Search Query Analysis Device Using Customer Attributes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing query log analysis techniques for search advertising fail to appropriately analyze search queries, leading to a lack of understanding about how customers are related to various targets such as events, companies, etc., as they only analyze queries based on frequency without considering customer attributes or query relevance.
Innovation Solution
A determination device and method that acquire search queries input by multiple customers who have input a reference query within a predetermined period, and determine whether the period is appropriate based on customer attributes or query satisfaction of predetermined conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If search queries are analyzed based on frequency only, then the analysis process is simple and fast, but the analysis precision and ability to understand customer relationships deteriorates
Solution Approach 1:
The patent segments the analysis by introducing multiple dimensions: time period segmentation (predetermined periods before reference time), customer attribute segmentation (first attributes and second attributes), and query type segmentation (search queries, viewed pages, clicked pages). This allows the system to maintain processing efficiency while achieving comprehensive multi-dimensional analysis that improves accuracy.
Solution Approach 2:
The patent transitions from one-dimensional frequency analysis to multi-dimensional analysis by adding time dimension (periods before reference time), customer attribute dimension (first and second attributes), and behavior type dimension (search queries, viewed pages, clicked pages). This dimensional expansion enables accurate customer relationship analysis without significantly increasing processing complexity.
2Measurement precision
If customer attributes and query relevance are considered in analysis, then the analysis accuracy and customer relationship understanding improve, but the device complexity and processing requirements increase
Solution Approach 1:
The patent performs preliminary actions by pre-defining the analysis period (predetermined period before reference time) and pre-categorizing data types (search queries, viewed pages, clicked pages) with their respective attributes. This preparation allows the determination device to systematically process complex data without requiring complex real-time computation, thus managing system complexity while maintaining high analysis accuracy.
3Loss of time
If only frequency-based analysis is performed, then the processing time is short, but the loss of information about customer relationships and event connections increases
Solution Approach 1:
The patent segments the information retrieval process into distinct periods before the reference time and categorizes different types of customer behaviors (search queries, viewed pages, clicked pages) with their specific attributes. This segmentation enables the system to efficiently process and retain valuable customer relationship information that would otherwise be lost in comprehensive multi-dimensional analysis.
Data Source
AI summary
A determination device according to the present application has an acquisition unit and a determination 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 a predetermined period. The determination unit determines whether a predetermined period is appropriate or not based on the attributes of the input customers who have input search queries or based on whether these search queries satisfy predetermined conditions or not.