Using application market log data to identify applications of interest

• US 8,566,173 B2
• Filed: 06/22/2012
• Issued: 10/22/2013
• Est. Priority Date: 05/09/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mahaniok, Ihar, Mehta, Bhaskar
• Primary Examiner(s): ZURITA, JAMES H
• Application Number:
  US13/530,242
• Publication Number:
  US 20120290441A1
• Time in Patent Office: 487 Days
• Field of Search: 705/26.1, 705/27.1
• US Class Current: 705/26.1
• CPC Class Codes: G06F 16/24 Querying
• CPC Class Codes: G06F 8/60 Software deployment
• CPC Class Codes: G06Q 30/02 Marketing; Price estimation or determination; Fundraising

Abstract

Methods, systems and apparatus, including computer programs encoded on a computer storage medium, for receiving a query log, the query log including data relating to information input to an application marketplace and one or more applications available through the application marketplace, generating a map based on the data of the query log, for at least one of the one or more applications, identifying one or more applications of interest based on the map, generating an index, the index associating the at least one of the one or more applications to the one or more applications of interest, storing the index in computer-readable memory, receiving a user selection of a particular application of the one or more applications, retrieving the one or more applications of interest based on the particular application using the generated index, and providing the one or more applications of interest for display.

Claims

1. A system, comprising:

one or more computers; and

a non-transitory computer-readable medium coupled to the one or more computers having instructions stored thereon which, when executed by the one or more computers, cause the one or more computers to perform operations comprising;

receiving a query log, the query log comprising one or more queries corresponding to one or more applications available through an application marketplace and data, for each query, associated with the one or more applications;

generating, for each query, a map to at least one application of the one or more applications based on the query log;

determining, for each map, a weight of each application of the one or more applications based on the data associated with the respective application;

determining for at least one of the one or more applications, a co-weight of one or more applications of interest based on the weight of each application of the one or more applications;

based on the co-weight of the one or more applications of interest, generating an index of co-weights of applications, the index of co-weights of applications associating the at least one of the one or more applications to the one or more applications of interest;

storing the index of co-weights of applications in computer-readable memory;

receiving a user selection of a particular application of the one or more applications;

retrieving the one or more applications of interest based on the particular application using the index of co-weights of applications; and

providing the one or more applications of interest for display.

2. The system of claim 1, wherein, for each query, the data comprises, for each of the one or more applications, one or more of a number of clicks, a number of installs, and a position within a list of search results.

3. The system of claim 1, wherein determining, for the at least one of the one or more applications, the co-weight of one or more applications of interest comprises:

calculating a normalized weight corresponding to a first application of the one or more applications and a second application of the one or more applications;

determining that the normalized weight is greater than a threshold normalized weight; and

in response to determining that the normalized weight is greater than the threshold normalized weight, identifying the second application as an application of interest relative to the first application.

4. The system of claim 3, wherein the normalized weight is calculated based on a total weight of the first application and a total weight of the second application.

5. The system of claim 4, wherein the total weight of the first application is calculated based on, for each query, a number of clicks and a number of installs associated with the first application, and the total weight of the second application is calculated based on, for each query, a number of clicks and a number of installs associated with the second application.

6. The system of claim 5, wherein the number of clicks is weighted relative to the number of installs.

7. The system of claim 1, wherein determining, for the at least one of the one or more applications, the co-weight of one or more applications of interest comprises:

calculating a first normalized weight corresponding to a first application of the one or more applications and a second application of the one or more applications;

calculating a second normalized weight corresponding to the first application and a third application of the one or more applications;

determining that the first and second normalized weights are each greater than a threshold normalized weight; and

in response to determining that the first and second normalized weights are greater than the threshold normalized weight, identifying the second application and the third application as being applications of interest relative to the first application.

8. The system of claim 7, wherein the operations further comprise:

determining that the first normalized weight is greater than the second normalized weight;

in response to determining that the first normalized weight is greater than the second normalized weight, defining a rank order that ranks the second application higher than the third application;

receiving user input corresponding to the first application; and

in response to receiving the user input, providing the second application and the third application to be displayed based in the rank order to the user.

9. The system of claim 1, the operations further comprising:

cleaning each query of the one or more queries to provide a plurality of cleaned queries, and

wherein generating the map further comprises generating the map for each cleaned query of the plurality of cleaned queries.

10. The system of claim 9, wherein cleaning each query further comprises generating a hash for each query to provide plurality of hash functions, and

wherein generating the map further comprises generating the map for each hash function.

11. The system of claim 1, wherein the operations further comprise:

receiving an additional query;

generating search results based on the additional query, the search results corresponding to the one or more applications; and

providing the search results for display to a user.

12. The system of claim 11, wherein the operations further comprise:

receiving user input, the user input indicating a selection of a search result from the search results, the search result corresponding to an application of the one or more applications;

in response to receiving the user input, accessing the index of co-weights of applications to identify at least one application of interest in view of the application; and

providing the application and the at least one application of interest for display to the user.

13. A non-transitory computer storage medium encoded with a computer program, the program comprising instructions that when executed by one or more computers cause the one or more computers to perform operations comprising:

receiving a query log, the query log comprising one or more queries corresponding to one or more applications available through an application marketplace and data, for each query, associated with the one or more applications;

generating, for each query a map to at least one application of the one or more applications based on the query log;

determining, for each map, a weight of each application of the one or more applications based on the data associated with the respective application;

determining for at least one of the one or more applications, a co-weight of one or more applications of interest based on the weight of each application of the one or more applications;

based on the co-weight of the one or more applications of interest, generating an index of co-weights of applications, the index of co-weights of applications associating the at least one of the one or more applications to the one or more applications of interest;

storing the index of co-weights of applications in computer-readable memory;

receiving a user selection of a particular application of the one or more applications;

retrieving the one or more applications of interest based on the particular application using the index of co-weights of applications; and

providing the one or more applications of interest for display.

14. The computer storage medium of claim 13, wherein determining, for the at least one of the one or more applications, the co-weight of one or more applications of interest comprises:

calculating a normalized weight corresponding to a first application of the one or more applications and a second application of the one or more applications;

determining that the normalized weight is greater than a threshold normalized weight; and

in response to determining that the normalized weight is greater than the threshold normalized weight, identifying the second application as an application of interest relative to the first application.

15. The computer storage medium of claim 14, wherein the normalized weight is calculated based on a total weight of the first application and a total weight of the second application.

16. The computer storage medium of claim 15, wherein the total weight of the first application is calculated based on, for each query, a number of clicks and a number of installs associated with the first application, and the total weight of the second application is calculated based on, for each query, a number of clicks and a number of installs associated with the second application.

17. A computer-implemented method comprising:

receiving a query log, the query log comprising one or more queries corresponding to one or more applications available through an application marketplace and data, for each query, associated with the one or more applications;

generating, by one or more processors, for each query, a map to at least one application of the one or more applications based on the query log;

determining, for each map, a weight of each application of the one or more applications based on the data associated with the respective application;

determining, for at least one of the one or more applications, a co-weight of one or more applications of interest based on the weight of each application of the one or more applications;

based on the co-weight of the one or more applications of interest, generating, by the one or more processors, an index of co-weights of applications, the index of co-weights of applications associating the at least one of the one or more applications to the one or more applications of interest;

storing the index of co-weights of applications in computer-readable memory;

receiving a user selection of a particular application of the one or more applications;

retrieving the one or more applications of interest based on the particular application using the index of co-weights of applications; and

providing the one or more applications of interest for display.