Granted Patent B2

US 12,217,298 · App. 17/930,302 · Granted Feb 4, 2025

Inventors: Yoky Matsuoka (Los Altos Hills, CA); Nitin Viswanathan (San Francisco, CA)

Assignee: Yohana LLC

G06Q30/0631G06F9/4831G06F9/54G06Q10/1097H04L67/306H04L67/535

Abstract

Claims (63)

1. A computer-implemented method comprising:

receiving calendar data for a particular user of a task facilitation service through an external application programming interface (API), wherein the calendar data is associated with a calendar of a calendar application;

accessing a user model corresponding to the particular user, wherein the user model is updated based on historic activity of the particular user;

processing the calendar data and the user model using a natural-language processing (NLP) model to generate a task recommendation, wherein the task recommendation indicates one or more recommended tasks for delegation by the particular user, wherein the NLP model was initially trained with a training dataset using unsupervised training and without user supervision, and wherein the training dataset includes training data associated with other users;

transmitting an indication corresponding to the task recommendation, wherein, when the indication is received by a computing device, the computing device is enabled to approve the task recommendation;

receiving an approval to proceed with performing the one or more recommended tasks;

accessing task-execution data associated with the one or more recommended tasks, wherein the task-execution data identifies performance statuses associated with the one or more recommended tasks; and

updating the NLP model based on the task-execution data, wherein updating includes adjusting one or more weights of the NLP model using the unsupervised training and without user supervision, and wherein the one or more weights of the NLP model are adjusted until a corresponding logarithmic loss exceeds a predetermined threshold.

2. The computer-implemented method of claim 1 , wherein the computing device is a user computing device corresponding to the particular user.

3. The computer-implemented method of claim 1 , wherein the computing device is a representative computing device different than a user computing device corresponding to the particular user, and wherein the representative computing device corresponds to a representative assigned to the particular user to facilitate task completion for the particular user.

4. The computer-implemented method of claim 1 , wherein the calendar data includes details for a calendar item of the calendar.

5. The computer-implemented method of claim 1 , wherein the calendar data includes details for a calendar item of the calendar, and wherein receiving the approval further includes:

transmitting an update for application data of the calendar application to indicate that the one or more recommended tasks have been generated for the calendar item.

6. The computer-implemented method of claim 1 , wherein receiving the approval further includes:

transmitting an update for application data of the calendar application to (i) create a calendar item corresponding to the task recommendation, and (ii) indicate that the one or more recommended tasks have been generated for the calendar item.

7. The computer-implemented method of claim 1 , wherein receiving the approval further includes:

transmitting a first update for updating first application data to indicate that the one or more recommended tasks have been generated for a calendar item of the calendar; and

transmitting a second update for updating second application data to create a new calendar item in a second calendar.

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

transmitting a calendar item modification recommendation, wherein, when the calendar item modification recommendation is received by the computing device, the computing device is enabled to approve the calendar item modification recommendation to modify a calendar item of the calendar;

receiving approval of the calendar item modification recommendation; and

transmitting an update for application data of the calendar application to modify the calendar item according to the calendar item modification recommendation.

9. The computer-implemented method of claim 1 , wherein the task-execution data includes sensor data that identify the performance statuses, and wherein the NLP model is updated further based on the sensor data.

10. A system comprising:

one or more processors; and

a non-transitory computer-readable storage medium that stores instructions that, when executed by the one or more processors, cause the one or more processors to perform operations of:

receiving calendar data for a particular user of a task facilitation service through an external application programming interface (API), wherein the calendar data is associated with a calendar of a calendar application;

accessing a user model corresponding to the particular user, wherein the user model is updated based on historic activity of the particular user;

processing the calendar data and the user model using a natural-language processing (NLP) model to generate a task recommendation, wherein the task recommendation indicates one or more recommended tasks for delegation by the particular user, wherein the NLP model was initially trained with a training dataset using unsupervised training and without user supervision, and wherein the training dataset includes training data associated with other users;

transmitting an indication corresponding to the task recommendation, wherein, when the indication is received by a computing device, the computing device is enabled to approve the task recommendation;

receiving an approval to proceed with performing the one or more recommended tasks;

accessing task-execution data associated with the one or more recommended tasks, wherein the task-execution data identifies performance statuses associated with the one or more recommended tasks; and

updating the NLP model based on the task-execution data, wherein updating includes adjusting one or more weights of the NLP model using the unsupervised training and without user supervision, and wherein the one or more weights of the NLP model are adjusted until a corresponding logarithmic loss exceeds a predetermined threshold.

11. The system of claim 10 , wherein receiving the approval further includes:

transmitting an update for application data of the calendar application to (i) create a calendar item corresponding to the task recommendation if the calendar item does not yet exist, and (ii) indicate that the one or more recommended tasks have been generated for the calendar item.

12. The system of claim 10 , wherein the instructions further cause the one or more processors to perform the operations of:

transmitting a calendar item modification recommendation, wherein, when the calendar item modification recommendation is received by the computing device, the computing device is enabled to approve the calendar item modification recommendation to modify a calendar item of the calendar;

receiving approval of the calendar item modification recommendation; and

transmitting an update for application data of the calendar application to modify the calendar item according to the calendar item modification recommendation.

13. The system of claim 10 , wherein the computing device is a representative computing device different than a user computing device corresponding to the particular user, and wherein the representative computing device corresponds to a representative assigned to the particular user to facilitate task completion for the particular user.

14. The system of claim 10 , wherein the task-execution data includes sensor data that identify the performance statuses, and wherein the NLP model is updated further based on the sensor data.

15. The system of claim 10 , wherein receiving the approval further includes:

transmitting a first update for updating first application data to indicate that the one or more recommended tasks have been generated for a calendar item of the calendar; and

transmitting a second update for updating second application data to create a new calendar item in a second calendar.

16. A non-transitory computer-readable storage medium that stores instructions that, when executed by one or more processors, cause the one or more processors to perform operations of:

receiving calendar data for a particular user of a task facilitation service through an external application programming interface (API), wherein the calendar data is associated with a calendar of a calendar application;

accessing a user model corresponding to the particular user, wherein the user model is updated based on historic activity of the particular user;

processing the calendar data and the user model using a natural-language processing (NLP) model to generate a task recommendation, wherein the task recommendation indicates one or more recommended tasks for delegation by the particular user, wherein the NLP model was initially trained with a training dataset using unsupervised training and without user supervision, and wherein the training dataset includes training data associated with other users;

transmitting an indication corresponding to the task recommendation, wherein, when the indication is received by a computing device, the computing device is enabled to approve the task recommendation;

receiving an approval to proceed with performing the one or more recommended tasks;

accessing task-execution data associated with the one or more recommended tasks, wherein the task-execution data identifies performance statuses associated with the one or more recommended tasks; and

updating the NLP model based on the task-execution data, wherein updating includes adjusting one or more weights of the NLP model using the unsupervised training and without user supervision, and wherein the one or more weights of the NLP model are adjusted until a corresponding logarithmic loss exceeds a predetermined threshold.

17. The non-transitory computer-readable storage medium of claim 16 , wherein receiving the approval further includes:

transmitting an update for application data of the calendar application to (i) create a calendar item corresponding to the task recommendation if the calendar item does not yet exist, and (ii) indicate that the one or more recommended tasks have been generated at the task facilitation service for the calendar item.

18. The non-transitory computer-readable storage medium of claim 16 , wherein the instructions further cause the one or more processors to perform the operations of:

transmitting a calendar item modification recommendation, wherein, when the calendar item modification recommendation is received by the computing device, the computing device is enabled to approve the calendar item modification recommendation to modify a calendar item of the calendar;

receiving approval of the calendar item modification recommendation; and

transmitting an update for application data of the calendar application to modify the calendar item according to the calendar item modification recommendation.

19. The non-transitory computer-readable storage medium of claim 16 , wherein the computing device is a representative computing device different than a user computing device corresponding to the particular user, and wherein the representative computing device corresponds to a representative assigned to the particular user to facilitate task completion for the particular user.

20. The non-transitory computer-readable storage medium of claim 16 , wherein the task-execution data includes sensor data that identify the performance statuses, and wherein the NLP model is updated further based on the sensor data.

21. The non-transitory computer-readable storage medium of claim 16 , wherein receiving the approval further includes:

transmitting a first update for updating first application data to indicate that the one or more recommended tasks have been generated for a calendar item of the calendar; and

transmitting a second update for updating second application data to create a new calendar item in a second calendar.

Assignments (2)

Continuity (2)

References Cited (50)