Augmented Search Query System for Entity Distinction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines often provide search results for queries containing entity references, such as a person's name, that are not sufficiently organized, comprehensive, or presented in a useful manner, failing to distinguish between distinct entities effectively.
Innovation Solution
A system that receives a search query with an entity reference, identifies attributes of the entities, generates additional search queries based on these attributes, and updates the results by selecting and refining the queries to provide a more comprehensive set of results, using natural language processing and knowledge graphs to distinguish between distinct entities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a search query is executed with an entity reference, then search results are provided, but the results are not sufficiently organized and fail to distinguish between distinct entities
Solution Approach 1:
The patent segments search results by distinct entities, creating separate result sets for each entity that matches the query. This allows the system to distinguish between multiple entities (e.g., different people with the same name) by organizing results into entity-specific groups, thereby improving both entity distinction accuracy and results organization
Solution Approach 2:
The patent introduces an intermediary entity resolution layer between the search query and results. This intermediary component analyzes query results to identify and distinguish distinct entities, then organizes results accordingly. This mediator improves entity distinction without requiring changes to the underlying search infrastructure
2Quantity of substance
If additional search queries are generated based on entity attributes, then comprehensiveness of results is improved, but system complexity increases
Solution Approach 1:
The patent performs preliminary extraction of entity attributes (such as occupation, location, relationships) from the initial search results before generating additional queries. By pre-identifying relevant attributes and entities, the system can generate targeted augmented queries without requiring complex real-time analysis, thus improving comprehensiveness while managing system complexity
Solution Approach 2:
The patent generates additional search queries selectively based on identified entity attributes rather than exhaustively searching all possible attributes. This partial action approach focuses on the most relevant attributes (e.g., if the entity is a person, search for their works, relationships, or locations) to improve result comprehensiveness without proportionally increasing system complexity
Data Source
AI summary
Methods and systems are provided for updating a set of results. In some implementations, a search query associated with an entity reference is received. The entity reference corresponds to one or more distinct entities. A set of results for the search query is provided, and the set of results distinguishes between distinct entities. One or more attributes for at least one entity of the one or more distinct entities are identified based at least in part on the set of results. One or more additional search queries are identified based on the search query, the at least one entity, and the one or more attributes. An input selecting at least one of the additional search queries is received. An updated set of results is provided based on the selected additional search queries. The updated set of results comprises at least one result not in the set of results.