SYSTEM AND METHOD FOR LEVERAGING PROXIMITY DATA IN A WEB-BASED SOCIALLY-ENABLED KNOWLEDGE NETWORKING ENVIRONMENT

• US 20100004975A1
• Filed: 07/03/2008
• Published: 01/07/2010
• Est. Priority Date: 07/03/2008
• Status: Abandoned Application

• Current Assignee: VCVC III LLC (Vulcan, Inc.)
• Original Assignee: VCVC III LLC (Vulcan, Inc.)
• Inventors: White, Scott, Spivack, Nova
• Application Number:
  US12/168,034
• Publication Number:
  US 20100004975A1
• Time in Patent Office: Days
• US Class Current: 705/10
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: G06Q 30/0201 Market modelling; Market analysis; Collecting market data

Abstract

Systems and methods for leveraging proximity data in a web-based socially-enabled information networking environment are disclosed. In one aspect, embodiments of the present disclosure include a method, which may be implemented on a system, of semantic advertising via semantic profiles. One embodiment can include, receiving a model profile from an advertiser, enforcing a set of rules that govern accessibility of the web content, parsing the model profile to obtain a first set of model user metadata associated with the ideal set of user characteristics, comparing model user metadata of the first set of model user metadata with user metadata of a set of user metadata of a semantic user profile of a user, and generating a correlation index to indicate a degree of correlation between the model profile and the semantic user profile.

Claims

1. A method of advertisement optimization via semantic profiles, comprising:

receiving a model profile from an advertiser, the model profile represents an ideal set of user characteristics of a model user specified by the advertiser;

parsing the model profile to obtain a first set of model user metadata associated with the ideal set of user characteristics;

comparing model user metadata of the first set of model user metadata with user metadata of a set of user metadata of a semantic user profile of a user; and

generating a correlation index to indicate a degree of correlation between the model profile and the semantic user profile.

2. The method of claim 1, further comprising, identifying a first referenced entity of the first set of model user metadata and a second referenced entity of the user metadata.

3. The method of claim 2, further comprising, adjusting the correlation index to indicate an increase in the degree of correlation responsive to, identifying that a predetermined relationship exists between the first referenced entity and the second referenced entity.

4. The method of claim 2, wherein the first referenced entity is the same entity as the second referenced entity.

5. The method of claim 2, further comprising, determining a proximity distance between the user and the second referenced entity and further adjusting the correlation index to indicate an increase in the degree of correlation based on the identified proximity.

6. The method of claim 5, wherein the increase in degree of correlation is associated with a smaller proximity distance between the user and the second referenced entity.

7. The method of claim 2, further comprising:

identifying a first relationship type between the model user and the first referenced entity based on the model user metadata; and

identifying a second relationship type between the user and the second referenced entity based on the user metadata.

8. The method of claim 7, further comprising, adjusting the correlation index to indicate an increase in the degree of correlation responsive to, determining that the first relationship type and the second relationship type are of a same type or related types.

9. The method of claim 7, further comprising, adjusting the correlation index to indicate a decrease in the degree of correlation responsive to, determining that the first relationship type and the second relationship type are of substantially opposite or unrelated types.

10. The method of claim 1, wherein the model profile further comprises a second set of model user metadata that represents a non-ideal set of user characteristics of the model user specified by the advertiser.

11. The method of claim 10, further comprising, adjusting the correlation index to indicate a decrease in the degree of correlation responsive to, identifying the predetermined relationship between a third referenced entity of the second set of model user data and the second referenced entity of the user metadata.

12. The method of claim 10, further comprising, comparing model user metadata of the set of model user data with user metadata of a plurality of semantic user profiles associated with a plurality of users and determining the degree of similarities between the model profile and the plurality of users.

13. A method of generating a semantic user profile, comprising:

identifying context-independent user metadata for generating a context-independent semantic user profile;

identifying context-dependent user metadata for generating a context-dependent semantic user profile;

identifying temporal user meta-data for generating a temporal semantic user profile; and

generating the semantic user profile from at least one of the context-independent semantic user profile, the context-dependent semantic user profile, and the temporal semantic user profile.

14. The method of claim 13, further comprising, generating the semantic user profile from at least two of the context-independent semantic user profile, the context-dependent semantic user profile, and the temporal semantic user profile.

15. The method of claim 14, wherein the relative weight of the at least two of the context-independent semantic user profile, the context-dependent semantic user profile, and the temporal semantic user profile when generating the semantic user profile is represented by a weighing factor associated with each of the semantic user profiles.

16. The method of claim 15, wherein the weighing factor is one or more of, predetermined, determined on-demand, and adaptive.

17. The method of claim 13, wherein the identifying the context-independent user metadata comprises:

receiving user submission;

identifying a plurality of relationships the user has with a plurality of entities;

wherein the plurality of entities comprises one or more of, tangible, intangible and software entities; and

tracking and compiling aggregate user behavior associated with the plurality of entities.

18. The method of claim 17, further comprising, identifying a set of context-independent meta-tags from one or more of, the user input and the plurality of entities.

19. The method of claim 17, wherein the user submission comprises one or more of, a user-generated search request and a user profile entry.

20. The method of claim 17, wherein the plurality of relationships comprises semantic relationships and social relationships.

21. The method of claim 17, further comprising, tracking user click-stream activity to track and compile data related to aggregate user behavior.

22. The method of claim 20, further comprising, determining the proximity between each of the plurality of entities and the user based on the plurality of relationships.

23. The method of claim 22, further comprising, weighing a context-independent meta-tag of the set of context-independent meta-tags relative to other context-independent meta-tags based on, proximity associated with an entity of the plurality of entities from which the context-independent meta-tag is identified.

24. The method of claim 13, wherein the identifying the context-dependent user metadata comprises:

identifying context-related activity in a web-based environment that the user is currently engaged in through a web-browser;

identifying a first set of entities of the plurality of entities in the web-based environment associated with the context-related activity; and

identifying a set of context-dependent meta-tags from the first set of entities.

25. The method of claim 24, wherein context-related activity, comprises, one or more of, a web-page the user is currently viewing, an email the user is currently reading, a search the user is currently performing, a soundtrack the user is currently listening to, and a video the user is currently watching.

26. The method of claim 13, wherein the identifying the set of temporal user metadata comprises:

aggregating a set of user activity performed in the web-based environment through the web-browser within a time window;

identifying a second set of entities of the plurality of entities in the web-based environment associated with the set of user activity; and

identifying a set of temporal meta-tags from the second set of entities.

27. The method of claim 26, wherein the time window is one or more of, predetermined, user-specified, and adaptive.

28. The method of claim 27, wherein the time window is, session based, weekly-based, hourly-based, and monthly-based.

29. A method of generating a context-independent semantic user profile in a web-based environment for a user, comprising:

receiving explicit user input from the user via web-submission;

identifying a plurality of relationships the user has with a plurality of entities in the web-based environment;

wherein the plurality of entities comprises one or more of, tangible, intangible and software entities; and

tracking user click-stream history to track and collect data related to aggregate user behavior in the web-based environment.

30. The method of claim 29, further comprising, identifying a set of context-independent meta-tags from one or more of, the explicit user input and the plurality of entities.

31. The method of claim 29, wherein the explicit user input comprises one or more of, a user-generated search request and a user profile entry.

32. The method of claim 29, wherein the plurality of relationships comprises semantic relationships.

33. The method of claim 29, further comprising, determining the proximity between each of the plurality of entities and the user based on the plurality of relationships.

34. A method of generating a context-dependent semantic user profile, comprising:

identifying context-related activity in a web-based environment that the user is currently engaged in through a web-browser;

identifying a first set of entities of the plurality of entities in the web-based environment associated with the context-related activity; and

identifying a set of context-dependent meta-tags from the first set of entities.

35. A method of generating a temporal semantic user profile, comprising:

aggregating a set of user activity performed in the web-based environment through the web-browser within a time window;

identifying a second set of entities of the plurality of entities in the web-based environment associated with the set of user activity; and

identifying a set of temporal meta-tags from the second set of entities.

36. The method of claim 35, wherein the time window is one or more of, predetermined, user-specified, and adaptive.

37. A method of determining proximity between entities in a web-space, comprising:

identifying a first set of neighboring entities having one degree of separation from a central entity, each of the first set of entities have a relationship with the central entity;

wherein the relationship is one of a plurality of types;

determining a set of relative probabilities corresponding to a likelihood of a user associated with the central entity to browse to each of the first set of entities, the set of relative probabilities to be determined based on a type of relationship between each of the first set of entities and the central entity;

computing a set of absolute probabilities by normalizing the set of relative probabilities such that the sum of the absolute probabilities of the user associated with the central entity to browse to each of the first set of entities is substantially one;

wherein the proximity between the central entity and each of the first set of entities is proportional to a corresponding absolute probability of the set of absolute probabilities.

38. The method of claim 37, further comprising, determining the proximity between the central entity and a second set of neighboring entities having two degrees of separation, each of the second set of neighboring entities have a relationship with the central entity.

39. The method of claim 38, further comprising, determining the proximity between the central entity and a target entity, wherein the determining further comprises:

continuously scanning pluralities of sets of entities having one or more degrees of separation from the central entity until the target entity is identified in one of the scanned pluralities of sets of entities;

wherein each entity of the pluralities of the sets of entities having N-degrees of separation from the central entity have a relationship with at least one entity of a set of entities with (N-1) degrees of separation;

identifying a plurality of paths defined by relationships to reach the target entity from the central entity via the scanned pluralities of sets of entities;

computing individual probability of reaching the target entity from the central entity via a path of the plurality of paths by multiplying the absolute probabilities of browsing to the N^th-entity from the (N-1)^th-entities along the path of the plurality of paths; and

summing the individual probability of each path of the plurality of paths to reach the target entity from the central entity to determine the proximity between the central entity and the target entity.

40. The method of claim 37, wherein the relationship comprises a plurality of semantic relationships;

wherein the plurality of semantic relationships are of a plurality of types.

41. The method of claim 37, wherein the relationship comprises social links.

42. The method of claim 40, wherein a first type of semantic relationship differs in relative probability from a second type of semantic relationship.

43. The method of claim 37, wherein the web-space comprises one or more web-based networking environments.

44. The method of claim 37, wherein an entity includes one or more of a user, a net, and an item in the web-space.

45. The method of claim 44, wherein the item is an intangible entity, a tangible entity, or a software entity.

46. A system, comprising:

a model analyzer module to receive a model profile from an advertiser, the model profile represents a desired set of user characteristics of a model user specified by the advertiser;

a parser module communicatively coupled to the model analyzer module, when, in operation, the parser module establishes a communication session with the model analyzer and parses the model profile provided by the model analyzer module to obtain a first set of model user metadata associated with the desired set of user characteristics;

a user database to store a set of user metadata of a semantic user profile of a user;

a comparison module communicatively coupled to the user database and the parser module, when in operation, the comparison module establishes a communication session with the parser module to retrieve the model user metadata and to compare model user metadata of the set of model user metadata with user metadata of a set of user metadata of a semantic user profile of a user; and

a matching module communicatively coupled to the comparison module to generate a correlation index to indicate a degree of correlation between the model profile and the semantic user profile.

47. A system for generating a semantic user profile, comprising:

a communications module, when, in operation, establishes a communication session with a user to receive user input;

a tracking module for tracking a set of user activity;

a metadata generator module communicatively coupled to the tracking module, when, in operation, the metadata generator module identifies a set of context-independent user metadata for generating a context-independent semantic user profile;

wherein, when, in operation, the metadata generator module identifies a set of context-dependent user metadata for generating a context-dependent semantic user profile;

a timing module communicatively coupled to the user tracking module, when, in operation, the timing module establishes a communication session with the user tracking module to track an amount of time user activity is being recorded;

wherein, when, in operation, the metadata generator module identifies a set of temporal user metadata for generating a temporal semantic user profile; and

a profile generator engine communicatively coupled to the metadata generator module for generating the semantic user profile from at least one of the context-independent semantic user profile, the context-dependent semantic user profile, and the temporal semantic user profile.

48. A system for semantic advertising, comprising:

means for, receiving a model profile from an advertiser, the model profile represents a desired set of user characteristics of a model user specified by the advertiser;

means for, parsing the model profile to obtain a first set of model user metadata associated with the ideal set of user characteristics;

means for, comparing model user metadata of the first set of model user metadata with user metadata of a set of user metadata of a semantic user profile of a user; and

means for, generating a correlation index to indicate a degree of correlation between the model profile and the semantic user profile.

49. A method of optimized targeted advertising based on semantic user profiles, comprising:

receiving a model profile from an advertiser, the model profile represents an ideal set of user characteristics of a model user to whom promotional content is to be presented;

generating a set of semantic user profiles for each of a set of users;

comparing the model profile and the set of semantic user profiles;

generating a set of correlation index for indicating the degree of correlation between the model user and the set of users; and

identifying a sub-set of the set of users as candidates to whom the promotional content is to be presented.