Multidimensional Relevancy Matching for Query Sentences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines often fail to accurately match query sentences, particularly questions, by focusing on keywords rather than the context and intent, leading to search results that do not align with user expectations.
Innovation Solution
A system that processes query sentences using a multidimensional relevancy determination mechanism, extracting features from both query and candidate sentences to rank results based on aggregate similarity scores, incorporating domain categorization, intent determination, and feature extraction to provide more relevant search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If search engines match query terms with keywords only, then the search process is simple and fast, but the search results do not reflect the real intent of the query
Solution Approach 1:
The patent segments the query analysis into multiple independent dimensions: domain categorization, intent determination, and feature extraction. Each dimension processes specific aspects of the query independently, then their results are combined to form the final matching score. This segmentation allows the system to achieve comprehensive analysis without overwhelming complexity in a single processing step.
Solution Approach 2:
The patent transitions from traditional single-dimension keyword matching to multi-dimensional query analysis. By adding dimensions such as domain category, user intent, and semantic features, the system evaluates queries from multiple perspectives simultaneously, significantly improving matching accuracy while maintaining manageable complexity through modular processing of each dimension.
2Reliability
If search engines analyze groups of keywords only, then the processing is straightforward, but the results do not account for the dynamics of the entire phrase or sentence
Solution Approach 1:
The patent divides sentence-level analysis into separable components: domain categorization identifies the topic area, intent determination captures the user's goal, and feature extraction identifies key semantic elements. Each component processes specific linguistic features independently, then integrates results to evaluate overall sentence relevance, achieving comprehensive analysis through structured segmentation.
Solution Approach 2:
The patent creates a multi-functional analysis framework where the same processing system handles diverse query types (questions, statements, commands) by adapting to different domains and intents. The system universally processes various sentence structures and languages through standardized feature extraction and scoring mechanisms, making the complex analysis applicable to broad ranges of search scenarios.
Data Source
AI summary
Described is a system that matches a query with a set of sentences. When a query is received, the system may extract features from the query including one or more words as tokens and retrieve a set of candidate sentences as potential results for the query. For example, the query may be in the form of a question, and the candidate sentences may be alternative phrasings of the query that potentially match the user's search intent. The relevant set of candidate sentences may be determined based on using multiple relevancy scores and the system may rank the candidates according to an overall or aggregate score. Accordingly, the set of results to a query may be provided by recognizing the sentence as a whole and, for example when the query is a question, the interrogative intent of the query.