Recommending posts to non-subscribing users

• US 8,825,759 B1
• Filed: 04/08/2010
• Issued: 09/02/2014
• Est. Priority Date: 02/08/2010
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Jackson, Todd, Bunner, Andrew A., Steiner, Matthew S., Pongsajapan, John, Cheng, Jessica Shih-Lan, Ho, Edward S., McBride, Sean E.
• Primary Examiner(s): SCOTT, RANDY A
• Application Number:
  US12/756,681
• Time in Patent Office: 1,608 Days
• Field of Search: 705/35, 705/38, 705/14.49, 707/723, 707/726, 707/23
• US Class Current: 709/204
• CPC Class Codes: G06Q 10/101 Collaborative creation, e.g. joint development of products or services
• CPC Class Codes: G06Q 10/105 Human resources
• CPC Class Codes: G06Q 10/107 Computer-aided management of electronic mailing [e-mailing]
• CPC Class Codes: G06Q 50/01 Social networking
• CPC Class Codes: H04L 67/02 based on web technology, e.g. hypertext transfer protocol [HTTP]

Abstract

In general, the subject matter described in this specification can be embodied in methods, systems and program products. A server system receives from a plurality of computing devices indications that a user of each of the computing devices requested to receive posts that a first user authors. The server system receives from a first computing device a post that was authored by the first user. The post is transmitted from the server system to the plurality of computing devices. A score for the post is determined to satisfy a criteria for transmission to a second user who has not requested to receive posts authored by the first user. The determination uses a distance of the second user to the first user in a social network graph. In response, the post is transmitted from the server system to a second computing device that is associated with the second user.

Claims

1. A computer-implemented method, the method comprising:

receiving, at a server system and from a plurality of computing devices, indications that a user of each of the computing devices provided user input requesting to receive transmissions of posts that a first user of a first computing device authors;

receiving, at the server system and from the first computing device, a post that includes text and that was authored by the first user of the first computing device;

transmitting the post from the server system to the plurality of computing devices;

identifying distances in a social network graph between (i) a second user that has not requested to receive posts that are authored by the first user, and (ii) users of the social network, other than the first user and the second user, that have commented on the post that was authored by the first user;

generating, based on the identified distances in the social network graph, a personalized score that is for the post and that is specific to the second user;

determining that the personalized score satisfies a criteria for transmission to the second user, wherein the criteria includes the personalized score exceeding a threshold; and

transmitting, in response to determining that the personalized score satisfies the criteria for transmission to the second user, the post from the server system to a second computing device that is associated with the second user.

2. The computer-implemented method of claim 1, wherein the server system does not provide, to the second user, posts that (i) are authored by the first user, and (ii) that are associated with personalized scores that do not meet the criteria.

3. The computer-implemented method of claim 1, wherein, in response to receiving the indications, the server system transmits to the plurality of computing devices, all posts that the first user subsequently authors.

4. The computer-implemented method of claim 1, wherein the post does not identify, as intended recipients of the post, the plurality of computing devices or the users of the plurality of computing devices.

5. The computer-implemented method of claim 1, wherein the generating the personalized scores for the post uses the distances between the second user and the users of the social network that have commented on the post to modify the personalized score.

6. The computer-implemented method of claim 1, wherein generating the personalized score for the post further comprises generating a score for the post by determining a quantity of comments that users have submitted in association with the post and comparing the quantity of comments to a historical quantity of comments that posts authored by the first user have received, and modifying the score to generate the personalized score.

7. The computer-implemented method of claim 1, wherein the social network graph is a data structure that identifies, for a plurality of users that can transmit and receive posts, an acquaintance relationship of the users in the plurality to each other.

8. The computer-implemented method of claim 7, wherein the social network graph identifies, for each acquaintance relationship, a strength of the acquaintance relationship.

9. The computer-implemented method of claim 8, wherein each of the distances is based on (i) a minimum number of acquaintance relationships to connect the second user and the other user, and (ii) a strength of the connecting relationships.

10. The computer-implemented method of claim 1, wherein the post includes an identification of a geographical posting location, and further comprising determining that the geographical posting location is within a threshold geographical distance of a geographical location of the second computing device, wherein transmitting the post to the second computing device is dependent upon determining that the criteria is met and determining that the geographical posting location is within the geographical threshold distance.

11. The computer-implemented method of claim 1, further comprising:

determining a collection of words that are common between instances of content that the second user has generated or viewed, wherein determining the collection of words includes not including, in the collection, words that are included in a pre-determined set of words that includes words that are frequently used in a particular language;

determining that the post includes one or more words from the collection; and

wherein transmitting the post to the second computing device is dependent upon determining that the post includes the one or more words from the collection.

12. The computer-implemented method of claim 11, wherein determining the collection of words includes identifying, as a word to include in the collection, a word from a query that the second user submitted to a search engine.

13. The computer-implemented method of claim 11, wherein determining the collection of words includes identifying, as a word to include in the collection, a word within a selected search engine result document, the selected search engine result document being a document that the user selected to view in response to being presented with a list of search results that are responsive to a search query that the user submitted.

14. A computer-implemented method, the method comprising:

receiving, at a server system and from a plurality of computing devices, indications that a user of each of the plurality of computing devices requested to subscribe to posts that are authored by a first user;

receiving, at the server system and from a first computing device, a post that was authored by the first user;

transmitting the post from the server system to the plurality of computing devices;

generating a personalized score that is for the post and is specific to a second user that has not requested to receive posts that are authored by the first user, the generation of the personalized score being based on distances in a social network graph between the second user and other users of the social network that have commented on the post that was authored by the first user;

determining that the personalized score exceeds a threshold; and

transmitting, in response to the determining, the post from the server system to a second computing device that is associated with the second user.

15. A computer-implemented method, the method comprising:

receiving, at a first computing device, user input that identifies multiple authors to which a first user is subscribing;

transmitting, from the first computing device to a server system, indications of the multiple authors to which the first user is subscribing;

receiving, at the first computing device and from the server system, a plurality of posts, wherein the plurality includes;

(i) subscribed posts that are created by authors to which the first user has subscribed, and

(ii) recommended posts that the server system has determined satisfy criteria for transmission to the first user, wherein the determination included (a) identifying one or more distances, in a social network graph, of the first user to one or more other users that did not author the recommended posts and that interacted with the recommended posts by commenting on the recommended posts, (b) generating one or more personalized scores that are for the recommended posts and that are specific to the first user, and (c) determining that the one or more personalized scores satisfy one or more criteria for transmission to the first user, the one or more criteria including the one or more personalized scores exceeding a threshold; and

presenting the plurality of posts as an integral stream of posts on a display of the first computing device.

16. The computer-implemented method of claim 15,

wherein the integral stream of posts includes every post of each author to which the first user has subscribed.

17. A system comprising:

a posting computerized device, wherein a posting user transmitted a post from the posting computerized device to a server system;

a first plurality of computerized devices, wherein a first plurality of users that have logged into the first plurality of computerized device have requested to receive posts authored by the posting user;

a second plurality of computerized devices, wherein a second plurality of users that have logged into the second plurality of computerized devices have not requested to receive posts authored by the posting user;

means to identify the second plurality of computerized devices as computerized devices to receive the post based on the second plurality of computerized devices satisfying criteria, the second plurality identified as computerized devices that satisfy the criteria for receiving the post based on personalized scores of the post exceeding a threshold, the personalized scores having been generated for the post based on distances, in a social network graph, between users that commented on the first post and each of the second plurality of users, the users that commented on the post being different than the first plurality of users; and

a re-transmission mechanism at the server system to receive the post from the posting computerized device and to transmit the post to the first plurality of computers and to the second plurality of computers.