Natural Language Query Interpretation via Term Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Natural language search queries often yield unsatisfactory results due to contextual relevance issues, as words not associated with specific keywords or genres are ignored, leading to incomplete search results.
Innovation Solution
A system that processes natural language search queries by identifying and associating terms with respective types, determining contextual relevance, and performing searches within appropriate domains, using machine learning and training data to enhance search results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If natural language search queries are processed by simply applying filters such as content type, then the processing system is simple and fast, but the search results are incomplete and unsatisfactory because contextual words are ignored
Solution Approach 1:
The system segments the natural language query into individual terms and identifies the term type for each term separately. This allows each term to be processed according to its specific type (keyword, genre, content type) while maintaining overall system organization and managing complexity through structured segmentation of the query analysis process
Solution Approach 2:
The patent introduces an intermediary classification layer that determines term types between the raw natural language query and the final search execution. This intermediary step categorizes each term (as keyword, genre, or content type) and facilitates appropriate search domain selection, improving result accuracy without requiring complete system redesign
2Adaptability or versatility
If each term in the query is processed individually within its own search domain, then the processing is straightforward, but adjacent terms with different term types are not properly combined leading to limited results
Solution Approach 1:
The system merges adjacent terms with different term types by determining their contextual relationship and combining them into a unified search query. For example, a keyword term and an adjacent genre term are combined to search for content that satisfies both conditions simultaneously, ensuring complete and versatile search results across multiple domains
3Productivity
If words not associated with specific keywords or genres are ignored, then the processing speed is maintained, but contextual relevance is lost and search intent is not accurately captured
Solution Approach 1:
The system changes the parameter of term evaluation by determining term types dynamically rather than relying on pre-associated keywords only. Each term is assigned a term type parameter (keyword, genre, content type) based on its characteristics, allowing previously ignored words to be properly processed while maintaining processing efficiency through systematic parameter assignment
Data Source
AI summary
Systems and methods are described herein for interpreting natural language search queries that account for contextual relevance of words of the search query that would ordinarily not be processed, including, for example, processing each word of the query. Each term or phrase is associated with a respective part of speech, and a frequency of occurrence of a combination of adjacent terms or phrases public domain is determined. A relevance of each term is then determined based on its respective type of term and frequency of occurrence in the public domain. The natural language search query is then interpreted based on the importance or relevance of each term.