IP Library Granted Patent US 11,347,483
Granted Patent B2
US 11,347,483 · App. 17/069,274 · Granted May 31, 2022

Linking stages in process flows with machine learning

Inventors: Claire Casaregola (New York, NY); David Dushaj (New York, NY); Michael Greene (New York, NY); Yair Pike (New York, NY); Alexander Chan (New York, NY); Lauren Miller (New York, NY)
Assignee: ADP, Inc.
G06F8/433G06F8/33G06F8/34G06N20/00
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 11,347,483
App. No.
17/069,274
Granted
May 31, 2022
Kind
B2
Abstract

A method for designing a logic flow for a user interface is provided. The method comprises receiving from a first task for an automation process file from a user. The automation process file defines a set of system activities. The first task is added to the automation process file and submitted to a machine learning engine, which determines a number of suggested tasks to be performed after the first task. The suggested tasks are based on frequencies with which previous users have used each task after the first task. The suggested tasks are then presented to the user. A second task is received from the user to be performed after the first task. The second task may be selected from the suggested tasks but not necessarily so. The second task is then added to the automation process file.

Claims (59)

1. A computer-implemented method of designing a logic flow for a user interface, the method comprising:

using a number of processors to perform the steps of:

receiving from a user a first task for an automation process file, wherein the automation process file defines a set of system activities;

adding the first task to the automation process file;

submitting the first task to a machine learning engine;

determining, with the machine learning engine, a number of suggested subsequent tasks to be performed after the first task, wherein the suggested subsequent tasks are based on frequencies with which previous users have used each suggested subsequent task after the first task;

providing the suggested subsequent tasks to the user;

receiving a second task from the user to be performed subsequent to the first task, wherein the second task may be selected from the suggested subsequent tasks; and

adding the second task to the automation process file.

2. The method of claim 1 , wherein the automation process file comprises:

a beginning task;

a number of user-defined tasks; and

a stop task.

3. The method of claim 1 , wherein all tasks added to the automation process file are selected from a menu of predefined tasks.

4. The method of claim 1 , wherein the tasks are defined as JSON objects.

5. The method of claim 1 , wherein providing the suggested subsequent tasks to the user comprises displaying the suggested subsequent tasks to the user through a drop-down menu.

6. The method of claim 1 , wherein the second task received from the user is not one of the suggested subsequent tasks.

7. The method of claim 1 , further comprising receiving a route from the user, wherein the route defines a process path from the first task.

8. The method of claim 7 , wherein the second task received from the user is connected to the first task by the route.

9. A system for designing a logic flow for a user interface, the system comprising:

a bus system;

a storage device connected to the bus system, wherein the storage device stores program instructions; and

a number of processors connected to the bus system, wherein the number of processors execute the program instructions to:

receive from a user a first task for an automation process file, wherein the automation process file defines a set of system activities;

add the first task to the automation process file;

submit the first task to a machine learning engine;

determine, with the machine learning engine, a number of suggested subsequent tasks to be performed after the first task, wherein the suggested subsequent tasks are based on frequencies with which previous users have used each suggested subsequent task after the first task;

provide the suggested subsequent tasks to the user;

receive a second task from the user to be performed subsequent to the first task, wherein the second task may be selected from the suggested subsequent tasks; and

add the second task to the automation process file.

10. The system of claim 9 , wherein the automation process file comprises:

a beginning task;

a number of user-defined tasks; and

a stop task.

11. The system of claim 9 , wherein all tasks added to the automation process file are selected from a menu of predefined tasks.

12. The system of claim 9 , wherein the tasks are defined as JSON objects.

13. The system of claim 9 , wherein providing the suggested subsequent tasks to the user comprises displaying the suggested subsequent tasks to the user through a drop-down menu.

14. The system of claim 9 , wherein the second task received from the user is not one of the suggested subsequent tasks.

15. The system of claim 9 , where in the process further execute instructions to receive a route from the user, wherein the route defines a process path from the first task.

16. The system of claim 15 , wherein the second task received from the user is connected to the first task by the route.

17. A computer program product for designing a logic flow for a user interface, the computer program product comprising:

a computer-readable storage medium having program instructions embodied thereon to perform the steps of:

receiving from a user a first task for an automation process file, wherein the automation process file defines a set of system activities;

adding the first task to the automation process file;

submitting the first task to a machine learning engine;

determining, with the machine learning engine, a number of suggested subsequent tasks to be performed after the first task, wherein the suggested subsequent tasks are based on frequencies with which previous users have used each suggested subsequent task after the first task;

providing the suggested subsequent tasks to the user;

receiving a second task from the user to be performed subsequent to the first task, wherein the second task may be selected from the suggested subsequent tasks; and

adding the second task to the automation process file.

18. The computer program product of claim 17 , wherein the automation process file comprises:

a beginning task;

a number of user-defined tasks; and

a stop task.

19. The computer program product of claim 17 , wherein all tasks added to the automation process file are selected from a menu of predefined tasks.

20. The computer program product of claim 17 , wherein the tasks are defined as JSON objects.

21. The computer program product of claim 17 , wherein providing the suggested subsequent tasks to the user comprises displaying the suggested subsequent tasks to the user through a drop-down menu.

22. The computer program product of claim 17 , wherein the second task received from the user is not one of the suggested subsequent tasks.

23. The computer program product of claim 17 , further comprising instructions for receiving a route from the user, wherein the route defines a process path from the first task.

24. The computer program product according to claim 23 , wherein the second task received from the user is connected to the first task by the route.

Assignments (2)
CHANGE OF NAME Recorded Feb 4, 2022
From: ADP, LLC
To: ADP, INC.
Reel/Frame 058959/0729 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Oct 13, 2020
From: CASAREGOLA, CLAIRE; DUSHAJ, DAVID; GREENE, MICHAEL; PIKE, YAIR; CHAN, ALEXANDER; MILLER, LAUREN
To: ADP, LLC
Reel/Frame 054040/0208 →
Cited By (4)
US 1,105,109 US 1,105,110 US 1,105,111 US 1,105,112