Port Connection Assistance Using Federated Learning Confidence Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The conventional method of connecting ports in model-driven development is cumbersome and inefficient, especially when dealing with complex models having numerous ports, leading to difficulties in finding target ports and requiring error correction, which affects connection efficiency.
Innovation Solution
A port connection assistance method using a federated learning model to determine port confidences, presenting recommended ports in a display list, and allowing users to switch or input port names for accurate and efficient connection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual connection method is used in complex models with hundreds of ports, then connection operations can be performed, but the process becomes cumbersome and inefficient with difficulties in finding target ports
Solution Approach 1:
The system provides real-time feedback by displaying a display list showing multiple candidate ports with their confidence scores, and presents auxiliary connection lines showing recommended connection paths. This feedback mechanism guides users to the correct target port without manual searching, significantly improving connection efficiency in complex models with hundreds of ports.
Solution Approach 2:
The federated learning model acts as an intermediary between the user's connection request and the target port selection. It automatically calculates port confidence scores and generates recommended connections, mediating the complex task of finding correct port matches in large-scale models, thereby improving both efficiency and ease of operation.
2Extent of automation
If automatic connection is implemented by selecting components with ports, then connection operations can be completed automatically, but connection can only be performed on 1st level components and accuracy is insufficient
Solution Approach 1:
The system segments the automatic connection process into multiple levels: it first identifies candidate ports within components, then calculates confidence scores for each candidate, and finally presents ranked options to the user. This segmented approach extends automation beyond 1st level components while maintaining accuracy through multi-stage filtering and confidence scoring.
Solution Approach 2:
The system dynamically adjusts the connection process by calculating real-time confidence scores for multiple candidate ports and presenting them in a ranked display list. This dynamic approach allows the system to adapt to different model complexities and provide accurate recommendations at any component level, not just 1st level, thereby improving both automation extent and measurement precision.
3Adaptability or versatility
If conventional manual connection method is used, then users have full control over connection selection, but the process is time-consuming and error-prone
Solution Approach 1:
The system performs preliminary actions by automatically calculating confidence scores for all candidate ports and generating a ranked display list before the user makes a selection. This preliminary preparation provides users with pre-processed, high-confidence connection recommendations, maintaining their selection flexibility while dramatically reducing the time required to identify correct target ports.
Solution Approach 2:
The federated learning model provides self-service by automatically analyzing port information, calculating confidence scores, and generating recommended connections without user intervention. Users can accept these automated recommendations directly or make adjustments, combining machine efficiency with human oversight to minimize time loss while preserving adaptability.
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
This application discloses a port connection assistance method, a model training method, and an apparatus. The method includes: When receiving a connection instruction for a first port, a first development platform determines a currently idle port as a second port, and obtains port information of the first port and port information of the second port for input into a federated learning model, where there is one or more second ports. The federated learning model may output a port confidence of port information of each second port relative to that of the first port, select n ports with highest port confidences for presentation to a user in a display list in a development interface, and present a connection line between a third port with a highest port confidence and the first port in the development interface. Because the port confidence is a correlation degree between the port information of the second port and the port information of the first port, accuracy of an auxiliary connection line and connection efficiency can be improved by selecting the third port as a connection port.