Relevance Ranking System Using Entity Rank and Recency
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search systems fail to effectively rank content items by relevance, often relying on alphabetical order or match level, which does not reflect user interest, and lack consideration of factors like popularity, proximity, and recency.
Innovation Solution
A system that assigns entity ranks to content items based on popularity, recency, and other attributes, categorizes them hierarchically, and modifies ranks in response to search queries, using factors like gross earnings, release date, and user interactions to create a relevance-based ranking system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search results are organized alphabetically or by match level, then the organization is simple and fast, but the relevance to user interest is not reflected
Solution Approach 1:
The patent transforms the ranking approach by changing from simple alphabetical or match-level parameters to a multi-dimensional parameter system including entity rank, proximity, recency, and popularity. This allows the system to measure relevance more precisely by considering multiple factors simultaneously, resolving the contradiction between measurement precision and system complexity.
Solution Approach 2:
The patent segments the ranking process into distinct components: entity rank calculation, proximity assessment, recency evaluation, and final relevance ranking. By dividing the complex ranking task into manageable segments, the system achieves high measurement precision while maintaining operational feasibility through modular processing.
2Measurement precision
If entity rank is modified at query time based on search matches, then the relevance accuracy improves, but the processing time increases
Solution Approach 1:
The patent performs preliminary calculation of entity ranks during the indexing phase, storing these pre-computed values for rapid retrieval during query processing. This preliminary action eliminates the need to recalculate entity ranks from scratch during each query, thereby maintaining high relevance accuracy while minimizing query processing time.
Solution Approach 2:
The patent creates and stores copies of entity rank data during indexing, allowing the system to quickly access and modify these pre-computed values during query processing without performing intensive calculations. This copying approach enables fast query response times while maintaining accurate relevance rankings through pre-prepared data.
Data Source
AI summary
Content items and other entities may be ranked or organized according to a relevance to a user. Relevance may take into consideration recency, proximity, popularity, air time (e.g., of television shows) and the like. In one example, the popularity and age of a movie may be used to determine a relevance ranking. Popularity (i.e., entity rank) may be determined based on a variety of factors. In the movie example, popularity may be based on gross earnings, awards, nominations, votes and the like. According to one or more embodiments, entities may initially be categorized into relevance groupings based on popularity and/or other factors. Once categorized, the entities may be sorted within each grouping and later combined into a single ranked list.