Content Relevance Model Using Contextual Keyword Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current search engines struggle to provide a comprehensive overview of documents relevant to a particular topic, as they primarily rely on word matching and fail to consider contextual relevance, leading to the overlook of many relevant documents.
Innovation Solution
A method for defining a content relevance model that identifies key word sets and their contextual significance, using a system that analyzes both relevant and irrelevant content segments to determine the likelihood of a document's relevance to a specific category, and evaluates new content segments based on these models.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If search engines use word matching and operators to find documents, then the search process is simple and fast, but many relevant documents are overlooked because contextual relevance is not considered
Solution Approach 1:
The patent segments the document into multiple content segments and analyzes each segment's context separately. It divides the search process into identifying key words, finding content segments containing those words, and evaluating contextual relevance of each segment. This segmentation allows comprehensive relevance analysis while maintaining manageable processing complexity through structured analysis steps.
Solution Approach 2:
The patent transitions from traditional one-dimensional word matching to a multi-dimensional evaluation that considers: (1) presence of key words, (2) contextual words surrounding key words, (3) relationships between content segments, and (4) overall document structure. This dimensional expansion enables detection of contextual relevance that word matching alone cannot achieve.
2Measurement precision
If search engines analyze contextual word sets and content segment relationships, then document classification accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by pre-identifying key words and pre-analyzing content segments before final relevance determination. It extracts key words from documents in advance and establishes relationships between content segments beforehand, so that when relevance is evaluated, the system only needs to match these pre-processed elements rather than analyzing everything from scratch, significantly reducing processing time.
Solution Approach 2:
The patent applies partial action by focusing analysis only on content segments that contain key words rather than analyzing all content segments uniformly. It selectively evaluates contextual relationships only where key words are present, avoiding unnecessary processing of irrelevant segments and reducing overall computational burden while maintaining high classification accuracy.
3Adaptability or versatility
If search engines consider multiple word sets and contextual relationships, then comprehensive overview of relevant documents is achieved, but the search system becomes more complex
Solution Approach 1:
The patent creates a universal relevance determination system that can handle multiple types of content segments and document structures through a single unified approach. The same key word identification and contextual analysis mechanism works across different content types, making the system adaptable to various search scenarios without requiring separate specialized algorithms for each content type.
Data Source
AI summary
Some embodiments provide a method for evaluating a content segment for relevancy to several of categories. The method retrieves the content segment. For each of the several categories, the method determines the relevancy of the content segment to the category by using a scoring model for the category. The scoring model accounts for (i) the presence of key word sets in the content segment and (ii) the context of the key word sets in the content segment. For each of the several categories, the method tags the content segment when the content segment is determined as relevant to the category.