Granted Patent B2

US 12,375,432 · App. 18/642,403 · Granted Jul 29, 2025

Inventors: David M. Barrett (San Francisco, CA); Melissa Aaron (San Francisco, CA)

Assignee: Expensify, Inc.

H04L51/02H04L51/046

Abstract

Claims (52)

1. A computing system implementing a chat service, the computing system comprising:

a network communication interface to communicate, over one or more networks, with computing devices of users of the chat service;

one or more processors; and

a memory storing a plug-in library and instructions that, when executed by the one or more processors, cause the computing system to:

receive, over the one or more networks, a chat query from a computing device of a user;

process the chat query using a set of rules to determine an intent associated with the chat query;

trigger a plug-in from the plug-in library based at least in part on a set of parameters associated with the intent;

utilize the plug-in to access one or more resources and determine a chat response for the chat query; and

transmit, over the one or more networks, the chat response to the computing device of the user.

2. The computing system of claim 1 , wherein:

the set of parameters includes (i) an action to perform and (ii) information used to perform the action,

the computing system automatically performs the action based on the information, and

the chat response indicates an outcome of the action.

3. The computing system of claim 1 , wherein the chat query comprises at least one of a text input from the user or a voice input from the user.

4. The computing system of claim 1 , wherein the computing system processes the chat query by performing at least one of:

matching one or more key words or phrases from the chat query to the intent; or

determining a context associated with the chat query based on one or more prior chats with the user or one or more external database resources.

5. The computing system of claim 1 , wherein the set of parameters includes a word pattern that is extracted from the chat query and matched the plug-in.

6. The computing system of claim 5 , wherein the set of parameters further comprises at least one of a state of a chat with the user or the chat response.

7. The computing system of claim 1 , wherein the one or more resources comprise one or more third-party resources requiring user-specific information of the user to enable access.

8. The computing system of claim 7 , wherein the memory further stores a knowledge graph that includes the user-specific information of the user, and wherein the executed instructions cause the computing system to perform a lookup in the knowledge graph for the user-specific information and utilize the user-specific information to access the one or more third-party resources.

9. The computing system of claim 8 , wherein the user-specific information comprises at least one of personal information of the user or one or more passwords of the user.

10. The computing system of claim 1 , wherein the chat response comprises a request for additional contextual information from the user, and the executed instructions further cause the computing system to:

receive, over the one or more networks, a response to the request for the additional contextual information from the computing device of the user; and

parse the response to determine the plug-in.

11. A non-transitory computer readable medium storing instructions for implementing a chat service, wherein the instructions, when executed by one or more processors of a computing system, cause the computing system to:

receive, over one or more networks, a chat query from a computing device of a user;

process the chat query using a set of rules to determine an intent associated with the chat query;

trigger a plug-in from a plug-in library based at least in part on a set of parameters associated with the intent;

utilize the plug-in to access one or more resources and determine a chat response for the chat query; and

transmit, over the one or more networks, the chat response to the computing device of the user.

12. The non-transitory computer readable medium of claim 11 , wherein:

the set of parameters includes an action to perform based on the chat query and information used to perform the action,

the computing system automatically performs the action, and

the chat response indicates that the action has been performed.

13. The non-transitory computer readable medium of claim 12 , wherein the chat response includes a request for additional contextual information from the user, and the executed instructions further cause the computing system to:

receive, over the one or more networks, a response to the request from the computing device of the user; and

perform an additional action based on one or more additional parameters associated with the response.

14. The non-transitory computer readable medium of claim 11 , wherein the executed instructions cause the computing system to identify one or more typos in the chat query and automatically correct the one or more typos prior to processing the chat query.

15. The non-transitory computer readable medium of claim 11 , wherein the chat query comprises a voice input by the user.

16. The non-transitory computer readable medium of claim 15 , wherein the executed instructions cause the computing system to:

determine a context of the chat query based at least in part on one or more sounds associated with the voice input; and

determine the chat response based at least in part on the context.

17. The non-transitory computer readable medium of claim 16 , wherein the context comprises at least one of an environment around the user, a location of the user, a language of the voice input, additional voices of people nearby the user, a likely activity, a mode of transportation, or a weather condition.

18. The non-transitory computer readable medium of claim 11 , wherein the one or more resources comprise at least one of a human operator or a chat library of prior chat sessions and events generated from the prior chat sessions.

19. The non-transitory computer readable medium of claim 11 , wherein the chat query is provided in a first language that is not native to the chat service, and wherein the executed instructions cause the computing system to translate the chat query into a second language that is native to the chat service.

20. A computer-implemented method of managing a chat service, the method being performed by one or more processors and comprising:

receiving, over one or more networks, a chat query from a computing device of a user;

processing the chat query using a set of rules to determine an intent associated with the chat query;

triggering a plug-in from a plug-in library based at least in part on a set of parameters associated with the intent;

utilizing the plug-in to access one or more resources and determine a chat response for the chat query; and

transmitting, over the one or more networks, the chat response to the computing device of the user.

Assignments (1)

Continuity (4)

References Cited (60)