Search Query Suggestion via Document-to-Query Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines struggle to provide users with efficient access to related yet diverse search results, relying on users to iteratively modify queries, which can be time-consuming and inefficient.
Innovation Solution
A method utilizing a document-to-query-to-document model that identifies and suggests alternative queries based on user behavior data, allowing users to explore related documents without altering their original query, by associating documents with previous queries and suggesting queries that produce diverse yet relevant results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If search engines provide only direct query results, then search precision is maintained, but users cannot efficiently access related yet diverse search results
Solution Approach 1:
The system pre-computes and stores document-to-query-to-document relationships in advance, creating a ready-to-use suggestion framework that enables rapid retrieval of related queries without requiring users to iteratively modify their searches
Solution Approach 2:
The patent introduces an intermediary suggestion system that mediates between the user's original query and the search results, providing intermediate queries that bridge to diverse yet relevant documents without requiring direct user query modification
2Adaptability or versatility
If search engines suggest queries directly related to original query terms, then query relevance is maintained, but users cannot discover queries not directly related to original terms
Solution Approach 1:
The system extracts document-to-query relationships from the search index, separating the suggestion generation from the original query terms, allowing suggestions to be based on document associations rather than direct query term matching
Solution Approach 2:
The patent creates a universal suggestion framework that can provide both directly related queries and indirectly related queries through the document-to-query-to-document model, making the system adaptable to different types of query relationships
Data Source
AI summary
In general, one aspect of the subject matter described can be embodied in a method that includes, obtaining a plurality of search results responsive to an initial search query, the search results including a first search result that identifies a first resource; determining, using a document-to-query-to-document model, that the first resource is relevant to a first suggested query different from the initial search query; generating a presentation of the search results responsive to the initial search query; and providing the presentation of the search results in response to the initial search query. Each search result in the presentation includes a link to a respective resource, wherein the first search result in the presentation includes a link that, upon a selection by a user, can cause the first suggested query to be submitted to a search engine.