Machine Learning Search Tagging for Domain Object Classification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Contemporary full-text search systems often provide only a nearest best match when domain data does not have a direct match for entered search terms, failing to deliver actual best matches without proper tagging and updating of search terms.
Innovation Solution
A method using a machine learning module to select features of search terms, map associations between search terms and domain objects, and tag domain objects for enhanced search results, allowing for subsequent searches to include permutations and matchings that improve search accuracy by appending non-matching terms to the search query string.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If full-text search is used without tagging, then search system simplicity is maintained, but search accuracy deteriorates providing only nearest best match
Solution Approach 1:
The system performs preliminary tagging of domain objects with relevant search terms before actual search queries are executed. This advance preparation creates an indexed mapping between search terms and domain objects, enabling accurate matching without requiring complex real-time processing during search operations.
Solution Approach 2:
The patent introduces tags as an intermediary layer between search queries and domain objects. These tags act as mediators that bridge the gap between user search terms and relevant domain data, improving match accuracy without requiring direct complex relationships between all possible search terms and domain objects.
2Measurement precision
If all possible search terms are tagged to every domain object, then search accuracy is improved, but processing time and computational resources increase
Solution Approach 1:
Instead of uniformly tagging all domain objects with all possible search terms, the system applies tagging locally and selectively - each domain object receives only the tags that are genuinely relevant to it. This localized approach maintains high search accuracy for matching queries while avoiding the computational overhead of comprehensive tagging.
Solution Approach 2:
The system implements partial tagging by focusing on the most relevant search terms for each domain object rather than exhaustively tagging with every possible term. This partial action achieves sufficient search accuracy for practical purposes while significantly reducing processing requirements compared to complete tagging.
3Reliability
If domain data is not properly tagged, then system simplicity is maintained, but search results provide only nearest best match rather than actual best match
Solution Approach 1:
The system enables domain objects to essentially tag themselves by automatically identifying and associating relevant search terms with appropriate domain objects through the machine learning module. This self-service approach improves search reliability without requiring manual tagging efforts or complex external tagging infrastructure.
Data Source
AI summary
A method and system operable for: receiving a search query including search terms; using a machine learning module, selecting features of the search terms and mapping an association between the search terms and a domain object, thereby generating a domain object classification; tagging the domain object with the domain object classification; and using the domain object tagged with the domain object classification to conduct a subsequent search. Conducting the subsequent search includes: receiving a subsequent search query including subsequent search terms; tokenizing the subsequent search terms; finding permutations of the tokenized subsequent search terms; matching the subsequent search terms to the domain object tagged with the domain object classification; and displaying subsequent search results via a user interface.