Context-Based Query Suggestions With Popularity-Adaptive Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing query suggestion techniques treat all queries uniformly and do not fully utilize contextual information, leading to suboptimal search assistance.
Innovation Solution
A system that generates query suggestions based on a user's previous queries, utilizing popularity scores and query pairs from user logs to adaptively provide more suggestions for popular queries and fewer for unpopular ones, while clustering similar queries to enhance relevance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If query suggestions are generated uniformly for all queries, then the system complexity is reduced, but the relevance and adaptability of suggestions deteriorates
Solution Approach 1:
The system dynamically adjusts the number of query suggestions based on the popularity of the preceding query. Popular queries receive more suggestions (e.g., 5-10 suggestions) while unpopular queries receive fewer suggestions (e.g., 3-5 suggestions). This dynamic adaptation allows the system to respond to user needs without requiring complex uniform processing for all queries.
Solution Approach 2:
The system changes the parameter of suggestion quantity based on query popularity. By determining a degree of popularity for each preceding query and using this to select the number of suggestions to generate, the system optimizes resource allocation and relevance without treating all queries uniformly.
2Measurement precision
If a fixed number of suggestions is generated for each query, then the processing time is reduced, but the relevance of suggestions to user intent deteriorates
Solution Approach 1:
The system dynamically adjusts processing time allocation based on query popularity. For popular queries, the system invests more processing time to generate and evaluate more suggestions (5-10), while for unpopular queries, it uses less processing time (3-5 suggestions). This dynamic approach optimizes the balance between relevance and processing time.
3Productivity
If all queries are treated uniformly, then the ease of operation is maintained, but the usefulness of suggestions for popular queries deteriorates
Solution Approach 1:
The system applies different processing qualities to different queries based on their popularity. Popular queries receive enhanced processing with more suggestions (5-10) to maximize usefulness, while unpopular queries receive standard processing (3-5 suggestions). This local differentiation maintains ease of operation while improving productivity where it matters most.
Data Source
AI summary
The present teaching relates to providing a query suggestion. In one example, a request is received for query suggestions with respect to a query prefix input by a user. A plurality of query suggestions is determined based on the query prefix and a preceding query input by the user. A degree of popularity of the preceding query is determined. One or more query suggestions are selected from the plurality of query suggestions based on the degree of popularity of the preceding query. The one or more query suggestions are provided as a response to the request.