Entity Co-occurrence Search System for Disambiguation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines often return irrelevant results when users query for information related to specific entities, as they mix results from entities with similar names, leading to a large number of non-relevant documents being retrieved.
Innovation Solution
A method utilizing entity co-occurrence analysis, where a search system with an entity extraction module and an entity co-occurrence knowledge base compares search query entities with a database to assign confidence scores, extracts relevant entities, and indexes them for precise search results, ensuring only relevant documents related to the query entities are returned.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a search engine uses historical references and keyword-based indexes to perform searches, then the search system can process queries efficiently, but the search results mix entities with similar names leading to low relevance and high information loss
Solution Approach 1:
The system pre-processes the corpus by identifying entity mentions, resolving ambiguities, and building an entity-indexed structure before search queries are executed. This preliminary organization of data by entity rather than keyword enables the search to directly retrieve documents containing the specific entity instances the user intends, preventing mixing of similar entities and eliminating irrelevant results.
2Quantity of substance
If a search engine returns a large number of documents to ensure comprehensive results, then more potential relevant information is available, but the user must sift through大量 non-relevant documents increasing time loss
Solution Approach 1:
The system extracts and isolates specific entity instances from the corpus by resolving ambiguities and creating entity-specific indexes. When a search query is processed, only documents containing the specific entity instance are retrieved, not all documents containing similar terms. This extraction approach delivers precisely the relevant documents needed without requiring users to filter through large volumes of irrelevant content.
3Device complexity
If a search system uses simple keyword matching to process queries, then the system complexity remains low and processing is fast, but the system cannot distinguish between entities with similar names reducing measurement precision
Solution Approach 1:
The system introduces an entity resolution component that acts as an intermediary between keyword matching and document retrieval. This intermediary resolves entity ambiguities by analyzing context, disambiguating entity mentions, and mapping them to unique entity identifiers. The added layer enables precise entity identification while maintaining system efficiency, as the resolution process occurs during the pre-processing phase and the resulting entity indexes enable fast retrieval.
Data Source
AI summary
A method for searching for related entities using entity co-occurrence is disclosed. Embodiments of the method may be employed in any search system that may include at least one search engine, at least one entity co-occurrence knowledge base, an entity extraction module, and at least an entity indexed corpus. The method may extract and disambiguate entities from search queries by using an entity co-occurrence knowledge base, find extracted entities in an entity indexed corpus and finally present search results as related entities of interest.