ASSESSING MOBILE READINESS OF A PAGE USING A TRAINED SCORER

• US 20080250009A1
• Filed: 04/05/2007
• Published: 10/09/2008
• Est. Priority Date: 04/05/2007
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Microsoft Corporation
• Inventors: Xie, Xing, Wen, Ji-Rong, Song, Jihwan
• Granted Patent: US 7,974,957 B2
• Time in Patent Office: Days
• US Class Current: 707/5
• CPC Class Codes: G06F 16/951 Indexing; Web crawling techniques

Abstract

A method and system for ranking pages of a search result based on the mobile readiness of the pages is provided. A mobile-readiness system receives an indication of pages that are to be ranked. The mobile-readiness system evaluates the mobile readiness for each of the pages. Mobile readiness indicates suitability of the page for a mobile device. The mobile readiness system then ranks the pages based on the generated mobile readiness and some other criterion such as a relevance score or an importance score. The mobile-readiness system may train a classifier to classify pages based on their mobile readiness.

Claims

1. A computer-readable medium encoded with instructions for ranking pages, by a method comprising:

receiving an indication of pages;

evaluating mobile readiness of the pages; and

ranking the pages based on the mobile readiness and another criterion.

2. The computer-readable medium of claim 1 wherein the other criterion is based at least in part on relevance of a page to a search request.

3. The computer-readable medium of claim 1 wherein the other criterion is based at least in part on importance of a page.

4. The computer-readable medium of claim 1 wherein the evaluating of mobile readiness includes generating features of the page and applying a mobile-readiness scorer to the generated features to generate a mobile-readiness score.

5. The computer-readable medium of claim 4 wherein the features are selected from a group of feature types consisting of page layout features, function availability features, horizontal scrolling features, understandability features, readability features, page length features, and vertical scrolling features.

6. The computer-readable medium of claim 4 wherein the mobile-readiness scorer is trained using training data that includes features of training pages and labels indicating mobile readiness of the training pages.

7. The computer-readable medium of claim 1 wherein the evaluating of the mobile readiness is performed before receiving the indication of the pages.

8. The computer-readable medium of claim 1 wherein the mobile readiness of a page is based at least in part on suitability of the page to be displayed on a display that is smaller than one the page was designed to fit.

9. The computer-readable medium of claim 1 wherein the mobile readiness of a page is evaluated by applying mobile-readiness scoring rules to the page.

10. The computer-readable medium of claim 1 wherein the indicated pages are pages of a search result for a search request.

11. The computer-readable medium of claim 10 wherein the criterion is based on relevance of a page to the search request and importance of the page.

12. A computing system for determining mobile readiness of a page, comprising:

a training data store of training pages;

a component for generating features of a page;

a component for labeling a training page indicating mobile readiness of the training page;

a component that trains a mobile-readiness scorer based on features and labels of the training pages; and

a component that generates a mobile-readiness score for a target page by applying the mobile-readiness scorer to features of the target page.

13. The computing system of claim 12 including a component that generates a ranking for pages of a search result for a search request based at least in part on a mobile-readiness score generated by the component that generates the mobile-readiness score.

14. The computing system of claim 13 wherein the ranking is additionally based on relevance of the pages to the search request.

15. The computing system of claim 13 wherein the ranking is additionally based on importance of the pages.

16. The computing system of claim 12 wherein the features are selected from a group of feature types consisting of page layout features, function availability features, and horizontal scrolling features.

17. A method in a computing system for ranking web pages of a search result, comprising:

receiving a search request;

identifying as the search result web pages that are relevant to the search request;

generating mobile-readiness scores for the web pages; and

ranking the web pages based on the generated mobile-readiness scores and relevance of the web pages to the search request.

18. The method of claim 17 wherein the generating of the mobile-readiness scores includes generating features of the web page and applying a mobile-readiness scorer to the generated features to generate the mobile-readiness score.

19. The method of claim 18 wherein the mobile-readiness scorer is trained using training data that includes features of training pages and labels indicating mobile readiness of the training pages.