Search Query Refinement via Collaborative Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users face difficulties in searching for desired items on web resources due to multiple possible interpretations of search queries, leading to inaccurate results and the need for repeated refinement.
Innovation Solution
The system refines user searches by identifying items of prior interest from user history and conducting collaborative filtering analysis to provide item relationship information, allowing for the decomposition of search requests into sub-requests and the transformation of search queries to include relevant item information, thereby enhancing search accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional search methods are used to search for items on web resources, then users can access the search function, but the search results are inaccurate and require repeated refinement
Solution Approach 1:
The system performs preliminary actions by analyzing user history data and generating relationship information between items before the actual search occurs. This pre-computed relationship data is stored and used to refine search results in real-time, eliminating the need for repeated search refinements by users.
Solution Approach 2:
The patent introduces an intermediary component that computes and stores relationship information between items based on user history. This intermediary layer processes the connection between user queries and item databases, providing refined search results that directly address user intent without requiring multiple refinement iterations.
2Adaptability or versatility
If multiple possible interpretations of search queries are considered, then comprehensive search coverage is achieved, but search accuracy deteriorates due to ambiguity
Solution Approach 1:
The system uses feedback from user history data to disambiguate search queries. By analyzing what items users have previously interacted with, the system provides feedback that clarifies the intended meaning of ambiguous search terms, allowing the search to remain versatile while maintaining high accuracy in results.
Solution Approach 2:
The patent applies local quality by providing different interpretation strategies for different parts of the search process. The relationship information computed from user history is applied locally to specific ambiguous terms or contexts, allowing the system to maintain overall query flexibility while resolving local ambiguities to improve accuracy.
Data Source
AI summary
Embodiments of methods, systems, and storage medium associated with processing a search request for items are disclosed herein. In one instance, the method may include determining that a search request includes an indication of intent to obtain information about items that are related to other items, obtaining information about a first set of items from a first data repository, including the obtained information as input in the search request, and obtaining, in response to the search request, information about a second set of items related to the items of the first set from a second data repository. The second data repository may include information about items, including relationship of the second set of items with the first set of items. The item relationship may be determined based on collaborative filtering of information associated with the first or second items. Other embodiments may be described and/or claimed.