In-Store Product Recommendation Using Customer Movement Flow Lines

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing product recommendation systems in stores fail to effectively recommend products to customers based on their movement flow lines, often suggesting products that have already been looked at but not purchased, leading to low purchase conversion rates.

Innovation Solution

An information processing apparatus that uses a combination of customer purchase data, movement flow line analysis, and machine learning to identify products likely to be purchased and recommend them to customers from areas not previously visited, thereby enhancing purchase likelihood.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If product recommendation is made without using customer movement flow line, then recommendation process is simple, but recommendation accuracy deteriorates leading to low purchase conversion

Engineering Contradiction:

Improverecommendation process complexityVSAvoidrecommendation accuracy

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The system performs preliminary tracking and analysis of customer movement flow lines before making product recommendations. By pre-collecting position data and analyzing shopping patterns in advance, the system prepares personalized recommendation data that improves accuracy without increasing the complexity of the actual recommendation delivery process.

Inventive Principle:

Principle #10Preliminary action

2Reliability

If product recommendation uses customer movement flow line analysis, then recommendation accuracy improves, but system complexity increases

Engineering Contradiction:

Improverecommendation accuracyVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system segments the complex recommendation task into distinct modules: movement flow line tracking, position analysis, shopping pattern recognition, and product recommendation generation. Each module handles a specific aspect of the analysis, which reduces overall system complexity while maintaining high recommendation accuracy through specialized processing at each stage.

Inventive Principle:

Principle #1Segmentation

3Adaptability or versatility

If recommendation targets products in already visited areas, then customer may have already considered these products, but recommendation effectiveness deteriorates

Engineering Contradiction:

Improverecommendation coverageVSAvoidpurchase conversion rate

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

Instead of recommending products in areas the customer has already visited, the system inverts the approach by identifying and recommending products in areas the customer has NOT yet visited. This inversion strategy discovers overlooked products that match customer preferences, thereby improving purchase conversion rates while maintaining broad recommendation coverage.

Inventive Principle:

Principle #13The other way round (Inversion)

Data Source

PatentUS20230130023A1Information processing apparatus, product recommendation system, and non-transitory computer readable medium storing program

Publication Date: 2023.04.27 FUJIFILM BUSINESS INNOVATION CORP

AI summary

An information processing apparatus includes a processor configured to specify, using information regarding a product selected as a purchase target by an in-store customer who visits a store and a movement flow line of the in-store customer in the store, a recommended product to be recommended to the in-store customer from among products displayed at a place not looked by the in-store customer in the store.