Learning Apparatus for Search Query Category Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional query log analysis techniques fail to appropriately analyze search queries, as they primarily rely on frequency, missing the connection between search queries and related events, companies, etc., and struggle to identify user needs effectively.
Innovation Solution
A learning device that acquires and analyzes search queries input by multiple users over different periods, specifies categories for each query, and uses a model to learn the characteristics of these categories, predicting future queries based on user behavior patterns.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If search queries are analyzed based on frequency only, then analysis simplicity is maintained, but user needs and preferences cannot be identified
Solution Approach 1:
The patent segments search queries into different categories (e.g., information-seeking, transactional, navigational) and analyzes user behavior patterns across multiple time periods. This segmentation allows the system to move beyond simple frequency counting while maintaining manageable analysis complexity through structured categorization.
Solution Approach 2:
The patent adds temporal dimension by analyzing queries across multiple time periods and categorizing queries by type and user intent. This multi-dimensional approach transforms one-dimensional frequency analysis into a comprehensive analysis that captures user needs, preferences, and behavior patterns over time.
2Speed
If conventional frequency-based analysis is used, then processing speed is maintained, but accuracy of user behavior understanding deteriorates
Solution Approach 1:
The patent performs preliminary categorization of search queries into predefined categories and identifies user behavior patterns in advance. This preliminary action organizes the data structure before detailed analysis, enabling faster processing while maintaining high accuracy in understanding user behavior and preferences.
Solution Approach 2:
The patent changes the analysis parameters from simple frequency counts to multi-dimensional parameters including query categories, temporal patterns, and user behavior characteristics. This parameter transformation enables more accurate measurement of user behavior while the structured approach maintains processing efficiency.
Data Source
AI summary
A learning device according to the present application has an acquisition unit, a specifying unit, and a learning unit. The acquisition unit acquires the search queries, which are the search queries input by a plurality of input customers who have input the reference query and input within mutually different periods. The specifying unit specifies the categories to which the search queries input by the input customer in each period belong. The learning unit causes a model to learn a characteristic of a change in the category specified by the specifying unit.