Systems and methods for determining a quality of provided items

• US 8,583,636 B1
• Filed: 10/18/2011
• Issued: 11/12/2013
• Est. Priority Date: 09/29/2004
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Franz, Alexander Mark, Henzinger, Monika H
• Primary Examiner(s): Yen, Syling
• Application Number:
  US13/275,981
• Time in Patent Office: 756 Days
• Field of Search: 707/706, 707/713, 707/722, 707/723, 707/736, 707/758, 707/781, 707999003- 7
• US Class Current: 707/723
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

A system may provide items during a time period and determine a quality of the items provided during the time period using a time series model.

Claims

1. A method comprising:

generating, by one or more processors, one or more values based on a measure of quality of first search results provided during a first time period and based on a first search query,

the one or more values corresponding to a predicted measure of quality of one or more second search results,

the one or more second search results being provided during a second time period and being based on a second search query,

the second time period being subsequent to the first time period, and

the one or more values being based on one or more user actions associated with the first search results provided during the first time period;

providing, by one or more processors, a list of the one or more second search results during the second time period;

determining, by one or more processors, an actual measure of quality of the one or more second search results in the list of the one or more second search results provided during the second time period;

comparing, by one or more processors, the predicted measure of quality to the actual measure of quality; and

taking, by one or more processors, one or more remedial measures when the actual measure of quality is outside of a range of the predicted measure of quality.

2. The method of claim 1, where the actual measure of quality is based on at least one of:

a percentage of times that a particular search result, in the list of the one or more second search results, is selected,

an average position of a search result that is selected first within the list of the one or more second search results,

a percentage of searches that did not have another search performed within a particular period of time, or

a percentage of searches that did not have a reformulated search performed within another particular period of time.

3. The method of claim 1, where the actual measure of quality is based on a percentage of times that a search result, in a top position in the list of the one or more second search results, is selected.

4. The method of claim 1, where the actual measure of quality is based on a percentage of times that a user stays on a page, associated with a search result in the list of the one or more second search results, for at least a predetermined amount of time.

5. The method of claim 4, where the predetermined amount of time is greater than three minutes.

6. The method of claim 1, where the actual measure of quality is determined using a time series model.

7. The method of claim 1, where the one or more remedial measures include at least one of:

removing an index segment used by the one or more processors to provide the list of the one or more second search results,

automatically removing a modification associated with the one or more processors, or

sending a notification.

8. A device comprising:

a memory containing instructions; and

a processor that executes the instructions to;

generate one or more values based on a measure of quality of first search results provided during a first time period and based on a first search query,

the one or more values corresponding to a predicted measure of quality of one or more second search results,

the one or more second search results being provided during a second time period and being based on a second search query,

 

the second time period being subsequent to the first time period, and

the one or more values being based on one or more user actions associated with the first search results provided during the first time period;

provide a list of the one or more second search results during the second time period;

determine an actual measure of quality of the one or more second search results in the list of the one or more second search results provided during the second time period;

compare the predicted measure of quality to the actual measure of quality; and

take one or more remedial measures when the actual measure of quality is outside a range of the predicted measure of quality.

9. The device of claim 8, where the actual measure of quality is based on at least one of:

a percentage of times that a particular search result, in the list of the one or more second search results, is selected,

an average position of a search result that is selected first within the list of the one or more second search results,

a percentage of searches that did not have another search performed within a particular period of time, or

a percentage of searches that did not have a reformulated search performed within another particular period of time.

10. The device of claim 8, where the actual measure of quality is based on a percentage of times that a search result, in a top position in the list of the one or more second search results, is selected.

11. The device of claim 8, where the actual measure of quality is based on a percentage of times that a user stays on a page, associated with a search result in the list of the one or more second search results, for at least a predetermined amount of time.

12. The device of claim 11, where the predetermined amount of time is greater than three minutes.

13. The device of claim 8, where the actual measure of quality is determined using a time series model.

14. The device of claim 8, where the one or more remedial measures include at least one of:

removing an index segment used by the processor to provide the list of the one or more second search results,

automatically removing a modification associated with the processor, or

sending a notification.

15. A non-transitory computer-readable medium storing instructions, the instructions comprising:

one or more instructions which, when executed by at least one processor, cause the at least one processor to generate one or more values based on a measure of quality of first search results provided during a first time period and based on a first search query,

the one or more values corresponding to a predicted measure of quality of one or more second search results,

the one or more second search results being provided during a second time period and being based on a second search query,

the second time period being subsequent to the first time period, and

the one or more values being based on one or more user actions associated with the first search results provided during the first time period;

one or more instructions which, when executed by the at least one processor, cause the at least one processor to provide a list of the one or more second search results during the second time period;

one or more instructions which, when executed by the at least one processor, cause the at least one processor to determine an actual measure of quality of the one or more second search results in the list of the one or more second search results provided during the second time period;

one or more instructions which, when executed by the at least one processor, cause the at least one processor to compare the predicted measure of quality to the actual measure of quality; and

one or more instructions which, when executed by the at least one processor, cause the at least one processor to take one or more remedial measures when the actual measure of quality is outside a range of the predicted measure of quality.

16. The non-transitory computer-readable medium of claim 15, where the actual measure of quality is based on at least one of:

a percentage of times that a particular search result, in the list of the one or more second search results, is selected,

an average position of a search result that is selected first within the list of the one or more second search results,

a percentage of searches that did not have another search performed within a particular period of time, or

a percentage of searches that did not have a reformulated search performed within another particular period of time.

17. The non-transitory computer-readable medium of claim 15, where the actual measure of quality is based on a percentage of times that a search result, in a top position in the list of the one or more second search results, is selected.

18. The non-transitory computer-readable medium of claim 15, where the actual measure of quality is based on a percentage of times that a user stays on a page, associated with a search result in the list of the one or more second search results, for at least a predetermined amount of time, where the predetermined amount of time is greater than three minutes.

19. The non-transitory computer-readable medium of claim 15, where the actual measure of quality is determined using a time series model.

20. The non-transitory computer-readable medium of claim 15, where the one or more remedial measures include at least one of:

removing an index segment used by the at least one processor to provide the list of the one or more second search results,

automatically removing a modification associated with the at least one processor, or

sending a notification.