AI-Guided Product Search for Bulk Procurement Decisions

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing product search systems face challenges in providing accurate search results for Class B buyers, who require professional decision factors for bulk procurement or customization, leading to high labor costs and user resentment due to numerous manual configuration requirements.

Innovation Solution

Implement an AI large model to generate and display interactive decision parameters related to bulk procurement or customization, allowing users to set parameter values in multiple rounds of interaction, with the AI model performing inference analysis on product and user behavior data to update search results.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual configuration of decision parameters is used for bulk procurement search, then professional decision factors can be provided, but labor costs increase and user resentment occurs due to numerous manual configuration requirements

Engineering Contradiction:
Improvesearch accuracyVSAvoidconfiguration complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system automatically generates and configures professional decision parameters using AI large models, eliminating the need for manual configuration. The AI model autonomously analyzes product information and user behavior data to create relevant parameters, allowing the system to serve itself rather than requiring manual intervention for each search scenario.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent dynamically adjusts decision parameters based on AI inference analysis of product information and user behavior data. Instead of fixed manual configurations, the system transforms and adapts parameters automatically according to the specific search context, product category, and user preferences, enabling flexible and accurate search without manual overhead.

Inventive Principle:
Principle #35Parameter changes

2Ease of operation

If traditional filtering functions are provided for product search, then users can narrow down search scope, but operational difficulties arise due to level-by-level category selection requirements

Engineering Contradiction:
Improvesearch convenienceVSAvoidsearch time
Core Design Contradiction:
Ease of operationVSLoss of time

Solution Approach 1:

The system pre-generates professional decision parameters and their corresponding parameter values using AI large models before users initiate searches. By preparing the filtering options in advance based on product information and user behavior analysis, the system eliminates the need for users to navigate through multiple category levels during the search process, significantly reducing search time and operational complexity.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The patent introduces AI-generated professional decision parameters as an intermediary layer between user intent and product results. Instead of requiring users to directly navigate category hierarchies, the AI parameters act as a mediator that translates user needs into filtered results, simplifying the interaction and reducing the time users spend on search operations.

Inventive Principle:
Principle #24Intermediary (Mediator)

3Measurement precision

If AI large model generates professional decision parameters for bulk procurement, then search accuracy improves for Class B buyers, but system complexity increases

Engineering Contradiction:
Improvesearch accuracyVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent employs a universal AI large model that can generate professional decision parameters across multiple product categories and industries. Rather than implementing separate parameter generation systems for each category, the single AI model performs multiple functions including analyzing product information, understanding user behavior patterns, and creating relevant decision parameters for diverse search scenarios, thereby managing system complexity while maintaining high search accuracy.

Inventive Principle:
Principle #6Universality (Multi-functionality)

Data Source

PatentEP4708184A1Product search method and electronic device
Publication Date: 2026.03.11 HANGZHOU ALIBABA INT INTERNET IND CO LTD
  • EP4708184A1 patent drawingFigure 1
  • EP4708184A1 patent drawingFigure 2
  • EP4708184A1 patent drawingFigure 3

AI summary

A product search method including: providing an interactive area in a product search result page after receiving a product search request input by a first user, wherein the interactive area is configured to provide a plurality of decision parameters, some or all of the decision parameters being associated with parameter value alternatives; and the decision parameters displayed in the interactive area comprise: a portion of professional decision parameters related to bulk procurement or customization of products in a category or industry to which a currently searched product belongs; the professional decision parameters are generated by an artificial intelligence AI large model after performing an inference analysis on product information and/or user behavior data in the category or industry; and updating product search results after receiving a parameter value setting result completed by the first user for the plurality of decision parameters.