Intelligent voice interaction method, device and computer readable storage medium

Patent metadata

Field	Value
Publication number	US-11189183-B2
Application number	US-201916566099-A
Country	US
Kind code	B2
Filing date	Sep 10, 2019
Priority date	Oct 25, 2018
Publication date	Nov 30, 2021
Grant date	Nov 30, 2021

Abstract

Embodiments of the present disclosure provide a method, a device, and a computer readable storage medium for intelligent voice interaction. The method includes: obtaining text information or drawing information input by a user on a digitizer tablet; identifying the text information or the drawing information to obtain an identification result; and transmitting audio information corresponding to the identification result to the digitizer tablet, enabling the digitizer tablet to play the audio information. According to the embodiments of the present disclosure, the digitizer tablet performs an intelligent voice interaction with the user according to the text information or the drawing information input by the user when the user practices calligraphy or drawing, thus increasing an interactivity between the user, especially a child, with the digitizer tablet, and enhancing the child's interest in learning.

First claim

What is claimed is:

1. An intelligent voice interaction method, comprising:
obtaining text information or drawing information input by a user on a digitizer tablet;
identifying the text information or the drawing information to obtain an identification result; and
transmitting audio information corresponding to the identification result to the digitizer tablet, enabling the digitizer tablet to play the audio information, wherein the audio information comprises whether a stroke order of a character written by the user is correct, or whether an object drawn by the user meets a drawing requirement proposed by the digitizer tablet to the user.

2. The method according to claim 1 , wherein the obtaining text information input by a user on a digitizer tablet comprises:
receiving dot matrix data of each stroke of the character and dot matrix data of the character as a whole written by the user on the digitizer tablet.

3. The method according to claim 2 , wherein the identifying the text information to obtain an identification result comprises:
determining whether a stroke order of the character written by the user is correct according to the dot matrix data of each stroke of the character written by the user on the digitizer tablet that is transmitted by the digitizer tablet; and
determining whether the character written by the user is standard according to the dot matrix data of the character as a whole.

4. The method according to claim 3 , wherein the determining whether a stroke order of the character written by the user is correct according to the dot matrix data of each stroke of the character written by the user on the digitizer tablet that is transmitted by the digitizer tablet comprises:
determining an image corresponding to each stroke of the character according to the dot matrix data of each stroke of the character; and
comparing the image corresponding to each stroke of the character with a standard stroke image of the character to determine whether the stroke order of the character written by the user is correct.

5. The method according to claim 3 , wherein the determining whether the character written by the user is standard according to the dot matrix data of the character as a whole comprises:
determining an image corresponding to the character according to the dot matrix data of the character as a whole; and
comparing the image corresponding to the character and a standard image of the character to determine whether the character written by the user is standard.

6. The method according to claim 1 , wherein the obtaining drawing information input by a user on a digitizer tablet comprises:
receiving dot matrix data of each stroke, transmitted by the digitizer tablet, when the user draws on the digitizer tablet.

7. The method according to claim 6 , wherein the identifying the drawing information to obtain an identification result comprises:
determining the object drawn by the user according to the dot matrix data of each stroke when the user draws on the digitizer tablet and an image database of simple drawings.

8. The method according to claim 7 , wherein the determining an object drawn by the user according to the dot matrix data of each stroke when the user draws on the digitizer tablet and an image database of simple drawings comprises:
determining a drawing image according to the dot matrix data of each stroke when the user draws on the digitizer tablet; and
identifying the drawing image through a neural network model pre-trained by the image database of simple drawings to determine the object drawn by the user.

9. A server, comprising:
a memory;
a processor;
a communication interface; and
a computer program;
wherein the computer program is stored in the memory and is configured to be implemented by the processor to:
obtain text information or drawing information input by a user on a digitizer tablet;

identify the text information or the drawing information to obtain an identification result; and
transmit, by the communication interface, audio information corresponding to the identification result to the digitizer tablet, enabling the digitizer tablet to play the audio information, wherein the audio information comprises whether a stroke order of a character written by the user is correct, or whether an object drawn by the user meets a drawing requirement proposed by the digitizer tablet to the user.

10. The server according to claim 9 , wherein when the processor obtains text information input by the user on the digitizer tablet, the processor is configured to:
receive dot matrix data of each stroke of the character and dot matrix data of the character as a whole written by the user on the digitizer tablet through the communication interface.

11. The server according to claim 10 , wherein when the processor identifies the text information to obtain the identification result, the processor is configured to:
determine whether a stroke order of the character written by the user is correct according to the dot matrix data of each stroke of the character written by the user on the digitizer tablet that is transmitted by the digitizer tablet; and
determine whether the character written by the user is standard according to the dot matrix data of the character as a whole.

12. The server according to claim 11 , wherein when the processor determines whether the stroke order of the character written by the user is correct according to the dot matrix data of each stroke of the character written by the user on the digitizer tablet that is transmitted by the digitizer tablet, the processor is configured to:
determine an image corresponding to each stroke of the character according to the dot matrix data of each stroke of the character; and
compare the image corresponding to each stroke of the character with a standard stroke image of the character to determine whether the stroke order of the character written by the user is correct.

13. The server according to claim 11 , wherein the processor determines whether the character written by the user is standard according to the dot matrix data of the character as a whole, the processor is configured to:
determine an image corresponding to the character according to the dot matrix data of the character as a whole; and
compare the image corresponding to the character and a standard image of the character to determine whether the character written by the user is standard.

14. The server according to claim 9 , wherein when the processor obtains the drawing information input by the user on the digitizer tablet, the processor is configured to:
receive dot matrix data of each stroke that is transmitted by the digitizer tablet through the communication interface when the user draws on the digitizer tablet.

15. The server according to claim 14 , wherein when the processor identifies the drawing information to obtain the identification result, the processor is configured to:
determine the object drawn by the user according to the dot matrix data of each stroke when the user draws on the digitizer tablet and an image database of simple drawings.

16. The server according to claim 15 , wherein when the processor determines the object drawn by the user according to the dot matrix data of each stroke when the user draws on the digitizer tablet and the image database of simple drawings, the processor is configured to:
determine a drawing image according to the dot matrix data of each stroke when the user draws on the digitizer tablet; and
identify the drawing image through a neural network model pre-trained by the

Assignees

• Baidu online network technology beijing co ltd
• Shanghai Xiaodu Tech Co Ltd

Inventors

• Luo Ronggang
• Lu Yongshuai

Classifications

• G06V30/347

  Sampling; Contour coding; Stroke extraction · CPC title

• G06F3/04883 Primary

  for inputting data by handwriting, e.g. gesture or text · CPC title

• G09B5/06

  with both visual and audible presentation of the material to be studied · CPC title

• G09B5/04 Primary

  with audible presentation of the material to be studied (sound recording or reproducing G11B) · CPC title

• G06F3/165

  Management of the audio stream, e.g. setting of volume, audio stream path · CPC title