AI Product Search Parameters for Bulk Procurement Filtering
Find Innovative SolutionsGenerate 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 options.
Innovation Solution
Implement an AI large model to generate professional decision parameters and parameter value alternatives through inference analysis on product information and user behavior data, allowing users to interactively set parameter values in multiple rounds to narrow down search scope.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional manual filtering functions are provided for product search, then users can narrow down search scope, but the operational complexity increases and user experience deteriorates due to level-by-level selection requirements
Solution Approach 1:
The patent replaces the traditional mechanical manual filtering system with an AI-based intelligent recommendation system. Instead of requiring users to manually navigate level-by-level filter options, the system uses AI large models to automatically generate professional decision parameters and recommend optimal filter settings based on user behavior data and product information, thereby maintaining search accuracy while significantly improving operational convenience
Solution Approach 2:
The system enables self-service by having the AI model automatically analyze user behavior data and product information to generate personalized filtering recommendations. The AI system serves itself by processing data and providing intelligent decisions without requiring manual user intervention in the filtering process, allowing users to simply select recommended parameters rather than configuring complex filters manually
2Measurement precision
If professional decision parameters for bulk procurement are added to product search, then search accuracy for Class B buyers improves, but system complexity increases due to numerous parameter configuration options
Solution Approach 1:
The patent applies preliminary action by having the AI large model pre-analyze product information and user behavior data before the user initiates a search. The system pre-generates professional decision parameters and pre-recommends optimal parameter settings based on historical data and patterns, so that when users perform search, the complexity of parameter configuration is already reduced through AI-driven pre-processing and recommendations
Solution Approach 2:
The AI large model serves as an intermediary between the complex parameter configuration system and the user. Instead of directly presenting users with numerous complex parameter options, the AI intermediary analyzes the data, generates simplified professional decision parameters, and provides intelligent recommendations that bridge the gap between raw data complexity and user-friendly interfaces
3Measurement precision
If multiple rounds of interactive parameter setting are implemented, then search scope narrowing effectiveness improves, but user time consumption increases
Solution Approach 1:
The patent implements feedback mechanisms where the AI large model continuously analyzes user interactions and adjusts recommendations in real-time. The system provides feedback by monitoring user behavior patterns and dynamically refining parameter recommendations, allowing the search scope to be narrowed effectively through intelligent adaptation rather than requiring multiple manual interaction rounds
Solution Approach 2:
The AI model performs preliminary analysis of user behavior data and product information before the search process begins, pre-generating optimized parameter settings. This preliminary action reduces the need for multiple interactive rounds during the actual search, as the system already has prepared intelligent recommendations based on pre-processed data
Data Source
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.