Automated Skeleton-Based Product Interest Rule Generation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for detecting customer interest in products are labor-intensive and time-consuming, requiring manual generation of detection rules for each product, which is impractical due to the large number of products and varying customer actions.
Innovation Solution
A system that generates detection rules based on past actions, presence or absence of product purchase, and basic movements in stages to identify customers highly effective in customer service, using cameras and an information processing device to analyze image data and generate rules that do not depend on specific products.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual detection rules are generated for each product, then detection accuracy for customer interest is improved, but labor intensity and time consumption increase significantly
Solution Approach 1:
The patent segments the detection rule generation process into automated stages: collecting skeletal information from multiple customers, extracting common action patterns through clustering, and generating detection rules automatically. This divides the previously manual monolithic process into systematic automated steps, reducing labor intensity while maintaining detection accuracy.
Solution Approach 2:
The system enables self-service detection rule generation by automatically collecting customer skeletal data, analyzing action patterns, and creating detection rules without human intervention. The system serves itself by processing its own data to generate the rules it needs, eliminating the need for manual rule creation for each product.
2Measurement precision
If manual detection rules are generated for each product, then detection accuracy for customer interest is improved, but labor intensity increases
Solution Approach 1:
The system enables self-service detection rule generation by automatically collecting customer skeletal data, analyzing action patterns, and creating detection rules without human intervention. The system serves itself by processing its own data to generate the rules it needs, eliminating the need for manual rule creation for each product.
Solution Approach 2:
The patent replaces the manual mechanical process of rule creation with an automated information processing system that collects skeletal data, performs clustering analysis, and generates detection rules algorithmically. This substitutes human labor with computational mechanisms, significantly reducing labor intensity.
3Adaptability or versatility
If detection rules are created for each product type, then adaptability to different products is improved, but device complexity increases
Solution Approach 1:
The patent creates a universal detection rule generation system that can handle multiple product types through automated pattern extraction. Instead of requiring separate rule creation mechanisms for each product, the system uses clustering algorithms to adaptively generate product-specific rules from general customer action data, making the system multi-functional and product-agnostic.
Solution Approach 2:
The system enables self-service detection rule generation by automatically collecting customer skeletal data, analyzing action patterns, and creating detection rules without human intervention. The system serves itself by processing its own data to generate the rules it needs, eliminating the need for manual rule creation for each product.
4Measurement precision
If comprehensive action analysis is performed for each product, then detection precision is improved, but processing time increases
Solution Approach 1:
The patent performs preliminary action by pre-collecting and storing skeletal information data from multiple customers during normal operation. This advance data collection and pattern extraction enables rapid detection rule application during actual customer service, separating the time-consuming analysis phase from the real-time detection phase.
Solution Approach 2:
The patent segments the detection rule generation process into automated stages: collecting skeletal information from multiple customers, extracting common action patterns through clustering, and generating detection rules automatically. This divides the previously manual monolithic process into systematic automated steps, reducing labor intensity while maintaining detection accuracy.
Data Source
Figure 1
Figure 2
Figure 3~4
AI summary
An information processing device (10) obtains each piece of image data captured within a period of time from entering until exiting of a person at a store. The information processing device (10) identifies joint positions of a skeleton related to the person by analyzing each piece of the image data. The information processing device (10) identifies, as an action which indicates a degree of interest of the person in the product, an action performed by the person to a product in the store from the entering until the exiting, on a basis of the joint positions of the skeleton. The information processing device (10) generates a detection rule that correlates the identified action and the product with each other.