Automatic localization of dynamic content

Patent metadata

Field	Value
Publication number	US-12236207-B2
Application number	US-202318111643-A
Country	US
Kind code	B2
Filing date	Feb 20, 2023
Priority date	Jun 30, 2020
Publication date	Feb 25, 2025
Grant date	Feb 25, 2025

Abstract

Implementations described herein relate to methods, systems, and computer-readable media to localize dynamic content. In some implementations, a computer-implemented method includes receiving visual content associated with a game from a first client locale, the visual content including text being represented at the first client locale by a first language, converting the text to generate translated text in at least a second language associated with a second client locale, and storing the translated text in a database in association with the visual content.

First claim

What is claimed is:

1. A computer-implemented method of automatic localization of dynamic content, the method comprising:
receiving visual content associated with a game from a first client locale, the visual content including text being represented at the first client locale by a first language and including visual data;
converting the text to generate translated text in at least a second language associated with a second client locale;

storing the translated text in a database in association with the visual content;
receiving a request for the visual content from a client device associated with the second client locale;
adjusting the visual data based on the translated text;
rendering localized content for the second client locale and based on the adjusted visual data; and
transmitting the localized content to the client device responsive to the request.

2. The computer-implemented method of claim 1 , wherein receiving the visual content comprises:
receiving, at a preprocessor, the visual content; and
extracting, by a conversion module of the preprocessor, the text, wherein the conversion module is configured to perform the converting of the text to generate the translated text.

3. The computer-implemented method of claim 2 , wherein the conversion module is further configured to extract the visual data from the received visual content.

4. The computer-implemented method of claim 3 , wherein the conversion module is further configured to direct the extracted visual data to one or more separate processing pipelines.

5. The computer-implemented method of claim 2 , wherein the preprocessor comprises a preprocessor pipeline including a plurality of evaluator engines configured to identify qualities of text from the extracted text.

6. The computer-implemented method of claim 5 , wherein the plurality of evaluator engines are further configured to generate a pool of candidate database entries of text for storage based on the extracted text.

7. The computer-implemented method of claim 1 , wherein the converting comprises:
creating candidate database entries based on the text and the visual content;
selecting a subset of the candidate database entries to obtain a pool of remaining database entries;
evaluating entries in the pool of remaining database entries to generate an importance ranking; and
filtering to remove one or more entries from the pool of remaining database entries that are associated with a respective importance ranking that does not meet a first importance threshold.

8. The computer-implemented method of claim 1 , wherein the translated text is associated with an importance ranking value that meets a first importance threshold.

9. The computer-implemented method of claim 8 , wherein the importance ranking value is a measure of importance of translated text being accurately represented at the second client locale.

10. The computer-implemented method of claim 9 , wherein the importance ranking value is based on one or more of a number of users that view the visual content, a number of sessions associated with the visual content, or a source of the visual content.

11. The computer-implemented method of claim 1 , wherein the converting comprises:
creating a pool of candidate database entries;
evaluating entries in the pool of candidate database entries to generate an engagement score; and
filtering to remove one or more entries with engagement scores that does not meet a first threshold.

12. A system comprising:
a memory with instructions stored thereon; and
a processing device, coupled to the memory, the processing device configured to access the memory and execute the instructions, wherein the instructions cause the processing device to perform operations including:
receiving visual content associated with a game from a first client locale, the visual content including text being represented at the first client locale by a first language and including visual data;
converting the text to generate translated text in at least a second language associated with a second client locale;
storing the translated text in a database in association with the visual content;
receiving a request for the visual content from a client device associated with the second client locale;
adjusting the visual data based on the translated text;
rendering localized content for the second client locale and based on the adjusted visual data; and
transmitting the localized content to the client device responsive to the request.

13. The system of claim 12 , further comprising a preprocessor having a conversion module, wherein receiving the visual content comprises:
receiving, at the preprocessor, the visual content; and
extracting, by the conversion module, the text, wherein the conversion module is configured to perform the converting of the text to generate the translated text.

14. The system of claim 13 , wherein the conversion module is further configured to extract visual data from the received visual content and to direct the extracted visual data to one or more separate processing pipelines of the system.

15. The system of claim 13 , wherein the preprocessor comprises a preprocessor pipeline including a plurality of evaluator engines configured to identify qualities of text from the extracted text.

16. The system of claim 15 , wherein the plurality of evaluator engines are further configured to generate a pool of candidate database entries of text for storage based on the extracted text.

17. The system of claim 12 , wherein the converting comprises:
creating candidate database entries based on the text and the visual content;
selecting a subset of the candidate database entries to obtain a pool of remaining database entries;
evaluating entries in the pool of remaining database entries to generate an importance ranking; and
filtering to remove one or more entries from the pool of remaining database entries that are associated with a respective importance ranking that does not meet a first importance threshold.

18. The system of claim 12 , wherein the translated text is associated with an importance ranking value that meets a first importance threshold.

19. The system of claim 18 , wherein the importance ranking value is a measure of importance of translated text being accurately represented at the second client locale; and wherein the importance ranking value is based on one or more of a number of users that view the visual content, a number of sessions associated with the visual content, or a source of the visual content.

20. A non-transitory computer-readable medium with instructions stored thereon that, responsive to execution by a processing device, causes the processing device to perform operations comprising:
receiving visual content associated with a game from a first client locale, the visual content including text being represented at the first client locale by a first language and including visual data;
converting the text to generate translated text in at least a second language associated with a second client locale;
storing the translated text in a database in association with the visual content;
receiving a request for the visual content from a client device associated with the second client locale;
adjusting the visual data based on the translated text;
rendering localized content for the second client locale and based on the adjusted visual data; and
transmitting the localized content to the client device responsive to the request.

Assignees

• Roblox Corp

Inventors

• Spence Kyle
• Phillips Peter John
• Collins Craig
• Gao Pengfei
• Xu Xiaochen
• Quartulli Alex
• Li Andrew
• Francis Andrew Gilmore
• Cutigni Jovanni Antonio
• Ramamurthy Shreya

Classifications

• G06F40/263

  Language identification · CPC title

• G06F40/30

  Semantic analysis · CPC title

• A63F13/79

  involving player-related data, e.g. identities, accounts, preferences or play histories · CPC title

• A63F13/87

  Communicating with other players during game play, e.g. by e-mail or chat · CPC title

• A63F13/63

  by the player, e.g. authoring using a level editor · CPC title