Machine-Learning Technology Matching for Faster Trade Commercialization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technology trade platforms face challenges in effectively connecting public technologies with technology consumers due to information gaps and reliance on expert searches, leading to low success rates in technology trade and commercialization.
Innovation Solution
A method and system utilizing machine-learning models to analyze public technology and consumer data, extracting feature data, and scoring potential matches based on success possibility, enabling more accurate and efficient technology trade matching.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional trade platforms provide only information focused on public technology or rely on expert searches, then the platform operation is simple, but the matching effectiveness and technology trade success rate are low
Solution Approach 1:
The patent introduces machine learning models as an intermediary between public technology providers and technology consumers. The ML models process technology data and consumer data to generate compatibility scores and matching recommendations, acting as a mediator that bridges the information gap without requiring complex human expert intervention on the platform side
Solution Approach 2:
The system enables self-service matching by allowing the machine learning models to automatically process and match technology data with consumer data without requiring manual expert search. The platform provides tools that allow technology providers and consumers to input their data and receive automated matching results, reducing the need for complex platform-mediated expert searches
2Productivity
If expert searches are used to match public technology with technology consumers, then the matching process is simple to implement, but the matching speed is slow and productivity is low
Solution Approach 1:
The patent replaces the mechanical process of expert human searches with automated machine learning models. The ML models process technology and consumer data through algorithmic operations to generate matching scores, substituting the manual mechanical search process with automated computational processes that operate at much higher speeds
Solution Approach 2:
The system changes the parameters of the matching process by using machine learning models that process multiple data parameters simultaneously (technology data, consumer data, compatibility factors) to generate comprehensive matching scores. This multi-parameter processing approach enables faster and more accurate matching compared to sequential expert search methods
3Measurement precision
If comprehensive data analysis is performed to improve matching accuracy, then the technology trade success possibility increases, but the processing time and computational resources increase
Solution Approach 1:
The patent implements preliminary action by pre-processing and structuring technology data and consumer data before the actual matching process. The machine learning models are trained in advance with historical data, and data is pre-formatted into suitable structures, enabling faster real-time matching while maintaining high accuracy through the preliminary preparation work
Solution Approach 2:
The system uses copying by creating feature representations and embeddings of technology and consumer data that capture essential characteristics in a compressed form. These copied representations enable efficient comparison and matching without requiring processing of the complete original datasets, reducing processing time while preserving matching accuracy
Data Source
AI summary
There is provided a method for matching a public technology with a technology consumer, the method being performed by a computing system. The method may comprise acquiring data about the public technology, applying the acquired data to a first machine-learning model to acquire technology feature data about the public technology, wherein the first machine-learning model is configured to output the technology feature data based on the data about the public technology and matching the public technology with at least one technology consumer, based on the technology feature data and a plurality of consumer feature data stored in a database.