Intent prediction for dialogue generation

Patent metadata

Field	Value
Publication number	US-12537780-B2
Application number	US-202418652785-A
Country	US
Kind code	B2
Filing date	May 1, 2024
Priority date	Dec 2, 2019
Publication date	Jan 27, 2026
Grant date	Jan 27, 2026

Abstract

In certain embodiments, intent prediction and dialogue generation may be facilitated. In some embodiments, a chat initiation request may be obtained from a user. The latest activity information associated with the user may be provided to a prediction model to obtain a first set of predicted intents of the user. For each intent of the first set of predicted intents, a candidate question may be selected from a question set based on the candidate question matching the intent. In some embodiments, the candidate questions may be simultaneously presented on the chat interface.

First claim

What is claimed is:

1 . A system comprising:
one or more processors and non-transitory media storing instructions that, when executed by the one or more processors, cause operations comprising:
starting a chat session initiated by a user;
in connection with starting the chat session initiated by the user, presenting, in a first dialogue of an interactive bot in the chat session, based on first predicted intents derived via a prediction model from user information associated with the user, a set of first dialogue items comprising a plurality of first user-selectable questions regarding one or more user accounts of the user; and
in response to receiving, from the user, a first user selection of a first dialogue item of the set of first dialogue items, and while the plurality of first user-selectable questions remains presented in a conversation feed of the chat session as part of the first dialogue of the interactive bot, presenting, in the conversation feed of the chat session, based on second predicted intents derived via the prediction model from (i) the first user selection and (ii) the user information, a set of second dialogue items comprising a plurality of second user-selectable questions in a first person point of view of the user.

2 . The system of claim 1 , wherein presenting the set of second dialogue items comprises, in response to receiving, from the user, the first user selection, and while the plurality of first user-selectable questions remains presented in the conversation feed of the chat session as part of the first dialogue of the interactive bot, presenting, in a second dialogue of the interactive bot in the conversation feed of the chat session, the plurality of second user-selectable questions in the user's first person point of view based on the second predicted intents.

3 . The system of claim 1 , wherein presenting the set of first dialogue items comprises presenting, in the first dialogue of the interactive bot in the conversation feed of the chat session, one or more user-selectable questions inquiring about one or more financial accounts of the user.

4 . The system of claim 1 , wherein presenting the set of first dialogue items comprises presenting, in the first dialogue of the interactive bot in the conversation feed of the chat session, one or more user-selectable questions in the user's first person point of view.

5 . A method comprising:
in connection with a chat session initiated by a user, presenting, as at least part of an interactive bot's dialogue in the chat session, based on one or more first predicted intents derived via a prediction model from user information associated with the user, a set of first dialogue items, comprising a plurality of first user-selectable options regarding one or more user accounts of the user; receiving, from the user, a first user selection of a first dialogue item of the set of first dialogue items; and while the plurality of first user-selectable options remains presented in a chat feed of the chat session, presenting, in the chat feed of the chat session, based on one or more second predicted intents derived via the prediction model from (i) the first user selection and (ii) the user information, a set of second dialogue items comprising a plurality of second user-selectable options in a first person point of view of the user.

6 . The method of claim 5 , wherein:
presenting the set of second dialogue items comprises, in response to receiving, from the user, the first user selection, and while the plurality of first user-selectable options remains presented in the chat feed of the chat session as part of a first dialogue of the interactive bot, presenting, in a second dialogue of the interactive bot in the chat feed of the chat session, the plurality of second user-selectable options in the user's first person point of view based on the one or more second predicted intents; the first dialogue is presented in the chat feed before a dialogue of the user is presented in the chat feed; and the second dialogue is presented in the chat feed after the dialogue of the user is presented in the chat feed.

7 . The method of claim 5 , wherein presenting the set of first dialogue items comprises presenting, in a first uninterrupted dialogue of the interactive bot in the chat feed of the chat session, the plurality of first user-selectable options based on the one or more first predicted intents.

8 . The method of claim 5 , wherein presenting the set of first dialogue items comprises presenting, as at least part of a welcome dialogue of the interactive bot in the chat feed of the chat session, the plurality of first user-selectable options based on the one or more first predicted intents.

9 . The method of claim 5 , wherein presenting the set of first dialogue items comprises presenting, as at least part of an uninterrupted introduction dialogue of the interactive bot in the chat feed of the chat session, the plurality of first user-selectable options based on the one or more first predicted intents.

10 . The method of claim 5 , wherein presenting the set of first dialogue items comprises presenting, in a first dialogue of the interactive bot in the chat feed of the chat session, a plurality of first user-selectable questions based on the one or more first predicted intents.

11 . The method of claim 5 , wherein presenting the set of first dialogue items comprises presenting, in a first dialogue of the interactive bot in the chat feed of the chat session, a plurality of first user-selectable statements based on the one or more first predicted intents.

12 . The method of claim 5 , wherein the prediction model comprises one or more neural networks.

13 . One or more non-transitory computer-readable media comprising instructions that, when executed by one or more processors, cause operations comprising:
in connection with a chat session initiated by a user, presenting, as at least part of an interactive bot's dialogue in the chat session, based on one or more first predicted intents derived via a prediction model from user information associated with the user, a set of first dialogue items, comprising a plurality of first user-selectable options related to one or more user accounts of the user; receiving, from the user, a first user selection of a first dialogue item of the set of first dialogue items; and in response to the first user selection of the first dialogue item, and while the plurality of first user-selectable options remains presented in a chat feed of the chat session, presenting, in the chat feed of the chat session, based on one or more second predicted intents derived via the prediction model from (i) the first user selection and (ii) the user information, a set of second dialogue items comprising a plurality of second user-selectable options in a first person point of view of the user.

14 . The one or more non-transitory computer-readable media of claim 13 , wherein:
presenting the set of second dialogue items comprises, in response to receiving, from the user, the first user selection, and while the plurality of first user-selectable options remains presented in the chat feed of the chat session as part of a first dialogue of the interactive bot, presenting, in a second dialogue of the interactive bot in the chat feed of the chat session, the plurality of second user-selectable options in the user's first person point of view based on the one or more second predicted intents; the first dialogue is presented in the chat feed before a dialogue of the user is presented in the chat feed; and the second dialogue is presented in the chat feed a

Assignees

• Capital One Services Llc

Inventors

• Miranda Victor Alvarez
• Zhang Rui
• Igure Vinay
• Karp Scott
• Mueller Erik
• Luke Tanushree
• Soiaporn Kunlaya

Classifications

• H04L51/04

  Real-time or near real-time messaging, e.g. instant messaging [IM] · CPC title

• G06N3/08

  Learning methods · CPC title

• G06F40/56

  Natural language generation · CPC title

• H04L51/02 Primary

  using automatic reactions or user delegation, e.g. automatic replies or chatbot-generated messages · CPC title

• G06N3/09

  Supervised learning · CPC title