Granted Patent B2

US 12,561,532 · App. 18/345,879 · Granted Feb 24, 2026

Inventors: Alexander Ping Tsun (Cupertino, CA); Jennifer Kloke (Austin, TX); Zhengming Xing (Palo Alto, CA); Vraj Vyas (Rochelle Park, NJ); Anjian Wu (Newark, CA); Dixon Lo (San Francisco, CA); Jefferson Lai (Seattle, WA); Marta Garcia Ruiz De Leon (Chicago, IL); Praveen Kumar Bodigutla (San Jose, CA)

Assignee: Microsoft Technology Licensing, LLC

G06F40/35G06F16/3329G06F40/20H04L51/52

Abstract

Claims (62)

1 . A method comprising:

receiving an input from a client device to facilitate electronic messaging between a first user associated with first attribute data and a second user, wherein the client device provides a messaging interface that facilitates the electronic messaging;

determining a messaging intent option based on the first attribute data of the first user, wherein the messaging intent option corresponds to a purpose of the electronic messaging;

causing the messaging intent option to be presented on the messaging interface;

receiving, from the client device, a selection of the messaging intent option;

mapping a set of attributes of the first attribute data to one or more prompt inputs based on the selection of the messaging intent option;

creating a prompt using the one or more prompt inputs and a plan of action, wherein the plan of action comprises an instruction to a generative language model to use a content requirement to generate a suggestion;

applying the generative language model to the prompt;

outputting, by the generative language model, based on the one or more prompt inputs and the plan of action, one or more suggestions for adding messaging content in the messaging interface; and

causing the one or more suggestions to be presented on the messaging interface.

2 . The method of claim 1 , further comprising:

extracting second attribute data from a second profile associated with the second user, wherein determining the messaging intent option is further based on the second attribute data.

3 . The method of claim 2 , further comprising:

extracting at least one of the first attribute data or the second attribute data from user activity associated with at least one of the first user or the second user.

4 . The method of claim 2 , further comprising:

determining a type of connection between the first user and the second user based on the first attribute data and the second attribute data, wherein mapping the set of attributes is further based on the connection.

5 . The method of claim 4 , wherein determining the messaging intent option comprises:

determining the messaging intent option based on the connection.

6 . The method of claim 1 ,

wherein the plan of action defines content requirements for the one or more suggestions.

7 . The method of claim 1 , further comprising:

receiving historical activity data for the first user, wherein determining the messaging intent option is based on the historical activity data.

8 . The method of claim 1 , further comprising:

receiving, from the client device, feedback on the one or more suggestions based on an interaction with the messaging interface.

9 . The method of claim 8 , further comprising:

training a machine learning model using the one or more prompt inputs and the feedback; and

generating an updated set of prompt inputs using the trained machine learning model.

10 . A system comprising:

at least one memory device; and

at least one processing device, operatively coupled with the at least one memory device, to:

receive an input from a client device to facilitate electronic messaging between a first user associated with first attribute data and a second user, wherein the client device provides a messaging interface that facilitates the electronic messaging;

determine a messaging intent option based on the first attribute data of the first user, wherein the messaging intent option corresponds to a purpose of the electronic messaging;

cause the messaging intent option to be presented on the messaging interface;

receive, from the client device, a selection of the messaging intent option;

map a set of attributes of the first attribute data to one or more prompt inputs based on the selection of the messaging intent option;

create a prompt using the one or more prompt inputs and a plan of action, wherein the plan of action comprises an instruction to a generative language model to use a content requirement to generate a suggestion;

apply the generative language model to the prompt;

output, by the generative language model, based on the one or more prompt inputs and the plan of action, one or more suggestions for adding messaging content in the messaging interface; and

cause the one or more suggestions to be presented on the messaging interface.

11 . The system of claim 10 , wherein the at least one processing device further:

extracts second attribute data from a second profile associated with the second user, wherein determining the messaging intent option is further based on the second attribute data.

12 . The system of claim 11 , wherein the at least one processing device further:

extracts at least one of the first attribute data or the second attribute data from user activity associated with at least one of the first user or the second user.

13 . The system of claim 11 , wherein the at least one processing device further:

determines a type of connection between the first user and the second user based on the first attribute data and the second attribute data, wherein mapping the set of attributes is further based on the connection.

14 . The system of claim 13 , wherein determining the messaging intent option comprises:

determining the messaging intent option based on the connection.

15 . The system of claim 10 , wherein the at least one processing device further:

creates a prompt using a plan of action and the one or more prompt inputs, wherein the plan of action defines content requirements for the one or more suggestions; and

applies the generative language model to the prompt to generate the one or more suggestions.

16 . At least one non-transitory computer-readable storage medium comprising at least one instruction that, when executed by at least one processing device, causes the at least one processing device to:

receive an input from a client device to facilitate electronic messaging between a first user associated with first attribute data and a second user, wherein the client device provides a messaging interface that facilitates the electronic messaging;

determine messaging intent option based on the first attribute data of the first user, wherein the messaging intent option corresponds to a purpose of the electronic messaging;

cause the messaging intent option to be presented on the messaging interface;

receive, from the client device, a selection of the messaging intent option;

map a set of attributes of the first attribute data to one or more prompt inputs based on the selection of the messaging intent option;

create a prompt using the one or more prompt inputs and a plan of action, wherein the plan of action comprises an instruction to a generative language model to use a content requirement to generate a suggestion;

apply the generative language model to the prompt;

output, by the generative language model, based on the one or more prompt inputs and the plan of action, one or more suggestions for adding messaging content in the messaging interface; and

cause the one or more suggestions to be presented on the messaging interface.

17 . The at least one non-transitory computer-readable storage medium of claim 1 , wherein the at least one processing device further:

extracts second attribute data from a second profile associated with the second user, wherein determining the messaging intent option is further based on the second attribute data.

Assignments (1)

Continuity (3)

References Cited (30)