Entity Identification in Search Results via Attribute Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search systems fail to effectively identify entities that match implicit questions in search queries, such as medical conditions associated with symptoms or movies featuring specific actors, by not providing relevant entity names directly in search results.
Innovation Solution
The system determines if a search query includes attributes related to specific entities, generates combined search queries with entity names, and uses the results to select and present relevant entity names to the user, adjusting scores based on inverse document frequency and refining queries based on user input.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the system performs combined search queries for each entity to identify relevant entities, then the precision of entity identification is improved, but the processing time and computational resources increase
Solution Approach 1:
The system performs preliminary analysis of the search query to determine whether it contains attributes associated with entities before executing combined search queries. This preliminary action filters out queries that do not require entity identification, reducing the number of combined searches needed and thereby decreasing processing time while maintaining precision for relevant queries.
Solution Approach 2:
The system generates combined search queries for a selected plurality of entities rather than all possible entities. By selectively applying the combined search approach only to entities that are likely to be relevant based on the query analysis, the system achieves sufficient identification precision without the excessive time cost of checking every possible entity.
2Loss of information
If the system presents entity names separately from search results, then the clarity and relevance of entity information is improved, but the complexity of the search result presentation increases
Solution Approach 1:
The system segments the search results into distinct components: traditional search results and entity names. By separating entity information from general search results and presenting them in a dedicated format, the system improves the clarity and accessibility of entity information while managing presentation complexity through structured organization.
3Measurement precision
If the system adjusts summary scores based on inverse document frequency, then the accuracy of entity ranking is improved, but the computational complexity increases
Solution Approach 1:
The system modifies the ranking parameter by adjusting summary scores based on inverse document frequency (IDF). This parameter change allows entities that are more distinctive and less commonly associated with the query to receive higher rankings, improving ranking accuracy. The IDF adjustment is a standard information retrieval technique that adds computational overhead but maintains manageable complexity through efficient implementation.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying entities using search results. One of the methods includes determining that a search query includes a respective text reference to each of one or more predetermined attributes, wherein each attribute is associated with an entity type; obtaining search results for the search query from a search engine, each search result identifying a respective resource; for each of a plurality of the obtained search results, determining an initial score for each of a plurality of entities of the entity type based on occurrences of names of the entity in the resource identified by the search result; generating a final score for each of the entities based on the initial scores; and selecting one or more names of entities of the entity type to include in a response to the search query based on the final scores.