IP Library Granted Patent US 10,733,614
Granted Patent B2
US 10,733,614 · App. 16/448,532 · Granted Aug 4, 2020

Assisting entities in responding to a request of a user

Inventors: Gustavo Sapoznik (Miami, FL); Hui Dai (New York, NY); Joseph Hackman (New York, NY)
Assignee: ASAPP, INC.
G06Q30/016G06F16/2237G06F16/245G06F16/3329G06F16/3344G06F16/9024G06F16/90332G06F16/9535G06F40/205G06F40/216G06F40/35G06N3/04G06N3/0445G06N3/0454G06N3/0472G06N3/08G06N3/088G06N5/003G06N5/022G10L15/26H04L51/02H04L51/32H04L67/02H04L67/20H04L67/306H04M3/42382H04M3/5141G06F40/211G06F40/40G06N20/10G06Q10/107G06Q10/1053G06Q30/01H04L41/04H04M3/5183
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 10,733,614
App. No.
16/448,532
Granted
Aug 4, 2020
Kind
B2
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.

Claims (69)

1. A computer-implemented method for assisting corporate entities in responding to users and implemented by a third-party service provider, the method comprising:

receiving, at the third-party service provider, a first request from a first user, wherein the first request relates to a first corporate entity;

obtaining first text corresponding to the first request;

transmitting a first application program interface (API) 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;

computing first natural language processing (NLP) features from the first text;

automatically generating first semantic processing results by processing the first NLP features and the first information with a neural network;

transmitting the first semantic processing results to the first user;

receiving, at the third-party service provider, a second request from a second user, wherein the second request relates to a second corporate entity and wherein the second corporate entity is different from the first corporate entity;

obtaining second text corresponding to the second request;

transmitting a second API 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;

computing second NLP features from the second text;

automatically generating second semantic processing results by processing the second NLP features and the second information with the neural network;

transmitting the second semantic processing results to the second user.

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

3. The computer-implemented method of claim 1 , wherein obtaining the first text comprises performing automated speech recognition on audio of the first request.

4. The computer-implemented method of claim 1 , wherein computing the first NLP features from the first text comprises one or more of computing a bag of words vector from the first text, computing a term frequency inverse document frequency vector from the first text, or obtaining word embeddings corresponding to the first text.

5. The computer-implemented method of claim 1 , wherein automatically generating the first semantic processing results comprises selecting a node from an action graph.

6. The computer-implemented method of claim 1 , wherein automatically generating the first semantic processing results comprises:

determining a text response to the first text; or

generating a completion to the first text.

7. The computer-implemented method of claim 1 , wherein the first request is received from a first device of the first user and the first semantic processing results are transmitted to the first device of the first user.

8. A system for assisting corporate entities in responding to users, 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, at a third-party service provider, a first request from a first user, wherein the first request relates to a first corporate entity;

obtain a first text corresponding to the first request;

transmit a first application program interface (API) request for first information from a server of the third-party service provider to a first server of the first corporate entity;

receive the first information from the first corporate entity;

compute first natural language processing (NLP) features from the first text;

automatically generate first semantic processing results by processing the first NLP features and the first information with a neural network;

transmit the first semantic processing results to the first user;

receive, at the third-party service provider, a second request from a second user, wherein the second request relates to a second corporate entity and wherein the second corporate entity is different from the first corporate entity;

obtain second text corresponding to the second request;

transmit a second API request for second information from a server of the third-party service provider to a second server of the second corporate entity;

receive the second information from the second corporate entity;

compute second NLP features from the second text;

automatically generate second semantic processing results by processing the second NLP features and the second information with the neural network;

transmit the second semantic processing results to the second user.

9. The system of claim 8 , wherein the first information comprises information about the first user.

10. The system of claim 8 , wherein the at least one server computer is configured to compute the first NLP features using a topic model, a latent semantic indexing model, a latent Dirichlet allocation model, or a second neural network.

11. The system of claim 8 , wherein the at least one server computer is configured to automatically generate the first semantic processing results by:

determining a text response to the first text; or

generating a completion to the first text.

12. The system of claim 8 , wherein the neural network comprises a classifier.

13. The system of claim 12 , wherein the classifier comprises a logistic regression classifier.

14. The system of claim 8 , wherein the first request is received via the first corporate entity and the first semantic processing results are transmitted via the first corporate entity.

15. 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, at a third-party service provider, a first request from a first user, wherein the first request relates to a first corporate entity;

obtaining a first text corresponding to the first request;

transmitting a first application program interface (API) 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;

computing first natural language processing (NLP) features from the first text;

automatically generating first semantic processing results by processing the first NLP features and the first information with a neural network;

transmitting the first semantic processing results to the first user;

receiving, at the third-party service provider, a second request from a second user, wherein the second request relates to a second corporate entity and wherein the second corporate entity is different from the first corporate entity;

obtaining second text corresponding to the second request;

transmitting a second API 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;

computing second NLP features from the second text;

automatically generating second semantic processing results by processing the second NLP features and the second information with the neural network;

transmitting the second semantic processing results to the second user.

16. The one or more non-transitory computer-readable media of claim 15 , wherein the first request comprises a customer support request.

17. The one or more non-transitory computer-readable media of claim 15 , wherein automatically generating the first semantic processing results comprises selecting a node from an action graph.

18. The one or more non-transitory computer-readable media of claim 15 , wherein automatically generating the first semantic processing results comprises:

determining a text response to the first text; or

generating a completion to the first text.

19. The one or more non-transitory computer-readable media of claim 15 , wherein the neural network comprises a classifier.

20. The one or more non-transitory computer-readable media of claim 19 , wherein the classifier comprises a logistic regression classifier.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Jun 25, 2019
From: SAPOZNIK, GUSTAVO; DAI, HUI; HACKMAN, JOSEPH
To: ASAPP, INC.
Reel/Frame 049575/0213 →
Continuity (3)
Continuation 15254101 · Sep 1, 2016
Provisional Application 62359841 · Jul 8, 2016
Related Publication 20190311375A1 · Oct 10, 2019
Cited By (8)
US 12,254,269 US 12,335,224 US 12,470,503 US 12,499,875 US 12,511,480 US 12,524,771 US 12,621,258 US 12,652,263