Search Engine Entity Ranking via Category Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines face challenges in efficiently presenting relevant information to users by categorizing and ranking entities associated with search queries, often providing lists of search results that include irrelevant information alongside relevant entities.
Innovation Solution
A method and system that involve receiving a query, identifying relevant entities, determining the category of the query based on associated documents and entities, and presenting a search result document that includes a ranked list of entities, using score generation techniques to prioritize relevance and category association.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If search engines provide comprehensive lists of search results, then the quantity of information is improved, but the relevance and focus of information deteriorates
Solution Approach 1:
The patent segments search results into distinct categories (entity results versus traditional document results). Entity results are structured, ranked lists of entities with standardized attributes, while traditional results remain as unstructured document links. This segmentation allows the system to provide comprehensive information while maintaining relevance by organizing content according to user intent and entity type.
Solution Approach 2:
The patent extracts entities from unstructured search results and presents them as separate, structured entity lists. By taking out entity information from the general document results and presenting it in a dedicated formatted section with ranked entities and standardized attributes, the system isolates relevant entity information from irrelevant document content, thereby improving overall result relevance.
2Measurement precision
If search engines categorize and rank entities, then the precision of search results is improved, but the complexity of processing increases
Solution Approach 1:
The patent performs preliminary entity recognition, extraction, and categorization during the indexing phase rather than at query time. Entities are pre-identified and structured in the index, allowing the search system to quickly retrieve and rank pre-categorized entities without performing complex processing during actual search operations. This preliminary action reduces real-time computational complexity while maintaining high precision.
Solution Approach 2:
The system uses self-service mechanisms where entities automatically generate their own structured representations and rankings based on intrinsic attributes. Rather than requiring complex external processing for each query, entities serve themselves by providing standardized attribute data and relevance scores that the search system can directly utilize, thereby reducing processing complexity while maintaining precision.
Data Source
AI summary
A device may be configured to receive a query; receive information regarding documents that are relevant to the query; identify one or more entities associated with the documents; determine a category for the query based on: the query, a topic of the documents, and the one or more entities; determine, based on the query and the category, that an entity list should be presented in response to the query; and present a search result document based on determining that the entity list should be presented in response to the query. The search result document may include a list with information identifying the one or more entities.