CONTENT ITEM AUDIENCE SELECTION

• US 20140258275A1
• Filed: 03/08/2013
• Published: 09/11/2014
• Est. Priority Date: 03/08/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Paritosh, Praveen
• Granted Patent: US 9,881,091 B2
• Time in Patent Office: Days
• US Class Current: 707/723
• CPC Class Codes: G06F 16/335 Filtering based on additional data, e.g. user or group profiles filtering in web context G06F16/9535, G06F16/9536
• CPC Class Codes: G06F 16/90324 using system suggestions
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for selecting an audience for content are disclosed. In one aspect, a method includes receiving, from a content item provider, a request to distribute content items to users that have been deemed interested in a particular entity. First users that have expressed an interest in the particular entity are identified. Expansion entities for the particular entity are identified in a knowledge graph. At least one of the expansion entities can be connected to the particular entity by a relationship path. Second users are identified. The second users are deemed interested in the particular entity based on the second users having expressed an interest in an expansion entity. The content items are provided to at least a portion of the first users and at least a portion of the second users.

Claims

1. A method, comprising:

receiving a request to distribute content to an audience of users interested in a particular entity;

identifying directly interested users that have expressed an interest in the particular entity though online activities;

identifying, by one or more data processing apparatus, socially connected users that are connected, in a social graph, to the directly interested users;

identifying, in a knowledge graph, candidate entities that are referenced by interests of the connected users;

identifying, for each of one or more of the candidate entities and based on the knowledge graph, a matching relationship between the candidate entity and the particular entity, the matching relationship being a relationship that each of the candidate entity and the particular entity share with a same entity;

determining, by one or more data processing apparatus, a relationship score for each matching relationship, the relationship score for the matching relationship being determined based on a portion of the connected users that have expressed an interest in an entity having the matching relationship with the same entity;

selecting an expansion relationship for the particular entity, the expansion relationship being selected based on relationship scores for matching relationships, the expansion relationship being a relationship representing a set of entities of interest to a user that has expressed an interest in the particular entity;

identifying, by one or more data processing apparatus and based on the social graph, a set of additional users that have expressed an interest in an entity having the expansion relationship; and

selecting, as an audience for the content, at least a portion of the directly interested users and at least a portion of the set of additional users.

2. The method of claim 1, wherein determining a relationship score for each matching relationship comprises:

for each of at least one matching relationship;

identifying a portion of the socially connected users that are directly interested users for an entity having the matching relationship;

identifying a portion of the candidate entities having the matching relationship; and

determining the relationship score based, at least in part, on the identified portion of the socially connected users and the identified portion of the candidate entities.

3. The method of claim 1, comprising:

obtaining a performance measure for the expansion relationship, the performance measure being based on a number of user interactions with the content that was provided to users that have expressed an interest in entities having the expansion relationship; and

updating the relationship score for the expansion relationship based on the obtained performance measures.

4. The method of claim 3, comprising:

receiving bid data specifying a first value that will be paid by a content item provider for distribution of the content to users that have been deemed interested in the particular entity; and

determining, based on the bid data, a second value that the content item provider will pay for distribution of the content to the set of additional users.

5. The method of claim 4, wherein determining the second value comprises determining an expansion bid for the expansion relationship, the expansion bid value being determined based, at least in part, on the relationship score for the expansion relationship, the expansion bid value being different from a bid value for distribution of the content item to the directly interested users.

6. The method of claim 5, wherein identifying directly interested users comprises identifying users that have interacted with a positive feedback user interface element associated with content referencing the particular entity.

7. A method, comprising:

receiving, from a content item provider, a request to distribute one or more content items to users interested in a particular entity;

identifying first users that have expressed an interest in the particular entity;

identifying, in a knowledge graph, one or more expansion entities for the particular entity, at least one of the expansion entities a being connected to the particular entity though a relationship path in the knowledge graph;

identifying second users that are interested in the particular entity based on the second users having expressed an interest in an expansion entity from the one or more identified expansion entities, the second users being different from the first users; and

providing the one or more content items to at least a portion of the first users and at least a portion of the second users.

8. A computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more data processing apparatus cause the one or more data processing apparatus to perform operations comprising:

receiving a request to distribute content to an audience of users interested in a particular entity;

identifying directly interested users that have expressed an interest in the particular entity through online activity;

identifying socially connected users that are connected, in a social graph, to the directly interested users;

identifying, in a knowledge graph, candidate entities that are referenced by interests of the connected users;

identifying, for each of one or more of the candidate entities and based on the knowledge graph, a matching relationship between the candidate entity and the particular entity, the matching relationship being a relationship that each of the candidate entity and particular entity share with a same entity;

determining a relationship score for each matching relationship, the relationship score for the matching relationship being determined based on a portion of the connected users that have expressed an interest in an entity having the matching relationship with the same entity;

selecting an expansion relationship for the particular entity, the expansion relationship being selected based on relationship scores for matching relationships, the expansion relationship being a relationship representing a set of entities of interest to a user that has expressed an interest in the particular entity;

identifying, based on the social graph, a set of additional users that have expressed an interest in an entity having the expansion relationship; and

selecting, as an audience for the content, at least a portion of the directly interested users and at least a portion of the set of additional users.

9. The computer storage medium of claim 8, wherein determining a relationship score for each matching relationship comprises:

for each of at least one matching relationship;

identifying a portion of the socially connected users that are directly interested users for an entity having the matching relationship;

identifying a portion of the candidate entities having the matching relationship; and

determining the relationship score based, at least in part, on the identified portion of the socially connected users and the identified portion of the candidate entities.

10. The computer storage medium of claim 8, wherein the instructions cause the data processing apparatus to perform operations comprising:

obtaining a performance measure for the expansion relationship, the performance measure being based on a number of user interactions with the content that was provided to users that have expressed an interest in entities having the expansion relationship; and

updating the relationship score for the expansion relationship based on the obtained performance measures.

11. The computer storage medium of claim 8, wherein the instructions cause the data processing apparatus to perform operations comprising:

receiving bid data specifying a first value that will be paid by a content item provider for distribution of the content to users that have been deemed interested in the particular entity; and

determining, based on the bid data, a second value that the content item provider will pay for distribution of the content to the set of additional users.

12. The computer storage medium of claim 11, wherein determining the second value comprises determining an expansion bid for the expansion relationship, the expansion bid value being determined based, at least in part, on the relationship score for the expansion relationship, the expansion bid value being different from a bid value for distribution of the content item to the directly interested users.

13. The computer storage medium of claim 12, wherein identifying directly interested users comprises identifying users that have interacted with a positive feedback user interface element associated with content referencing the particular entity.

16. The system of claim 8, wherein the instructions cause the data processing apparatus to perform operations comprising:

obtaining a performance measure for the expansion relationship, the performance measure being based on a number of user interactions with the content that was provided to users that have expressed an interest in entities having the expansion relationship; and

updating the relationship score for the expansion relationship based on the obtained performance measures.

14. A system comprising:

one or more data stores storing data representing a social graph and data representing a knowledge graph that is different from the social graph; and

one or more data processing apparatus that interact with the one or more data stores and execute instructions that cause the one or more data processing apparatus to perform operations comprising;

receiving a request to distribute content to an audience of users interested in a particular entity;

identifying directly interested users that have expressed an interest in the particular entity though online activity;

identifying socially connected users that are connected, in the social graph, to the directly interested users;

identifying, in the knowledge graph, candidate entities that are referenced by interests of the connected users;

identifying, for each of one or more of the candidate entities and based on the knowledge graph, a matching relationship between the candidate entity and the particular entity, the matching relationship being a relationship that each of the candidate entity and particular entity share with a same entity;

determining a relationship score for each matching relationship, the relationship score for the matching relationship being determined based on a portion of the connected users that have expressed an interest in an entity having the matching relationship with the same entity;

selecting an expansion relationship for the particular entity, the expansion relationship being selected based on relationship scores for matching relationships, the expansion relationship being a relationship representing a set of entities of interest to a user that has expressed an interest in the particular entity;

identifying, based on the social graph, a set of additional users that have expressed an interest in an entity having the expansion relationship; and

selecting, as an audience for the content, at least a portion of the directly interested users and at least a portion of the set of additional users.

15. The system of claim 14, wherein determining a relationship score for each matching relationship comprises:

for each of at least one matching relationship;

identifying a portion of the socially connected users that are directly interested users for an entity having the matching relationship;

identifying a portion of the candidate entities having the matching relationship; and

determining the relationship score based, at least in part, on the identified portion of the socially connected users and the identified portion of the candidate entities.

17. The system of claim 14, wherein the instructions cause the data processing apparatus to perform operations comprising:

receiving bid data specifying a first value that will be paid by a content item provider for distribution of the content to users that have been deemed interested in the particular entity; and

determining, based on the bid data, a second value that the content item provider will pay for distribution of the content to the set of additional users.

18. The system of claim 17, wherein determining the second value comprises determining an expansion bid for the expansion relationship, the expansion bid value being determined based, at least in part, on the relationship score for the expansion relationship, the expansion bid value being different from a bid value for distribution of the content item to the directly interested users.

19. The system of claim 18, wherein identifying directly interested users comprises identifying users that have interacted with a positive feedback user interface element associated with content referencing the particular entity.

20. The system of claim 19, wherein identifying directly interested users comprises identifying users that have interacted with a positive feedback user interface element associated with content referencing the particular entity.