Optimistic Facet Set Selection for Dynamic Search
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing dynamic facet generation techniques struggle to detect redundant, useless, and non-discriminative facets, leading to inefficient search result refinement in human-computer information retrieval systems.
Innovation Solution
The proposed solution involves an optimistic facet set selection method that determines an initial rank and probability of relevance for each document, revises ranks based on candidate facets, selects minimum ranks, calculates expected discounted cumulative gain, and chooses facets to maximize this gain.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If existing dynamic facet generation techniques are used, then facets are provided for search result refinement, but redundant and non-discriminative facets are not detected leading to inefficient search refinement
Solution Approach 1:
The patent changes the parameter of facet selection by introducing an optimistic selection criterion based on expected discounted cumulative gain. Instead of using traditional facet generation methods, the system calculates a score for each facet based on the probability of relevance and minimum rank, then selects facets that maximize this score. This parameter change enables the system to automatically identify and prioritize discriminative facets while filtering out redundant ones, thereby improving search refinement efficiency without losing important information.
2Productivity
If all candidate facets are considered for selection, then comprehensive search refinement is achieved, but virtual memory usage and search space increase
Solution Approach 1:
The patent extracts only the most relevant facets from the set of all candidate facets by applying an optimistic selection criterion. Instead of processing and presenting all candidate facets to the user, the system calculates expected discounted cumulative gain for each facet and selects only those that maximize this metric. This extraction process reduces the quantity of facets presented to users, thereby reducing virtual memory usage and search space while maintaining comprehensive search refinement through the selection of high-value facets.
Data Source
AI summary
Determining an initial rank and a probability of relevance of each of a retrieved plurality of electronic documents relevant to a query. For each of a plurality of candidate facets, determine a revised rank for each of the retrieved plurality of electronic documents relevant to the query. Selecting, for each of the retrieved plurality of electronic documents relevant to the query, a minimum rank from among the initial rank and the revised rank for each of the plurality of candidate facets. Determine an expected discounted cumulative gain based on the probability of relevance and the minimum rank for each of the retrieved plurality of electronic documents relevant to the query. Select a set of optimistic facets based on maximizing the expected discounted cumulative gain.