Document Summary Visual Emphasis for Search Relevance
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Search engines face challenges in presenting relevant results due to the lack of document-specific salient terms, which are not tailored to individual documents, leading to inconsistent conveyance of content importance and user intent.
Innovation Solution
The extraction of document-specific salient terms using various algorithms on search engine logs, metadata, and other sources, combined with visual emphasis to improve search result summaries and user relevance, enabling more informative and visually discriminable search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If traditional bolded text is used to emphasize query terms in document summaries, then the summaries become easier to parse visually, but the query terms and query expansion/alterations cannot consistently convey document content and relative importance as compared to other search results
Solution Approach 1:
The patent applies different visual emphasis strategies to different terms within document summaries. Instead of uniformly bolding all query terms, the system identifies and emphasizes only those terms that are both query-related and salient to the specific document content. This local differentiation resolves the contradiction by maintaining visual ease of parsing while improving precision in conveying document importance through selective emphasis of truly relevant terms.
Solution Approach 2:
The system dynamically adjusts the emphasis parameters based on document-specific salience calculations. By computing salience scores for each term relative to the specific document and query, the system varies the degree and application of visual emphasis, transforming static bolding into a dynamic, context-aware emphasis system that consistently conveys document content importance across different search results.
2Loss of information
If web pages include numerous entities to provide comprehensive information, then the document content becomes more informative, but the query terms cannot consistently convey document content and relative importance
Solution Approach 1:
The patent extracts and isolates the most salient terms from within the comprehensive entity-rich document content. By calculating salience scores that weigh both query relevance and document importance, the system extracts only the critical terms that truly represent the document's relevance to the query. This extraction process resolves the contradiction by maintaining complete information in the full document while presenting a refined set of emphasis terms in the summary that clearly convey relative importance.
3Reliability
If document-specific salient terms are extracted and applied to improve result summaries, then user success in finding relevant documents improves, but the system complexity increases due to multiple algorithms and data sources
Solution Approach 1:
The patent creates a universal salience calculation framework that serves multiple functions simultaneously. The same salience computation mechanism is used across different document types, query formats, and emphasis applications. This multi-functional approach resolves the complexity issue by providing a single, unified system that handles term extraction, relevance ranking, and visual emphasis determination, rather than requiring separate specialized systems for each function.
Solution Approach 2:
The system performs preliminary salience term extraction and calculation before the actual search result generation and display. By pre-computing salience scores and identifying emphasis terms in advance, the system reduces the computational complexity during the actual search operation. This preliminary action allows the complex analysis to be done once during indexing or pre-processing, rather than repeatedly during each search execution, thereby improving reliability while managing system complexity.
Data Source
AI summary
Architecture that enables the extraction of document-specific salient terms from documents for use improving the result summaries on a search engine result page (SERP), and methods to extract the salient terms from the documents using search engine logs, document metadata, and other algorithms. Document-specific salient terms can provide additional information and significantly improve user success in finding relevant documents while disregarding non-relevant documents. The architecture also enables the extraction of entity information from a variety of sources, some of which are at a query level, and other sources that are specific to a single document. All the entities available are aggregated for a set of results and the most relevant results are identified. The final set of results is then used to determine where in the document summary to apply visual emphasis or cues (e.g., bolding).