Method and apparatus for providing recommendation channels

• US 8,621,563 B2
• Filed: 03/29/2011
• Issued: 12/31/2013
• Est. Priority Date: 03/29/2011
• Status: Active Grant

• Current Assignee: Beijing Xiaomi Mobile Software Co., Ltd. (Xiaomi Corp.)
• Original Assignee: Nokia Corporation
• Inventors: Sathish, Sailesh Kumar
• Primary Examiner(s): Song, Hosuk
• Application Number:
  US13/074,380
• Publication Number:
  US 20120254970A1
• Time in Patent Office: 1,008 Days
• Field of Search: 726 1- 9, 725/1, 725 25- 30, 725 37- 40, 725 52- 57
• US Class Current: 726/2
• CPC Class Codes: G06F 16/90335 Query processing
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

An approach is presented for providing recommendation channels. A recommendation platform receives an input for creating at least one recommendation channel, the input specifying at least one category. Next, the recommendation platform determines one or more tokens based, at least in part, on the at least one category, wherein at least one of the one or more tokens represents context information. Then, the recommendation platform determines to create the at least one recommendation channel based, at least in part, on the one or more tokens.

Claims

1. A method comprising facilitating a processing of and/or processing (1) data and/or (2) information and/or (3) at least one signal, the (1) data and/or (2) information and/or (3) at least one signal based, at least in part, on the following:

an input for creating at least one recommendation channel, the input specifying at least one category;

at least one determination, by at least one processor, of one or more tokens based, at least in part, on the at least one category, wherein at least one of the one or more tokens represents context information; and

at least one determination to create the at least one recommendation channel based, at least in part, on the one or more tokens.

2. A method of claim 1, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a processing of the one or more tokens to determine one or more other tokens; and

at least one determination to associate the one or more other tokens to the at least one recommendation channel.

3. A method of claim 2, wherein the processing and/or facilitating of a processing of the one or more tokens comprises, at least in part, application of one or more language models.

4. A method of claim 1, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination of one or more data structures based, at least in part, on the one or more tokens,

wherein the one or more data structures store, at least in part, content information relevant to the at least one recommendation channel.

5. A method of claim 4, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a processing of the content information to populate the at least one or more data structures based, at least in part, on a comparison of the content information against the one or more tokens.

6. A method of claim 5, wherein the populating of the one or more data structures is based, at least in part, on one or more heuristics.

7. A method of claim 5, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a parsing of the content information to determine relevance information with respect to the one or more tokens,

wherein the populating of the one or more data structures is based, at least in part, on the relevance information.

8. A method of claim 7, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination to generate a frequency distribution of the one or more tokens with respect to the content information,

wherein the relevance information is based, at least in part, on the frequency distribution.

9. A method of claim 8, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

at least one determination to update the one or more tokens based, at least in part, on the frequency distribution.

10. A method of claim 1, wherein the (1) data and/or (2) information and/or (3) at least one signal are further based, at least in part, on the following:

a request, from a user, for a recommendation;

at least one determination of other context information associated with the user, a device associated with the user, or a combination thereof; and

a processing of the request, the other context information, the at least one recommendation channel, the one or more tokens, or a combination thereof to generate the recommendation.

11. An apparatus comprising:

at least one processor; and

at least one memory including computer program code for one or more programs,

the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,

receive an input for creating at least one recommendation channel, the input specifying at least one category;

determine one or more tokens based, at least in part, on the at least one category, wherein at least one of the one or more tokens represents context information; and

determine to create the at least one recommendation channel based, at least in part, on the one or more tokens.

12. An apparatus of claim 11, wherein the apparatus is further caused to:

process and/or facilitate a processing of the one or more tokens to determine one or more other tokens; and

determine to associate the one or more other tokens to the at least one recommendation channel.

13. An apparatus of claim 12, wherein the processing of the one or more tokens comprises, at least in part, application of one or more language models.

14. An apparatus of claim 11, wherein the apparatus is further caused to:

determine one or more data structures based, at least in part, on the one or more tokens,

wherein the one or more data structures store, at least in part, content information relevant to the at least one recommendation channel.

15. An apparatus of claim 14, wherein the apparatus is further caused to:

process and/or facilitate a processing of the content information to populate the one or more data structures based, at least in part, on a comparison of the content information against the one or more tokens.

16. An apparatus of claim 15, wherein the populating of the one or more data structures is based, at least in part, on one or more heuristics.

17. An apparatus of claim 15, wherein the apparatus is further caused to:

cause, at least in part, parsing of the content information to determine relevance information with respect to the one or more tokens,

wherein the populating of the one or more data structures is based, at least in part, on the relevance information.

18. An apparatus of claim 17, wherein the apparatus is further caused to:

determine to generate a frequency distribution of the one or more tokens with respect to the content information,

wherein the relevance information is based, at least in part, on the frequency distribution.

19. An apparatus of claim 18, wherein the apparatus is further caused to:

determine to update the one or more tokens based, at least in part, on the frequency distribution.

20. An apparatus of claim 11, wherein the apparatus is further caused to:

receive a request, from a user, for a recommendation;

determine other context information associated with the user, a device associated with the user, or a combination thereof; and

process and/or facilitate a processing of the request, the other context information, the at least one recommendation channel, the one or more tokens, or a combination thereof to generate the recommendation.