Resource Scoring via Entity Selection Values
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines face challenges in accurately ranking resources with insufficient search and selection data, as they lack reliable performance inference, leading to inconsistent scoring and reduced coverage of behavioral-based adjustments.
Innovation Solution
The method involves determining search term-entity selection values by accessing resource data and user selection data to adjust resource rankings, using a search term-entity selection evaluator and a search score adjuster to boost or demote resources based on entity references and user interactions, even for resources with limited behavioral data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If behavioral-based scoring adjustments are applied to resources with sufficient search and selection data, then resource ranking accuracy is improved, but resources with insufficient data cannot be reliably adjusted
Solution Approach 1:
The patent introduces entity information as an intermediary to bridge the gap between search terms and resources. By determining entity information for each search term and obtaining entity-resource relationships, the system can indirectly assess resources that lack direct behavioral data through their associated entities, thereby extending coverage while maintaining reliability
Solution Approach 2:
The patent enables resources with insufficient behavioral data to self-assess through their entity associations. By leveraging entity-resource relationships and entity-level selection values, resources can derive their own scoring adjustments without requiring extensive direct user interaction history, allowing newly published resources to participate in behavioral-based adjustments
2Adaptability or versatility
If traditional resource scoring is used for newly published resources without sufficient search and selection data, then resource coverage is maintained, but ranking accuracy and performance inference are reduced
Solution Approach 1:
The patent performs preliminary actions by pre-determining entity information for search terms and pre-obtaining entity-resource relationships before scoring adjustments are needed. This allows the system to have entity-level selection values ready, enabling accurate scoring adjustments for resources with insufficient data when they are first evaluated, rather than waiting for behavioral data to accumulate
Solution Approach 2:
By introducing entity information as a mediator layer between search terms and resources, the system can infer resource performance through entity associations. This intermediary approach allows the system to maintain resource coverage including newly published resources while achieving accurate performance inference through indirect entity-based measurements
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, are provided for resource scoring adjustment based on entity selection. In one aspect, a method includes the actions of accessing resource data that specifies, for each of a plurality of resources, a resource identifier and one or more referenced entities, and accessing search term data that specifies a plurality of search terms, and for each search term, a selection value for each resource, each selection value being based on user selections of search results that referenced the resource to which the selection value corresponds. From the resource data and search term data, for each search term and each entity, a search term-entity selection value is determined that is based on the selection values of resources that reference the entity and that were referenced by search results in response to a query that included the search term.