SYSTEM AND METHOD FOR IDENTIFYING SIMILAR MEDIA OBJECTS

• US 20140040280A1
• Filed: 02/21/2013
• Published: 02/06/2014
• Est. Priority Date: 08/13/2007
• Status: Active Grant

• Current Assignee: R2 Solutions LLC (Acacia Research Corporation)
• Original Assignee: Yahoo! Inc. (Apollo Global Management, Inc.)
• Inventors: Slaney, Malcolm, White, William
• Granted Patent: US 10,152,517 B2
• Time in Patent Office: Days
• US Class Current: 707/748
• CPC Class Codes: G06F 16/24578 using ranking
• CPC Class Codes: G06F 16/634 Query by example, e.g. query by humming
• CPC Class Codes: G06F 16/637 Administration of user profiles, e.g. generation, initialization, adaptation or distribution
• CPC Class Codes: G06F 16/639 using playlists
• CPC Class Codes: G06F 16/68 Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
• CPC Class Codes: G06F 16/686 using information manually generated, e.g. tags, keywords, comments, title or artist information, time, location or usage information, user ratings

Abstract

The systems and methods described create a mathematical representation of each of the media objects for which user ratings are known. The mathematical representations take into account the subjective rating value assigned by a user to the respective media object and the user that assigned the rating value. The media object with the mathematical representation closest to that of the seed media object is then selected as the most similar media object to the seed media object. In an embodiment, the mathematical representation is a vector representation in which each user is a different dimension and each user'"'"'s rating value is the magnitude of the vector in that dimension. Similarity between two songs is determined by identifying the closest vectors to that of the seed song. Closeness may be determined by subtracting or by calculating the dot product of each of the vectors with that of the seed media object.

Claims

1-30. -30. (canceled)

31. A method, comprising:

receiving at a computing device a user request for one or more media objects similar to a seed media object, the seed media object being identified by the user request;

accessing a datastore comprising a plurality of media objects and further comprising user ratings of the plurality of media objects utilizing a processor of the computing device; and

identifying the one or more media objects similar to the seed media object utilizing the processor of the computing device at least in part by generating mathematical expressions of individual media objects of the plurality of media objects and at least in part by comparing at least a subset of the mathematical expressions, the mathematical expressions to be stored in a memory of the computing device.

32. The method of claim 31, wherein said generating mathematical expressions of individual media objects of the plurality of media objects comprises characterizing the plurality of media objects individually as vectors having a plurality of dimensions and magnitudes.

33. The method of claim 32, wherein individual dimensions of the plurality of dimensions correspond to respective user identifiers and wherein individual magnitudes of the plurality of dimensions correspond to a rating value assigned by a respective user.

34. The method of claim 33, further comprising normalizing the individual vectors of the plurality of media objects to a specified scalar value.

35. The method of claim 33, wherein said comparing the at least a subset of the mathematical expressions comprises calculating a dot product of a seed object vector with individual vectors of the plurality of media objects.

36. The method of claim 33, wherein said comparing the at least a subset of the mathematical expressions comprises calculating a Euclidian distance between a seed object vector and respective vectors of the plurality of media objects.

37. The method of claim 31, further comprising transmitting a response to the user request to a user computing device specifying the identified one or more media objects similar to the seed media object.

38. The method of claim 37, wherein said transmitting the response comprises transmitting the identified one or more media objects similar to the seed media object.

39. The method of claim 31, wherein said identifying the one or more media objects similar to the seed media object comprises filtering out one or more media objects based at least in part on one or more criteria specified by the user.

40. The method of claim 31, wherein said identifying the one or more media objects similar to the seed media object comprises filtering out one or more media objects based at least in part on past media object consumption history for the user.

41. A server computing device, comprising:

a communication module to receive a user request for one or more media objects similar to a seed media object from a user computing device, the seed media object being identified by the user request;

a processor to access a datastore comprising a plurality of media objects and further comprising user ratings of the plurality of media objects, the processor to generate mathematical expressions of individual media objects of the plurality of media objects;

a memory to store the mathematical expressions, and

a comparison engine to identify the one or more media objects similar to the seed media object at least in part comparing at least a subset of the mathematical expressions, the communication module further to transmit a response to the user request to the user computing device specifying the identified one or more media objects similar to the seed media object.

42. The server of claim 41, the processor to generate mathematical expressions of individual media objects of the plurality of media objects at least in part by characterizing the plurality of media objects individually as vectors having a plurality of dimensions and magnitudes.

43. The server of claim 42, wherein individual dimensions of the plurality of dimensions correspond to respective user identifiers and wherein individual magnitudes of the plurality of dimensions correspond to a rating value assigned by a respective user.

44. The server of claim 43, further comprising normalizing the individual vectors of the plurality of media objects to a specified scalar value.

45. The server of claim 43, the comparison engine to compare the at least a subset of the mathematical representations at least in part by calculating a dot product of a seed object vector with individual vectors of the plurality of media objects.

46. The server of claim 43, the comparison engine to comparing the at least a subset of the mathematical expressions at least in part by calculating a Euclidian distance between a seed object vector and respective vectors of the plurality of media objects.

47. The server of claim 41, the comparison engine to identify the one or more media objects similar to the seed media object at least in part by filtering out one or more media objects based at least in part on one or more criteria specified by the user and/or based at least in part on past media object consumption history for the user.

48. An article, comprising:

a non-transitory computer-readable storage medium having stored thereon instructions executable by a processor of a server computing platform to;

receive a user request for one or more media objects similar to a seed media object, the seed media object being identified by the user request;

access a datastore comprising a plurality of media objects and further comprising user ratings of the plurality of media objects; and

identify the one or more media objects similar to the seed media object at least in part by generating mathematical expressions of individual media objects of the plurality of media objects and at least in part by comparing at least a subset of the mathematical expressions.

49. The article of claim 48, wherein the computer-readable medium has stored thereon further instructions executable by the processor to generate mathematical expressions of individual media objects of the plurality of media objects at least in part by characterizing the plurality of media objects individually as vectors having a plurality of dimensions and magnitudes, wherein individual dimensions of the plurality of dimensions correspond to respective user identifiers and wherein individual magnitudes of the plurality of dimensions correspond to a rating value assigned by a respective user.

50. The article of claim 49, wherein the computer-readable medium has stored thereon further instructions executable by the processor to compare the at least a subset of the mathematical expressions at least in part by calculating a dot product of a seed object vector with individual vectors of the plurality of media objects.