Method and system for facilitating convergence

Patent metadata

Field	Value
Publication number	US-12314876-B2
Application number	US-202217707710-A
Country	US
Kind code	B2
Filing date	Mar 29, 2022
Priority date	Dec 14, 2021
Publication date	May 27, 2025
Grant date	May 27, 2025

Abstract

A system and method for facilitating convergence includes receiving data relating to a first user's history of connections with other users, receiving contextual data about the first user, the contextual data including organizational graph data, providing the data and the contextual data as inputs to a trained machine-learning (ML) model for identifying a second user for the first user to connect with based on the data and the contextual data, receiving the identified second user as an output from the trained ML model, and providing the identified second user as a connection suggestion for display in a user interface element.

First claim

What is claimed is:

1. A data processing system comprising:
a processor; and
a memory in communication with the processor, the memory comprising executable instructions that, when executed by the processor, cause the data processing system to perform functions of:
receiving data relating to a first user's history of connections with other users;
receiving contextual data about the first user, the contextual data including organizational graph data;
providing the data and the contextual data as inputs to a trained machine-learning (ML) model for identifying a second user for the first user to connect with based on the data, the contextual data, and a geographic proximity of the first user to the second user, the second user being identified based on a determination that a connection between the first user and the second user is weakening or based on identification of bias in the first user's connections;
receiving the identified second user as an output from the trained ML model; and
providing the identified second user as a connection suggestion for display in a user interface element,
wherein a training dataset used to train the trained ML model is continually updated and the trained ML model is regenerated to reflect updates to the training dataset.

2. The data processing system of claim 1 , wherein identifying the second user is further based on achieving an objective.

3. The data processing system of claim 2 , wherein achieving an objective includes at least one of achieving a career objective, achieving a project objective, and achieving a company objective.

4. The data processing system of claim 1 , wherein the memory comprises executable instructions that, when executed by processor, further cause the data processing system to perform functions of:
determining a location of the first user and the second user; and
providing the identified second user as the connection suggestion when the location of the first user is within a given geographical proximity to the location of the second user at a given time.

5. The data processing system of claim 4 , wherein providing the identified second user as the connection suggestion includes providing at least one of the given time, the location of the first user, and the location of the second user for display.

6. The data processing system of claim 4 , wherein the location of the first user is determined by using at least one of user data, contextual data, and facility data.

7. The data processing system of claim 1 , wherein the memory comprises executable instructions that, when executed by the processor, further cause the data processing system to perform functions of:
receiving a request to schedule a meeting;
providing information about the meeting as an input to the trained ML model; and
receiving the identified second user as a suggested meeting attendee for the meeting from the trained ML model.

8. The data processing system of claim 1 , wherein the memory comprises executable instructions that, when executed by processor, further cause the data processing system to perform functions of displaying a selectable user interface element for making a connection with the second user.

9. A method for facilitating convergence, the method comprising,
with a processor and a memory comprising executable instructions for execution by the processor, performing each of:
receiving, at a connection identifier engine, data relating to a first user's history of connections with other users;
receiving, at a connection identifier engine, contextual data about the first user, the contextual data including organizational graph data;
providing the data and the contextual data as inputs to a trained machine-learning (ML) model for identifying a second user for the first user to connect with based on the data, the contextual data, and a geographic proximity of the first user to the second user, the second user being identified based on a determination that a connection between the first user and the second user is weakening or based on identification of bias in the first user's connections;
receiving the identified second user as an output from the trained ML model; and
providing the identified second user as a connection suggestion for display in a user interface element displayed by a client device,
wherein a training dataset used to train the trained ML model is continually updated and the trained ML model is regenerated using the updated training dataset to reflect updates to the training dataset;
the method further comprising:
determining a location of the first user and the second user; and
providing the identified second user as the connection suggestion when the location of the first user is within a given geographical proximity to the location of the second user at a given time.

10. The method of claim 9 , wherein identifying the second user is further based on achieving an objective.

11. The method of claim 9 , wherein providing the identified second user as the connection suggestion includes providing at least one of the given time, the location of the first user, and the location of the second user for display.

12. The method of claim 9 , wherein the location of the first user is determined by using at least one of user data, contextual data, and facility data.

13. The method of claim 9 , further comprising:
receiving a request to schedule a meeting;
providing information about the meeting as an input to the trained ML model; and
receiving the identified second user as a suggested meeting attendee for the meeting from the trained ML model.

14. The method of claim 9 , further comprising displaying a selectable user interface element for making a connection with the second user.

15. A non-transitory computer readable medium on which are stored instructions that, when executed, cause a programmable device to perform functions of:
receiving data relating to a first user's history of connections with other users;
receiving contextual data about the first user, the contextual data including organizational graph data;
providing the data and the contextual data as inputs to a trained machine-learning (ML) model for identifying a second user for the first user to connect with based on the data, the contextual data, and a geographic proximity of the first user to the second user, the second user being identified based on a determination that a connection between the first user and the second user is weakening or based on identification of bias in the first user's connections;
receiving the identified second user as an output from the trained ML model; and
providing the identified second user as a connection suggestion for display in a user interface element,
wherein a training dataset used to train the trained ML model is continually updated and the trained ML model is regenerated using the updated training dataset to reflect updates to the training dataset.

16. The non-transitory computer readable medium of claim 15 , wherein identifying the second user is further based on achieving an objective.

17. The non-transitory computer readable medium of claim 15 , wherein the instructions when executed, further cause a programmable device to perform functions of:
determining a location of the first user and the second user; and
providing the identified second user as the connection suggestion when the location of the first user is within a given geographical proximity to the location of the second user at a given time.

18. The non-transitory computer readable medium of claim 17 , wherein

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Kenyon Heidi
• Chong Choo Yei
• Slater Megan Elizabeth
• Dollar Christopher Michael
• Copfer Wende Ellen
• Kannepalli Venkata Sreekanth
• Erfani Shabnam
• Huang Amy Lieh-An
• Shah Neha Parikh
• Doran Edward Michael

Classifications

• G06Q10/1093

  Calendar-based scheduling for persons or groups · CPC title

• G06N20/00

  Machine learning · CPC title

• G06N5/04

  Inference or reasoning models · CPC title

• G06Q10/06

  Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling · CPC title

• G06Q10/00

  Administration; Management · CPC title