Computer-implemented systems configured for automated electronic calendar item predictions for calendar item rescheduling and methods of use thereof

Patent metadata

Field	Value
Publication number	US-11288636-B2
Application number	US-202016750825-A
Country	US
Kind code	B2
Filing date	Jan 23, 2020
Priority date	Jan 23, 2020
Publication date	Mar 29, 2022
Grant date	Mar 29, 2022

Abstract

In order to facilitate automatic electronic calendar rescheduling in response to out-of-office statuses, systems and methods are described including receiving, by processors, an out-of-office notification associated with meeting attendees. The processors identify a need-to-reschedule meeting data item of respective need-to-reschedule meetings. The processors utilize a meeting scheduling machine learning model to predict a plurality of parameters of a meeting room object representing respective candidate rescheduled meetings based at least in part on schedule information and location information associated with the at least one need-to-reschedule meeting data items. The processors cause to display an indication of the respective candidate rescheduled meetings in response to the out-of-office notification on a screen of a computing device associated with the respective attendees. The processors receive a selection of the at least one respective candidate rescheduled meeting from the at least one respective attendee and dynamically secure the respective candidate rescheduled meetings.

First claim

The invention claimed is:

1. A method comprising:
detecting, by at least one processor, data record notification associated with an automatic notification setting of a software application;
identifying, by the at least one processor, at least one additional data record having a time period attribute in common with a notification time period attribute of the data record notification;
wherein the at least one additional data record comprises at least one user identifier identifying at least one entity associated with the at least one additional data record;

utilizing, by the at least one processor, a time period machine learning model to predict a plurality of parameters of at least one resource associated with the at least one additional data record;
wherein the time period machine learning model is configured to predict the plurality of parameters based at least in part on software application data associated with the at least one user and location information associated with the at least one user;
wherein the plurality of parameters of the at least one resource comprises:
i) a location parameter, and
ii) a time parameter;

wherein the software application data comprises:
i) an availability data identifying at least one open time period associated with each entity of the at least one user obtained from each respective record set of at least one record set comprising the at least one additional data record associated with the at least one user,
ii) a data record history associated with the at least one user,
wherein the data record history comprises:
1) cancellation data identifying cancelled data records, and
2) modified data identifying modified data records;

wherein the location information comprises:
i) an user location data identifying at least one location associated with the at least one user,
ii) available resource data identifying all available resources, and
iii) a resource location associated with each available resource;

dynamically securing, by the at least one processor, the at least one resource within an electronic calendar object of an electronic calendar associated with the at least one user according to the plurality of parameters;
transmitting, by the at least one processor, instructions to display the electronic calendar object with the at least one resource on a screen of at least one computing device associated with the at least one user;
receiving, by the at least one processor, a selection of at least one modification to the at least one resource from the at least one user;
creating, by the at least one processor, a training pair comprising the plurality of parameters of the at least one resource and the at least one modification;
training, by the at least one processor, the time period machine learning model using the training pair to update the time period machine learning model; and
applying, by the at least one processor, the time period machine learning model to dynamically secure at least one subsequent resource within the electronic calendar object of the electronic calendar associated with the at least one user in response to a subsequent data record notification.

2. The method of claim 1 , wherein the location information further comprises meeting room needs associated with the at least one additional data record;
wherein the meeting room needs comprise:
i) meeting room resources, and
ii) a meeting room size.

3. The method of claim 2 , wherein the entity location data associated with the at least one user comprises a real-time location based on tracking an employee badge.

4. The method of claim 2 , wherein the user location data associated with the at least one user comprises a real-time location based on global positioning (GPS) data associated with an user mobile device.

5. The method of claim 1 , further comprising determining, by the at least one processor, traffic data identifying a traffic delay for a transit time associated a transit from each user location to each resource location.

6. The method of claim 1 , further comprising determining, by the at least one processor, a cancellation prediction using the time period machine learning model based at least in part on the cancellation data associate with each of the at least one respective user.

7. The method of claim 1 , wherein the time period machine learning model is further utilized to predict an user prioritization parameter to prioritize an availability associated with the at least one user according to each respective hierarchical position associated with the at least one user;
wherein the attendee prioritization parameter comprises:
i) a prioritization of the schedule information associated with the at least one user, and
ii) the location information associated with the at least one user;

wherein the hierarchical position of each of the at least one user is based on an organization chart.

8. The method of claim 1 , further comprising training, by the at least one processor, the time period machine learning model based on a meeting result.

9. The method of claim 8 , wherein the meeting result comprises meeting disposition data identifying a completed meeting according to the plurality of parameters.

10. The method of claim 8 , wherein the meeting disposition data comprises one of selection comprising a cancellation indication and a reschedule indication;
wherein the cancellation indication identifies:
i) a cancelling of the location parameter, and
ii) a cancelling of the time parameter;

wherein the reschedule indication identifies:
i) a rescheduling of the location parameter, and
ii) a rescheduling of the time parameter.

11. A system comprising:
a calendar database configured to store calendar data associated with each user of at least one user;
a meeting room database configured to store meeting room characteristics of possible meeting rooms; and
at least one processor in communication with the calendar database and the meeting room database;
wherein the at least one processor is configured to:
detect data record notification associated with an automatic notification setting of a software application;
identify at least one additional data record having a time period attribute in common with a notification time period attribute of the data record notification;
wherein the at least one additional data record comprises at least one user identifier identifying the at least one user associated with the at least one additional data record;

utilize a time period machine learning model to predict a plurality of parameters of at least one resource associated with the at least one additional data record;
wherein the time period machine learning model is configured to predict the plurality of parameters based at least in part on software application data associated with the at least one user and location information associated with the at least one user;
wherein the plurality of parameters of the at least one resource comprises:
 i) a location parameter, and
 ii) a time parameter;
wherein the software application data comprises:
 i) an availability data identifying at least one open time period associated with each user of the at least one user obtained from each respective record set of at least one record set comprising the at least one additional data record associated with the at least one user,
 ii) a data record history associated with the at least one entity user,
 wherein the data record history comprises:
 1) cancellation data identifying cancelled data records, and
 2) modified data identifying modified data records;
wherein the location information comprises:
 i) an user location data identifying at least one l

Assignees

• Capital One Services Llc

Inventors

• ZARAKAS James
• Bergeron George
• Vukich Adam

Classifications

• G06N3/045

  Combinations of networks · CPC title

• G06N3/09

  Supervised learning · CPC title

• G06N3/0464

  Convolutional networks [CNN, ConvNet] · CPC title

• G06Q10/1093 Primary

  Calendar-based scheduling for persons or groups · CPC title

• G06N3/084

  Backpropagation, e.g. using gradient descent · CPC title