Contents' relationship visualizing apparatus, contents' relationship visualizing method and its program

• US 9,026,643 B2
• Filed: 10/06/2010
• Issued: 05/05/2015
• Est. Priority Date: 10/14/2009
• Status: Active Grant

• Current Assignee: Sony Corporation (Sony Group Corp.)
• Original Assignee: Sony Corporation (Sony Group Corp.)
• Inventors: Ishioka, Takuya
• Primary Examiner(s): DOAN, DUYEN MY
• Application Number:
  US12/899,036
• Publication Number:
  US 20110087773A1
• Time in Patent Office: 1,672 Days
• Field of Search: 709/224, 707748-751
• US Class Current: 709/224
• CPC Class Codes: G06F 16/26 Visual data mining; Browsing structured data

Abstract

There is provided a contents'"'"' relationship visualizing apparatus including a usage history acquiring unit for acquiring usage histories of multiple contents, a users'"'"' set specifying unit for specifying a content'"'"'s users'"'"' set indicating users utilizing each content by use of the contents'"'"' usage histories, a similarity calculating unit for calculating a similarity between the specified users'"'"' sets by use of a similarity index, and a network creating unit for creating a network indicating a relationship between the contents by use of the calculated similarity between the users'"'"' sets.

Claims

1. A contents'"'"' relationship visualizing apparatus comprising:

at least one memory storing instructions; and

at least one processor programmed via the instructions to;

acquire a usage history comprising, for each one of a plurality of items of content, a user set comprising a plurality of elements each corresponding to a user who has utilized the one item of content;

compare the plurality of elements in each user set to identify a set of elements common to each user set;

calculate a similarity between the user sets by comparing the elements common to each user set to at least one of a total number of elements in at least one user set, a minimum number of elements contained in each user set, and a distance between the user sets;

generate information representing a network, the network indicating one or more relationships between the plurality of items of content along a time-line comprising a plurality of usage time periods, the one or more relationships being based at least in part on the calculated similarity between the user sets.

2. The contents'"'"' relationship visualizing apparatus according to claim 1, wherein the at least one processor is programmed to extract a partial network meeting a predetermined reference from the network.

3. The contents'"'"' relationship visualizing apparatus according to claim 2, wherein the at least one processor is programmed to extract the partial network made of contents whose similarity between users'"'"' sets meets the predetermined reference from the network.

4. The contents'"'"' relationship visualizing apparatus according to claim 2, wherein the at least one processor is programmed to extract the partial network made of contents belonging to a cluster meeting the predetermined reference from the network.

5. The contents'"'"' relationship visualizing apparatus according to claim 2, wherein the at least one processor is programmed to extract the partial network made of contents having a characteristic meeting the predetermined reference from the network.

6. The contents'"'"' relationship visualizing apparatus according to claim 1, wherein the at least one processor is programmed to aggregate multiple contents meeting a predetermined reference into one content and aggregating usage histories of the multiple contents into one usage history.

7. The contents'"'"' relationship visualizing apparatus according to claim 1, wherein the usage history for each one of the plurality of items of content possesses attributes corresponding to the one item'"'"'s user set.

8. The contents'"'"' relationship visualizing apparatus according to claim 1, wherein the generated information is usable by a device to display the network indicating an item of content using a node and indicating a relationship between items of content using a link connecting the nodes.

9. The contents'"'"' relationship visualizing apparatus according to claim 1, wherein the plurality of usage time periods are mutually exclusive.

10. The contents'"'"' relationship visualizing apparatus according to claim 1, wherein the at least one processor is programmed to calculate a similarity between the user sets by comparing the elements common to each set to a total number of elements in at least one set to calculate a Jaccard coefficient, by comparing the elements common to each set to a minimum number of elements contained in each set to calculate a Simpson'"'"'s coefficient, and/or by comparing the elements common to each set to a distance between the sets to calculate a cosine similarity.

11. The contents'"'"' relationship visualizing apparatus according to claim 1, wherein the at least one processor is programmed to calculate a similarity between the user sets using any one similarity index among Pearson'"'"'s product-moment correlation coefficient, Euclidean distance, Mahalanobis distance and kernel function.

12. A contents'"'"' relationship visualizing method, the method comprising:

determining, using at least one processor, a usage history comprising, for each one of a plurality of items of content, a user set comprising a plurality of elements each corresponding to a user who has utilized the one item of content;

comparing, using the at least one processor, the plurality of elements in each user set to identify a set of elements common to each user set;

calculating, using the at least one processor, a similarity between the user sets by comparing the elements common to each user set to at least one of a total number of elements in at least one user set, a minimum number of elements contained in each user set, and a distance between the user sets; and

generating, using the at least processor, information representing a network, the network indicating one or more relationships between the plurality of items of content along a time-line comprising a plurality of usage time periods, the one or more relationships being based at least in part on the calculated similarity between the user sets; and

providing the generated information to a device configured to visually display the network.

13. At least one non-transitory computer-readable medium having encoded thereon instructions which, when executed, cause a computer to perform a contents'"'"' relationship visualizing method, the method comprising:

acquiring a usage history comprising, for each one of a plurality of items of content, a user set comprising a plurality of elements each corresponding to a user who has utilized the one item of content;

comparing the plurality of elements in each user set to identify a set of elements common to each user set;

calculating a similarity between the user sets by comparing the elements common to each user set to at least one of a total number of elements in at least one user set, a minimum number of elements contained in each user set, and a distance between the user sets; and

generating information representing a network, the network indicating one or more relationships between the plurality of items of content along a time-line comprising a plurality of usage time periods, the one or more relationships being based at least in part on the calculated similarity between the user sets.