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

Patent metadata

Field	Value
Publication number	US-12517958-B2
Application number	US-201916566504-A
Country	US
Kind code	B2
Filing date	Sep 10, 2019
Priority date	Oct 18, 2018
Publication date	Jan 6, 2026
Grant date	Jan 6, 2026

Abstract

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.

First claim

What is claimed is:

1 . A system for next step prediction for ICS (integration cloud services) flow using artificial intelligence/machine learning, comprising:
a computer including one or more microprocessors; an integration platform running on the computer, the integration platform comprising an integration flow designer, the integration flow designer having access to a library comprising a plurality of objects, each object comprising one of an application, an operation, and a business object, each object being selectable to be utilized within an integration flow designed within the integration flow designer; wherein the computer performs steps comprising:
start a design template for an integration flow within the integration flow designer;
collect user context and process context related to the integration flow;
based on the collected user context, process context, and a selected step of the integration flow, select and concurrently provide, as selectable options displayed via a graphical user interface, a plurality of next step predictions from the plurality of objects, each of the plurality of next step predictions capable of being used within the integration flow, wherein at least one of the provided plurality of next step predictions comprises a predicted next task at a first index level, the first index level corresponding to an immediate next task from the selected step, and wherein at least another of the provided next step predictions comprises another predicted task at a second index level, the second index level being higher than the first index level, the second index level corresponding to a next task following the predicted next task in the integration flow, said selection of the plurality of next step predictions being based on a query, by the computer, to a tree structure comprising a hierarchical clustering model of pattern recognition process models, said query comprising both the user context and the process context;
receive a selection of a selected next step prediction of the plurality of next step predictions;
automatically populate, by an auto-completion engine, the selected next step prediction into the integration flow within the integration flow designer; and
upon the automatic population of the selected next step prediction into the integration flow, and based upon the selected next step prediction and the user context and the process context, automatically update the selectable options displayed via the graphical user interface to comprise a new set of next step predictions capable of being used within the integration flow.

2 . The system of claim 1 , wherein the user context and process context take into account organization, subsidiary, department, sub-departments, and user information.

3 . The system of claim 2 , wherein the hierarchical clustering model of pattern recognition process models is utilized in providing the plurality of next step predictions.

4 . The system of claim 3 , wherein the hierarchical clustering model of pattern recognition of process models utilizes stored machine learning knowledge of process design as a hierarchy of clusters.

5 . The system of claim 4 , wherein the hierarchical clustering model of pattern recognition of process models further utilizes machine learning models based on the collected user context.

6 . The system of claim 1 , wherein a ranking generator is used in providing the plurality of next step predictions.

7 . The system of claim 6 , wherein the ranking generator utilizes an input pattern to rank a plurality of output patterns matched with the input pattern, the ranking utilizing one or more inputs; and
wherein the input pattern is created in part from the collected user context.

8 . A method for next step prediction for ICS (integration cloud services) flow using artificial intelligence/machine learning, comprising:
providing a computer that includes one or more microprocessors; providing an integration platform running on the computer, the integration platform comprising an integration flow designer, the integration flow designer having access to a library comprising a plurality of objects, each object comprising one of an application, an operation, and a business object, each object being selectable to be utilized within an integration flow designed within the integration flow designer; starting a design template for an integration flow within the integration flow designer; collecting user context and process context related to the integration flow; based upon the collected user context, process context, and a selected step of the integration flow, selecting and concurrently providing, as selectable options displayed via a graphical user interface, a plurality of next step predictions from the plurality of objects, each of the plurality of next step predictions capable of being used within the integration flow, wherein at least one of the provided plurality of next step predictions comprises a predicted next task at a first index level, the first index level corresponding to an immediate next task from the selected step, and wherein at least another of the provided next step predictions comprises another predicted task at a second index level, the second index level being higher than the first index level, the second index level corresponding to a next task following the predicted next task in the integration flow, said selection of the plurality of next step predictions being based on a query, by the computer, to a tree structure comprising a hierarchical clustering model of pattern recognition process models, said query comprising both the user context and the process context; receiving a selection of a selected next step prediction of the plurality of next step predictions; automatically populating, by an auto-completion engine, the selected next step prediction into the integration flow within the integration flow designer; and upon the automatic population of the selected next step prediction into the integration flow, and based upon the selected next step prediction and the user context and the process context, automatically updating the selectable options displayed via the graphical user interface to comprise a new set of next step predictions capable of being used within the integration flow.

9 . The method of claim 8 , wherein the user context and process context take into account organization, subsidiary, department, sub-departments, and user information.

10 . The method of claim 9 , wherein the hierarchical clustering model of pattern recognition process models is utilized in providing the plurality of next step predictions.

11 . The method of claim 10 , wherein the hierarchical clustering model of pattern recognition process models utilizes stored machine learning knowledge of process design as a hierarchy of clusters.

12 . The method of claim 11 , wherein the hierarchical clustering model of pattern recognition process models further utilizes machine learning models based on the collected user context.

13 . The method of claim 8 , wherein a ranking generator is used in providing the plurality of next step predictions.

14 . The method of claim 13 , wherein the ranking generator utilizes an input pattern to rank a plurality of output patterns matched with the input pattern, the ranking utilizing one or more inputs; and wherein the input pattern is created in part from the collected user context.

15 . A non-transitory computer readable storage medium, having instructions for next step prediction for ICS (integration cloud services) flow using artificial intelligence/machine learning, which

Assignees

• Oracle Int Corp

Inventors

• Andrabi Syed Najeeb
• Modi Rajan
• Mohanram Venkatesh
• Palanisamy Muthukumar
• Hwang Michael

Classifications

• G06F8/34

  Graphical or visual programming · CPC title

• G06F18/231

  Hierarchical techniques, i.e. dividing or merging pattern sets so as to obtain a dendrogram · CPC title

• G06N5/047

  Pattern matching networks; Rete networks · CPC title

• G06N20/20

  Ensemble learning · CPC title

• G06N20/00

  Machine learning · CPC title