Granted Patent B2

US 12,711,499 · App. 18/759,399 · Granted Aug 18, 2026

Inventors: Soujanya Lanka (Singapore, SG); Guangsen Wang (Singapore, SG); Reyha Verma (Bangalore Urban, IN)

Assignee: PayPal, Inc.

G06Q20/386G06F40/30G06Q10/06393G06Q10/06395H04L51/02

Abstract

Claims (69)

1 . A system comprising:

a non-transitory memory; and

one or more hardware processors coupled with the non-transitory memory and configured to execute instructions from the non-transitory memory to cause the system to:

receive an utterance from a device via a chat interface during a chat session;

predict, for an artificial intelligence (AI) model, an intent of a user of the device based on the utterance, wherein the AI model is communicatively coupled with a plurality of backend modules, and wherein each backend module in the plurality of backend modules is configured to perform transactions corresponding to a different transaction type;

select, from the plurality of backend modules, a particular backend module for performing a transaction for the user during the chat session based on the intent;

access, from a data storage that stores a plurality of prompt templates corresponding to the plurality of backend modules, a particular prompt template corresponding to the particular backend module;

provide the particular prompt template to the AI model, wherein the particular prompt template enables the AI model to (i) conduct a set of dialogs with the user that prompts the user for data usable by the particular backend module to perform the transaction and (ii) generate instructions for instructing the particular backend module to perform the transaction;

instruct, by the AI model and using the instructions, the particular backend module to perform the transaction for the user based on the utterance and the intent;

generate, by the AI model, content for the chat session based on a result from the particular backend module performing the transaction; and

transmit the content to the device via the chat interface.

2 . The system of claim 1 , wherein executing the instructions further causes the system to:

generate, by the AI model, a first question that prompts the user for the data.

3 . The system of claim 2 , wherein executing the instructions further causes the system to:

determine that a first answer obtained from the device via the chat interface does not correspond to a set of data requirements indicated in the particular prompt template; and

generate, by the AI model, a second question that prompts the user for the data.

4 . The system of claim 3 , wherein the second question has a different syntax than the first question.

5 . The system of claim 1 , wherein executing the instructions further causes the system to:

obtain, by the AI model and from the particular backend module, an output based on the performing the transaction, wherein the content is generated further based on the output.

6 . The system of claim 5 , wherein the output indicates whether the transaction has been completed, has been denied, or requires additional data to complete.

7 . The system for claim 1 , wherein executing the instructions further causes the system to:

format the utterance based on a set of policies; and

provide the formatted utterance to the AI model, wherein the intent is further predicted based on the formatted first utterance.

8 . A method, comprising:

receiving, via a chat interface during a chat session between a device and a computer system, a request for performing a transaction corresponding to a first transaction type;

selecting, from a plurality of modules, a first module for a user of the device based on the first transaction type;

selecting, from a plurality of templates, a first template corresponding to the first module;

providing the first template to an artificial intelligence (AI) model, wherein the first template enables the AI model to generate one or more questions that prompt the user for data usable by the first module to perform the transaction;

transmitting the one or more questions to the device via the chat interface;

generating, by the AI model, instructions for the first module to perform the transaction based on information extracted from the request and the data obtained from the user;

providing, by the AI model, the instructions to the first module;

generating, by the AI model, content for the chat session based on an output produced by the first module; and

providing, by the AI model, the content to the device via the chat interface as a response to the request.

9 . The method of claim 8 , wherein the output comprises second data associated with the computer system obtained from a plurality of data sources, and wherein the content comprises a summary of the second data.

10 . The method of claim 8 ,

wherein the first template indicates a communication protocol for communicating with the first module, and wherein the instructions are generated further based on the first template.

11 . The method of claim 8 , wherein the instructions comprise an application programming interface (API) call, and wherein the method further comprises:

inserting one or more input parameters to the API call based on the extracted information.

12 . The method of claim 8 , wherein the content is first content, and wherein the method further comprises:

subsequent to providing the first content on the device, receiving a second request from the device via the chat interface during the chat session, wherein the second request is for performing a second transaction corresponding to a second transaction type;

selecting, from the plurality of modules, a second module for the user based on the second transaction type;

providing, by the AI model, second instructions to the second module;

generating, by the AI model, second content for the chat session based on a second output produced by the second module; and

providing the second content to the user via the chat interface.

13 . The method of claim 8 , wherein the request comprises an utterance, and wherein the method further comprises:

processing the utterance based on a set of policies; and

providing the processed utterance to the AI model, wherein the instructions are generated further based on the processed utterance.

14 . The method of claim 13 , wherein the processing the utterance comprises:

identifying one or more words associated with a particular word type in the utterance; and

removing the one or more words from the utterance.

15 . A non-transitory machine-readable medium having stored thereon machine-readable instructions executable to cause a machine to perform operations comprising:

in response to receiving a first utterance from a device via a chat interface during a chat session, determining that the first utterance corresponds to a request for performing a transaction of a particular transaction type;

selecting, from a plurality of computer modules, a particular computer module for performing the transaction based on the particular transaction type;

providing a particular prompt template corresponding to the particular computer module to an artificial intelligence (AI) model, wherein the particular prompt template enables the AI model to generate a set of questions that prompts the user for data usable by the particular computer module to perform the transaction;

transmitting the set of questions to the device via the chat interface;

generating, by the AI model, instructions that cause the particular computer module to perform the transaction for a user of the device based on the data obtained from the user;

generating, by the AI model, content for the chat session based on a result from the particular computer module performing the transaction; and

transmitting the content to the device via the chat interface.

16 . The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise:

obtaining additional information via the chat interface, wherein the particular computer module is configured to perform the transaction for the user further based on the additional information.

17 . The non-transitory machine-readable medium of claim 16 , wherein the operations further comprise:

generating, by the AI model, the set of questions for the user based on data types or content required by the particular computer module for performing the transaction; and

obtaining the data from the user via the chat interface.

18 . The non-transitory machine-readable medium of claim 17 , wherein the operations further comprise:

determining the data types or content required by the particular computer module for performing the transaction based on the particular prompt template.

19 . The non-transitory machine-readable medium of claim 15 , wherein the operations further comprise:

detecting that a first language used in the first utterance is incompatible with the AI model; and

translating the first utterance from the first language to a second language that is compatible with the AI model.

20 . The non-transitory machine-readable medium of claim 15 , wherein the result indicates whether the transaction has been completed, has been denied, or requires additional data to complete.

Assignments (1)

Priority Claims (2)

Continuity (1)

References Cited (70)