AI Supplier Ranking System Using Keyword Extraction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional keyword searching methods for finding service suppliers are inefficient and fail to distinguish quality, often returning noise information and unqualified suppliers, requiring significant time and effort to filter through results.
Innovation Solution
A system and method using artificial intelligence models to extract keywords, calculate similarity scores, and assess risk, presenting potential suppliers in a graphical user interface (GUI) ranked by similarity and risk scores, allowing for efficient identification of high-quality suppliers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional keyword searching methods are used to find service suppliers, then the search process is simple and fast, but the returned results contain noise information and unqualified suppliers, reducing result quality
Solution Approach 1:
The system performs preliminary actions by pre-selecting potential service suppliers and pre-extracting their information before the actual search query. When a user searches, the system has already prepared candidate suppliers with extracted data, enabling rapid filtering and ranking without real-time analysis of all suppliers, thus improving result quality while reducing time loss.
Solution Approach 2:
The system introduces an intermediary mechanism - an artificial intelligence model that acts as a mediator between the search query and the supplier database. This model extracts relevant information from pre-selected suppliers and ranks them according to query relevance, filtering out unqualified suppliers automatically. This intermediary processing layer significantly improves result quality while reducing the time users spend filtering through irrelevant results.
2Measurement precision
If conventional keyword searching methods are used, then the search operation is simple, but the system cannot distinguish the quality of potential suppliers or identify negative news
Solution Approach 1:
An artificial intelligence model serves as an intermediary between the simple keyword search interface and the complex task of quality assessment. The model automatically extracts information from supplier web pages, analyzes news articles, identifies negative information, and ranks suppliers by quality. This intermediary handles the complexity internally while maintaining a simple user interface, thus improving quality distinction capability without significantly increasing perceived system complexity for users.
Solution Approach 2:
The system replaces manual quality assessment mechanisms with automated artificial intelligence models. Instead of requiring users to manually evaluate supplier quality or hire analysts to review news, the system uses AI to automatically extract information, analyze sentiments, identify negative news, and rank suppliers. This substitution of mechanical human evaluation with automated intelligent systems improves quality distinction while managing system complexity through automation.
3Productivity
If users manually go through numerous search results to determine supplier qualification, then no additional system resources are used, but it requires large amounts of time and effort from users
Solution Approach 1:
The system implements self-service by automatically performing the filtering and ranking tasks that would otherwise require user effort. The artificial intelligence model autonomously extracts information from pre-selected suppliers, analyzes their qualifications, identifies negative news, and ranks them by relevance and quality. This self-service automation dramatically improves productivity in supplier identification while reducing user time and effort to minimal interaction with the results.
Data Source
AI summary
Disclosed herein are embodiments of systems, methods, and products comprises a server, which identifies optimized potential suppliers based on the client's request. The request comprises search specification and preselected bidders. The server extracts a first set of keywords from the search specification and finds web pages of potential suppliers based on the first set of keywords. The server identifies the websites of the preselected bidders, extracts a second set of keywords from the websites, and finds web pages of more potential suppliers based on the second set of keywords. The server determines the web pages are associated with real suppliers by excluding non-supplier web pages. The server determines a similarity score for each potential supplier by vectorizing keywords extracted from the supplier's web pages. The server determines a risk score for each potential supplier. The server generates a GUI comprising a list of suppliers ranked based on the similarity scores.