IP Library › Granted Patent US 12,619,479
Granted Patent B2
US 12,619,479 · App. 17/646,994 · Granted May 5, 2026

Artificial intelligence model management

Inventors: Prateek Goyal (Indore, IN); Manish Anand Bhide (Hyderabad, IN); Trent A. Gray-Donald (Ottawa, CA)
Assignee: International Business Machines Corporation
G06F9/541
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,619,479
App. No.
17/646,994
Granted
May 5, 2026
Kind
B2
Abstract

A computer implemented method manages an artificial intelligence model. A number of processor units detect a change in a format used to exchange information between the artificial intelligence model and an application using the artificial intelligence model. The number of processor units changes the format of the information into an expected format used by the artificial intelligence model and the application. The number of processor units exchanges the information between the artificial intelligence model and the application using the expected format.

Claims (59)

1 . A computer implemented method for managing an artificial intelligence model by an artificial intelligence manager running on a server data processing system coupled to a client device via a communication network, the computer implemented method comprising:

receiving, by a number of processor units using the artificial intelligence manager running on the server data processing system, a request generated by an application using the artificial intelligence model, wherein the application is running on the client device;

sending, by the number of processor units using the artificial intelligence manager running on the server data processing system, the request to the artificial intelligence model;

receiving, by the number of processor units using the artificial intelligence manager running on the server data processing system, a reply generated by the artificial intelligence model;

sending, by the number of processor units using the artificial intelligence manager running on the server data processing system, the reply to the application running on the client device;

detecting, by the number of processor units using the artificial intelligence manager running on the server data processing system, a change in a data transmission format used to exchange information over the communication network between the artificial intelligence model and the application;

changing, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format used to exchange the information over the communication network between the artificial intelligence model and the application into an expected data transmission format used by the artificial intelligence model and the application in response to the artificial intelligence manager detecting the change in the data transmission format; and

exchanging, by the number of processor units using the artificial intelligence manager running on the server data processing system, the information between the artificial intelligence model and the application using the expected data transmission format in response to the artificial intelligence manager changing the data transmission format of the information, wherein the information exchanged between the artificial intelligence model and the application is selected from one of an output from the artificial intelligence model, an input to the artificial intelligence model, and the output from the artificial intelligence model and the input to the artificial intelligence model, wherein the input to the artificial intelligence model is a query request sent to the artificial intelligence model from the application via the communication network and the output from the artificial intelligence model is a query request result generated by the artificial intelligence model as a result of the artificial intelligence model receiving the query request sent to the artificial intelligence model from the application via the communication network.

2 . The computer implemented method of claim 1 , wherein detecting, by the number of processor units using the artificial intelligence manager running on the server data processing system, the change in the data transmission format used to exchange the information between the artificial intelligence model and the application comprises:

detecting, by the number of processor units using the artificial intelligence manager running on the server data processing system, a framework change for the artificial intelligence model, wherein the framework change for the artificial intelligence model changes the data transmission format of how the information is exchanged between the artificial intelligence model and the application using the artificial intelligence model.

3 . The computer implemented method of claim 2 , wherein changing, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of the information exchanged between the artificial intelligence model and the application comprises:

changing, by the number of processor units using the artificial intelligence manager running on the server data processing system, the output of the artificial intelligence model from the framework format for the framework into a prior data transmission format used by the application; and

changing, by the number of processor units using the artificial intelligence manager, the input to the artificial intelligence model from the prior data transmission format used by the application into the framework format for the artificial intelligence model.

4 . The computer implemented method of claim 1 , wherein detecting, by the number of processor units using the artificial intelligence manager running on the server data processing system, the change in the data transmission format used to exchange the information between the artificial intelligence model and the application comprises:

profiling, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of an input and an output of the artificial intelligence model by comparing, by the number of processor units, the input and the output of the artificial intelligence model to a prior input and a prior output for the artificial intelligence model identified from a historical database of inputs and outputs for the artificial intelligence model to form a comparison; and

using, by the number of processor units using the artificial intelligence manager running on the server data processing system, the comparison to detect the change in at least one of the input or the output of the artificial intelligence model.

5 . The computer implemented method of claim 1 , wherein changing, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of the information comprises:

automatically mapping, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of the input from the application to the expected data transmission format used by the artificial intelligence model.

6 . The computer implemented method of claim 1 , wherein changing, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of the information comprises:

automatically mapping, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of the output from the artificial intelligence model to the expected data transmission format used by the application.

7 . The computer implemented method of claim 1 , wherein changing, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of the information comprises:

receiving, by the number of processor units via the communication network using the artificial intelligence manager running on the server data processing system, a format mapping logic for mapping the data transmission format of the information into the expected data transmission format used by at least one of the artificial intelligence model or the application; and

changing, by the number of processor units using the artificial intelligence manager running on the server data processing system, the data transmission format of the information into the expected data transmission format used by the artificial intelligence model and the application using the format mapping logic received by the number of processor units via the communication network.

8 . The computer implemented method of claim 1 , wherein the data transmission format of the information exchanged between the artificial intelligence model and the application is changed into the expected data transmission format used by the artificial intelligence model and the application using at least one of an application programming interface or code containing a logic for converting the information into the expected data transmission format.

9 . A computer system for managing an artificial intelligence model by an artificial intelligence model management system coupled to a client device via a communication network, comprising:

a number of processor units, wherein the number of processor units executes program instructions to:

receive, using the artificial intelligence model management system, a request generated by an application using the artificial intelligence model, wherein the application is running on the client device;

send, using the artificial intelligence model management system, the request to the artificial intelligence model;

receive, using the artificial intelligence model management system, a reply generated by the artificial intelligence model;

send, using the artificial intelligence model management system, the reply to the application running on the client device;

detect, using the artificial intelligence model management system, a change in a data transmission format used to exchange information over the communication network between an artificial intelligence model and the application;

change, using the artificial intelligence model management system, the data transmission format used to exchange the information over the communication network between the artificial intelligence model and the application into the expected data transmission format used by the artificial intelligence model and the application in response to the artificial intelligence model management system detecting the change in the data transmission format; and

exchange, using the artificial intelligence model management system, the information between the artificial intelligence model and the application using the expected data transmission format in response to the artificial intelligence model management system changing the data transmission format of the information, wherein the information exchanged between the artificial intelligence model and the application is selected from one of an output from the artificial intelligence model, an input to the artificial intelligence model, and the output from the artificial intelligence model and the input to the artificial intelligence model, wherein the input to the artificial intelligence model is a query request sent to the artificial intelligence model from the application via the communication network and the output from the artificial intelligence model is a query request result generated by the artificial intelligence model as a result of the artificial intelligence model receiving the query request sent to the artificial intelligence model from the application via the communication network.

10 . The computer system of claim 9 , wherein in detecting the change in the data transmission format used to exchange the information between the artificial intelligence model and the application, the number of processor units executes program instructions to:

detect, using the artificial intelligence model management system, a framework change for the artificial intelligence model, wherein the framework change for the artificial intelligence model changes the data transmission format of how the information is exchanged between the artificial intelligence model and the application using the artificial intelligence model.

11 . The computer system of claim 9 , wherein in changing the data transmission format of the information exchanged between the artificial intelligence model and the application, the number of processor units executes program instructions to:

changing, using the artificial intelligence model management system, the output of the artificial intelligence model from the framework format for the framework into a prior data transmission format used by the application; and

changing, using the artificial intelligence model management system, the input to the artificial intelligence model from the prior data transmission format used by the application into the framework format for the artificial intelligence model.

12 . The computer system of claim 9 , wherein the computer system comprises a plurality of data processing systems coupled together via the communication network, wherein the application runs on a client data processing system of the plurality of data processing systems and the artificial intelligence model runs on a server data processing system of the plurality of data processing systems, and wherein in detecting the change in the data transmission format used to exchange the information between the artificial intelligence model and the application, the number of processor units executes program instructions to:

profile, using the artificial intelligence model management system, the data transmission format of an input and an output of the artificial intelligence model, including compare the input and the output of the artificial intelligence model to a prior input and a prior output for the artificial intelligence model identified from a historical database of inputs and outputs for the artificial intelligence model to form a comparison; and

use, using the artificial intelligence model management system, the comparison to detect the change in at least one of the input or the output of the artificial intelligence model.

13 . The computer system of claim 12 , wherein changing the data transmission format of the information, the number of processor units executes program instructions to:

receive, via the communication network using the artificial intelligence model management system, a format mapping logic for mapping the data transmission format of the information into the expected data transmission format used by at least one of the artificial intelligence model or the application; and

change, using the artificial intelligence model management system, the data transmission format of the information into the expected data transmission format used by the artificial intelligence model and the application using the format mapping logic received by the number of processor units via the communication network.

14 . The computer system of claim 9 , wherein in changing the data transmission format of the information, the number of processor units executes program instructions to:

automatically map, using the artificial intelligence model management system, the data transmission format of the input from the application to the expected data transmission format used by the artificial intelligence model.

15 . The computer system of claim 9 , wherein in changing the data transmission format of the information, the number of processor units executes program instructions to:

automatically map, using the artificial intelligence model management system, the data transmission format of the output from the artificial intelligence model to the expected data transmission format by used the application.

16 . The computer system of claim 9 , wherein the data transmission format of the information exchanged between the artificial intelligence model and the application is changed into the expected data transmission format used by the artificial intelligence model and the application using at least one of an application programming interface or code containing a logic for converting the information into the expected data transmission format.

17 . A computer program product for managing an artificial intelligence model by an artificial intelligence manager running on a server data processing system coupled to a client device via a communication network, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a computer system to cause the computer system to perform a method of:

receiving, using the artificial intelligence manager running on the server data processing system, a request generated by an application using the artificial intelligence model, wherein the application is running on the client device;

sending, using the artificial intelligence manager running on the server data processing system, the request to the artificial intelligence model;

receiving, using the artificial intelligence manager running on the server data processing system, a reply generated by the artificial intelligence model;

sending, using the artificial intelligence manager running on the server data processing system, the reply to the application running on the client device;

detecting, using the artificial intelligence manager running on the server data processing system, a change in a data transmission format used to exchange information over the communication network between the artificial intelligence model and the application;

changing, using the artificial intelligence manager running on the server data processing system, the data transmission format used to exchange the information over the communication network between the artificial intelligence model and the application into an expected data transmission format used by the artificial intelligence model and the application in response to the artificial intelligence manager detecting the change in the data transmission format; and

exchanging, using the artificial intelligence manager running on the server data processing system, the information between the artificial intelligence model and the application using the expected data transmission format in response to the artificial intelligence manager changing the data transmission format of the information, wherein the information exchanged between the artificial intelligence model and the application is selected from one of an output from the artificial intelligence model, an input to the artificial intelligence model, and the output from the artificial intelligence model and the input to the artificial intelligence model, wherein the input to the artificial intelligence model is a query request sent to the artificial intelligence model from the application via the communication network and the output from the artificial intelligence model is a query request result generated by the artificial intelligence model as a result of the artificial intelligence model receiving the query request sent to the artificial intelligence model from the application via the communication network, and wherein detecting, by the number of processor units, the change in the data transmission format used to exchange information between the artificial intelligence model and an application comprises:

profiling, using the artificial intelligence manager running on the server data processing system, the data transmission format of an input and an output of the artificial intelligence model by comparing, by the number of processor units, the input and the output of the artificial intelligence model to a prior input and a prior output for the artificial intelligence model identified from a historical database of inputs and outputs for the artificial intelligence model to form a comparison; and

using, using the artificial intelligence manager running on the server data processing system, the comparison to detect the change in at least one of the input or the output of the artificial intelligence model.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jan 4, 2022
From: GOYAL, PRATEEK; BHIDE, MANISH ANAND; GRAY-DONALD, TRENT A.
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 058546/0647 →
Continuity (1)
Related Publication 20230214276A1 · Jul 6, 2023
References Cited (13)
US 10026041B2 · Narayanan · 2018 [cited by examiner]
US 11636377B1 · Xu · 2023 [cited by examiner]
US 20190384804A1 · Bhide et al. · 2019 [cited by applicant]
US 20210027136A1 · Hwang · 2021 [cited by examiner]
US 20210049497A1 · Jia et al. · 2021 [cited by applicant]
US 20210117859A1 · Rogers et al. · 2021 [cited by applicant]
US 20210136170A1 · Katre · 2021 [cited by examiner]
US 20220027793A1 · Bang · 2022 [cited by examiner]
US 20220058512A1 · Noorizadeh · 2022 [cited by examiner]
US 20220366723A1 · Numaoka · 2022 [cited by examiner]
“Data model automatic upgrade,” An IP.com Prior Art Database Technical Disclosure, Sep. 8, 2011, 3 pages. [cited by applicant]
Akhotia, “How to Integrate Machine Learning into Web Applications with Flask,” Sep. 5, 2020, 18 pages, available at http://www.analyticsvidhya.com/blog/. [cited by applicant]
Mell et al., “The NIST Definition of Cloud Computing”, Computer Security Division, National Institute of Standards and Technology, Jan. 2011, 7 pages. [cited by applicant]