Refining Search Queries via Entity Ranking and Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current internet search engines require significant user interaction to obtain alternatives to an input search query, leading to inefficiencies in time, precision, accuracy, and coverage of search results due to ambiguities in query interpretations.
Innovation Solution
A system that generates refined search queries by identifying and combining entities associated with search results, using techniques such as inverse document frequency scoring and entity ranking, to provide alternative search queries that capture relevant and contextually accurate options.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If search engines require significant user interaction to obtain alternatives to an input search query, then users can explore different search options, but this increases the time and complexity of the search process
Solution Approach 1:
The system performs preliminary action by automatically generating multiple alternative search queries before the user needs them. The patent creates refined search queries with different interpretations and meanings proactively, so when users want to explore alternatives, they are already available without requiring additional user interaction or time investment.
2Measurement precision
If search engines provide more search query alternatives, then search coverage and accuracy improve, but the complexity of the search system increases
Solution Approach 1:
The patent applies segmentation by breaking down the complex task of generating search alternatives into distinct components: identifying different meanings of search terms, creating refined queries for each meaning, and organizing them systematically. This segmentation approach manages complexity by handling each aspect separately rather than attempting to solve the entire problem at once.
Solution Approach 2:
The system uses an intermediary approach by introducing a structured process that mediates between the simple input query and the complex need for multiple accurate alternatives. The patent creates an intermediate layer of refined search queries that systematically explore different interpretations, acting as a bridge that manages complexity while improving accuracy.
3Reliability
If search engines capture alternatives to input search queries, then search precision and coverage improve, but the complexity of query processing increases
Solution Approach 1:
The system performs preliminary action by pre-identifying and capturing alternative search queries before the actual search execution. The patent analyzes the input query in advance, identifies different meanings and interpretations, and prepares refined search queries beforehand, which reduces the complexity during actual query processing while maintaining comprehensive coverage.
Data Source
AI summary
Methods, systems, and apparatus, including computer program products, for refining search queries. In one implementation, a method includes obtaining a submitted search query, and in response to obtaining the search query: obtaining search results responsive to the search query; selecting a document from a group of documents identified by the search results; generating from a subset of one or more entities associated with the document one or more candidates for refined search queries, including: identifying one or more terms in the search query, where the one or more terms occur in the search query in a particular order relative to each other, and combining the one or more terms with the entity to generate a candidate, where the one or more terms occur in the particular order relative to each other; and identifying one or more of the candidates as being refined search queries for providing with the search results.