AI-Guided ICS Flow Completion for Next-Step Prediction

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Integration cloud service (ICS) flow development is complex and time-consuming, particularly for novice users, who may miss mandatory steps and require extensive consultation or research to follow best practices, leading to increased effort and error rates.

Innovation Solution

Utilizing artificial intelligence and machine learning to predict and suggest the next set of actions in ICS flow design, providing real-time cues and recommended connections based on user and process context, thereby simplifying the development process and reducing errors.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If manual flow design is used, then users have full control over the design process, but the process becomes complex and time-consuming with high error rates

Engineering Contradiction:

Improveerror rateVSAvoidtime to create flow

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system enables self-service by using machine learning models to automatically predict and suggest next actions in flow design based on user context and historical data, reducing manual effort and errors without requiring extensive user expertise

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system implements feedback by continuously learning from user interactions and flow design patterns, using this feedback to improve prediction accuracy and provide increasingly relevant suggestions as the system adapts to user behavior and best practices

Inventive Principle:

Principle #23Feedback

2Reliability

If comprehensive best practices are enforced, then flow quality improves, but user effort and complexity increase

Engineering Contradiction:

Improveflow qualityVSAvoiduser effort

Core Design Contradiction:

ReliabilityVSEase of operation

Solution Approach 1:

The system performs preliminary action by pre-analyzing user context, available actions, and best practices to generate predicted next actions before the user needs to make decisions, thereby guiding users toward quality flows without increasing their operational effort

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The machine learning model acts as an intermediary between user intentions and best practice requirements, translating user needs into suggested actions that naturally align with quality standards without users directly confronting complex rules

Inventive Principle:

Principle #24Intermediary (Mediator)

3Productivity

If AI/ML prediction is added, then time to create flow decreases, but system complexity increases

Engineering Contradiction:

Improveflow creation speedVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system applies segmentation by dividing the complex AI/ML system into modular components including separate prediction models, context analysis modules, and suggestion generation systems, allowing independent development and maintenance of each functional segment

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS12517958B2System and method for next step prediction of ICS flow using artificial intelligence/machine learning

Publication Date: 2026.01.06 ORACLE INT CORP

AI summary

In accordance with an embodiment, described herein are systems and methods for auto-completion of ICS flow using artificial intelligence/machine learning. Next actions prediction is a service that assists users in modeling the flows quickly by predicting and suggesting the next set of actions a user might be thinking of adding. The service also assists the user to follow some of the best practices while creating an integration flow.