Emoticon package generation method and apparatus, device and medium

Patent metadata

Field	Value
Publication number	US-11521340-B2
Application number	US-202017280142-A
Country	US
Kind code	B2
Filing date	Jul 3, 2020
Priority date	Feb 28, 2020
Publication date	Dec 6, 2022
Grant date	Dec 6, 2022

Abstract

Provided are an emoticon package generation method and apparatus, a device and a medium which relate to the field of graphic processing and in particular to Internet technologies. The specific implementation solution is: determining at least one of associated text of an emoticon picture or a similar emoticon package of an emoticon picture, where the associated text of the emoticon picture includes at least one of main part information, scenario information, emotion information, action information or connotation information; determining target matching text from the at least one of the associated text of the emoticon picture or associated text of the similar emoticon package; and superimposing the target matching text on the emoticon picture to generate a new emoticon package.

First claim

What is claimed is:

1. A method for generating an emoticon package, comprising:
determining at least one of associated text of an emoticon picture or a similar emoticon package of an emoticon picture, wherein the associated text of the emoticon picture comprises at least one of main part information, scenario information, emotion information, action information or connotation information;
determining target matching text from at least one of the associated text of the emoticon picture or associated text of the similar emoticon package;
superimposing the target matching text on the emoticon picture to generate a new emoticon package; and
determining a position at which the target matching text is superimposed, which comprises:
detecting a background area in the emoticon picture;
determining a largest inscribed graphic region in the background area; and
using the largest inscribed graphic region as the position at which the target matching text is superimposed.

2. The method of claim 1 , wherein determining the associated text of the emoticon picture comprises:
determining the associated text of the emoticon picture according to the associated text of the similar emoticon package.

3. The method of claim 2 , wherein determining the associated text of the emoticon picture according to the associated text of the similar emoticon package comprises:
determining target text from the associated text of the similar emoticon package based on a word use frequency; and
determining the associated text of the emoticon picture from the target text.

4. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of claim 2 .

5. The method of claim 3 , wherein determining the associated text of the emoticon picture from the target text comprises:
matching a recognition result of the emoticon picture with the target text;
determining repeated text according to a matching result; and
filtering out the repeated text from the recognition result of the emoticon picture and the target text to obtain the associated text of the emoticon picture, wherein the recognition result of the emoticon picture comprises the emotion information and the main part information.

6. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of claim 3 .

7. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of claim 5 .

8. The method of claim 1 , wherein determining the similar emoticon package of the emoticon picture comprises:
matching image information of the emoticon picture with image information of an existing emoticon package, and matching information about the associated text of the emoticon picture with information about associated text of the existing emoticon package; and
in response to an image matching degree or a text matching degree satisfying a set condition, using the existing emoticon package as the similar emoticon package.

9. The method of claim 8 , wherein the image information comprises emoticon package category information and object category information.

10. The method of claim 1 , wherein determining the target matching text from the at least one of the associated text of the emoticon picture or the associated text of the similar emoticon package comprises:
determining the target matching text from candidate matching text based on at least one of a word use frequency, a word length or word semantics, wherein the candidate matching text comprises the at least one of the associated text of the emoticon picture or the associated text of the similar emoticon package.

11. The method of claim 10 , wherein determining the target matching text from the candidate matching text based on the word length comprises:
in response to a word length of the candidate matching text being within a set length range, determining the candidate matching text as the target matching text.

12. The method of claim 10 , wherein determining the target matching text from the candidate matching text based on the word semantics comprises:
determining that word semantics of the candidate matching text comprises word information about at least one of an emotion word, a popular word or an entity word; and
determining the target matching text from the candidate matching text according to the word information.

13. The method of claim 1 , before determining the at least one of the associated text of the emoticon picture or the similar emoticon package of the emoticon picture, further comprising:
extracting a video image comprising a target part of a target object from a video;
performing recognition of at least one of a speaking or an action execution amplitude on the extracted video image; and
determining the emoticon picture from the video image according to a recognition result.

14. An electronic device, comprising:
at least one processor; and
a memory communicatively connected to the at least one processor;
wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the method of claim 1 .

15. A non-transitory computer-readable storage medium storing computer instructions for causing a computer to perform the method of claim 1 .

16. An apparatus for generating an emoticon package, comprising:
an associated text determination module, which is configured to determine at least one of associated text of an emoticon picture or a similar emoticon package of an emoticon picture, wherein the associated text of the emoticon picture comprises at least one of main part information, scenario information, emotion information, action information or connotation information;
a matching text determination module, which is configured to determine target matching text from the at least one of the associated text of the emoticon picture or associated text of the similar emoticon package; and
an emoticon package generation module, which is configured to superimpose the target matching text on the emoticon picture to generate a new emoticon package;
a background detection module, which is configured to detect a background area in the emoticon picture;
a region determination module, which is configured to determine a largest inscribed graphic region in the background area; and
a position determination module, which is configured to use the largest inscribed graphic region as the position at which the target matching text is superimposed.

17. The apparatus of claim 16 , wherein the associated text determination module comprises:
an associated text determination unit, which is configured to determine the associated text of the emoticon picture according to the associated text of the similar emoticon package.

18. The apparatus of claim 16 , wherein the associated text determination module comprises:
an emoticon picture matching unit, which is configured to perform at least one of matching image information of the emoticon picture with image information of an existing emoticon package or

Assignees

• Beijing Baidu Netcom Sci & Tech Co Ltd

Inventors

• Xu Xianglong
• Zhu Jianfeng
• Cui Jiahua
• Xiang Jing
• Li Hongtao
• Han Chen
• Lin Shufei
• Su Ying
• Li Shicao
• Li Huiqin
• Gan Xiaochu
• Gao Fei
• Yang Jiale
• Ma Xueyun
• Li Guohong

Classifications

• G06V40/20

  Movements or behaviour, e.g. gesture recognition (recognition of facial expressions G06V40/16) · CPC title

• G06F16/3344

  using natural language analysis · CPC title

• G06T11/60 Primary

  Creating or editing images; Combining images with text · CPC title

• G06F16/5866 Primary

  using information manually generated, e.g. tags, keywords, comments, manually generated location and time information · CPC title

• G06F40/30 Primary

  Semantic analysis · CPC title