Solution Approach 1:
The patent transforms article data from traditional structured knowledge graph format into vector space representations. By changing the parameter representation from discrete entities to continuous vector spaces, the system enables more precise measurement of article associations through vector distance calculations, directly improving association accuracy while maintaining system reliability
Solution Approach 2:
The patent replaces the traditional mechanical knowledge graph matching mechanism with a vector space model. Instead of using rigid entity-relationship matching, the system substitutes this with vector distance-based association detection, allowing for more nuanced and accurate measurement of article relationships, thereby improving both precision and user experience
2Measurement precision
If vector space methods are used to determine article associations, then association accuracy improves, but computational complexity increases
Solution Approach 1:
The patent applies preliminary action by pre-computing and storing article vectors in a vector space before actual association queries. This advance preparation allows the system to perform simple distance calculations during runtime rather than complex analysis, reducing real-time computational complexity while maintaining high association accuracy
Solution Approach 2:
The patent creates vector representations (copies) of articles that capture their semantic meaning. These vector copies enable efficient comparison and association detection without requiring access to the full original article content, reducing computational complexity while preserving measurement precision
Data Source
AI summary
Embodiments of the present disclosure relate to an article processing method, electronic device, and computer program product. The method includes: determining, based on content of a target article, a target article vector associated with the target article; acquiring a reference article vector set associated with a reference article set; and determining, based on a distance in an article vector space between the target article vector and a reference article vector in the reference article vector set, a reference article vector associated with the target article vector in the reference article vector set as an association article vector. By using the technical solution of the present disclosure, an association article associated with a target article can be accurately provided based on the target article selected by a user, so that reports on the target article and its association articles can be further provided to the user for analysis and selection.