Granted Patent B2

US 12,670,334 · App. 18/614,788 · Granted Jun 30, 2026

Inventors: Amanda Buchanan (Toronto, CA); Sophie Na-Hyun Park (Toronto, CA); John Jong-Suk Lee (Toronto, CA); Robert Alojz Skaljin (Hamilton, CA); Jillian Margaret Pigot Rivard (Ottawa, CA); Steven Anthony Ghose (Burlington, CA); Seonaid Marlaine Eggett (Toronto, CA); John Anthony Caligaris, III (Ballston Spa, NY); Kaycee Lee MacQueen (London, CA); Vinodhini Pandurangan (Chester Springs, PA); Hilary Wing-Mun Chan (Toronto, CA)

Assignee: The Toronto-Dominion Bank

G06F40/35H04L51/02

Abstract

Claims (35)

1 . An apparatus comprising:

a memory; and

a processor coupled to the memory, the processor configured to:

execute an interaction with an account via a chatbot within a chat element running on an account device,

determine a next response for the chatbot to output within the chat element based on an execution of an artificial intelligence (AI) model on content within the chat element,

determine an interaction attribute of the next response based on an execution of a second AI model on the content from the chat element and on historical chat content of the account device and the chatbot, and

output the next response via the chatbot within the chat element based on the determined interaction attribute,

wherein a slow down of a pace of the interaction is determined based on the interaction attribute, and in response, the content from the next response is removed prior to the next response being output within the chat element.

2 . The apparatus of claim 1 , wherein the interaction attribute comprises one or more of a humorous tone, a serious tone, an assertive tone, an optimistic tone, an informative tone, a formal tone, and an aggressive tone.

3 . The apparatus of claim 1 , wherein the processor is further configured to at least one of modify a word within the next response and add a new word to the next response based on the interaction attribute, prior to the next response being output within the chat element, wherein an AI agent performs an action based on the next response.

4 . The apparatus of claim 1 , wherein the processor is further configured to extract text content from previous chat interactions between the account and the chatbot and train the AI model based on the extracted text content from the previous chat interactions.

5 . The apparatus of claim 1 , wherein the processor is further configured to determine to speed up a pace of the interaction based on the interaction attribute, and in response, add additional content to the next response prior to the next response being output within the chat element.

6 . The apparatus of claim 1 , wherein the processor is configured to determine to add humorous text to the next response based on the interaction attribute, wherein the humorous text comprises one or more humorous words selected from a predefined list of humorous words.

7 . The apparatus of claim 1 , wherein the processor is configured to determine to use a previous interaction element of the account from a previous chat interaction between the account and the chatbot based on the execution of the second AI model.

8 . The apparatus of claim 1 , wherein the interaction attribute is a tone.

9 . A method comprising:

executing an interaction with an account via a chatbot within a chat element running on an account device;

determining a next response for the chatbot to output within the chat element based on an execution of an artificial intelligence (AI) model on content within the chat element;

determining an interaction attribute of the next response based on an execution of a second AI model on the content from the chat element and on historical chat content of the account device and the chatbot; and

outputting the next response via the chatbot within the chat element based on the determined interaction attribute,

wherein a slow down of a pace of the interaction is determined based on the interaction attribute, and in response, the content from the next response is removed prior to the next response being output within the chat element.

10 . The method of claim 9 , wherein the interaction attribute comprises one or more of a humorous tone, a serious tone, an assertive tone, an optimistic tone, an informative tone, a formal tone, and an aggressive tone.

11 . The method of claim 9 , wherein the method further comprises at least one of modifying a word within the next response and adding a new word to the next response based on the interaction attribute, prior to the next response being output within the chat element, wherein an AI agent performs an action based on the next response.

12 . The method of claim 9 , wherein the method further comprises extracting text content from previous chat interactions between the account and the chatbot and training the AI model based on the extracted text content from the previous chat interactions.

13 . The method of claim 9 , wherein the method further comprises determining to speed up a pace of the interaction based on the interaction attribute, and in response, adding additional content to the next response prior to the next response being output within the chat element.

14 . The method of claim 9 , wherein the outputting comprises adding humorous text to the next response based on the interaction attribute, wherein the humorous text comprises one or more humorous words selected from a predefined list of humorous words.

15 . The method of claim 9 , wherein the determining the interaction attribute comprises determining to use a previous interaction element of the account from a previous chat interaction between the account and the chatbot based on the execution of the second AI model.

16 . The method of claim 9 , wherein the interaction attribute is a tone.

17 . A non-transitory computer-readable storage medium comprising instructions stored therein which when executed by a processor cause the processor to perform:

executing an interaction conversation with an account via a chatbot within a chat element running on an account device;

determining a next response for the chatbot to output within the chat element based on an execution of an artificial intelligence (AI) model on content within the chat element;

determining an interaction attribute of the next response based on an execution of a second AI model on the content from the chat element and on historical chat content of the account device and the chatbot; and

outputting the next response via the chatbot within the chat element based on the determined interaction attribute,

wherein a slow down of a pace of the interaction is determined based on the interaction attribute, and in response, the content from the next response is removed prior to the next response being output within the chat element.

18 . The non-transitory computer-readable storage medium of claim 17 , wherein the interaction attribute comprises one or more of a humorous tone, a serious tone, an assertive tone, an optimistic tone, an informative tone, a formal tone, and an aggressive tone.

Assignments (1)

Continuity (1)

References Cited (400)