Systems and methods for providing automated natural language dialogue with customers

Patent metadata

Field	Value
Publication number	US-11735157-B2
Application number	US-202117245109-A
Country	US
Kind code	B2
Filing date	Apr 30, 2021
Priority date	Mar 9, 2017
Publication date	Aug 22, 2023
Grant date	Aug 22, 2023

Abstract

A system includes one or more memory devices storing instructions, and one or more processors configured to execute the instructions to perform steps of providing automated natural dialogue with a customer. The system may generate one or more events and commands temporarily stored in queues to be processed by one or more of a dialogue management device, an API server, and an NLP device. The dialogue management device may create adaptive responses to customer communications using a customer context, a rules-based platform, and a trained machine learning model.

First claim

We claim:

1. A system for automating natural language dialogue with a customer, comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
responsive to receiving an incoming customer dialogue message via an automated dialogue interaction channel, generate an event to be placed in an event queue, the event queue being monitored by a dialogue management device;
responsive to processing the event and based on data indicative of a customer context, the data derived from customer interaction history information, generate, by the dialogue management device, a command to a natural language processing device to determine a meaning of the incoming customer dialogue message based on the customer context;
responsive to an execution of the command by the natural language processing device, retrieving customer data; and
responsive to processing the customer data, generate, by the dialogue management device and based on the customer context, a response dialogue message based at least in part on retrieved customer data as processed by the dialog management device.

2. The system of claim 1 , wherein the response dialog message comprises unrequested information based on a predictive analysis of one or more determined needs of the customer.

3. The system of claim 1 wherein the event comprises an indication that the incoming customer dialogue message was received via one of the following types of channels: SMS, an instant messaging program, a website-based chat program, a mobile application, a voice-to-text device, or an email.

4. The system of claim 3 wherein the dialogue management device generates the response dialogue message based on a type of channel the incoming customer dialogue message was received on.

5. The system of claim 1 wherein the customer context is further derived from customer information associated with a particular customer stored in a database, the customer information comprising one or more of: account types, account statuses, transaction history, people models, an estimate of customer sentiment, customer goals, and customer social media information.

6. The system of claim 5 wherein the customer context is updated each time the dialogue management device receives an event.

7. A system for automating natural language dialogue with a customer, comprising:
one or more processors; and
memory in communication with the one or more processors and storing instructions that, when executed by the one or more processors, are configured to cause the system to:
responsive to receiving an incoming customer dialogue message via an automated dialogue interaction channel, generate an event to be placed in an event queue, the event queue being monitored by a dialogue management device, the dialogue management device comprising a trained machine learning model;
responsive to processing the event and based on data indicative of a customer context, the data derived from customer interaction history information, determining a meaning of the incoming customer dialogue message based on the customer context;
responsive to determining the meaning of the incoming customer dialogue message, generate, by the dialogue management device and based on one or more of trained machine learning model or the customer context, a response dialogue message based at least in part on retrieved customer data as processed by the dialog management device; and
transmit the response dialogue message via a communication channel that was used to deliver the incoming customer dialogue message.

8. The system of claim 7 , wherein the event queue comprises one or more events for processing by one or more of a natural language processing device, an API server, or a communication interface.

9. The system of claim 8 , wherein the event causes to the natural language processing device to determine the meaning of the incoming customer dialogue message.

10. The system of claim 7 , wherein the event initiates one or more of: retrieval of customer data, account action, customer authentication, or an opt-in/opt-out process.

11. The system of claim 7 wherein the customer context is further derived from customer information, the customer information comprising one or more of: account types, account statuses, transaction history, people models, an estimate of customer sentiment, customer goals, or customer social media information.

12. The system of claim 11 wherein the customer context is updated each time the dialogue management device receives an event.

13. The system of claim 12 wherein the customer context is updated by receiving updated customer information.

14. The system of claim 12 , further comprising outputting, from the dialogue management device, a record of a customer interaction related to the event.

15. The system of claim 8 , wherein the natural language processing device determines the meaning of an incoming customer dialogue message by utilizing one or more of the following artificial intelligence techniques: intent classification, named entity recognition, sentiment analysis, relation extraction, semantic role labeling, question analysis, rule extraction and discovery, or story understanding.

16. The system of claim 8 , wherein the natural language processing device generates natural language by utilizing one or more of the following artificial intelligence techniques: content determination, discourse structuring, referring expression generation, lexicalization, linguistic realization, or explanation generation.

17. A method for providing automated natural language dialogue with a customer, comprising:
receiving an event to be placed in an event queue, the event queue being monitored by a dialogue management device via an automated dialogue interaction channel, the dialogue management device comprising a trained machine learning model;
responsive to processing the event and based on data indicative of a customer context comprising data derived from customer interaction history information, generating, by the dialogue management device, one or more commands for execution by one or more of a natural language processing device, an API server, or a communication interface;
determining a meaning of an incoming customer dialogue message based on the customer context; and
generating, by the dialogue management device and based on one or more of the trained machine learning model or the customer context, a response dialogue message based at least in part on retrieved customer data.

18. The method of claim 17 , wherein the response dialog message comprises unrequested information based on a predictive analysis of one or more determined needs of the customer.

19. The method of claim 17 , wherein the one or more commands comprise a command to the natural language processing device to determine the meaning of the incoming customer dialogue message.

20. The method of claim 17 , wherein the customer context is further derived from customer information, the customer information comprising one or more of: account types, account statuses, transaction history, people models, an estimate of customer sentiment, customer goals, or customer social media information.

Assignees

• Capital One Services Llc

Inventors

• Zoller Gregory W
• Karp Scott
• Jacob Sujay Eliphaz
• Mueller Erik
• Hay Stephanie
• Paynter Adam Roy

Classifications

• G06Q10/40

  Business processes related to social networking or social networking services · CPC title

• G10L13/027 Primary

  Concept to speech synthesisers; Generation of natural phrases from machine-based concepts (generation of parameters for speech synthesis out of text G10L13/08) · CPC title

• G06F9/542

  Event management; Broadcasting; Multicasting; Notifications · CPC title

• G06F40/284

  Lexical analysis, e.g. tokenisation or collocates · CPC title

• G06F40/35

  Discourse or dialogue representation · CPC title