Assisting entities in responding to a request of a user

Patent metadata

Field	Value
Publication number	US-10387888-B2
Application number	US-201615254101-A
Country	US
Kind code	B2
Filing date	Sep 1, 2016
Priority date	Jul 8, 2016
Publication date	Aug 20, 2019
Grant date	Aug 20, 2019

Abstract

A third-party service may be used to assist entities in responding to requests of users. A third-party service may receive, directly or indirectly, a request of a first user for assistance from a first entity. The third-party service may request information about the first user by sending a request to a computer of the first entity. The third-party service may use the request of the first user and the information about the first user to automatically generate a response to the request of the first user. The third-party service may then transmit, directly or indirectly, the response to the first user.

First claim

What is claimed is:

1. A computer-implemented method for assisting corporate entities in responding to customer support requests and implemented by a third-party service provider, the method comprising:
receiving, at the third-party service provider, a first customer support request from a first customer, wherein the first customer support request seeks assistance from a first corporate entity;
obtaining a first text corresponding to the first customer support request;
transmitting a first request for first information from a server of the third-party service provider to a first server of the first corporate entity;
receiving the first information from the first corporate entity;
automatically generating a first response to the first customer support request using semantic processing of the first text and using the first information, wherein automatically generating the first response comprises selecting a first node from a first action graph;
transmitting the first response to the first customer;
receiving, at the third-party service provider, a second customer support request from a second customer, wherein the second customer support request seeks assistance from a second corporate entity and wherein the second corporate entity is different from the first corporate entity;
obtaining second text corresponding to the second customer support request;
transmitting a second request for second information from a server of the third-party service provider to a second server of the second corporate entity;
receiving the second information from the second corporate entity;
automatically generating a second response to the second customer support request using semantic processing of the second text and using the second information, wherein automatically generating the second response comprises selecting a second node from a second action graph; and
transmitting the second response to the second customer.

2. The computer-implemented method of claim 1 , wherein the first request comprises information identifying the first customer.

3. The computer-implemented method of claim 1 , wherein the first information comprises information about the first customer.

4. The computer-implemented method of claim 1 , wherein the first customer is a customer of the first corporate entity and the second customer is a customer of the second corporate entity.

5. The computer-implemented method of claim 1 , wherein automatically generating the first response comprises processing the first text with a neural network.

6. The computer-implemented method of claim 1 , wherein the first request is received from a first device of the first customer and the first response is transmitted to the first device of the first customer.

7. A system for assisting corporate entities in responding to customers, the system comprising:
at least one server computer comprising at least one processor and at least one memory, the at least one server computer configured to:
receive a first text from a first customer seeking assistance from a first corporate entity;
transmit a first request for first information to a first server of the first corporate entity;
receive the first information from the first corporate entity;
automatically generate a first response to the first text using semantic processing of the first text, using the first information, and by selecting a first node from a first action graph;
transmit the first response to the first customer;
receive second text from a second customer seeking assistance from a second corporate entity and wherein the second corporate entity is different from the first corporate entity;
transmit a second request for second information to a second server of the second corporate entity;
receive the second information from the second corporate entity;
automatically generate a second response to the second text using semantic processing of the second text, using the second information, and by selecting a second node from a second action graph; and
transmit the second response to the second customer.

8. The system of claim 7 , wherein the first information comprises information about the first customer.

9. The system of claim 7 , wherein the at least one server computer is configured to automatically generate the first response by processing the first text with a neural network.

10. The system of claim 7 , wherein the at least one server computer is configured to automatically generate the first response using a first classifier.

11. The system of claim 10 , wherein the first classifier comprises a logistic regression classifier.

12. The system of claim 7 , wherein the first request is received from the first corporate entity and the first response is transmitted to the first corporate entity.

13. One or more non-transitory computer-readable media comprising computer executable instructions that, when executed, cause at least one processor to perform actions comprising:
receiving a first text from a first user seeking assistance from a first corporate entity;
transmitting a first request for first information to a first server of the first corporate entity;
receiving the first information from the first corporate entity;
automatically generating a first response to the first text using semantic processing of the first text and using the first information, wherein automatically generating the first response comprises selecting a first node from a first action graph;
transmitting the first response to the first user;
receiving second text from a second user seeking assistance from a second corporate entity and wherein the second corporate entity is different from the first corporate entity;
transmitting a second request for second information to a second server of the second corporate entity;
receiving the second information from the second corporate entity;
automatically generating a second response to the second text using the second text and the second information, wherein automatically generating the second response comprises selecting a second node from a second action graph; and
transmitting the second response to the second user.

14. The one or more non-transitory computer-readable media of claim 13 , wherein the first information comprises information about the first user.

15. The one or more non-transitory computer-readable media of claim 13 , wherein automatically generating the first response comprises processing the first text with a neural network.

16. The one or more non-transitory computer-readable media of claim 13 , wherein automatically generating the first response comprises using a first classifier.

17. The one or more non-transitory computer-readable media of claim 16 , wherein the first classifier comprises a logistic regression classifier.

18. The computer-implemented method of claim 1 , wherein automatically generating the first response using semantic processing comprises:
determining a text response by processing the first text with a classifier to understand a meaning of the first text; or
generating a completion to the first text by processing the first text with a neural network.

Assignees

• Asapp Inc

Inventors

• Sapoznik Gustavo
• Dai Hui
• Hackman Joseph

Classifications

• G06N3/08

  Learning methods · CPC title

• G06N3/04

  Architecture, e.g. interconnection topology · CPC title

• G06N3/044

  Recurrent networks, e.g. Hopfield networks · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/047

  Probabilistic or stochastic networks · CPC title