Search Ranking Using Document Features for Access-Restricted Documents
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing search engine technologies are ineffective in ranking access restricted documents and publicly accessible documents with limited interaction data, as they rely on user interaction data that may not be available for personal or rarely interacted documents.
Innovation Solution
The use of document features and query features to determine presentation characteristics for search results, leveraging past interactions with other documents sharing similar features, including access restricted documents, to generate query-dependent and query-independent measures for ranking and presentation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search engines rely on user interaction data for ranking documents, then ranking accuracy is improved for publicly accessible documents, but ranking effectiveness deteriorates for access restricted documents and documents with limited interaction data
Solution Approach 1:
The patent introduces document features as an intermediary to bridge the gap between query and document ranking. Instead of directly relying on user interaction data, the system uses document features (such as content, structure, metadata) as a mediator to infer relevance and generate ranking measures, enabling effective ranking of access restricted documents that lack user interaction history.
Solution Approach 2:
The patent creates a virtual representation of document relevance through query-dependent measures that copy the ranking logic from publicly accessible documents to access restricted documents. By generating measures based on document features rather than direct user interactions, the system replicates the ranking effectiveness across different document types without requiring actual user interaction data for each document.
2Measurement precision
If search engines use query-dependent measures based on past interactions with similar documents, then presentation relevance is improved, but system complexity increases
Solution Approach 1:
The patent segments the ranking process into distinct components: query feature identification, document feature extraction, and measure generation. By dividing the complex ranking task into these manageable segments, the system can process query-dependent measures based on past interactions with similar documents without overwhelming complexity, making the system more maintainable and scalable.
Solution Approach 2:
The patent changes the parameters used for ranking from direct user interaction metrics to document feature-based measures. By transforming the ranking approach to use document features (content, structure, metadata) as parameters, the system achieves presentation relevance through query-dependent measures while managing complexity through standardized feature extraction and matching processes.
Data Source
AI summary
Methods and apparatus related to using document feature(s) of a document that is responsive to a query, and optionally query feature(s) of the query, to determine a presentation characteristic for presenting a search result that corresponds to the document. In some implementations, measures associated with the document feature(s) and/or query feature(s) may be used to determine the presentation characteristic. The measures may be based on past interactions, by corresponding users, with other documents that share one or more of the document features with the document, where a plurality of the other documents are different from the document (and optionally each different from one another). In some implementations, the document and/or the other documents include, or are restricted to, documents that are access restricted.