Affinity propagation in adaptive network-based systems
First Claim
1. An apparatus, comprising:
- a structural aspect comprising objects;
a usage aspect comprising usage behaviors that correspond to usage behavior categories; and
logic circuitry configured to;
identify affinities between the objects based on the usage behaviors;
derive an influence metric based on the affinities between the objects; and
identify a subset of the objects based on the influence metric;
wherein the influence metric comprises first degree and second degree influences.
3 Assignments
0 Petitions
Accused Products
Abstract
Adaptive applications of affinity propagation are described to facilitate effective and computationally efficient means of clustering computer-based objects such as items of content, and/or to determine exemplars associated with a set of objects. Affinity propagation is also applied by the present invention to define system user affinity groups and/or exemplar users. The present invention applies usage behaviors as a basis for influencing clustering through methods such as initializing exemplar attractor values based on usage behaviors and/or basing similarity values between pairs of objects or users on usage behaviors associated with system objects, or usage behaviors that are associated with, directly or indirectly, specific system users.
201 Citations
30 Claims
-
1. An apparatus, comprising:
-
a structural aspect comprising objects; a usage aspect comprising usage behaviors that correspond to usage behavior categories; and logic circuitry configured to; identify affinities between the objects based on the usage behaviors; derive an influence metric based on the affinities between the objects; and identify a subset of the objects based on the influence metric; wherein the influence metric comprises first degree and second degree influences. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8, 9)
-
-
10. An apparatus, comprising:
-
a structural aspect comprising objects; a usage aspect comprising a plurality of usage behaviors that correspond to a plurality of usage behavior categories; and a computing device configured to; identify affinities between the objects based on the plurality of usage behaviors; derive an influence metric based on the affinities between the objects; and identify a subset of the objects based on the influence metric; wherein the influence metric comprises first degree and second degree influences. - View Dependent Claims (11, 12, 13)
wherein the computing device is configured to generate the influence metric based on different degrees of separation of the affinities from the users.
-
-
12. The apparatus of claim 11, wherein the computing device is configured to identify the affinities between the users based on affinity propagation message values associated with the users.
-
13. The apparatus of claim 10, wherein the computing device is configured to initialize exemplar attractor values based on the influence metric.
-
14. A method, comprising:
-
accessing, by a computing device, a structural aspect comprising objects; accessing, by the computing device, a usage aspect comprising usage behaviors that correspond to a plurality of usage behavior categories; and identifying, by the computing device, a subset of the structural aspect by initializing exemplar attractor values for the objects based on an influence metric derived from the plurality of usage behaviors; wherein the influence metric comprises first degree and second degree influences. - View Dependent Claims (15, 16, 17, 18, 19, 20)
-
-
21. A method, comprising:
-
identifying, by a computing device, a structural aspect comprising objects; identifying, by the computing device, a usage aspect comprising usage behaviors that correspond to usage behavior categories; identifying, by the computing device, affinities between the objects based on the usage behaviors; deriving, by the computing device, an influence metric based on the affinities between the objects; and identifying, by the computing device, a subset of the objects based on the influence metric; wherein the influence metric comprises first degree and second degree influences. - View Dependent Claims (22, 23, 24, 25, 26, 27, 28, 29, 30)
-
Specification