METHOD AND APPARATUS FOR PROVIDING RULE-BASED RECOMMENDATIONS

• US 20120303561A1
• Filed: 05/25/2011
• Published: 11/29/2012
• Est. Priority Date: 05/25/2011
• Status: Active Grant

• Current Assignee: Nokia Technologies Oy (Nokia Corporation)
• Original Assignee: Nokia Corporation
• Inventors: Sathish, Sailesh Kumar
• Granted Patent: US 9,129,225 B2
• Time in Patent Office: Days
• US Class Current: 706/14
• CPC Class Codes: G06F 16/954 Navigation, e.g. using categorised browsing
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 3/004 Artificial life, i.e. computing arrangements simulating life
• CPC Class Codes: G06N 5/025 Extracting rules from data
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06N 7/01 Probabilistic graphical models, e.g. probabilistic networks
• CPC Class Codes: G06Q 30/0282 Rating or review of business operators or products

Abstract

An approach is provided for providing rule-based recommendations. The approach involves a processing of one or more user profile tags, context tags, content tags, channel tags and/or other context information. The approach further involves a determination of one or more weighting factors of one or more of the user profile tags, context tags, content tags, channel tags and other context information. The approach also involves an application of one or more rule sets that bases a determination of a recommendation on the weighting factor. The approach, then, generates one or more recommendations.

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:

a processing of one or more user profile tags, context tags, content tags, channel tags, other context information or any combination thereof;

a determination of one or more weighting factors of one or more of the user profile tags, context tags, content tags, channel tags and other context information;

an application of one or more rule sets that bases a determination of a recommendation on the weighting factor; and

a generation of one or more recommendations.

2. A method according 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 a determination to link two or more rule sets to address two or more context scenarios;

a processing of a determination of one or more context combinations of the two or more context scenarios; and

a generation of the at least one recommendation based on the linked rule sets and the determined combination of context scenarios.

3. 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 a dynamic addition, removal, modification, or combination thereof of the one or more rule sets by way of an administrative interface.

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:

building a user profile based on one or more interactions with the recommendation; and

a processing of a modification of the one or more weighting factors based on the user profile.

5. 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 a determination of the weighting factor to be between 0 and 1, a multiplier, an addition, or a negative number.

6. A method of claim 5, wherein the rule set defines a type of context and the weighting factor to apply for generating the one or more recommendations.

7. A method of claim 1, wherein the context tags are one or more of location specific tags provided by a location resolver, time specific tags provided by a time resolver, other context tags provided by context specific resolvers, and the user profile tags are provided by a profile engine.

8. 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 determination of a limitation of a number of tags that are processed, the limitation being set by a user preference or a default value; and

a determination of tags having the most heavily weighted weighting factors that satisfy the limited number of tags,

wherein the application of the one or more rule sets bases the determination of the one or more recommendations on the limited number of tags having the most heavily weighted weighting factors.

9. 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 determination to query a recommendation engine for one or more recommendation tokens from a database.

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:

an output of three sets of tags, each of which are context specific tags, profile specific tags and a combination of context and profile tags; and

embedding the type of tags that are output in a response to the query.

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;

process and/or facilitate a processing of one or more user profile tags, context tags, content tags, channel tags, other context information or any combination thereof;

cause, at least in part, a determination of one or more weighting factors of one or more of the user profile tags, context tags, content tags, channel tags and other context information;

cause, at least in part, an application of one or more rule sets that bases a determination of a recommendation on the weighting factor; and

cause, at least in part, generation of one or more recommendations.

12. An apparatus of claim 11, wherein the apparatus is further caused to perform at least the following:

process and/or facilitate a processing of a determination to link two or more rule sets to address two or more context scenarios;

process and/or facilitate a processing of a determination of one or more context combinations of the two or more context scenarios; and

cause, at least in part, a generation of the at least one recommendation based on the linked rule sets and the determined combination of context scenarios.

13. An apparatus of claim 11, wherein the apparatus is further caused to perform at least the following:

process and/or facilitate a processing of a dynamic addition, removal, modification, or combination thereof of the one or more rule sets by way of an administrative interface.

14. An apparatus of claim 11, wherein the apparatus is further caused to perform at least the following:

cause, at least in part, building a user profile based on one or more interactions with the recommendation; and

process and/or facilitate a processing of a modification of the one or more weighting factors based on the user profile.

15. An apparatus of claim 11, wherein the apparatus is further caused to perform at least the following:

process and/or facilitate a processing of a determination of the weighting factor to be between 0 and 1, a multiplier, an addition, or a negative number.

16. An apparatus of claim 15, wherein the rule set defines a type of context and the weighting factor to apply for generating the one or more recommendations.

17. An apparatus of claim 11, wherein the context tags are one or more of location specific tags provided by a location resolver, time specific tags provided by a time resolver, other context tags provided by context specific resolvers, and the user profile tags are provided by a profile engine.

18. An apparatus of claim 11, wherein the apparatus is further caused to perform at least the following:

cause, at least in part, a determination of a limitation of a number of tags that are processed, the limitation being set by a user preference or a default value; and

cause, at least in part, a determination of tags having the most heavily weighted weighting factors that satisfy the limited number of tags,

wherein the application of the one or more rule sets bases the determination of the one or more recommendations on the limited number of tags having the most heavily weighted weighting factors.

19. An apparatus of claim 11, wherein the apparatus is further caused to perform at least the following:

cause, at least in part, a determination to query a recommendation engine for one or more recommendation tokens from a database.

20. An apparatus of claim 11, wherein the apparatus is further caused to perform at least the following:

cause, at least in part, an output of three sets of tags, each of which are context specific tags, profile specific tags and a combination of context and profile tags; and

cause, at least in part, embedding the type of tags that are output in a response to the query.

21-47. -47. (canceled)