Artificial intelligence integrator

Patent metadata

Field	Value
Publication number	US-12432122-B2
Application number	US-202318456766-A
Country	US
Kind code	B2
Filing date	Aug 28, 2023
Priority date	Aug 28, 2023
Publication date	Sep 30, 2025
Grant date	Sep 30, 2025

Abstract

A method for integrating heterogeneous systems is presented including initiating a conversation between a consumer system having a first artificial intelligence (AI) integrator and a producer system having a second AI integrator, training the first and second AI integrators to enable the conversation between the consumer system and the producer system, upon a data request from a client, enabling the consumer system to receive an application programming interface specification (API Spec) and locate the producer system that provides service in conformance with the API Spec, determining missing data needed to conform to the API Spec to build source code, if the producer system determines that it can support the data request, triggering the producer system to generate a contract, and after consensus is provided, in a deployment phase, generating by the producer system the source code to provide information pertaining to the data request.

First claim

The invention claimed is:

1. A method for integrating heterogeneous systems, the method comprising:
initiating a conversation between a consumer system having a first artificial intelligence (AI) integrator and a producer system having a second AI integrator;
training the first and second AI integrators to enable the conversation between the consumer system and the producer system;
upon a data request from a client, enabling the consumer system to receive an application programming interface specification (API Spec) and locate the producer system that provides service in conformance with the API Spec;
determining missing data needed to conform to the API Spec to build source code;
if the producer system determines that it can support the data request, triggering the producer system to generate a contract; and
after consensus is provided, in a deployment phase, generating by the producer system the source code to provide information pertaining to the data request.

2. The method of claim 1 , wherein the training enables the consumer system to understand its role, understand input and output needs, understand format, business context, and perform mapping between system context summary with the input and output.

3. The method of claim 1 , wherein the training allows the first AI integrator to understand specifications of different software programs in an integration context.

4. The method of claim 1 , wherein the contract includes a sample response that satisfies the API Spec, an authentication mechanism, a data format, and pricing information.

5. The method of claim 4 , wherein, in an evaluation phase, the consumer system evaluates the sample response, interprets the authentication mechanism, and if in an agreement, provides the consensus.

6. The method of claim 5 , wherein the evaluation phase includes evaluation of data sufficiency, data format compatibility, and pricing assessment.

7. The method of claim 1 , wherein, if the producer system determines that data is missing and deviations are identified, the producer system reaches out to other configured AI integrators to obtain the missing data.

8. A computer program product comprising a computer readable storage medium having program instructions embodied therewith for integrating heterogeneous systems, the program instructions executable by a computer to cause the computer to:
initiate a conversation between a consumer system having a first artificial intelligence (AI) integrator and a producer system having a second AI integrator;
train the first and second AI integrators to enable the conversation between the consumer system and the producer system;
upon a data request from a client, enable the consumer system to receive an application programming interface specification (API Spec) and locate the producer system that provides service in conformance with the API Spec;
determine missing data needed to conform to the API Spec to build source code;
if the producer system determines that it can support the data request, trigger the producer system to generate a contract; and
after consensus is provided, in a deployment phase, generate by the producer system the source code to provide information pertaining to the data request.

9. The computer program product of claim 8 , wherein the training enables the consumer system to understand its role, understand input and output needs, understand format, business context, and perform mapping between system context summary with the input and output.

10. The computer program product of claim 8 , wherein the training allows the first AI integrator to understand specifications of different software programs in an integration context.

11. The computer program product of claim 8 , wherein the contract includes a sample response that satisfies the API Spec, an authentication mechanism, a data format, and pricing information.

12. The computer program product of claim 11 , wherein, in an evaluation phase, the consumer system evaluates the sample response, interprets the authentication mechanism, and if in an agreement, provides the consensus.

13. The computer program product of claim 12 , wherein the evaluation phase includes evaluation of data sufficiency, data format compatibility, and pricing assessment.

14. The computer program product of claim 8 , wherein, if the producer system determines that data is missing and deviations are identified, the producer system reaches out to other configured AI integrators to obtain the missing data.

15. A system for integrating heterogeneous systems, the system comprising:
a memory; and
one or more processors in communication with the memory configured to:
initiate a conversation between a consumer system having a first artificial intelligence (AI) integrator and a producer system having a second AI integrator;
train the first and second AI integrators to enable the conversation between the consumer system and the producer system;
upon a data request from a client, enable the consumer system to receive an application programming interface specification (API Spec) and locate the producer system that provides service in conformance with the API Spec;
determine missing data needed to conform to the API Spec to build source code;
if the producer system determines that it can support the data request, trigger the producer system to generate a contract; and
after consensus is provided, in a deployment phase, generate by the producer system the source code to provide information pertaining to the data request.

16. The system of claim 15 , wherein the training enables the consumer system to understand its role, understand input and output needs, understand format, business context, and perform mapping between system context summary with the input and output.

17. The system of claim 15 , wherein the training allows the first AI integrator to understand specifications of different software programs in an integration context.

18. The system of claim 15 , wherein the contract includes a sample response that satisfies the API Spec, an authentication mechanism, a data format, and pricing information.

19. The system of claim 18 , wherein, in an evaluation phase, the consumer system evaluates the sample response, interprets the authentication mechanism, and if in an agreement, provides the consensus.

20. The system of claim 19 , wherein the evaluation phase includes evaluation of data sufficiency, data format compatibility, and pricing assessment.

Assignees

• IBM

Inventors

• Rangarajan Arvind
• Jayarathanasamy Pradeep Raj
• Thangaraj Srithar Rajan

Classifications

• G06Q10/06375

  Prediction of business process outcome or impact based on a proposed change · CPC title

• H04L45/306

  Route determination based on the nature of the carried application · CPC title

• G16B50/20

  Heterogeneous data integration · CPC title

• H04W24/08

  Testing, {supervising or monitoring} using real traffic · CPC title

• G06Q20/02

  involving a neutral party, e.g. certification authority, notary or trusted third party [TTP] · CPC title