Online ranking metric

• US 7,953,741 B2
• Filed: 10/18/2007
• Issued: 05/31/2011
• Est. Priority Date: 10/18/2006
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Sah, Adam, Takahashi, Ryohei, Rohrs, Christopher, Tarlow, Daniel S., Shih, Lawrence Wen-Kai, Yang, Beverly
• Primary Examiner(s): Le; Debbie
• Application Number:
  US11/874,893
• Publication Number:
  US 20080097987A1
• Time in Patent Office: 1,321 Days
• Field of Search: 707 1- 7
• US Class Current: 707/751
• CPC Class Codes: G06F 16/334 Query execution G06F16/335 takes precedence
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation

Abstract

Methods, systems, and apparatus, including computer program products, for ranking resources. One or more signals reporting one or more actions by the plurality of users related to a respective resource are received, where a reported action is a presentation of the respective resource, an addition of the respective resource, or a deletion of the respective resource. The reported actions include one or more short deletions of the respective resource. A respective long-addition click-through rate (LACTR) is determined for the respective resource based on a number of reported presentations of the respective resource and a difference between a number of reported additions of the respective resource and a number of short deletions of the respective resource. The plurality of resources are ranked based on the respective LACTRs for the plurality of resources. The ranking of the plurality of resources are provided.

Claims

1. A computer-implemented method, comprising:

for each of a plurality of resources presented to a plurality of users by a data processing service;

receiving one or more signals originating from the data processing service reporting one or more actions by the plurality of users related to the respective resource, wherein a reported action is a presentation of the respective resource, an addition of the respective resource, or a deletion of the respective resource, wherein the reported actions comprise one or more short deletions of the respective resource, a short deletion of the respective resource being a deletion of the respective resource occurring within a predefined time period after a corresponding addition of the respective resource;

determining a number of long additions for the respective resource by subtracting a number of short deletions of the respective resource from a number of reported additions of the respective resource; and

determining a respective long-addition click-through rate (LACTR) for the respective resource by dividing the number of long additions for the respective resource by a number of reported presentations of the respective resource;

ranking the plurality of resources based on the respective LACTRs for the plurality of resources; and

providing the ranking of the plurality of resources to the data processing service,

wherein receiving, determining, ranking, and providing are performed by one or more computers.

2. The method of claim 1, wherein:

providing the ranking of the resources comprises providing representations of at least a subset of the resources in ranking order.

3. The method of claim 1, wherein:

the one or more signals each specify a context in which the respective reported actions occur; and

determining a respective LACTR for the respective resource comprises determining a respective LACTR for the respective resource in the context based on the reported actions related to the respective resource in the context.

4. The method of claim 3, wherein the context is one or more of language, geographic region, or topical category.

5. The method of claim 1, wherein the one or more signals are embedded in one or more Universal Resource Locators (URLs).

6. The method of claim 1, further comprising:

identifying first users of the plurality of users, the first users associated with an action history that indicates a preference for a first resource and a second resource of the plurality of resources;

identifying a second user of the plurality of users, the second users associated with an action history that indicates a preference for the first resource; and

modifying a ranking of the second resource with respect to the second user based on the indicated preference for the first resource by the first and second users.

7. A system, comprising:

one or more processors; and

instructions configured for execution by the one or more processors, the instructions comprising instructions to;

for each of a plurality of resources presented to a plurality of users by a data processing service;

receive one or more signals originating from the data processing service reporting one or more actions by the plurality of users related to the respective resource, wherein a reported action is a presentation of the respective resource, an addition of the respective resource, or a deletion of the respective resource, wherein the reported actions comprise one or more short deletions of the respective resource, a short deletion of the respective resource being a deletion of the respective resource occurring within a predefined time period after a corresponding addition of the respective resource;

including;

determine a number of long additions for the respective resource by subtracting a number of short deletions of the respective resource from a number of reported additions of the respective resource; and

determine a respective long additional click-through rate (LACTR) for the respective resource by dividing the number of long additions for the respective resource by a number of reported presentations of the respective resource;

rank the plurality of resources based on the respective LACTRs for the plurality of resources; and

provide the ranking of the plurality of resources.

8. The system of claim 7, wherein:

the instructions to provide the ranking of the resources comprise instructions to provide representations of at least a subset of the resources in ranking order.

9. The system of claim 7, wherein:

the one or more signals each specify a context in which the respective reported actions occur; and

the instructions to determine a respective LACTR for the respective resource comprise instructions to determine a respective LACTR for the respective resource in the context based on the reported actions related to the respective resource in the context.

10. The system of claim 9, wherein the context is one or more of language, geographic region, or topical category.

11. The system of claim 7, wherein the one or more signals are embedded in one or more Universal Resource Locators (URLs).

12. The system of claim 7, the instructions further comprising instructions to:

identify first users of the plurality of users, the first users associated with an action history that indicates a preference for a first resource and a second resource of the plurality of resources;

identify a second user of the plurality of users, the second users associated with an action history that indicates a preference for the first resource; and

modify a ranking of the second resource with respect to the second user based on the indicated preference for the first resource by the first and second users.

13. A computer storage medium encoded with a computer program, the program comprising instructions that when executed by data processing apparatus cause the data processing apparatus to perform operations comprising:

for each of a plurality of resources presented to a plurality of users by a data processing service;

receiving one or more signals originating from the data processing service reporting one or more actions by the plurality of users related to the respective resource, wherein a reported action is a presentation of the respective resource, an addition of the respective resource, or a deletion of the respective resource, wherein the reported actions comprise one or more short deletions of the respective resource, a short deletion of the respective resource being a deletion of the respective resource occurring within a predefined time period after a corresponding addition of the respective resource;

including;

determining a number of long additions for the respective resource by subtracting a number of short deletions of the respective resource from a number of reported additions of the respective resource; and

determining a respective long addition click-through rate (LACTR) for the respective resource by dividing the number of long additions for the respective resource by a number of reported presentations of the respective resource;

ranking the plurality of resources based on the respective LACTRs for the plurality of resources; and

providing the ranking of the plurality of resources.

14. The computer storage medium of claim 13, wherein:

providing the ranking of the resources comprises providing representations of at least a subset of the resources in ranking order.

15. The computer storage medium of claim 13, wherein:

the one or more signals each specify a context in which the respective reported actions occur; and

determining a respective LACTR for the respective resource comprises determining a respective LACTR for the respective resource in the context based on the reported actions related to the respective resource in the context.

16. The computer storage medium of claim 15, wherein the context is one or more of language, geographic region, or topical category.

17. The computer storage medium of claim 13, wherein the one or more signals are embedded in one or more Universal Resource Locators (URLs).

18. The computer storage medium of claim 13, the operations further comprising:

identifying first users of the plurality of users, the first users associated with an action history that indicates a preference for a first resource and a second resource of the plurality of resources;

identifying a second user of the plurality of users, the second users associated with an action history that indicates a preference for the first resource; and

modifying a ranking of the second resource with respect to the second user based on the indicated preference for the first resource by the first and second users.