Social media platform with recommendation engine refresh

Patent metadata

Field	Value
Publication number	US-12455933-B2
Application number	US-202217935902-A
Country	US
Kind code	B2
Filing date	Sep 27, 2022
Priority date	Sep 27, 2022
Publication date	Oct 28, 2025
Grant date	Oct 28, 2025

Abstract

A computing system is provided, including one or more processors configured to provide a social media platform configured to serve a content feed to a user. The processor is further configured to generate user content interaction information by detecting user interactions with the content feed and provide a recommendation engine that selects content items for display in the content feed based on the generated user content interaction information. The processor is further configured to receive a refresh request to refresh the recommendation engine and refresh the recommendation engine at least in part by masking or resetting the user content interaction information upon receiving the refresh request. After the refresh, the processor is further configured to generate, via the recommendation engine, post-refresh content items based on the masked or reset user content interaction information, and transmit the post-refresh content items to the user device for display in the content feed.

First claim

The invention claimed is:

1. A computing system, comprising:
one or more processors configured to execute instructions stored in memory to:
provide a social media platform configured to serve a content feed to a user computing device of a user;
generate user content interaction information by detecting user interactions with the content feed;
provide a recommendation engine that selects content items for display in the content feed based on the generated user content interaction information and user information including at least a user identification for the user;
receive a refresh request to refresh the recommendation engine;
in response to receiving the refresh request, refresh the recommendation engine at least in part by masking or resetting the user content interaction information and the user information including the user identification; and
after masking or resetting, unmask at least part of the user content interaction information and the user information based on a number of views of post-refresh content items by the user.

2. The computing system of claim 1 , wherein the one or more processors are further configured to:
input the masked or reset user content interaction information to the recommendation engine;
generate, via the recommendation engine, the post-refresh content items based on the masked or reset user content interaction information; and
transmit the post-refresh content items to the user computing device for display in the content feed.

3. The computing system of claim 1 , wherein the one or more processors are further configured to:
serve a graphical user interface (GUI) configured to display the content feed to the user computing device, the GUI including a refresh selector; and
receive the refresh request from the user computing device upon user selection of the refresh selector.

4. The computing system of claim 1 , wherein
the recommendation engine selects the content items for display based on the generated user content interaction information, the user information, and device information of the user.

5. The computing system of claim 1 , wherein the refresh of the recommendation engine includes a first temporary refresh that masks or resets the user content interaction information and the user information including the user identification until a first predetermined threshold number of views is reached.

6. The computing system of claim 5 , wherein the refresh of the recommendation engine includes a second temporary refresh that unmasks the user content interaction information and the user information except for the user identification and masks the user identification after the first predetermined threshold number of views has occurred and until a second predetermined threshold number of views is reached.

7. The computing system of claim 6 , wherein one or more processors are further configured to end the second temporary refresh by unmasking the user identification after the second predetermined threshold number of views is reached.

8. The computing system of claim 1 , wherein the one or more processors are further configured to:
generate embedding information based on the user content interaction information; and
refresh the recommendation engine by masking or resetting the user content interaction information by masking or resetting embedding information representing the user content interaction information.

9. The computing system of claim 1 , wherein the one or more processors are further configured to:
receive a request from a user to undo the recommendation engine refresh; and
undo the recommendation engine refresh in response to receiving the request.

10. A computerized method for refreshing a recommendation engine, the method comprising:
providing a social media platform configured to serve the content feed to a user computing device of a user;
generating user content interaction information by detecting user interactions with the content feed;
providing a recommendation engine that selects content items for display in the content feed based on the generated user content interaction information and user information including at least a user identification for the user;
receiving a refresh request to refresh the recommendation engine;
in response to receiving the refresh request, refreshing the recommendation engine at least in part by masking or resetting the user content interaction information and the user information including the user identification; and
after masking or resetting, unmask at least part of the user content interaction information and the user information based on a number of views of post-refresh content items by the user.

11. The computerized method of claim 10 , further comprising:
inputting the masked or reset user content interaction information to the recommendation engine;
generating, via the recommendation engine, the post-refresh content items based on the masked or reset user content interaction information; and
transmitting the post-refresh content items to the user computing device for display in the content feed.

12. The computerized method of claim 10 , further comprising:
serving a graphical user interface (GUI) configured to display the content feed to a user computing device, the GUI including a refresh selector; and
receiving the refresh request from the user computing device upon user selection of the refresh selector.

13. The computerized method of claim 10 , wherein the refresh of the recommendation engine includes a first temporary refresh that masks or resets the user content interaction information and the user information including the user identification for a first predetermined threshold number of views.

14. The computerized method of claim 13 , wherein the refresh of the recommendation engine includes a second temporary refresh that unmasks the user content interaction information and the user information except for the user identification and masks the user identification for a second predetermined threshold number of views.

15. The computerized method of claim 10 , further comprising:
generating embedding information based on the user content interaction information; and
refreshing the recommendation engine by masking or resetting the user content interaction information by masking or resetting embedding information representing the user content interaction information.

16. A non-transitory computer readable medium including instructions stored thereon, the instructions, when executed by one or more processors, causing the one or more processors to execute steps of:
providing a social media platform configured to serve a content feed to a user computing device of a user;
generating user content interaction information by detecting user interactions with the content feed;
providing a recommendation engine that selects content items for display in the content feed based on the generated user content interaction information, user information including at least a user identification, and device information of the user;
receiving a refresh request to refresh the recommendation engine;
in response to receiving the refresh request, refresh the recommendation engine at least in part by masking or resetting the user content interaction information and the user information including the user identification;
inputting the masked or reset user content interaction information, the masked or reset user information, and the device information of the user to the recommendation engine;
generating, via the recommendation engine, post-refresh recommendation content items base

Assignees

• Lemon Inc
• Douyin Vision Co Ltd

Inventors

• Furlong Jordan
• Cheng Han
• Farley Ciaran
• Yee Alan
• Shah Isha Mukesh
• Gish Riley
• Hanna Amanda
• Lu Jinyi
• Zhang Wenrong
• Chen Yiming
• Leung Tsz Ling Christina

Classifications

• G06Q10/40 Primary

  Business processes related to social networking or social networking services · CPC title

• G06Q30/06311

  based on purchase or browsing history · CPC title

• G06F16/9536

  Search customisation based on social or collaborative filtering · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title

• G06Q50/01

  Physics · mapped topic