IP Library Granted Patent US 12670479
Granted Patent B2
US 12670479 · App. 18/662,455 · Granted Jun 30, 2026

Computer-based systems configured for automated electronic calendar management and work task scheduling and methods of use thereof

Inventor: Adam Vukich (Alexandria, VA)
Assignee: Capital One Services, LLC
G06Q10/1093G06N20/00G06Q10/1097
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 12670479
App. No.
18/662,455
Granted
Jun 30, 2026
Kind
B2
Abstract

In order to facilitate automated electronic calendar task management with automatic task scheduling, systems and methods are described including receiving and electronic meeting request to schedule a meeting. Work task data items identifying work tasks associated with the attendees are determined. A task estimation machine learning model predicts work parameters of meeting task objects based on the work task data items, and a work history data identifying work history of each attendee. A meeting scheduling machine learning model predicts parameters of unavailability period objects representing unavailability periods required to complete the work tasks based on the meeting task object, schedule information and location information. An indication of the at least one unavailability period is displayed on a screen of a computing device associated with each attendee. Selections of the unavailability period is received from the attendees, and the unavailability period is dynamically secured prior to the meeting.

Claims (79)

1 . A method comprising:

accessing, by at least one processor, a task completion period object associated with a task of a user;

wherein the task completion period object comprises:

i) at least one task parameter representing at least one work task that the user completed, and

ii) a task completion period representing a duration associated with completion of the at least one work task;

receiving, by the at least one processor, a user selection of a response to the task completion period;

calculating, by the at least one processor, based on the user selection, an error associated with the task completion period;

training, by the at least one processor, a task estimation machine learning model backpropagating the error to the task estimation machine learning model to update the task estimation machine learning model and produce a trained task estimation machine learning model trained to predict a plurality of work parameters of the task completion period object based at least in part on:

i) the at least one task parameter, and

ii) work history data identifying a work history of the user; and

wherein the at least one task parameter comprises a task duration parameter representing a predicted time that the user requires to complete the task; and

outputting, by the at least one processor, at least one instruction to at least one calendar software tool to cause the at least one calendar software tool to dynamically secure a corresponding unavailability period calendar object prior to a meeting by automatically book a meeting room at the specified time and location and updating, in real-time, at least one calendar database based at least in part on the task duration parameter.

2 . The method of claim 1 , further comprising:

receiving, by the at least one processor, an electronic meeting request to schedule at least one subsequent meeting;

wherein the electronic meeting request comprises an attendee data item identifying attendees comprising the attendee;

determining, by the at least one processor, at least one work task data item identifying at least one work task associated with the attendee; and

causing to display, by the at least one processor, an indication of at least one subsequent unavailability period calendar object in response to the electronic meeting request on a screen of at least one computing device associated with the attendee.

3 . The method of claim 2 , wherein the at least one work task data item is stored in at least one task database.

4 . The method of claim 1 , further comprising training, by the at least one processor, task estimation machine learning model using meeting history data comprising:

cancellation data identifying meeting cancellations, and

rescheduling data identifying meeting rescheduling occurrences.

5 . The method of claim 1 , wherein the work history data comprises:

i) prior work task data items identifying at least one completed work task, and

ii) prior task duration data items identifying a time that took the user to complete the at least one completed work task.

6 . The method of claim 1 , further comprising:

receiving, by the at least one processor, a user selection of a modification to an unavailability period calendar object associated with the unavailability period calendar object;

wherein the modification to the unavailability period calendar object comprises:

a modified unavailability period duration parameter representing a modification to the duration associated with the unavailability period calendar object;

training, by the at least one processor, the task estimation machine learning model to produce the trained task estimation machine learning model to predict the plurality of work parameters of at least one meeting task object based at least in part on a difference between the predicted unavailability period duration parameter and the modified unavailability period duration parameter.

7 . The method of claim 1 , further comprising:

determining, by the at least one processor, a plurality of emails associated with the user; and

parsing, by the at least one processor, text of the plurality of emails to identify the task parameter.

8 . The method of claim 1 , further comprising receiving, by the at least one processor, the at least one work task of the task parameter from a task scheduling application.

9 . The method of claim 1 , further comprising determining, by the at least one processor, one or more related documents in a cloud storage based at least in part on the at least one work task of the task parameter.

10 . The method of claim 1 , further comprising determining, by the at least one processor, an error associated with the task parameter based at least in part on the response;

wherein the user selection of the response comprises at least one of:

i) an acceptance, and

ii) a denial; and

wherein updating the trained task estimation machine learning model comprises updating the trained task estimation machine learning model based at least in part on the error.

11 . A system comprising:

at least one processor in communication with at least one non-transitory computer-readable medium having software instructions stored thereon, wherein the at least one processor is configured, upon execution of the software instructions, to:

access a task completion period object associated with a task of a user;

wherein the task completion period object comprises:

i) at least one task parameter representing at least one work task that the user completed, and

ii) a task completion period representing a duration associated with completion of the at least one work task;

receive a user selection of a response to the task completion period;

calculate based on the user selection, an error associated with the task completion period;

train a task estimation machine learning model backpropagating the error to the task estimation machine learning model to update the task estimation machine learning model and produce a trained task estimation machine learning model trained to predict a plurality of work parameters of the task completion period object based at least in part on:

i) the at least one task parameter, and

ii) work history data identifying a work history of the user; and

wherein the at least one task parameter comprises a task duration parameter representing a predicted time that the user requires to complete the task; and

output at least one instruction to at least one calendar software tool to cause the at least one calendar software tool to dynamically secure a corresponding unavailability period calendar object prior to a meeting by automatically book a meeting room at the specified time and location and updating, in real-time, at least one calendar database based at least in part on the task duration parameter.

12 . The system of claim 11 , wherein the at least one processor further configured to execute software instructions that cause the at least one processor to perform steps to:

receive an electronic meeting request to schedule at least one subsequent meeting;

wherein the electronic meeting request comprises an attendee data item identifying attendees comprising the attendee;

determine at least one work task data item identifying at least one work task associated with the attendee; and

causing to display, by the at least one processor, an indication of at least one subsequent unavailability period calendar object in response to the electronic meeting request on a screen of at least one computing device associated with the attendee.

13 . The system of claim 12 , wherein the at least one work task data item is stored in at least one task database.

14 . The system of claim 11 , wherein the at least one processor further configured to execute software instructions that cause the at least one processor to perform steps to train task estimation machine learning model using meeting history data comprising:

cancellation data identifying meeting cancellations, and

rescheduling data identifying meeting rescheduling occurrences.

15 . The system of claim 11 , wherein the work history data comprises:

i) prior work task data items identifying at least one completed work task, and

ii) prior task duration data items identifying a time that took the user to complete the at least one completed work task.

16 . The system of claim 11 , wherein the at least one processor further configured to execute software instructions that cause the at least one processor to perform steps to:

receive a user selection of a modification to an unavailability period calendar object associated with the unavailability period calendar object;

wherein the modification to the unavailability period calendar object comprises:

a modified unavailability period duration parameter representing a modification to the duration associated with the unavailability period calendar object;

train the task estimation machine learning model to produce the trained task estimation machine learning model to predict the plurality of work parameters of at least one meeting task object based at least in part on a difference between the predicted unavailability period duration parameter and the modified unavailability period duration parameter.

17 . The system of claim 11 , wherein the at least one processor further configured to execute software instructions that cause the at least one processor to perform steps to:

determine a plurality of emails associated with the user; and

parse text of the plurality of emails to identify the task parameter.

18 . The system of claim 11 , wherein the at least one processor further configured to execute software instructions that cause the at least one processor to perform steps to receive the at least one work task of the task parameter from a task scheduling application.

19 . The system of claim 11 , wherein the at least one processor further configured to execute software instructions that cause the at least one processor to perform steps to determine one or more related documents in a cloud storage based at least in part on the at least one work task of the task parameter.

20 . The system of claim 11 , wherein the at least one processor further configured to execute software instructions that cause the at least one processor to perform steps to determine an error associated with the task parameter based at least in part on the response;

wherein the user selection of the response comprises at least one of:

i) an acceptance, and

ii) a denial; and

wherein updating the trained task estimation machine learning model comprises updating the trained task estimation machine learning model based at least in part on the error.