Search Entity Recognition with Pre-computed Relationships
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Internet search engines face challenges in identifying and presenting relevant entities related to a user's search query, often requiring multiple queries to find related information, which can be cumbersome and inefficient.
Innovation Solution
A method that receives a search query, determines the primary entity, identifies related entities of a predetermined type, and transmits information about these entities as part of the search results, including images and ranking scores based on co-occurrence and user search frequency, to provide comprehensive information in a single response.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If the search engine returns only basic search results, then the search system remains simple and fast, but users must perform multiple queries to find related information
Solution Approach 1:
The system pre-computes and stores entity relationships (such as co-occurrence patterns and entity types) in advance before search queries are submitted. This preliminary preparation allows the system to quickly retrieve and present related entities without performing complex computations during the actual search, thus reducing user waiting time while maintaining reasonable system complexity.
Solution Approach 2:
The patent introduces an intermediary entity recognition layer that sits between the basic search engine and the user interface. This intermediary component identifies entities in search results and retrieves pre-computed related entity information, acting as a mediator that enhances user experience without fundamentally redesigning the entire search system.
2Ease of operation
If the system presents comprehensive entity information in search results, then user experience is enhanced, but the amount of information to be processed increases
Solution Approach 1:
The system selectively presents different types of entity information based on the specific query and context. Rather than uniformly presenting all possible entity data, it tailors the information presentation to match user needs - for example, showing related products for shopping queries, related articles for news queries, or entity relationships for informational queries. This localized information presentation improves ease of operation while controlling information quantity.
Solution Approach 2:
The search results are segmented into distinct components: basic search results, entity identifications, and related entity information. This segmentation allows users to easily navigate and selectively consume information at different levels of detail, making the overall system easier to operate while managing the quantity of information presented in an organized manner.
3Reliability
If the system identifies and presents related entities of predetermined types, then information relevance is improved, but the processing complexity increases
Solution Approach 1:
Entity types and relationships are pre-classified and stored in databases before search operations. The system performs entity type identification and relationship mapping in advance, creating structured data that can be quickly retrieved during search. This preliminary classification ensures information relevance while avoiding complex processing during actual search operations.
Solution Approach 2:
The system uses pre-computed entity relationship data and templates that are copied and applied to specific search queries. Rather than performing complex entity relationship analysis for each query, it retrieves and adapts pre-established entity models and relationship patterns, ensuring consistent and relevant information presentation while reducing processing complexity.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for identifying entities that are related to an entity to which a search query is directed. One of the methods includes receiving a search query, wherein the search query has been determined to relate to a first entity of a first entity type, and wherein one or more entities of a second entity type have a relationship with the first entity; receiving search results for the search query; determining that a count of search results identifying a resource containing a reference to the first entity satisfies a first threshold value; determining that a count of search results identifying a resource having the second entity type as a relevant entity type satisfies a second threshold value; and transmitting information identifying the one or more entities of the second entity type as part of the response to the search query.