Entity page recommendation based on post content

Patent metadata

Field	Value
Publication number	US-9727926-B2
Application number	US-201414194966-A
Country	US
Kind code	B2
Filing date	Mar 3, 2014
Priority date	Mar 3, 2014
Publication date	Aug 8, 2017
Grant date	Aug 8, 2017

Abstract

Methods, systems, and computer programs are presented for an online community management system. One method includes an operation for detecting a post on a social network, where the post is associated with an article. The social network has a plurality of entity pages associated with respective entities. Further, the method includes operations for determining a topic of the article based on a content of the article, and for determining whether the topic is associated with a related entity page on the social network. The related entity page is recommended to a user accessing the post when the topic is associated with the related entity page.

First claim

What is claimed is:

1. A method comprising:
detecting, by a processing device, a post on a social network, the post being associated with an article, the social network comprising a plurality of entity pages associated with respective entities of a plurality of entities;
determining a topic of the article based on content of the article, wherein the determining of the topic of the article comprises:
checking the content against a data structure comprising attributes and relationships of one or more entities of the plurality of entities to determine one or more candidate topics;
identifying probabilities of the one or more candidate topics being the topic of the article based on the checking; and
selecting the topic of the article based on the identified probabilities; and
recommending following a related entity page to a user in response to determining that:
the topic is associated with the related entity page of the plurality of entity pages;
the user accessing the post is not following the related entity page and the related entity page has not been recommended to the user;
a respective entity associated with the related entity page has posted in the related entity page within a threshold amount of time; and
the related entity page is not age restricted, not blocked, and not identified as spam.

2. The method as recited in claim 1 , further including:
annotating the post in the social network by storing an identifier of the related entity page with the post in response to the determining that the topic is associated with the related entity page.

3. The method as recited in claim 1 , wherein the data structure comprises a knowledge graph holding properties and associated values modeling the attributes and the relationships of the one or more entities of the plurality of entities.

4. The method as recited in claim 1 , wherein the determining that the topic is associated with the related entity page comprises:
identifying one or more candidate entity pages that are related to the topic; and
selecting one of the candidate entity pages that is an official entity page associated with the topic as the related entity page.

5. The method as recited in claim 4 , wherein the identifying the one or more candidate entity pages is performed by a machine learning system.

6. The method as recited in claim 1 , wherein the recommending following the related entity page comprises:
detecting that the user has selected a link in the post;
detecting that the user has returned to the social network after selecting the link;
identifying the related entity page from metadata stored with the post; and
recommending the related entity page to the user.

7. The method as recited in claim 1 , wherein the article is one or more of a photo, a link to a photo, a video, a link to a video, a sound recording, a link to a sound recording, a slide show, a link to a slide show, a link to a webpage, or content found in a link entered by the user in a post.

8. The method as recited in claim 1 , further including:
storing a record of the recommending following the related entity page to the user in a history of recommendations for the user to avoid presenting duplicate recommendations to the user.

9. The method as recited in claim 1 , wherein the article is associated with a uniform resource locator (URL), wherein the URL is provided by a publisher of the article.

10. The method as recited in claim 9 , further including:
recommending a publisher entity page for the publisher of the article.

11. The method as recited in claim 1 , wherein the plurality of entity pages comprises personal pages and entity pages associated with the respective entities, wherein each entity of the respective entities comprises at least one of a business, a famous person, a famous figure, a commercial figure, an artist, a celebrity, a government group, a brand, a political figure, a community association, or an organization.

12. The method as recited in claim 1 , wherein the recommending following the related entity page comprises:
providing an interface for the recommendation, the interface including information about the related entity page and a selectable option for following the related entity page.

13. The method as recited in claim 1 , further including:
performing statistics on a plurality of recommended entity pages and a plurality of user acceptances of the plurality of recommended entity pages.

14. The method as recited in claim 1 , further including:
enabling a follow operation of the related entity page by the user in response to the user accepting the recommendation.

15. A system comprising:
a memory; and
a processing device, coupled to the memory, to:
detect a post on a social network, the post being associated with an article, the social network comprising a plurality of entity pages associated with respective entities of a plurality of entities;
determine a topic of the article based on content of the article, wherein determining of the topic of the article comprises the processing device to:
check the content against a data structure comprising attributes and relationships of one or more entities of the plurality of entities to determine one or more candidate topics;
identify probabilities of the one or more candidate topics being the topic of the article based on checking of the content; and
select the topic of the article based on the identified probabilities; and
recommend following a related entity page to a user in response to determining that:
the topic is associated with the related entity page of the plurality of entity pages;
the user accessing the post is not following the related entity page and the related entity page has not been recommended to the user;
a respective entity associated with the related entity page has posted in the related entity page within a threshold amount of time; and
the related entity page is not age restricted, not blocked, and not identified as spam.

16. The system as recited in claim 15 , wherein the processing device is to provide a graphical user interface (GUI) to display the post and to receive user input to follow one or more of the plurality of entity pages.

17. The system as recited in claim 16 , wherein the GUI provides an interface to display information about the related entity page and a selectable option for following the related entity page.

18. The system as recited in claim 16 , wherein the GUI presents a hover card when user hovers a mouse pointer over information of the related entity page in the post.

19. A non-transitory machine-readable storage medium storing instructions which, when executed, cause a processing device to perform operations comprising:
detecting, by the processing device, a post on a social network, the post being associated with an article, the social network comprising a plurality of entity pages associated with respective entities of a plurality of entities;
determining a topic of the article based on content of the article, wherein the determining of the topic of the article comprises:
checking the content against a data structure comprising attributes and relationships of one or more entities of the plurality of entities to determine one or more candidate topics;
identifying probabilities of the one or more candidate topics being the topic of the article in view of the checking; and
selecting the topic of the article based on the identified probabilities;
recommending following a related entity page to a user in response to determining that:
the

Assignees

• Google Inc

Inventors

• Napper Jon
• Liu Tsung-Yuan
• Polderman Bruce Leendert
• Chung Grace
• Kessler Edward

Classifications

• G06Q10/40 Primary

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

• G06Q50/01 Primary

  Physics · mapped topic

• H04L51/32

  Electricity · mapped topic

• G06F17/30867

  Physics · mapped topic

• H04L51/52 Primary

  for supporting social networking services · CPC title