Pivoted Search Queries for Intent Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often submit imprecise search queries, leading to excessive time spent refining queries as they navigate through search query/response cycles, with existing search engines relying on statistical relationships to provide related queries that may not accurately reflect the user's intent.
Innovation Solution
A method and system that identify entities in a search query, select a pivot entity, and generate a search results page including both search results and pivoted search queries related to the pivot entity, visually grouping the pivoted queries to enhance user relevance and scope expansion.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If search engines use statistical relationships to provide related queries, then the search results page can be generated quickly, but the relevance of the queries to user intent deteriorates
Solution Approach 1:
The patent introduces an intermediary entity selection mechanism that identifies a pivot entity from the search query entities and uses it to mediate between the user's original query intent and the generated related queries. This intermediary approach allows the system to maintain relevance by grounding related queries in a semantically connected pivot entity rather than relying solely on statistical co-occurrence patterns.
Solution Approach 2:
The system changes the parameter of query generation from statistical co-occurrence-based to entity-relationship-based. By selecting a pivot entity and generating related queries through entity relationships (e.g., via knowledge graphs or entity attributes), the system transforms the query generation process to better reflect user intent while maintaining efficiency.
2Measurement precision
If users iteratively refine search queries to improve precision, then the search accuracy improves, but the time required for search deteriorates
Solution Approach 1:
The system performs preliminary action by pre-identifying entities in the search query and pre-selecting a pivot entity before generating related queries. This preliminary entity analysis and pivot selection enables the system to provide relevant related queries in advance, reducing the need for users to iteratively refine their queries and saving time while maintaining search accuracy.
3Device complexity
If search engines provide related queries based on statistical relationships, then the search results page structure remains simple, but the quality of query suggestions deteriorates
Solution Approach 1:
The patent segments the search query into multiple entities and then selects a pivot entity from these segments to generate related queries. This segmentation approach allows the system to maintain a relatively simple overall page structure while improving query suggestion quality by organizing related queries around a semantically meaningful pivot entity rather than using complex statistical models.
Data Source
AI summary
Systems and methods for responding to search queries with search results and related pivoted search queries is presented. Responsive to a search query, one or more entities related to the search query are identified as pivot entities. For each pivot entity a set of pivoted search queries is identified and included among the search results responsive to the search query.