Determining and utilizing contextual meaning of digital standardized image characters

Patent metadata

Field	Value
Publication number	US-2022067084-A1
Application number	US-202117341100-A
Country	US
Kind code	A1
Filing date	Jun 7, 2021
Priority date	Dec 1, 2015
Publication date	Mar 3, 2022
Grant date	—

Abstract

One or more embodiments of the disclosure include a character management system that determines and utilizes contextual meaning with regard to standardized image characters. In particular, the character management system determines contextual meaning with regard to standardized characters based on the manner in which the standardized characters are utilized in a repository of electronic documents. Moreover, the character management system can utilize the contextual meaning to search, recommend, analyze, and translate with regard to the use of standardized image characters.

First claim

What is claimed is:

1 . A method comprising:
determining contextual meanings for a plurality of standardized image characters based on a manner in which the plurality of standardized image characters are utilized in a repository of electronic documents; identifying digital text in an electronic communication of a client device; and providing, for display via the client device, a digital text suggestion based on the digital text in the electronic communication and a contextual meaning of a standardized image character from the contextual meanings for the plurality of standardized image characters.

2 . The method of claim 1 , wherein determining contextual meanings for the plurality of standardized image characters based on the manner in which the standardized image characters are utilized in the repository of electronic documents comprises utilizing a word to vector algorithm to generate a vector representation of the standardized image character based on the repository of electronic documents.

3 . The method of claim 1 , wherein the digital text suggestion comprises the standardized image character and further comprising determining the digital text suggestion comprising the standardized image character by comparing the digital text in the electronic communication with the contextual meanings for the plurality of standardized image characters.

4 . The method of claim 3 , wherein comparing the digital text in the electronic communication with the contextual meanings for the plurality of standardized image characters comprises comparing a vector representation of the digital text with vector representations of the standardized image characters.

5 . The method of claim 1 , wherein the digital text in the electronic communication comprises the standardized image character and further comprising determining the digital text suggestion by comparing the contextual meaning for the standardized image character with a plurality of alternate digital texts.

6 . The method of claim 1 , wherein the digital text in the electronic communication comprises the standardized image character and additional digital text, and further comprising:
determining a conflict between the contextual meaning for the standardized image character and the additional digital text; and providing the digital text suggestion by providing a suggested replacement text based on the conflict.

7 . The method of claim 1 , wherein the digital text in the electronic communication comprises a first standardized image character and the digital text suggestion comprises a second standardized image character and further comprising determining the second standardized image character by comparing a contextual meaning of the first standardized image character and a contextual meaning of the second standardized image character.

8 . A system comprising:
at least one processor; and at least one non-transitory computer readable storage medium storing instructions that, when executed by the at least one processor, cause the system to: determine contextual meanings for a plurality of standardized image characters based on a manner in which the plurality of standardized image characters are utilized in a repository of electronic documents; identify digital text in an electronic communication of a client device; and provide, for display via the client device, a digital text suggestion based on the digital text in the electronic communication and a contextual meaning of a standardized image character from the contextual meanings for the plurality of standardized image characters.

9 . The system of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the system to determine contextual meanings for the plurality of standardized image characters based on the manner in which the standardized image characters are utilized in the repository of electronic documents by utilizing a word to vector algorithm to generate a vector representation of the standardized image character based on the repository of electronic documents.

10 . The system of claim 8 , wherein the digital text suggestion comprises the standardized image character and further comprising instructions that, when executed by the at least one processor, cause the system to determine the digital text suggestion comprising the standardized image character by comparing the digital text in the electronic communication with the contextual meanings for the plurality of standardized image characters.

11 . The system of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the system to compare the digital text in the electronic communication with the contextual meanings for the plurality of standardized image characters by comparing a vector representation of the digital text with vector representations of the standardized image characters.

12 . The system of claim 8 , wherein the digital text in the electronic communication comprises the standardized image character and further comprising instructions that, when executed by the at least one processor, cause the system to determine the digital text suggestion by comparing the contextual meaning for the standardized image character with a plurality of alternate digital texts.

13 . The system of claim 8 , wherein the digital text in the electronic communication comprises the standardized image character and additional digital text, and further comprising instructions that, when executed by the at least one processor, cause the system to:
determine a conflict between the contextual meaning for the standardized image character and the additional digital text; and provide the digital text suggestion by providing a suggested replacement text based on the conflict.

14 . The system of claim 8 , wherein the digital text in the electronic communication comprises a first standardized image character and the digital text suggestion comprises a second standardized image character and further comprising instructions that, when executed by the at least one processor, cause the system to determine the second standardized image character by comparing a contextual meaning of the first standardized image character and a contextual meaning of the second standardized image character.

15 . A non-transitory computer readable medium storing instructions thereon that, when executed by at least one processor, cause a computer system to:
determine contextual meanings for a plurality of standardized image characters based on a manner in which the plurality of standardized image characters are utilized in a repository of electronic documents; identify digital text in an electronic communication of a client device; and provide, for display via the client device, a digital text suggestion based on the digital text in the electronic communication and a contextual meaning of a standardized image character from the contextual meanings for the plurality of standardized image characters.

16 . The non-transitory computer readable medium of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the computer system to determine contextual meanings for the plurality of standardized image characters based on the manner in which the standardized image characters are utilized in the repository of electronic documents by utilizing a word to vector algorithm to generate a vector representation of the standardized image character based on the repository of electronic documents.

17 . The non-transitory computer readab

Assignees

• Facebook Inc

Inventors

• Dimson Thomas Frederick
• State Bogdan
• Kalyanaraman Shankar
• Azhar Hamdan

Classifications

• G06F16/5838 Primary

  using colour · CPC title

• G06F16/583 Primary

  using metadata automatically derived from the content · CPC title