Query Augmentation via Semantic Tag Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Users often fail to discover content of interest due to lack of knowledge about its existence, limiting their ability to conduct effective searches for relevant information.
Innovation Solution
A computer-implemented method that monitors and analyzes user queries and content, generates tags for semantic analysis, and stores them in central and user repositories to identify user interests, augmenting queries with relevant terms to include content not previously known to the user.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If users conduct searches based only on content they already know, then search queries are simple and direct, but users fail to discover content of interest that they were previously unaware of
Solution Approach 1:
The system performs preliminary actions by monitoring and analyzing user queries and content in advance, generating content tags and query tags before the actual search occurs. These tags are stored in a central repository, enabling the system to automatically augment future queries with relevant terms that users may not have known to search for, thus discovering unknown content before the user even completes their search intent
Solution Approach 2:
The system introduces an intermediary component that acts as a bridge between the user's simple query and the comprehensive search results. This intermediary analyzes the query, retrieves relevant content tags from the central repository, and augments the original query with additional terms. This intermediary layer enables users to discover unknown content without having to manually construct complex queries themselves
2Measurement precision
If the system analyzes all user queries and content to generate tags, then search accuracy and personalization improve, but processing time and computational resources increase
Solution Approach 1:
The system performs tag generation and analysis in advance as a preliminary action, creating content tags and query tags before they are needed for actual search queries. By pre-processing and storing these tags in a central repository during idle or batch processing periods, the system avoids the time-consuming analysis during real-time query execution, thus maintaining high precision while reducing perceived processing time for users
Solution Approach 2:
The system extracts only the essential semantic elements (tags) from user queries and content, separating these key features from the full text. By extracting and storing only the relevant tags rather than analyzing complete queries each time, the system achieves accurate user interest identification while significantly reducing the computational burden and processing time required for each search operation
3Adaptability or versatility
If the system stores and analyzes all query tags and content tags in a central repository, then semantic similarity matching improves, but data storage requirements and system complexity increase
Solution Approach 1:
The system extracts only the essential semantic elements (tags) from queries and content, storing these condensed representations in the central repository rather than storing complete queries and content. This extraction approach maintains the system's ability to perform semantic similarity matching while dramatically reducing the volume of data that needs to be stored and processed, as tags are much more compact than full-text data
Solution Approach 2:
The system transforms queries and content into a different parameter space by converting them into tags with associated weights and semantic attributes. This parameter transformation enables efficient semantic matching through mathematical operations on tag vectors rather than text comparison, improving adaptability while reducing storage requirements through dimensionality reduction and compression of the data representation
Data Source
AI summary
A computer-implemented method, system and computer program product for improving query searches. After receiving a query from a user to conduct a content search, the query is analyzed for its semantic meaning and a categorized group of query tags and content tags in the central repository that is most semantically similar in meaning to the meaning of the query is identified. Furthermore, the content tags and query tags in the user's repository are analyzed to determine the interests of the user. The query may then be augmented to include one or more other terms of interest from the identified categorized group of query tags and content tags in the central repository that match the determined interests of the user within a threshold degree of relatedness, where these other terms of interest correspond to the content tags and query tags of the identified categorized group based on their assigned weight.