DYNAMIC ARTIFICIAL INTELLIGENCE / MACHINE LEARNING MODEL UPDATE, OR RETRAIN AND UPDATE, IN DIGITAL PROCESSES AT RUNTIME

• US 20200134374A1
• Filed: 12/20/2019
• Published: 04/30/2020
• Est. Priority Date: 12/20/2019
• Status: Active Grant

• Current Assignee: UiPath Inc.
• Original Assignee: UiPath Inc.
• Inventors: Oros, Andrei Robert
• Granted Patent: US 11,822,913 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06F 8/65 Updates security arrangements therefor G06F21/57
• CPC Class Codes: G06F 8/656 while running
• CPC Class Codes: G06F 8/71 Version control security arrangements therefor G06F21/57; Configuration management
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/044 Recurrent networks, e.g. Hopfield networks
• CPC Class Codes: G06N 3/08 Learning methods
• CPC Class Codes: G06N 3/105 Shells for specifying net layout
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks

Abstract

Dynamically updating, or retraining and updating, artificial intelligence (AI)/machine learning (ML) models in digital processes at runtime is disclosed. Production operation may not need to be stopped for AI/ML model update or retraining and update. The update steps and/or retraining steps for the AWL model may be included as part of the digital process. The AI/ML model update may be requested from internal logic (e.g., from the evaluation of a condition, by an that expression calls for the AI/ML model, etc.), external requests (e.g., from external triggers in a finite state machine (FSM), such as a file change, database data, a service call, etc.), or both. Automation of AI/ML model updates or retraining and updates may be provided, where the software reloads/reinitializes/re-instantiates with a retrained and/or updated AWL model after (and possibly immediately after) the AI/ML model becomes available.

Claims

1. A computer-implemented method, comprising:

listening for an update request for an artificial intelligence (AI)/machine learning (ML) model, by a digital process executing on a computing system; and

when the update request is received to update the AWL model, reinitializing or re-instantiating the digital process to call an updated version of the AWL model and listening for another update request, by the digital process executing on the computing system, wherein

the updating of the AI/ML, model occurs during runtime of the digital process.

2. The computer-implemented method of claim 1, further comprising:

listening for a retraining request for the AI/ML model, by the digital process executing on the computing system; and

when the retraining request is received to retrain the AWL model, initiating retraining of the AWL model, by the digital process executing on the computing system, wherein

the retraining of the AI/ML model occurs during runtime of the digital process.

3. The computer-implemented method of claim 2, wherein the retraining of the AI/ML model occurs on one or more other computing systems different than the computing system executing the digital process.

4. The computer-implemented method of claim 2, further comprising:

using a current version of the AI/ML, model during the retraining, by the digital process running on the computing system, until the update request is received.

5. The computer-implemented method of claim 2, further comprising:

comparing performance of the retrained AI/ML model to a performance threshold, against performance of a previous version of the AI/ML model, or both, by the digital process executing on the computing system; and

updating the AI/ML model when the retrained AI/ML model exceeds the performance threshold, the performance of the previous version of the AI/ML model, or both, by the digital process executing on the computing system.

6. The computer-implemented method of claim 1, further comprising:

automatically initiating retraining of the AI/ML model, by the digital process executing on the computing system, after a predetermined amount of training data is received, after a predetermined amount of time has elapsed since a last retraining, or both.

7. The computer-implemented method of claim 1, wherein the digital process comprises a robotic process automation (RPA) workflow, a business process management (BPM) flowchart, a sequential flow, or a finite state machine (FSM).

8. The computer-implemented method of claim 1, wherein the digital process comprises an RPA workflow and the AWL model is called by an activity of the RPA workflow.

9. The computer-implemented method of claim 8, wherein the AWL model is embedded directly in the activity of the RPA workflow.

10. The computer-implemented method of claim 1, wherein the digital process comprises an initialization state that loads the AWL model from storage or makes the AI/ML model callable by the digital process.

11. The computer-implemented method of claim 1, further comprising:

receiving a request to run the AI/ML model, by the digital process running on the computing system;

executing the AWL model, or causing the AWL model to be executed, by the digital process running on the computing system; and

returning results of the execution of the AI/ML model, by the digital process running on the computing system.

12. A computer program comprising a digital process and embodied on a non-transitory computer-readable medium, the program configured to cause at least one processor to:

listen for a retraining request or an update request for an artificial intelligence (AI)/machine learning (ML) model;

when the retraining request is received to retrain the AWL model, initiate retraining of the AWL model; and

when the update request is received to update the AWL model, reinitialize or re-instantiate the digital process to call an updated version of the AI/ML model and listen for another retraining request or update request, wherein

the retraining or updating of the AI/ML model occurs during runtime of the digital process.

13. The computer program of claim 12, wherein the program is further configured to cause the at least one processor to:

use a current version of the AWL model during the retraining until the update request is received.

14. The computer program of claim 12, wherein the program is further configured to cause the at least one processor to:

compare performance of the retrained AI/ML model to a performance threshold, against performance of a previous version of the AI/ML model, or both; and

update the AWL model when the retrained AWL model exceeds the performance threshold, the performance of the previous version of the AI/ML model, or both.

15. The computer program of claim 12, wherein the program is further configured to cause the at least one processor to:

automatically initiate retraining of the AI/ML model after a predetermined amount of training data is received, after a predetermined amount of time has elapsed since a last retraining, or both.

16. The computer program of claim 12, wherein the digital process comprises an RPA workflow and the AI/ML model is called by an activity of the RPA workflow.

17. The computer program of claim 12, wherein the program is further configured to cause the at least one processor to:

receive a request to run the AI/ML model;

execute the AI/ML model or cause the AI/ML model to be executed; and

return results of the execution of the AI/ML model.

18. A computing system, comprising:

memory storing computer program instructions comprising a digital process; and

at least one processor configured to execute the computer program instructions, the instructions configured to cause the at least one processor to;

listen for a retraining request for an artificial intelligence (AI)/machine learning (ML) model, and

when the retraining request is received to retrain the AWL model, initiate retraining of the AI/ML model, wherein

the retraining of the AI/ML model occurs during runtime of the digital process.

19. The computing system of claim 18, wherein the instructions are further configured to cause the at least one processor to:

listen for an update request for the AI/ML model; and

when the update request is received to update the AWL model, reinitialize or re-instantiate the digital process to call an updated version of the AI/ML model and listen for another update request, by the digital process executing on the computing system, wherein

the updating of the AI/ML model occurs during runtime of the digital process.

20. The computing system of claim 18, wherein the program is further configured to cause the at least one processor to:

use a current version of the AWL model during the retraining until the update request is received.

21. The computing system of claim 18, wherein the program is further configured to cause the at least one processor to:

compare performance of the retrained AI/ML model to a performance threshold, against performance of a previous version of the AI/ML model, or both; and

update the AWL model when the retrained AWL model exceeds the performance threshold, the performance of the previous version of the AI/ML model, or both.

22. The computing system of claim 18, wherein the program is further configured to cause the at least one processor to:

automatically initiate retraining of the AI/ML model after a predetermined amount of training data is received, after a predetermined amount of time has elapsed since a last retraining, or both.

23. The computing system of claim 18, wherein the digital process comprises an RPA workflow and the AI/ML model is called by an activity of the RPA workflow.

24. The computing system of claim 18, wherein the program is further configured to cause the at least one processor to:

receive a request to run the AWL model;

execute the AI/ML model or cause the AWL model to be executed; and

return results of the execution of the AI/ML model.

25. A computer-implemented method for dynamic update, or retraining and update, of an artificial intelligence (AI)/machine learning (ML) model, comprising:

listening for an update request for the AWL model, by a robotic process automation (RPA) digital process executing on a computing system; and

when the update request is received to update the AWL model, reinitializing or re-instantiating the RPA digital process to call an updated version of the AI/ML model and listening for another update request, by the RPA digital process executing on the computing system, wherein

the updating of the AI/ML model occurs during runtime of the RPA digital process, and

the RPA digital process comprises an RPA workflow and the AI/ML model is called by an activity of the RPA workflow.

26. The computer-implemented method of claim 25, further comprising:

listening for a retraining request for the AI/ML model, by the RPA digital process executing on the computing system; and

when the retraining request is received to retrain the AWL model, initiating retraining of the AI/ML model, by the RPA digital process executing on the computing system, wherein

the retraining of the AI/ML model occurs during runtime of the RPA digital process.

27. The computer-implemented method of claim 26, further comprising:

using a current version of the AI/ML, model during the retraining, by the RPA digital process running on the computing system, until the update request is received.

28. The computer-implemented method of claim 26, further comprising:

comparing performance of the retrained AI/ML model to a performance threshold, against performance of a previous version of the AI/ML model, or both, by the RPA digital process executing on the computing system; and

updating the AI/ML model when the retrained AI/ML model exceeds the performance threshold, the performance of the previous version of the AI/ML model, or both, by the RPA digital process executing on the computing system.

29. The computer-implemented method of claim 25, further comprising:

automatically initiating retraining of the AI/ML model, by the RPA digital process executing on the computing system, after a predetermined amount of training data is received, after a predetermined amount of time has elapsed since a last retraining, or both.

30. The computer-implemented method of claim 25, further comprising:

receiving a request to run the AI/ML model, by the RPA digital process running on the computing system;

executing the AWL model, or causing the AWL model to be executed, by the RPA digital process running on the computing system; and

returning results of the execution of the AI/ML model, by the RPA digital process running on the computing system.