Techniques to filter media content based on entity reputation

• US 8,566,262 B2
• Filed: 05/18/2012
• Issued: 10/22/2013
• Est. Priority Date: 04/07/2008
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Deyo, Roderic C.
• Primary Examiner(s): Gaffin, Jeffrey A
• Assistant Examiner(s): OLUDE AFOLABI, OLATOYOSI
• Application Number:
  US13/474,760
• Publication Number:
  US 20120278264A1
• Time in Patent Office: 522 Days
• Field of Search: 706/12, 705/1
• US Class Current: 706/12
• CPC Class Codes: G06Q 10/10 Office automation; Time management

Abstract

Techniques to filter media content based on entity reputation are described. An apparatus may comprise a reputation subsystem that manages an entity reputation score for an entity. The reputation subsystem comprising a reputation manager component and a reputation input/output (I/O) component. The reputation manager component may include a data collection module that collects reputation information for an entity from a selected set of multiple reputation sources. The reputation manager component may also comprise a feature manager module, communicatively coupled to the data collection module, that extracts a selected set of reputation features from the reputation information. The reputation manager component may further comprise a reputation scoring module, communicatively coupled to the feature manager module, that generates an entity reputation score based on the reputation features using a supervised or unsupervised machine learning algorithm. Other embodiments are described and claimed.

Claims

1. A method comprising:

collecting reputation information for an entity from a selected set of multiple reputation sources;

extracting a set of reputation features from the reputation information, the reputation features representing at least one of an encounter or a transaction between entity members of a digital online community;

creating and persistently storing indexed reputation features from the reputation information; and

generating an entity reputation score based on a probability estimate based on past community ratings of previous transactions or encounters.

2. The method of claim 1, wherein the probability estimate represents an estimate for the probability of whether an entity'"'"'s next encounter or transaction will receive a positive rating from another entity.

3. The method of claim 2, comprising:

fixing a set of entities in the digital online community from which to determine reputation, including at least a first entity and a second entity;

initializing a set of relations between ordered pairs of entities from the set of entities;

representing the set of entities and the set of relations as a directed graph having the entities as nodes and the relations as directed edges, wherein a directed relation describes an encounter or transaction between two entities;

determining a reputation for the first entity as a conditional probability that the second entity having an encounter with the first entity will report a positive rating;

using the community reputation information to generate an entity reputation score from the determined reputations; and

performing activity scoring based on keeping track of events and performing accounting and rollup operations to generate the final entity reputation score.

4. The method of claim 1, comprising receiving a request for the entity reputation score from a content server for use in determining whether to allow the entity to submit media content to the content server.

5. The method of claim 1, comprising sending the entity reputation score to a content server for use in filtering media content submitted by the entity.

6. The method of claim 1, comprising filtering media content submitted by the entity based on the entity reputation score.

7. An apparatus, comprising:

a processing unit;

a reputation subsystem executing on the processing unit operative to manage an entity reputation score for an entity, the reputation subsystem comprising a reputation manager component and a reputation input/output component, the reputation manager component comprising;

a data collection module executing on the processing unit operative to collect reputation information for an entity from a selected set of multiple reputation sources;

a feature manager module executing on the processing unit and communicatively coupled to the data collection module, the feature manager module operative to extract a set of reputation features from the reputation information, the reputation features representing at least one of an encounter or a transaction between entity members of a digital online community, and to create and persistently store indexed reputation features from the reputation information; and

a reputation scoring module executing on the processing unit and communicatively coupled to the feature manager module, the reputation scoring module operative to generate an entity reputation score based on a probability estimate based on past community ratings of previous transactions or encounters.

8. The apparatus of claim 7, wherein the probability estimate represents an estimate for the probability of whether an entity'"'"'s next encounter or transaction will receive a positive rating from another entity.

9. The apparatus of claim 8, the reputation scoring module to:

fix a set of entities in the digital online community from which to determine reputation, including at least a first entity and a second entity;

initialize a set of relations between ordered pairs of entities from the set of entities;

represent the set of entities and the set of relations as a directed graph having the entities as nodes and the relations as directed edges, wherein a directed relation describes an encounter between two entities;

determine a reputation for the first entity as a conditional probability that the second entity having an encounter with the first entity will report a positive rating;

use the community reputation information to generate an entity reputation score from the determined reputations; and

perform activity scoring based on keeping track of events and performing accounting and rollup operations to generate the final entity reputation score.

10. The apparatus of claim 7, the reputation input/output component to receive a request for the entity reputation score from a content server for use in determining whether to allow the entity to submit media content to the content server.

11. The apparatus of claim 7, the reputation input/output component to send the entity reputation score to a content server for use in filtering media content submitted by the entity.

12. The apparatus of claim 7, comprising a content filter to receive the entity reputation score, compare the entity reputation score with a defined reputation threshold score to find an entity result value, and filter media content based on the entity result value.

13. An article comprising a non-transitory storage medium containing instructions that when executed cause a system to:

collect reputation information for an entity from a selected set of multiple reputation sources;

extract a set of reputation features from the reputation information, the reputation features representing at least one of an encounter or a transaction between entity members of a digital online community;

create and persistently store indexed reputation features from the reputation information; and

generate an entity reputation score based on a probability estimate that is based on past community ratings of previous transactions or encounters.

14. The article of claim 13, wherein the probability estimate represents an estimate for the probability of whether an entity'"'"'s next encounter or transaction will receive a positive rating from another entity.

15. The article of claim 14, further comprising instructions that when executed cause the system to:

fix a set of entities in the digital online community from which to determine reputation, including at least a first entity and a second entity;

initialize a set of relations between ordered pairs of entities from the set of entities;

represent the set of entities and the set of relations as a directed graph having the entities as nodes and the relations as directed edges, wherein a directed relation describes an encounter between two entities;

determine a reputation for the first entity as a conditional probability that the second entity having an encounter with the first entity will report a positive rating;

use the community reputation information to generate an entity reputation score from the determined reputations; and

perform activity scoring based on keeping track of events and performing accounting and rollup operations to generate the final entity reputation score.

16. The article of claim 13, further comprising instructions that when executed cause the system to receive a request for the entity reputation score from a content server for use in determining whether to allow the entity to submit media content to the content server.

17. The article of claim 13, further comprising instructions that when executed cause the system to send the entity reputation score to a content server for use in filtering media content submitted by the entity.

18. The article of claim 13, further comprising instructions that when executed cause the system to filter media content submitted by the entity based on the entity reputation score.