Granted Patent B2

US 11,863,706 · App. 18/149,655 · Granted Jan 2, 2024

Inventors: Matthew DiMaria (Brentwood, TN); Daniel Bohannon (Livermore, CA)

Assignee: Virtual Hold Technology Solutions, LLC

H04M3/5231H04L67/306H04M3/5183

Abstract

Claims (55)

1. A system for a cloud callback platform, comprising:

a computing device comprising a memory and a processor;

a callback manager comprising a first plurality of programming instructions stored in the memory and operating on the processor, wherein the first plurality of programming instructions, cause the computing device to:

initiate a session when first contact is made with a callback requestor;

receive a request for a callback to a callback recipient from the callback requester;

instantiate a callback object;

send session attributes to a context analysis engine;

obtain a context summary report;

link the context summary report and the callback object;

provide the context summary report to the callback recipient at a scheduled callback time; and

execute callback requests; and

an operations analyzer comprising a second plurality of programming instructions stored in the memory and operating on the processor, wherein the second plurality of programming instructions, cause the computing device to:

train a statistical model to determine a success score of a communication channel of a plurality of communication channels;

determine an appropriate communications channel to execute the callback between the callback requestor and the callback recipient;

monitor for points of failure in the cloud callback platform;

use the trained statistical model to determine the success score for each remaining communication channel of the plurality communication channels;

compare the plurality of success scores to determine an alternative communication channel; and

bridge the callback requestor and callback recipient using the alternate communication channel when a callback attempt fails as a result of a monitored failure in the cloud callback platform.

2. The system of claim 1 , further comprising the context analysis engine comprising a third plurality of programming instructions stored in the memory and operating on the processor, wherein the third plurality of programming instructions, cause the computing device to:

receive the session attributes;

generate, in response to the session attributes, context content pertaining to at least one of the callback requestor, the callback recipient, and the session attributes; and

forward the context content to a data message aggregator.

3. The system of claim 2 , further comprising a context aggregator mechanism comprising a fourth plurality of programming instructions stored in the memory and operating on the processor, wherein the fourth plurality of programming instructions, cause the computing device to:

generate a context summary report by parsing, aggregating, and formatting the context content; and

send the context summary report to the callback manager.

4. The system of claim 1 , wherein the statistical model is a logistic regression model.

5. The system of claim 1 , wherein the statistical model is a neural network.

6. The system of claim 1 , wherein the statistical model is trained using a training dataset comprising at least requestor or recipient preferences, defines rules, date and time data, device data, acceptance rate, and network data.

7. The system of claim 6 , wherein the device data further comprises at least one of location data, battery strength data, and network signal data.

8. A method for managing callbacks using a cloud callback platform, comprising the steps of:

initiating a session when first contact is made with a callback requestor;

receiving a request for a callback to a callback recipient from a callback requester;

instantiating a callback object;

sending session attributes to a context analysis engine;

obtaining a context summary report;

linking the context summary report and the callback object;

providing the context summary report to the callback recipient at a scheduled callback time;

executing callback requests;

training a statistical model to determine a success score of a communication channel of a plurality of communication channels;

determining an appropriate communications channel to execute the callback between the callback requestor and the callback recipient;

monitoring for points of failure in the cloud callback platform;

using the trained statistical model to determine the success score for each remaining communication channel of the plurality communication channels;

comparing the plurality of success scores to determine an alternative communication channel; and

bridging the callback requestor and callback recipient using the alternate communication channel when a callback attempt fails as a result of a monitored failure in the cloud callback platform.

9. The method of claim 8 , further comprising the steps of:

receiving the session attributes;

generating, in response to the session attributes, context content pertaining to at least one of the callback requestor, the callback recipient, and the session attributes; and

forwarding the context content to a data message aggregator.

10. The method of claim 9 , further comprising the steps of:

generating a context summary report by parsing, aggregating, and formatting the context content; and

sending the context summary report to the callback manager.

11. The method of claim 8 , wherein the statistical model is a logistic regression model.

12. The method of claim 8 , wherein the statistical model is a neural network.

13. The method of claim 8 , wherein the statistical model is trained using a training dataset comprising at least requestor or recipient preferences, defines rules, date and time data, device data, acceptance rate, and network data.

14. The method of claim 13 , wherein the device data further comprises at least one of location data, battery strength data, and network signal data.

Assignments (2)

Continuity (21)