IP Library › Granted Patent US 12,748,930
Granted Patent B2
US 12,748,930 · App. 18/166,309 · Granted Sep 29, 2026

Programatically invokable conversational chatbot

Inventors: Constantin Mihai (Redmond, WA); Nagarajan Mani (Bothell, WA); Deepak Bansal (Bothell, WA); Madhusudhan Reddy Avancha (Redmond, WA)
Assignee: MICROSOFT TECHNOLOGY LICENSING, LLC
G06F40/40G06F3/0482H04L51/02
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,748,930
App. No.
18/166,309
Granted
Sep 29, 2026
Kind
B2
Abstract

The programmatical invocation of a chatbot is disclosed. An application may detect a trigger condition associated with user interaction with the application, and, in response, invoke a chatbot. During chatbot invocation, the application provides contextual information to the chatbot to select a conversational workflow and input data to populate the controls of the selected conversational workflow. The populated conversation workflow is then displayed to the user in a graphical user interface. The user may then provide user input to the conversational workflow. The chatbot advances the conversation based on the user input.

Claims (73)

1 . A method for programmatically invoking a chatbot, comprising:

receiving, by a chatbot application in response to the satisfaction of a trigger condition comprising a user interaction with a first application violating a rule, contextual information associated with the user interaction;

selecting, by the chatbot application based on the contextual information, a conversational workflow comprising a control;

populating the contextual information into the control of the conversational workflow;

causing display of the populated conversational workflow in a graphical user interface (GUI) window;

receiving, via the GUI window, user input at the populated conversational workflow; and

advancing the populated conversational workflow based on the user input.

2 . The method of claim 1 , wherein the chatbot application determines an intent based on the contextual information, and selects the conversational workflow from a plurality of conversational workflows based on the determined intent.

3 . The method of claim 2 , wherein the chatbot application determines the intent based on natural language processing of the contextual information.

4 . The method of claim 1 , wherein said receiving contextual information comprises:

receiving, by the chatbot application, an attribute value that maps to an input field of the conversational workflow; and

wherein said causing the display of the populated conversational workflow comprises:

causing the display of the input field of the conversational workflow prepopulated with the attribute value.

5 . The method of claim 1 , wherein the chatbot application:

transmits a request to a remote service based on the contextual information;

receives a response to the request; and

populates the control of the conversational workflow based on the response.

6 . The method of claim 1 , further comprising:

causing display to a user, in response to the satisfaction of the trigger condition, a deep link capable of invoking the chatbot application in response to interaction with the deep link, the deep link including the contextual information; and

wherein said receiving contextual information is performed in response to selection of the deep link by the user.

7 . The method of claim 1 , wherein the trigger condition comprises at least one of:

an error condition;

a business rule condition;

an invalid user input condition; or

an idle timer condition.

8 . A system for programmatically invoking a chatbot, comprising:

a processor;

a computer-readable storage medium comprising executable instructions that, when executed by the processor, cause the processor to:

receive, by a chatbot application in response to the satisfaction of a trigger condition comprising a user interaction with a first application violating a rule, contextual information associated with the user interaction;

select, by the chatbot application based on the contextual information, a conversational workflow comprising a control;

populate the contextual information into the control of the conversational workflow;

cause display of the populated conversational workflow in a graphical user interface (GUI) window;

receive, via the GUI window, user input at the populated conversational workflow; and

advance the conversational workflow based on the user input.

9 . The system of claim 8 , wherein the chatbot application determines an intent based on the transmitted contextual information, and selects the conversational workflow from a plurality of conversational workflows based on the determined intent.

10 . The method of claim 2 , wherein the chatbot application determines the intent based on natural language processing of the contextual information.

11 . The system of claim 8 , wherein, to receive the contextual information, the executable instructions, when executed by the processor, cause the processor to:

receive, by the chatbot application, an attribute value that maps to an input field of the conversational workflow; and

wherein, to cause display of the populated conversational workflow, the executable instructions, when executed by the processor, cause the processor to:

cause display of the input field of the conversational workflow prepopulated with the attribute value.

12 . The system of claim 8 , wherein the chatbot application:

transmits a request to a remote service based on the contextual information;

receives a response to the request; and

populates the control of the conversational workflow based on the response.

13 . The system of claim 8 , wherein the executable instructions, when executed by the processor, further cause the processor to:

cause display to a user, in response to the satisfaction of the trigger condition, a deep link capable of invoking the chatbot application in response to interaction with the deep link, the deep link including the contextual information; and

wherein said receive the contextual information is performed in response to selection of the deep link by the user.

14 . The system of claim 8 , wherein the trigger condition comprises one or more of:

an error condition;

a business rule condition;

an invalid user input condition; or

an idle timer condition.

15 . A computer-readable storage medium comprising executable instructions that, when executed by a processor, cause the processor to:

receive, by a chatbot application in response to the satisfaction of a trigger condition comprising a user interaction with a first application violating a rule, contextual information associated with the user interaction;

select, by the chatbot application based on the contextual information, a conversational workflow comprising a control;

populate the contextual information into the control of the conversational workflow;

cause display of the populated conversational workflow in a graphical user interface (GUI) window;

receive, via the GUI window, user input at the populated conversational workflow; and

advance the conversational workflow based on the user input.

16 . The computer-readable storage medium of claim 15 , wherein the chatbot application determines an intent based on the transmitted contextual information, and selects the conversational workflow from a plurality of conversational workflows based on the determined intent.

17 . The computer-readable storage medium of claim 15 , wherein the chatbot service determines the intent based on natural language processing of the contextual information.

18 . The computer-readable medium of claim 15 , wherein, to receive the contextual information, the executable instructions, when executed by the processor, cause the processor to:

receive, by the chatbot application, an attribute value that maps to an input field of the conversational workflow; and

wherein, to cause display of the populated conversational workflow, the executable instructions, when executed by the processor, cause the processor to:

cause display of the input field of the conversational workflow prepopulated with the attribute value.

19 . The computer-readable storage medium of claim 15 , wherein the executable instructions, when executed by the processor, further cause the processor to:

cause display to a user, in response to the satisfaction of the trigger condition, a deep link capable of invoking the chatbot application in response to interaction with the deep link, the deep link including the contextual information; and

wherein said receive the contextual information is performed in response to selection of the deep link by the user.

20 . The computer-readable storage medium of claim 15 , wherein the trigger condition comprises one or more of:

an error condition;

a business rule condition;

an invalid user input condition; or

an idle timer condition.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Feb 8, 2023
From: MIHAI, CONSTANTIN; MANI, NAGARAJAN; BANSAL, DEEPAK; AVANCHA, MADHUSUDHAN REDDY
To: MICROSOFT TECHNOLOGY LICENSING, LLC
Reel/Frame 062631/0740 →
Continuity (1)
Related Publication 20240265211A1 · Aug 8, 2024
References Cited (6)
US 11381530B2 · Jacobson · 2022 [cited by applicant]
US 20200097247A1 · Molina · 2020 [cited by applicant]
US 20210083996A1 · Moon · 2021 [cited by examiner]
EP 3531360A1 · 2019 [cited by applicant]
International Search Report and Written Opinion received for PCT Application No. PCT/US2024/013633 May 31, 2024, 11 pages. [cited by applicant]
International Preliminary Report on Patentability received for PCT Application No. PCT/US2024/013633 mailed on Aug. 21, 2025, 06 pages. [cited by applicant]