Method for user communication with information dialogue system

Patent metadata

Field	Value
Publication number	US-9564149-B2
Application number	US-201514721012-A
Country	US
Kind code	B2
Filing date	May 26, 2015
Priority date	Nov 28, 2012
Publication date	Feb 7, 2017
Grant date	Feb 7, 2017

Abstract

Provided is a method for user communications with an information dialog system, which may be used for organizing user interactions with the information dialog system based on a natural language. The method may include activating a user input subsystem in response to a user entering a request; receiving and converting the request of the user into text by the user input subsystem; sending the text obtained as a result of the conversion of the request to a dialog module; processing, by the dialog module, the text; forming, by the dialog module, the response to the request; sending the response to the user; and displaying and/or reproducing the formed response, where, after the displaying and/or the reproducing of the formed response, the user input subsystem is automatically activated upon entering a further request or a clarification request by the user.

First claim

What is claimed is:

1. A method for user communications with an information dialogue system, the method comprising:
activating, by a user device, a user input subsystem associated with the user device upon a request entered by a user;
receiving, by the user input subsystem, the request;
converting, by the user input subsystem, the request into text;
sending, by the user input subsystem, the text obtained as a result of the converting of the request to a dialogue module associated with the user device;
upon sending the text, deactivating the user input subsystem;
processing the text by the dialogue module;
forming, by the dialogue module, a response to the request, the response including an instruction for activating the user input subsystem, the instruction including at least metadata and a time period required for the user to review the response;
sending, by the dialogue module, the response to the user;
reproducing the response by a voice generation and reproduction subsystem associated with the user device;
upon the reproducing of the response, determining, based on the metadata contained in the instruction, expiration of the time period required for the user to review the response;
based on the determining, re-activating, by the user device, the user input subsystem; and
receiving a further request or a clarification request, the further request or the clarification request being entered by the user.

2. The method of claim 1 , further comprising displaying the response, the response including the text.

3. The method of claim 1 , wherein the request is entered by the user using one or more of the following: a voice command and a keyboard.

4. The method of claim 1 , wherein the response is formed by the dialogue module in a form of the text.

5. The method of claim 1 , wherein the reproducing the response includes reproducing the response by a voice generation and reproduction subsystem.

6. The method of claim 1 , wherein the reproducing the response includes reproducing the response using a voice cue.

7. The method of claim 1 , wherein the text is processed by the dialogue module using additional systems and subsystems.

8. The method of claim 1 , wherein the response formed by the dialogue module includes additional metadata.

9. The method of claim 8 , wherein the additional metadata includes instructions for sending to additional systems and subsystems.

10. A system for user communications with an information dialogue system, the system comprising:
a user input subsystem, wherein the user input subsystem is activated by a user and is operable to:
receive a request entered by the user;
convert the request into text;
send the text obtained as a result of the converting the request to a dialogue module; and
receive a further request or a clarification request, the further request or the clarification request being entered by the user,
wherein the user input subsystem is deactivated upon sending the text;

the dialogue module in communication with the user input subsystem, the dialogue module being operable to:
process the text;
form a response to the request, the response including an instruction for activating the user input subsystem, the instruction including at least metadata and a time period required for the user to review the response; and
send the response to the user; and

a voice generation and reproduction subsystem in communication with the dialogue module, the voice generation and reproduction subsystem being operable to:
reproduce the response;
upon the reproducing of the response, determining, based on the metadata contained in the instruction, expiration of the time period required for the user to review the response; and
based on the determining, re-activate the user input subsystem.

11. The system of claim 10 , further comprising a display, the display being operable to display the response, wherein the display of the response includes displaying the text.

12. The system of claim 10 , wherein the user input subsystem comprises a voice record and recognition component and a keyboard, wherein the request is entered by the user using one or more of the following: a voice command and the keyboard.

13. The system of claim 10 , wherein the dialogue module forms the response in a form of the text.

14. The system of claim 10 , wherein the voice generation and reproduction subsystem is operable to reproduce the response using a voice cue.

15. The system of claim 10 , further comprising additional systems and subsystems, wherein the dialogue module processes the text using the additional systems and subsystems.

16. The system of claim 10 , wherein the response formed by the dialogue module includes additional metadata.

17. The system of claim 16 , wherein the additional metadata include instructions for sending to additional systems and subsystems.

Assignees

• OOO “Speaktoit”
• Google Inc

Inventors

• Gelfenbeyn Ilya Genadevich
• Goncharuk Artem
• Platonov Ilya Andreevich
• Gelfenbeyn Olga Aleksandrovna
• Sirotin Pavel Aleksandrovich

Classifications

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title

• G10L15/1807

  using prosody or stress · CPC title

• G10L25/63 Primary

  for estimating an emotional state · CPC title

• G10L21/18

  Details of the transformation process · CPC title

• G10L2015/227

  of the speaker; Human-factor methodology · CPC title