AI Service Composition for Validated Public Cloud Chaining

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Automating the deployment of complex composite services in cloud environments is challenging due to the complexity of integrating heterogeneous technologies, requiring manual intervention and understanding service parameters, attributes, and prerequisites, which can lead to inefficiencies and potential service unavailability during execution.

Innovation Solution

An AI-based model is trained to recommend services for a cloud computing platform, iteratively learning from user selections to suggest optimized service chains, ensuring compatibility and prerequisite validation, thereby automating the service chaining process.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If manual intervention is used to integrate heterogeneous technologies for complex composite services, then service deployment can be controlled and validated, but the process becomes time-consuming and inefficient

Engineering Contradiction:

Improveservice deployment efficiencyVSAvoidmanual intervention requirement

Core Design Contradiction:

ProductivityVSEase of operation

Solution Approach 1:

The system enables automated service chaining where the AI model independently analyzes service metadata, validates prerequisites, and sequences services without manual intervention. The orchestration layer automatically executes the generated service chains, allowing the system to serve itself rather than requiring continuous human oversight.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The patent replaces manual mechanical processes (human analysts reviewing and configuring service integrations) with an AI-based automated system. The machine learning model processes service metadata, identifies dependencies, and generates optimized service chains, substituting human cognitive and manual operations with automated intelligent systems.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Productivity

If service chaining is automated without validation, then deployment speed increases, but service unavailability and compatibility issues arise

Engineering Contradiction:

Improvedeployment speedVSAvoidservice availability

Core Design Contradiction:

ProductivityVSReliability

Solution Approach 1:

The system performs validation actions before actual service deployment. The AI model analyzes service metadata and validates prerequisites, compatibility, and dependencies in advance, generating a verified service chain configuration before execution. This preliminary validation ensures reliability while maintaining deployment speed.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The orchestration layer monitors service chain execution and provides feedback on service availability and performance. This feedback mechanism allows the system to detect and respond to issues during execution, ensuring service reliability while maintaining automated deployment processes.

Inventive Principle:

Principle #23Feedback

3Reliability

If comprehensive service metadata analysis is performed to ensure compatibility, then service integration reliability improves, but processing time and complexity increase

Engineering Contradiction:

Improveservice integration compatibilityVSAvoidmetadata processing complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system extracts only the essential metadata elements required for service compatibility validation, rather than processing all available service information. The AI model identifies and processes specific metadata fields related to prerequisites, dependencies, and compatibility requirements, reducing processing complexity while maintaining integration reliability.

Inventive Principle:

Principle #2Taking out (Extraction)

4Measurement precision

If iterative AI training with user selections is implemented, then recommendation accuracy improves, but training time and computational resources increase

Engineering Contradiction:

Improveservice recommendation accuracyVSAvoidtraining time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The AI model operates in a continuous iterative training process where user selections are immediately incorporated into subsequent training cycles. The system continuously refines its recommendations based on real-world usage patterns without interrupting service operations, maintaining accurate recommendations while efficiently utilizing training time.

Inventive Principle:

Principle #20Continuity of useful action

Data Source

PatentUS20260052072A1Ai based service composer advisory for complex public cloud services

Publication Date: 2026.02.19 KYNDRYL INC

AI summary

An approach is disclosed for training an artificial intelligence (AI) model to recommend services for a complex composite service chain in a cloud computing platform. The training uses metadata from various services provided by different service providers. The method involves inputting a first service into the trained AI model, which then suggests recommended services. These recommendations are displayed to a user, who selects one of the suggested services. The selected service is displayed as part of the service chain. The AI model then processes metadata from the selected service to provide additional service recommendations. This iterative process continues, with the AI model being further trained based on user selections to improve its recommendations.