API Governance via ML Similarity Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The proliferation of redundant APIs within organizations leads to duplication of effort, increased fragility, operating costs, data integrity issues, and security concerns, making API management challenging.
Innovation Solution
A computer-implemented method using a trained machine learning model to identify existing API specifications similar to a new API specification by extracting keywords and generating feature vectors, allowing for the recommendation of existing APIs with similar context and intent, thereby reducing the need for creating redundant APIs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If organizations allow free creation of new APIs, then developers can quickly meet functional requirements, but redundant APIs proliferate causing duplication of effort and increased complexity
Solution Approach 1:
The system performs preliminary analysis by extracting keywords from new API specifications and using machine learning models to identify similar existing APIs before the new API is fully created. This preliminary action prevents redundancy by alerting developers to existing alternatives early in the development process, thus maintaining productivity while avoiding API proliferation.
2Reliability
If organizations implement strict API governance, then API quality and consistency improve, but development efficiency decreases due to additional review processes
Solution Approach 1:
The system enables self-service governance by automatically analyzing API specifications through keyword extraction and machine learning comparison. The governance process does not require manual review of every API, as the system autonomously identifies similarities and provides recommendations, thereby maintaining high API quality without significantly impacting development efficiency.
3Adaptability or versatility
If developers create new APIs for each requirement, then functional requirements are met, but development and management costs increase
Solution Approach 1:
The system provides feedback to developers by comparing new API specifications against existing APIs using machine learning models. When similarities are detected, the system alerts developers to potential reuse opportunities, enabling them to adapt existing APIs rather than creating new ones. This feedback loop maintains functional flexibility while reducing development costs by preventing redundant API creation.
4Adaptability or versatility
If multiple similar APIs exist, then developers have more options, but data integrity and security issues arise
Solution Approach 1:
The system takes preliminary anti-action by preventing the creation of redundant APIs that could lead to data integrity and security issues. Through keyword extraction and machine learning-based similarity detection, the system identifies existing APIs that fulfill the same functional requirements before new APIs are created, thus avoiding the proliferation of similar APIs that would compromise data integrity and security.
Data Source
AI summary
In one aspect, an example methodology implementing the disclosed techniques includes receiving a new application programming interface (API) specification and extracting one or more keywords from the new API specification. The method also includes identifying, using a trained machine learning (ML) model, one or more existing API specifications that are similar to the new API specification based on the one or more keywords from the new API specification and, responsive to the identification, outputting information regarding the one or more existing API specifications that are similar to the new API specification.