System and Method for Efficiently Providing a Recommendation

• US 20090063439A1
• Filed: 10/31/2008
• Published: 03/05/2009
• Est. Priority Date: 09/24/1999
• Status: Active Grant

• Current Assignee: CDN Innovations, LLC (IP Investments Group LLC)
• Original Assignee: Thalveg Data Flow LLC (Intellectual Ventures LLC)
• Inventors: Guralnik, Valerie, Rauser, John
• Granted Patent: US 8,548,987 B2
• Time in Patent Office: Days
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising
• CPC Class Codes: Y10S 707/99932 Access augmentation or optimizing
• CPC Class Codes: Y10S 707/99935 Query augmenting and refining, e.g. inexact access

Abstract

A system and method for applying a first filter and a second filter, such as a recommendation and a constraint filter, to a plurality of items, including determining a cost of applying the first filter and the second filter to the plurality of items, and determining an order of applying the first and second filters based on the cost of applying the first and second filters.

Claims

1. A method for applying a recommendation filter and a constraint filter to a plurality of items in a data processing system, comprising the steps of:

receiving a recommendation request;

specifying a constraint filter that selects ones of items satisfying a constraint;

determining the order of the filters based on a cost of applying the filters, including;

applying the constraint filter first when a cost of applying the filters when the constraint filter is applied first is lower than a cost of applying the filters when the recommendation filter is applied first, and

applying the recommendation filter first when the cost of applying the filters when the recommendation filter is applied first is lower than the cost of applying the filters when the constraint filter is applied first.

2. The method of claim 1, wherein determining the order of the filters further includes:

analyzing a cost for applying the filters to the ones of the items; and

determining a probability that the ones of the items will pass both filters.

3. The method of claim 1, wherein the cost of applying the filters is determined by the equation:

C=M/P(G+R),

wherein M is a number of desired items, P is a probability that the ones of the items will pass a second applied filter, G is a time to retrieve the ones of the items, and R is a time to decide if the ones of the items will pass a second applied filter.

4. The method of claim 1, further comprising:

calculating the cost of applying the filters based at least on a probability that a randomly selected item of the plurality of items will pass a second applied filter of the recommendation and constraint filters.

5. The method of claim 4, wherein the calculating is further based on a cost of applying a first applied filter of the recommendation and constraint filters to generate a single item.

6. The method of claim 4, wherein the calculating is further based on a cost of applying a second applied filter of the recommendation and constraint filters to a single item.

7. The method of claim 4, wherein the calculating is further based on a number of results required.

8. A method comprising:

determining an order for applying a first filter and a second filter to a plurality of items, comprising calculating a cost of applying the first filter and the second filter in a first order based at least on (i) a number of results required, (ii) a probability that a randomly selected item of the plurality of items will pass a second applied filter of the first filter and the second filter, (iii) a cost of applying a first applied filter of the first filter and the second filter to generate a single item, and (iv) a cost of applying the second applied filter of the first filter and the second filter to the single item; and

generating a recommendation list, comprising applying the first filter and the second filter to the plurality of items according to the determined order.

9. The method of claim 8, further comprising:

receiving a recommendation request.

10. The method of claim 8, further comprising:

displaying the recommendation list.

11. The method of claim 8, wherein the determining an order comprises calculating the cost using the equation:

cost=(number of results required/probability that a randomly selected item will pass the second applied filter)*(cost of applying the first applied filter to generate a single item+cost of applying the second applied filter to the single item).

12. A system, comprising:

a recommendation server configured to;

receive a recommendation request,

determine an order for applying a first filter and a second filter to a plurality of items based on a cost of applying the first filter and the second filter, and

generate a recommendation list, comprising applying the first filter and the second filter in the determined order.

13. The system of claim 12, wherein the cost is based at least on a probability that a randomly selected item of the plurality of items will pass a second applied filter of the first filter and the second filter.

14. The system of claim 12, wherein the cost is based at least on a cost of applying a first applied filter of the first filter and the second filter to generate a single item.

15. The system of claim 12, wherein the cost is based at least on a cost of applying a second applied filter of the first filter and the second filter to a single item.

16. The system of claim 12, wherein the cost is based at least on a number of results required.

17. A computer program product comprising a tangible computer readable storage medium having control logic stored therein, the control logic, when executed, causing a processor to perform a method comprising:

receiving a recommendation request;

determining an order for applying a first filter and a second filter to a plurality of items based on a cost of applying the first filter and the second filter; and

generating a recommendation list, comprising applying the first filter and the second filter in the determined order.

18. The computer program product of claim 17, wherein the cost is based at least on (i) a number of results required, (ii) a probability that a randomly selected item of the plurality of items will pass a second applied filter of the first filter and the second filter, (iii) a cost of applying a first applied filter of the first filter and the second filter to generate a single item, and (iv) a cost of applying the second applied filter of the first filter and the second filter to the single item.

19. A system, comprising:

means for receiving a recommendation request from a user;

means for determining an order for applying a first filter and a second filter to a plurality of items based on a cost of applying the first filter and the second filter; and

means for generating a recommendation list, comprising applying the first filter and the second filter in the determined order.

20. The system of claim 19, wherein the cost is based at least on (i) a number of results required, (ii) a probability that a randomly selected item of the plurality of items will pass a second applied filter of the first filter and the second filter, (iii) a cost of applying a first applied filter of the first filter and the second filter to generate a single item, and (iv) a cost of applying the second applied filter of the first filter and the second filter to the single item.

21. A method, comprising:

sending a recommendation request to a server;

receiving a recommendation list generated by the application of a first filter and a second filter in an order based on a cost of applying the first filter and the second filter.

22. The method of claim 21, wherein the cost is based at least on (i) a number of results required, (ii) a probability that a randomly selected item of the plurality of items will pass a second applied filter of the first filter and the second filter, (iii) a cost of applying a first applied filter of the first filter and the second filter to generate a single item, and (iv) a cost of applying the second applied filter of the first filter and the second filter to the single item.