Information Processing Apparatus for Personalized Item Recommendations

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current systems fail to effectively utilize browsing and purchase history information to recommend items based on complementarity and substitutability relationships, limiting personalized recommendations for users.

Innovation Solution

A non-transitory computer readable medium and information processing apparatus that calculates complementarity and substitutability values from browsing and purchase history information, using a controller to perform clustering, probability calculations, and item recommendations based on these values to suggest items to users.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If browsing and purchase history information is collected and analyzed, then personalized item recommendations can be provided, but system complexity and data processing requirements increase

Engineering Contradiction:

Improvepersonalized recommendation capabilityVSAvoidsystem complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent segments the recommendation system into distinct functional modules: a relationship information generation unit that calculates complementarity and substitutability values, and a recommendation unit that uses these values to generate recommendations. This segmentation allows complex analysis to be broken down into manageable, independent components that can be processed separately and efficiently.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary analysis by pre-calculating and storing relationship information (complementarity and substitutability values) between items before actual recommendation requests. This preliminary action transforms raw browsing and purchase history data into structured relationship metrics that can be quickly retrieved and applied during recommendation generation, reducing real-time processing complexity.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If relationship analysis between multiple items is performed, then recommendation accuracy improves, but calculation time and processing load increase

Engineering Contradiction:

Improverecommendation accuracyVSAvoidcalculation time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs relationship analysis in advance by calculating complementarity and substitutability values between items and storing them as pre-processed relationship information. When generating recommendations, the system simply retrieves these pre-calculated values rather than performing complex calculations in real-time, significantly reducing calculation time while maintaining high recommendation accuracy.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent transforms complex relationship analysis into simplified quantitative parameters (complementarity values and substitutability values). By converting qualitative item relationships into measurable numerical parameters, the system enables efficient comparison and ranking of items while maintaining analytical precision.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS10430808B2Non-transitory computer readable medium and information processing apparatus

Publication Date: 2019.10.01 FUJIFILM BUSINESS INNOVATION CORP

AI summary

A non-transitory computer readable medium stores a program causing a computer to execute a process including calculating a value indicating a complementarity and a value indicating a substitutability, the values each being calculated as information indicating a relationship between multiple items on a basis of browsing history information and purchase history information of the items.