Query Search via Generic Attribute Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Category-based search engines have limited coverage and high maintenance costs due to manual establishment and updating of mapping tables, leading to poor expansibility and low accuracy in matching query keywords with categories.
Innovation Solution
The implementation of a search process that extracts generic attribute features from query data, such as word-level, syntax, semantic, click, selection, and session features, to calculate confidence degrees for categorization, allowing for automatic selection of relevant categories and improved search results without the need for extensive mapping tables.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual mapping tables are used for category-based search, then search accuracy for matched keywords is improved, but coverage rate and expansibility deteriorate
Solution Approach 1:
The system automatically extracts generic attributes from query data and performs self-categorization without requiring manual mapping table updates. The search engine serves itself by learning from query patterns and automatically expanding its categorization capabilities, eliminating the need for continuous manual maintenance while improving both accuracy and coverage
Solution Approach 2:
The invention transitions from static manual mapping tables to dynamic automatic categorization based on extracted generic attributes. By changing the parameter of category assignment from manual fixed mapping to automatic attribute-based classification, the system achieves both high accuracy through feature extraction and high coverage through automatic adaptation to new query types
2Measurement precision
If manual mapping tables are established and updated, then category classification accuracy is improved, but maintenance cost and time consumption increase
Solution Approach 1:
The system performs automatic categorization by extracting generic attributes from queries, eliminating the need for manual mapping table maintenance. The search engine autonomously handles category classification without human intervention, reducing maintenance time to zero while maintaining accurate classification through attribute-based matching
Solution Approach 2:
The invention replaces the mechanical process of manual mapping table creation and updates with an automated computational system that extracts generic attributes and performs category classification algorithmically, substituting human labor with machine-based attribute extraction and classification
3Adaptability or versatility
If extensive mapping tables are used, then search coverage is improved, but system complexity and update frequency requirements increase
Solution Approach 1:
The system extracts only the essential generic attributes from query data that are necessary for categorization, rather than maintaining extensive mapping tables for all possible keyword-category relationships. By extracting relevant attributes dynamically, the system achieves comprehensive coverage without the complexity of exhaustive mapping tables
Solution Approach 2:
The generic attribute extraction mechanism serves multiple functions simultaneously: it categorizes queries, adapts to new query types, and provides the basis for search without requiring separate mapping tables for different scenarios. This multi-functional approach reduces system complexity while maintaining broad coverage
Data Source
AI summary
Searching information includes: receiving current query data from a client; extracting generic attribute features of the current query data, wherein the generic attribute features are used for calculating a plurality of confidence degrees of the current query data that correspond to a plurality of categories, each of the confidence degrees indicating a degree of confidence that the current query data belongs to a respective one of the plurality of categories; determining the plurality of confidence degrees of the current query data based at least in part on the generic attribute features; selecting a category based at least in part on the plurality of confidence degrees, the selected category being one of the plurality of categories and having a confidence degree higher than a confidence degree of another category; searching in the selected category for a search result that corresponds to the current query data; and returning the search result.