Generative AI User Matching for Merchandise History Alignment

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional techniques for determining similar users based on merchandise buying and selling behaviors fail to provide services that align with users' interests and tastes, and ensure user safety.

Innovation Solution

An information processing apparatus that utilizes generative AI to match users with similar merchandise histories, recommending similar users and generating profile screens tailored to user histories, thereby enhancing user connection and safety.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If conventional techniques for determining similar users are used, then user matching can be performed, but the service cannot align with users' interests and tastes in merchandise buying and selling

Engineering Contradiction:

Improvealignment with user interestsVSAvoiduser safety

Core Design Contradiction:

Adaptability or versatilityVSReliability

Solution Approach 1:

The patent changes the parameter for user similarity measurement from conventional methods to generative AI-based semantic analysis. The system inputs user profile information and use history data into generative AI models to compute similarity scores, enabling nuanced alignment with user interests while maintaining safety through controlled AI interactions.

Inventive Principle:

Principle #35Parameter changes

2Manufacturing precision

If conventional user matching techniques are applied, then basic user connection is achieved, but high-quality profile screens tailored to user histories cannot be generated

Engineering Contradiction:

Improveprofile screen qualityVSAvoidsystem complexity

Core Design Contradiction:

Manufacturing precisionVSDevice complexity

Solution Approach 1:

The patent introduces generative AI as an intermediary component between user data and profile screen generation. The AI model processes user profile information and use history, transforming raw data into high-quality, personalized profile screens while managing system complexity through a dedicated AI processing layer.

Inventive Principle:

Principle #24Intermediary (Mediator)

3Adaptability or versatility

If generative AI is used for user selection, then services aligned with user interests can be provided, but computational resources and processing time increase

Engineering Contradiction:

Improveservice alignmentVSAvoidcomputational resource consumption

Core Design Contradiction:

Adaptability or versatilityVSUse of energy by moving object

Solution Approach 1:

The patent applies partial action by using generative AI selectively for user similarity assessment rather than for all system operations. The AI model is invoked only when user matching is required, while other system functions use conventional processing methods, thereby reducing overall computational resource consumption while maintaining service alignment quality.

Inventive Principle:

Principle #16Partial or excessive action

Data Source

PatentUS20250209546A1Information processing apparatus, information processing method, and non-transitory computer readable storage medium

Publication Date: 2025.06.26 LY CORP

AI summary

An information processing apparatus according to the present application includes an acquisition unit, a selection unit, and a recommendation unit. The acquisition unit acquires a use history of a user, the use history being related to buying and selling of merchandise. The selection unit selects another user to be recommended by inputting, to generative AI, a first prompt instructing selection of another user having a use history similar to that of the user. The recommendation unit recommends that the user follow the other user selected by the selection unit.