Content-Item Query Suggestions for Search Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search technologies primarily rely on query suggestions based on the original search query, failing to provide relevant alternatives derived from content items such as search results, advertisements, or other informational content, which may not fully capture user interests.
Innovation Solution
Systems and methods for determining and presenting query suggestions based on content items, such as search query result items, advertisements, or other informational content, to offer more focused alternatives, with the option to dynamically expose these suggestions in response to user interactions like hovering over content items.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If query suggestions are based solely on the original search query, then the system complexity is low, but the relevance and accuracy of suggestions to user interests deteriorates
Solution Approach 1:
The system segments the source of query suggestions into multiple independent components: original query-based suggestions and content-item-based suggestions. Each component operates independently, analyzing different data sources (original query vs. content items from search results) to generate suggestions, which are then combined to provide comprehensive relevant recommendations
Solution Approach 2:
The system introduces content items (search result items, advertisements, informational content) as intermediary elements between the original query and the query suggestions. These content items serve as mediators that bridge the gap between what the user searched for and what suggestions should be provided, enabling more accurate and contextually relevant recommendations
2Ease of operation
If query suggestions are dynamically exposed in response to user actions, then the user experience is improved, but the response time and processing load increases
Solution Approach 1:
The system performs preliminary actions by pre-generating and caching query suggestions based on content items before user interactions occur. When content items are loaded or indexed, the system proactively computes potential query suggestions and stores them for rapid retrieval, eliminating the need for real-time computation during user interactions
Solution Approach 2:
The system implements dynamic exposure of query suggestions based on user actions such as hovering over content items. The suggestions are conditionally displayed or hidden based on user engagement state, allowing the interface to adapt dynamically to user behavior while maintaining pre-computed suggestion data for fast response
Data Source
AI summary
Systems and methods for determining query suggestions based upon content items are provided. Content items may include, without limitation, a search query result item, e.g., displayed on a search results web page, an advertisement, and a query-based query suggestion. Once determined content-item-based query suggestions are presented to the user. If desired, such presentation may be dynamically exposed in response to a user action, for instance, in response to a user hovering over a portion of the associated content item for at least a predetermined period of time.