Content recommendation device

• US 7,797,710 B2
• Filed: 12/15/2005
• Issued: 09/14/2010
• Est. Priority Date: 12/17/2004
• Status: Expired due to Fees

• Current Assignee: Sovereign Peak Ventures, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Panasonic Corporation (Panasonic Holdings Corporation)
• Inventors: Misaki, Masayuki, Icho, Keiji, Horii, Noriaki
• Primary Examiner(s): Kelley; Christopher
• Assistant Examiner(s): Shepard; Justin E
• Application Number:
  US11/792,826
• Publication Number:
  US 20080229360A1
• Time in Patent Office: 1,734 Days
• Field of Search: 725/34
• US Class Current: 725/32
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: H04N 21/25891 being end-user preferences retrieval of video data in a video database based on user preferences G06F16/739; arrangements for recognizing users' preferences H04H60/46; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/4532 involving end-user characteristics, e.g. viewer profile, preferences monitoring of user activities for profile generation for accessing a video database G06F16/739; user profiles in network data switching protocols H04L67/306; processing of user preferences or user profiles in wireless networks H04W8/18
• CPC Class Codes: H04N 21/454 Content or additional data filtering, e.g. blocking advertisements

Abstract

Preferences of a user are analyzed with respect to each of a plurality of pieces of content already viewed by the user, and a piece viewing motivation information that is a combination of attribute entities of the piece of content is generated. A primary viewing motivation portion and a secondary viewing motivation portion are determined from the generated pieces of viewing motivation information, and pieces of viewing motivation information having a common primary viewing motivation portion are grouped together. Content having the determined primary viewing motivation portion and the secondary viewing motivation portion is selected from content not yet viewed by the user, and content information about the selected content is presented to the user in correspondence with the primary viewing motivation portion and the secondary viewing motivation portion.

Claims

1. A content recommendation apparatus, comprising:

a preference analysis unit operable to, with respect to each respective piece of content of a plurality of pieces of content already viewed by a user, (i) analyze a preference of the user, and (ii) generate a piece of viewing motivation information that is a combination of attribute entities of the respective piece of content;

a motivation analysis unit operable to, with respect to each respective generated piece of viewing motivation information of the generated pieces of viewing motivation information, (i) determine a primary viewing motivation portion of the respective generated piece of viewing motivation information that shows a portion of the respective generated piece of viewing motivation information that particularly motivated the user to view the respective piece of content, and (ii) divide the respective generated piece of viewing motivation information into the primary viewing motivation portion and a secondary viewing motivation portion;

a hierarchical structuring unit operable to cause a common primary viewing motivation portion of the primary viewing motivation portions of the generated pieces of viewing motivation information to be shared, and arrange the secondary viewing motivation portion below the common primary viewing motivation portion, so as to put the common primary viewing motivation portion and the secondary viewing motivation portion into a hierarchical structure;

a selection unit operable to select one or more pieces of content having a combination of the primary viewing motivation portion and the secondary viewing motivation portion as attribute entities; and

a presentation unit operable to present, to the user, content information of the selected one or more pieces of content in correspondence with the primary viewing motivation portion and the secondary viewing motivation portion that have been put into the hierarchical structure,

wherein each respective generated piece of viewing motivation information is a combination of attribute entities that, from among combinations of attribute entities of the respective piece of content, appears with a frequency equal to or higher than a predetermined threshold value in the content information of the plurality of pieces of already-viewed content.

2. The content recommendation apparatus of claim 1,

wherein the primary viewing motivation portion of a respective generated piece of viewing motivation information is a combination of attribute entities that, from among combinations of attribute entities included in the respective generated piece of viewing motivation information, are included most frequently in other generated pieces of viewing motivation information generated by the preference analysis unit, and

wherein the secondary viewing motivation portion of the respective generated piece of viewing motivation information is a combination of attribute entities included in the respective generated piece of viewing motivation information other than the attribute entities determined as the primary viewing motivation portion of the respective generated piece of viewing motivation information.

3. The content recommendation apparatus of claim 1,

wherein the primary viewing motivation portion of a respective generated piece of viewing motivation information is a combination of attribute entities that are most frequently appearing combinations of attribute entities included in the generated pieces of viewing motivation information, and

wherein the secondary viewing motivation portion of the respective generated piece of viewing motivation information is a combination of attribute entities included in the respective generated piece of viewing motivation information other than the attribute entities determined as the primary viewing motivation portion of the respective generated piece of viewing motivation information.

4. The content recommendation apparatus of claim 1,

wherein the content recommendation apparatus further comprises a clock unit operable to clock time,

wherein each respective piece of the plurality of already-viewed pieces of content corresponds to a date and time of viewing, and

wherein each respective generated piece of viewing motivation information of each respective piece of the plurality of already-viewed pieces of content is a combination of attribute entities, from among combinations of attribute entities of content, for which, in a predetermined period of time, a ratio of (a) appearance times in the content information of the already-viewed pieces of content and (b) appearance times in the content information of all content is equal to or greater than a predetermined threshold value.

5. The content recommendation apparatus of claim 4,

wherein the primary viewing motivation portion of a respective generated piece of viewing motivation information is a combination of attribute entities that, in the generated pieces of viewing motivation information in the predetermined period of time, are most frequently included in the content information of content viewed within a period of time that is longer that the predetermined period of time, and

wherein the secondary viewing motivation portion of the respective generated piece of viewing motivation information is a combination of attribute entities included in the respective generated piece of viewing motivation information other than the attribute entities determined as the primary viewing motivation portion of the respective generated piece of viewing motivation information.

6. The content recommendation apparatus of claim 4,

wherein the primary viewing motivation portion of a respective generated piece of viewing motivation information is a combination of attribute entities that, in the generated pieces of viewing motivation information in the predetermined period of time, are included in the content information of a piece of content having an oldest date and time that is before a predetermined point in time, and

wherein the secondary viewing motivation portion of the respective generated piece of viewing motivation information is a combination of attribute entities included in the respective generated piece of viewing motivation information other than the attribute entities determined as the primary viewing motivation portion of the respective generated piece of viewing motivation information.

7. The content recommendation apparatus of claim 1, wherein the preference analysis unit includes a keyword extraction subunit operable to, based on the generated pieces of viewing motivation information, extract a characteristic keyword from newest information attached to content, or advertisement information.

8. The content recommendation apparatus of claim 1,

wherein the content recommendation apparatus further comprises an information retrieval unit operable to, based on the generated pieces of viewing motivation information, retrieve information via a network, and

wherein the selected one or more pieces of content includes the information retrieved by the information retrieval unit.

9. A content recommendation method, comprising

analyzing by a processor, with respect to each respective piece of content of a plurality of pieces of content already viewed by a user, a preference of the user;

generating, with respect to each respective piece of content of the plurality of pieces of content already viewed by the user, a piece of viewing motivation information that is a combination of attribute entities of the respective piece of content;

determining, with respect to each respective generated piece of viewing motivation information of the generated pieces of motivation information, a primary viewing motivation portion of the respective generated piece of viewing motivation information that shows a portion of the respective generated piece of viewing motivation information that particularly motivated the user to view the respective piece of content;

dividing, with respect to each respective generated piece of viewing motivation information, the respective generated piece of viewing motivation information into the primary viewing motivation portion and a secondary viewing motivation portion;

hierarchical structuring to cause a common primary viewing motivation portion of the primary viewing motivation portions of the generated pieces of viewing motivation information to be shared, and arrange the secondary viewing motivation portion below the common primary viewing motivation portion, thereby putting so as to put the common primary viewing motivation portion and the secondary viewing motivation portion into a hierarchical structure;

selecting one or more pieces of content having a combination of the primary viewing motivation portion and the secondary viewing motivation portion as attribute entities; and

presenting, to the user, content information of the selected one or more pieces of content in correspondence with the primary viewing motivation portion and the secondary viewing motivation portion that have been put into the hierarchical structure,

wherein each respective generated piece of viewing motivation information is a combination of attribute entities that, from among combinations of attribute entities of the respective piece of content, appears with a frequency equal to or higher than a predetermined threshold value in the content information of the plurality of pieces of already-viewed content.

10. A computer-readable recording medium having a program recorded thereon, the program causing a computer to execute a method comprising:

analyzing, with respect to each respective piece of content of a plurality of pieces of content already viewed by a user, a preference of the user;

generating, with respect to each respective piece of content of the plurality of pieces of content already viewed by the user, a piece of viewing motivation information that is a combination of attribute entities of the respective piece of content;

determining, with respect to each respective generated piece of viewing motivation information of the generated pieces of motivation information, a primary viewing motivation portion of the respective generated piece of viewing motivation information that shows a portion of the respective generated piece of viewing motivation information that particularly motivated the user to view the respective piece of content;

dividing, with respect to each respective generated piece of viewing motivation information, the respective generated piece of viewing motivation information into the primary viewing motivation portion and a secondary viewing motivation portion;

hierarchical structuring to cause a common primary viewing motivation portion of the primary viewing motivation portions of the generated pieces of viewing motivation information to be shared, and arrange the secondary viewing motivation portion below the common primary viewing motivation portion, so as to put the common primary viewing motivation portion and the secondary viewing motivation portion into a hierarchical structure;

selecting one or more pieces of content having a combination of the primary viewing motivation portion and the secondary viewing motivation portion as attribute entities; and

presenting, to the user, content information of the selected one or more pieces of content in correspondence with the primary viewing motivation portion and the secondary viewing motivation portion that have been put into hierarchical structure,

wherein each respective generated piece of viewing motivation information is a combination of attribute entities that, from among combinations of attribute entities of the respective piece of content, appears with a frequency equal to or higher than a predetermined threshold value in the content information of the plurality of pieces of already-viewed content.

11. A content recommendation integrated circuit, comprising:

a preference analysis unit operable to, with respect to each respective piece of content of a plurality of pieces of content already viewed by a user, (i) analyze a preference of the user, and (ii) generate a piece of viewing motivation information that is a combination of attribute entities of the respective piece of content;

a motivation analysis unit operable to, with respect to each respective generated piece of viewing motivation information of the generated pieces of viewing motivation information, (i) determine a primary viewing motivation portion of the respective generated piece of viewing motivation information that shows a portion of the respective generated piece of viewing motivation information that particularly motivated the user to view the respective piece of content, and (ii) divide the respective generated piece of viewing motivation information into the primary viewing motivation portion and a secondary viewing motivation portion;

a hierarchical structuring unit operable to cause a common primary viewing motivation portion of the primary viewing motivation portions of the generated pieces of viewing motivation information to be shared, and arrange the secondary viewing motivation portion below the common primary viewing motivation portion, so as to put the common primary viewing motivation portion and the secondary viewing motivation portion into a hierarchical structure;

a selection unit operable to select one or more pieces of content having a combination of the primary viewing motivation portion and the secondary viewing motivation portion as attribute entities; and

a presentation unit operable to present, to the user, content information of the selected one or more pieces of content in correspondence with the primary viewing motivation portion and the secondary viewing motivation portion that have been put into the hierarchical structure,

wherein each respective generated piece of viewing motivation information is a combination of attribute entities that, from among combinations of attribute entities of the respective piece of content, appears with a frequency equal to or higher than a predetermined threshold value in the content information of the plurality of pieces of already-viewed content.