Systems and methods for initiating communication between users based on machine learning techniques

Patent metadata

Field	Value
Publication number	US-11140102-B1
Application number	US-201916370505-A
Country	US
Kind code	B1
Filing date	Mar 29, 2019
Priority date	Mar 29, 2019
Publication date	Oct 5, 2021
Grant date	Oct 5, 2021

Abstract

Systems and methods for initiating communication between users of a user group based on machine learning techniques. The disclosed systems and methods provide a novel framework for automating communication scheduling and communication initiation based on user communication objectives and machine learning techniques. The disclosed framework operates by leveraging available user provided communication parameters, user provided objectives, and various real-time data associated with the users, and using the aforementioned data as inputs for machine learning models, in order to schedule communication between the users, automatically initiate communication between the users, or transmit communication notifications to the users.

First claim

What is claimed is:

1. A computer-implemented method for initiating electronic communication sessions between users of a communication group, including group comprising:
receiving, at a server processor, a first set of input data from a first user device of a first user, the first set of input data including first communication parameters and first communication objectives of the first user;
receiving, at the server processor, a second set of input data from a second user device of a second user, the second set of input data including second communication parameters and second communication objectives of the second user, wherein the first user and the second user are opt-in members of a communication group;
receiving, at the server processor, first objective measurements of one or more electronic communication sessions between the first user and the second user, wherein the first objective measurements include time-between-communication information and tone-of-communication information, the tone-of-communication information including at least one of a tone signal indicating user vocal pitch and an image signal based on user facial recognition;
updating, by the server processor, a machine learning model based on the one or more electronic communication sessions between the first user and the second user, wherein updating the machine learning model includes (i) the first communication parameters and the first communication objectives of the first user, (ii) the second communication parameters and the second communication objectives of the second user, and (iii) the first objective measurements of the one or more electronic communication sessions between the first user and the second user;
receiving, at the server processor, real-time data from an external server, the real-time data corresponding to at least one of the first user and the second user;
determining, by the server processor, a communication availability score for the one or more electronic communication sessions between the first user and the second user, the communication availability score based on a comparison between the real-time data received from the external server and the updated machine learning model;
based on the communication availability score exceeding a predetermined threshold, transmitting, by the server processor, an electronic notification to one or both of the first user device of the first user and the second user device of the second user, the electronic notification including instructions for scheduling a second electronic communication session between the first user and the second user; and
monitoring post-communication actions of the first user and the second user in order to schedule one or more subsequent electronic communication sessions.

2. The computer-implemented method of claim 1 , wherein the first communication parameters and the second communication parameters further include one or more of:
user options for opting out of the communication group;
user options for modifying data-gathering constraints corresponding to inputs in an electronic communication application; and
user options for removing one or more users from the communication group.

3. The computer-implemented method of claim 1 , wherein the first communication objectives and the second communication objectives further include one or more of:
user options for selecting a preferred communication medium;
user options for providing user satisfaction with the one or more electronic communication sessions;
user options for setting a duration for the one or more electronic communication sessions; and
user options for requesting an electronic communication session with a first tone signal.

4. The computer-implemented method of claim 3 , wherein the electronic notification further includes availability information of one of the first user and the second user; and wherein one or more of the first communication objectives matches at least matches one or more of the second communication objectives.

5. The computer-implemented method of claim 1 , wherein updating the machine learning model is further based on an update to one or more of the first communication parameters, the first communication objectives, the second communication parameters, and the second communication objectives.

6. The computer-implemented method of claim 1 , wherein updating the machine learning model is further based on an update to one or more of the electronic notifications transmitted to one or more members of the communication group.

7. The computer-implemented method of claim 1 , wherein updating the machine learning model is further based on monitoring post-communication actions of the first user and the second user, wherein the post-communication actions include one or more of: user purchasing habits, user device location data, media consumption, user inputs on third party applications, and user device settings.

8. A system for initiating electronic communication between users of a communication group, comprising:
receiving, at a server processor, a first set of input data from a first user device of a first user, the first set of input data including first communication parameters and first communication objectives of the first user;
receiving, at the server processor, a second set of input data from a second user device of a second user, the second set of input data including second communication parameters and second communication objectives of the second user, wherein the first user and the second user are opt-in members of a communication group;
receiving, at the server processor, first objective measurements of one or more electronic communication sessions between the first user and the second user, wherein the first objective measurements include time-between-communication information and tone-of-communication information, the tone-of-communication information including at least one of a tone signal indicating user vocal pitch and an image signal based on user facial recognition;
updating, by the server processor, a machine learning model based on the one or more electronic communication sessions between the first user and the second user, wherein updating the machine learning model includes (i) the first communication parameters and the first communication objectives of the first user, (ii) the second communication parameters and the second communication objectives of the second user, and (iii) the first objective measurements of the one or more electronic communication sessions between the first user and the second user;
receiving, at the server processor, real-time data from an external server, the real-time data corresponding to at least one of the first user and the second user;
determining, by the server processor, a communication availability score for the one or more electronic communication sessions between the first user and the second user, the communication availability score based on a comparison between the real-time data received from the external server and the updated machine learning model;
based on the communication availability score exceeding a predetermined threshold, transmitting, by the server processor, an electronic notification to one or both of the first user device of the first user and the second user device of the second user, the electronic notification including instructions for scheduling a second electronic communication session between the first user and the second user; and
monitoring post-communication actions of the first user and the second user in order to schedule one or more subsequent electronic communication sessions.

9. The system of claim 8 , wherein the first communication parameters and the second communication parameters further include one or

Assignees

• Oath Inc
• Verizon Media Inc

Inventors

• Bax Eric
• Williams Kimberly
• Donald John
• Giaffo Lisa
• Sharma Tanisha
• Thompson Nikki
• Gerber Melissa

Classifications

• G06N3/047

  Probabilistic or stochastic networks · CPC title

• G06N5/01

  Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N7/01

  Probabilistic graphical models, e.g. probabilistic networks · CPC title

• G06N3/045

  Combinations of networks · CPC title