Query Rewriting Using Location Context for Entity Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in retrieving information about entities, such as locations or businesses, without knowing their exact names or how to spell them, leading to inefficient querying and increased bandwidth and computational demands on search systems.
Innovation Solution
The system identifies entities based on a user's approximate location and rewrites queries to explicitly reference these entities, allowing users to submit queries implicitly about their surroundings without needing to know the entity's name or proper spelling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If users submit queries without knowing the exact entity name or spelling, then ease of operation improves, but measurement precision of the query intent deteriorates
Solution Approach 1:
The patent introduces location data as an intermediary to bridge the gap between vague user queries and specific entity identification. By incorporating geographic location information, the system can resolve ambiguous queries like 'best restaurant nearby' without requiring users to know specific entity names, thus maintaining ease of operation while improving query accuracy through spatial context
Solution Approach 2:
The system changes the parameter space by adding location coordinates to the query parameters. Instead of relying solely on text-based entity names, the system transforms the query into a multi-dimensional search space that includes geographic parameters, enabling accurate entity identification even when users provide incomplete or imprecise entity names
2Loss of information
If the system processes multiple queries to retrieve entity information, then information retrieval completeness improves, but bandwidth consumption and computational requirements increase
Solution Approach 1:
The system performs preliminary actions by pre-fetching and caching entity information based on location data before the user actually submits the query. When a user queries about entities in their area, the system has already gathered relevant information, eliminating the need for multiple sequential queries and reducing both bandwidth consumption and computational overhead while maintaining complete information retrieval
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for receiving a query provided from a user device, and determining that the query is implicitly about some entity, and in response: obtaining an approximate location of the user device when the user device provided the query, obtaining a set of entities including one or more entities, each entity in the set of entities being associated with the approximate location, and determining that the query is implicitly about an entity in the set of entities, and in response: providing a revised query based on the query and the entity, the revised query explicitly referencing the entity.