Auto playlist generator
First Claim
1. A system having processor and memory associated therewith for generating one or more lists, the system comprising:
- means for learning, the means for learning employing descriptive metadata from a training set of media objects to learn;
means for generating a fingerprint of a media object from a plurality of descriptive metadata attributes, at least one of the plurality of descriptive metadata attributes being a subjective attribute;
means for comparing the fingerprint to a reference fingerprint to produce an output indicative of the similarity between the fingerprints;
means for translating the output into a similarity value, wherein the means for translating is generated at least in part by the means for learning; and
means for generating a list of similar media objects based on the similarity value, wherein the similarity value is a difference vector, where the difference is taken between two different feature vectors, each of which describes an item in the media library data store and a training item.
2 Assignments
0 Petitions
Accused Products
Abstract
A system and method for generating a list is provided. The system includes a seed item input subsystem, an item identifying subsystem, a descriptive metadata similarity determining subsystem and a list generating subsystem that builds a list based, at least in part, on similarity processing performed on seed item descriptive metadata and user item descriptive metadata and user selected thresholds applied to such similarity processing. The method includes inexact matching between identifying metadata associated with new user items and identifying metadata stored in a reference metadata database. The method further includes subjecting candidate user items to similarity processing, where the degree to which the candidate user items are similar to the seed item is determined, and placing user items in a list of items based on user selected preferences for (dis)similarity between items in the list and the seed item.
-
Citations
11 Claims
-
1. A system having processor and memory associated therewith for generating one or more lists, the system comprising:
-
means for learning, the means for learning employing descriptive metadata from a training set of media objects to learn; means for generating a fingerprint of a media object from a plurality of descriptive metadata attributes, at least one of the plurality of descriptive metadata attributes being a subjective attribute; means for comparing the fingerprint to a reference fingerprint to produce an output indicative of the similarity between the fingerprints; means for translating the output into a similarity value, wherein the means for translating is generated at least in part by the means for learning; and means for generating a list of similar media objects based on the similarity value, wherein the similarity value is a difference vector, where the difference is taken between two different feature vectors, each of which describes an item in the media library data store and a training item. - View Dependent Claims (2, 3, 4, 5, 6, 7)
-
-
8. A method for generating one or more lists, the system comprising:
-
generating a fingerprint of a media object from a plurality of descriptive metadata attributes, at least one of the plurality of descriptive metadata attributes being a subjective attribute; comparing the fingerprint of the training media object to the fingerprint of a media object in the user data store to produce an output indicative of the similarity between the fingerprints; translating the output into a similarity value; and generating a list of similar media objects based on the similarity value, wherein the similarity value is a difference vector, where the difference is taken between two different feature vectors, each of which describes an item in the media library data store and a training item. - View Dependent Claims (9, 10, 11)
-
Specification