Ranking of native application content
View Patent ↗Methods, systems, and apparatus, including computer programs encoded on a computer storage medium for normalizing native application scores. In an aspect, a system ranks web resources and native applications based on web resource scores and normalized native application scores that are normalized to the web resource scores. The ranking is indicative of the relevance of each web resource and native application for a search operation relative to each other web resource and native application.
1. A computer-implemented method performed by data processing apparatus comprising one or more computers in data communication, the method comprising:
receiving, by the data processing apparatus, web resource scores, each web resource score corresponding to a web resource and being a measure of a relevance of the web resource for a search operation;
determining, for native applications, native application scores, each native application score corresponding to a native application and being a measure of a relevance of the native application for the search operation;
determining a first proper subset of the native applications, each of the native applications in the first proper subset of native application being a native application determined to have a corresponding web resource for the native application;
determining, from the native application scores of the native applications in the first proper subset and from the web resource scores of the corresponding web resources for the native applications in the first proper subset, a normalization factor that adjusts the native application scores to a notionally common scale;
applying the normalization factor to the native application scores to generate normalized native application scores; and
ranking the web resources and the native applications based on the web resource scores and the normalized native application scores, the ranking being indicative of the relevance of each web resource and native application for the search operation relative to each other web resource and native application.
2. The computer-implemented method of claim 1 , wherein determining a normalization factor that adjusts the native application scores to a notionally common scale comprises linearly regressing the native application scores as variable dependent on the corresponding web scores.
3. The computer-implemented method of claim 1 , wherein determining a native application score comprises, for each native application:
determining a number of links to the native application; and
determining, for each of the links, a quality score for the link; and
generating the native application score base, in part, on the number of links to the native application and the quality scores for the links.
4. The computer-implemented method of claim 3 , wherein the links include application links from application pages of other native applications to the native application.
5. The computer-implemented method of claim 3 , wherein the links include web links from web resources to the native application.
6. The computer-implemented method of claim 1 , wherein determining a native application score comprises, for each native application:
determining, for each the applications, a number of downloads of the application; and
generating the native application score based, in part, on the number of downloads of the native application.
7. The computer-implemented method of claim 1 , wherein determining a native application score comprises, for each native application:
selecting application page data of pages of the native application from an index of application pages, the application page data describing the content of each application page; and
generating the native application score based, in part, on the application page data and a search query.
8. The computer-implemented method of claim 1 , wherein determining a native application score comprises, for each native application:
determining device specific data for a user device from which a search query was received; and
generating the native application score based, in part, on the device specific data.
9. The computer-implemented method of claim 8 , wherein determining device specific data for a user device comprises:
determining data describing whether the native application is installed on the user device; and
determining data describing frequency of use of the native application on the user device.
10. A system, comprising:
a data processing apparatus; and
software stored in non-transitory computer readable storage medium storing instructions executable by the data processing apparatus and that upon such execution cause the data processing apparatus to perform operations comprising:
receiving web resource scores, each web resource score corresponding to a web resource and being a measure of a relevance of the web resource for a search operation;
determining, for native applications, native application scores, each native application score corresponding to a native application and being a measure of a relevance of the native application for the search operation;
determining a first proper subset of the native applications, each of the native applications in the first proper subset of native application being a native application determined to have a corresponding web resource for the native application;
determining, from the native application scores of the native applications in the first proper subset and from the web resource scores of the corresponding web resources for the native applications in the first proper subset, a normalization factor that adjusts the native application scores to a notionally common scale;
applying the normalization factor to the native application scores to generate normalized native application scores; and
ranking the web resources and the native applications based on the web resource scores and the normalized native application scores, the ranking being indicative of the relevance of each web resource and native application for the search operation relative to each other web resource and native application.
11. The system of claim 10 , wherein determining a normalization factor that adjusts the native application scores to a notionally common scale comprises linearly regressing the native application scores as variable dependent on the corresponding web scores.
12. The system of claim 10 , wherein determining a native application score comprises, for each native application:
determining a number of links to the native application; and
determining, for each of the links, a quality score for the link; and
generating the native application score base, in part, on the number of links to the native application and the quality scores for the links.
13. The system of claim 11 , wherein the links include application links from application pages of other native applications to the native application.
14. The system of claim 12 , wherein the links include web links from web resources to the native application.
15. The system of claim 10 , wherein determining a native application score comprises, for each native application:
determining, for each the applications, a number of downloads of the application; and
generating the native application score based, in part, on the number of downloads of the native application.
16. The system of claim 10 , wherein determining a native application score comprises, for each native application:
selecting application page data of pages of the native application from an index of application pages, the application page data describing the content of each application page; and
generating the native application score based, in part, on the application page data and a search query.
17. The system of claim 10 , wherein determining a native application score comprises, for each native application:
determining device specific data for a user device from which a search query was received; and
generating the native application score based, in part, on the device specific data.
18. The system of claim 17 , wherein determining device specific data for a user device comprises:
determining data describing whether the native application is installed on the user device; and
determining data describing frequency of use of the native application on the user device.
19. A non-transitory computer readable storage medium storing instructions executable by a data processing apparatus and that upon such execution cause the data processing apparatus to perform operations comprising:
receiving web resource scores, each web resource score corresponding to a web resource and being a measure of a relevance of the web resource for a search operation;
determining, for native applications, native application scores, each native application score corresponding to a native application and being a measure of a relevance of the native application for the search operation;
determining a first proper subset of the native applications, each of the native applications in the first proper subset of native application being a native application determined to have a corresponding web resource for the native application;
determining, from the native application scores of the native applications in the first proper subset and from the web resource scores of the corresponding web resources for the native applications in the first proper subset, a normalization factor that adjusts the native application scores to a notionally common scale;
applying the normalization factor to the native application scores to generate normalized native application scores; and
ranking the web resources and the native applications based on the web resource scores and the normalized native application scores, the ranking being indicative of the relevance of each web resource and native application for the search operation relative to each other web resource and native application.