API Interface Definition Updating for Accurate ML Calling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Developers face challenges in creating API definitions that are understandable by both clients and machine learning models, leading to increased difficulty and cost in interface development, with inaccuracies in API calling.
Innovation Solution
Obtain an interface definition, provide it along with a prompt to a machine learning model to generate updated definition content, and update the interface definition based on this content to facilitate easier understanding and accurate API calling.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of manufacture
If developers manually create API definitions for both clients and machine learning models, then the interface can be developed with clear structure, but the development difficulty and cost increase significantly
Solution Approach 1:
The patent introduces an intermediary system that automatically generates machine learning model-compatible API definitions from client-facing API definitions. This intermediary process eliminates the need for developers to manually create separate definitions for both clients and machine learning models, thereby reducing development difficulty and cost while maintaining clear interface structure.
Solution Approach 2:
The patent performs preliminary generation of machine learning model definitions based on client API definitions before the machine learning model needs to call these interfaces. By pre-generating the definitions and storing them in advance, the system avoids the need for complex manual configuration later, thereby improving ease of manufacture.
2Adaptability or versatility
If developers create separate API definitions for clients and machine learning models, then each can be optimized independently, but the development cost and time increase
Solution Approach 1:
The system performs preliminary generation of machine learning model API definitions based on client API definitions before actual usage. By pre-generating these definitions and storing them, the system eliminates the need for time-consuming manual creation and optimization processes, thereby reducing development time while maintaining adaptability.
Solution Approach 2:
The patent creates a copy of the client API definition and transforms it into a machine learning model-compatible definition automatically. This copying and transformation process preserves the adaptability of the original definition while eliminating the need for separate manual optimization, thereby reducing development time.
3Reliability
If manual API definition creation is used, then accuracy can be controlled, but inaccuracies in API calling still occur and increase development cost
Solution Approach 1:
The system enables self-service by automatically generating machine learning model API definitions from client definitions without requiring manual intervention. This automated process reduces human error and improves API calling accuracy while simultaneously making interface development easier by eliminating manual definition creation.
Solution Approach 2:
The patent implements a feedback mechanism where the generated machine learning model definitions are validated against the original client definitions to ensure accuracy. This feedback loop maintains high reliability in API calling while keeping the development process automated and easy.
Data Source
AI summary
A method, a device, and a storage medium for interface processing are provided. In the method, in response to a request to create an interface, an interface definition for the interface is obtained, a first definition content in the interface definition and a prompt are provided to a machine learning model, to obtain a second definition content generated by the machine learning model for the interface. The interface definition for the interface is updated based on the second definition content, and the interface is created with the updated interface definition.