Restricted-Local Synonym Scoring for Search Accuracy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines fail to accurately differentiate between synonyms in search queries, leading to irrelevant search results due to the assumption that all synonyms are equally effective, ignoring nuanced differences in confidence, trust, and reliability.
Innovation Solution
Implementing a scoring system that classifies synonyms as restricted-locality synonyms, which are scored differently based on their occurrence in relation to other query terms, using specific criteria such as morphological variants, acronym, abbreviation, and confidence values, to adjust their contribution to document scores.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all synonyms are treated as equally effective in search scoring, then the search system is simple to implement, but the search result accuracy deteriorates due to ignoring nuanced differences in synonym reliability
Solution Approach 1:
The patent segments synonyms into different categories (restricted-locality synonyms versus other synonyms) based on their reliability characteristics. This segmentation allows the system to apply different scoring rules to different synonym types, improving measurement precision without treating all synonyms uniformly, thus resolving the contradiction between accuracy and simplicity.
Solution Approach 2:
The patent applies local quality by making the scoring treatment of synonyms location-dependent and context-dependent. Restricted-locality synonyms are only counted when they appear in specific local contexts (near query terms), while other synonyms are counted more freely. This localized differentiation improves search accuracy while maintaining reasonable system complexity.
2Reliability
If restricted-locality synonyms are counted in all occurrences, then the search system is easier to operate, but the search result relevance deteriorates due to including unreliable synonym occurrences
Solution Approach 1:
The patent introduces dynamic scoring behavior where the treatment of restricted-locality synonyms changes based on their contextual occurrence. The scoring mechanism dynamically adjusts whether to count a synonym occurrence based on proximity to query terms and other contextual factors, thereby improving reliability while adapting the complexity only when necessary for accurate scoring.
3Adaptability or versatility
If a uniform scoring model is used for all query terms and synonyms, then the system complexity is reduced, but the ability to capture nuanced synonym differences is lost
Solution Approach 1:
The patent changes the scoring parameters dynamically based on synonym type and contextual occurrence. Restricted-locality synonyms have different scoring parameters (only counted when near query terms) compared to other synonyms (counted more freely). This parameter differentiation improves adaptability while keeping the underlying scoring model structure relatively simple.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for identifying and scoring restricted-locality synonyms. In one aspect, a method includes receiving a search query including a query term and a synonym for the query term. The synonym is evaluated using one or more predetermined criteria and based on the evaluation is designated as a restricted-locality synonym. A first scoring model is selected that specifies how to score occurrences of restricted-locality synonyms in documents. A document is received that is identified as being responsive to the search query. A document score for the document is determined using the first scoring model.