Ranking computer-implemented search results based upon static scores assigned to webpages

Patent metadata

Field	Value
Publication number	US-11263225-B2
Application number	US-202016878083-A
Country	US
Kind code	B2
Filing date	May 19, 2020
Priority date	May 19, 2020
Publication date	Mar 1, 2022
Grant date	Mar 1, 2022

Abstract

Technologies pertaining to ranking webpages in response to receipt of a query are described. A search engine receives a query and identifies webpages that are germane to the query. The search engine ranks the identified webpages to form a ranked list, wherein a first webpage is positioned in the ranked list based upon a static score assigned to the first webpage. The static score is based upon a weight assigned to a hyperlink in a second webpage, wherein the hyperlink points to the first webpage, and further wherein the weight is based upon a value of a feature of the hyperlink, such as a location of the hyperlink on the second webpage when the second webpage is rendered. Further, the second webpage includes several hyperlinks that point to different webpages, wherein each of the several hyperlinks has a different weight assigned thereto.

First claim

What is claimed is:

1. A computing system that is configured to rank webpages in response to receipt of a query, the computing system comprising:
a processor; and
memory storing instructions that, when executed by the processor, cause the processor to perform acts comprising:
receiving the query from a client computing device;
identifying a plurality of webpages as being germane to the query, wherein the plurality of webpages includes a first webpage, and further wherein a second webpage includes a hyperlink that points to the first webpage; and
ordering the plurality of webpages into a ranked list, wherein the first webpage is positioned in the ranked list based upon a static score assigned to the first webpage, wherein the static score is based upon a weight assigned to the hyperlink in the second webpage, wherein the weight is assigned to the hyperlink based upon a value of a feature of the hyperlink, wherein the second webpage comprises several hyperlinks with different weights assigned thereto, and further wherein the value of the feature of the hyperlink is generated based upon a rendered image of the second webpage.

2. The computing system of claim 1 , wherein the value of the feature of the hyperlink is a label assigned to the hyperlink that identities a section of the second webpage that includes the hyperlink in the rendered image of the second webpage.

3. The computing system of claim 1 , wherein the value of the feature of the hyperlink identifies a location of the hyperlink in the second webpage in the rendered image of the second webpage.

4. The computing system of claim 1 , wherein the value of the feature of the hyperlink is a size of anchor text of the hyperlink.

5. The computing system of claim 1 , wherein a third webpage is positioned in the ranked list based upon a second static score assigned to the third webpage, wherein the second static score is based upon a second weight assigned to a second hyperlink in the second webpage, the second hyperlink points to the third webpage, the second weight is assigned to the second hyperlink based upon a second value of the feature, and further wherein the second weight is different from the weight.

6. The computing system of claim 5 , wherein the second weight is greater than the weight due to the second hyperlink being positioned above the hyperlink in the second webpage when the second webpage is rendered.

7. The computing system of claim 1 , wherein the weight assigned to the hyperlink is based upon a value of a second feature of the hyperlink, wherein the value of the second feature indicates whether a named entity in anchor text of the hyperlink matches a named entity in text of the first webpage.

8. The computing system of claim 1 , wherein the static score assigned to the first webpage is based upon a second weight assigned to a second hyperlink in a third webpage, where the second hyperlink points to the first webpage, and further wherein the second weight is based upon a position of the second hyperlink in the third webpage.

9. A method executed by at least one processor of a computing system, the method comprising:
rendering a first webpage, wherein the first webpage includes a hyperlink that points to a second webpage;
generating an image of the first webpage;
assigning a weight to the hyperlink in a first webpage, wherein the weight is assigned based upon a value of a feature that pertains to the hyperlink, and further wherein the value of the feature is generated based upon the image of the first webpage;
computing a static score for the second webpage based upon the weight assigned to the hyperlink;
assigning the static score to the second webpage in a search engine index;
receiving a query from a client computing device subsequent to assigning the static score to the second webpage;
searching the search engine index based upon the received query, wherein a plurality of webpages are identified as being relevant to the query, and further wherein the plurality of webpages include the second webpage;
ordering the plurality of webpages into a ranked list of webpages, wherein the second webpage is positioned in the ranked list of webpages based upon the static score assigned to the second webpage; and
transmitting the ranked list of webpages to the client computing device.

10. The method of claim 9 , further comprising:
assigning a second weight to a second hyperlink in the first webpage, wherein the second weight is assigned based upon a second value of the feature, wherein the second hyperlink points to a third webpage, and further wherein the second weight is different from the first weight; and
computing a second static score for the third webpage based upon the second weight assigned to the second hyperlink, wherein the plurality of webpages includes the third webpage, and further wherein the third webpage is positioned in the ranked list of webpages based upon the second static score assigned to the third webpage.

11. The method of claim 9 , further comprising:
identifying sections of the first webpage based upon the image of the rendered first webpage;
identifying a section in the sections that includes the hyperlink; and
assigning a label to the hyperlink based upon the section that is identified as including the hyperlink, wherein the value of the feature is the label assigned to the hyperlink.

12. The method of claim 11 , wherein the label indicates that the hyperlink is included in one of a title of the first webpage, a body of the first webpage, a sidebar of the first webpage, or a footer of the first webpage.

13. The method of claim 11 , wherein identifying sections of the first webpage comprises identifying boundaries of the sections of the first webpage, and further wherein identifying the section in the sections that includes the hyperlink comprises:
identifying a position of the hyperlink in the webpage; and
ascertaining that the position of the hyperlink is within an identified boundary of the section.

14. The method of claim 11 , wherein the sections of the first webpage are identified based upon semantic information in text of the first webpage as output by a natural language processing module.

15. The method of claim 9 , wherein the value of the feature identifies a location of the hyperlink on the first webpage when the first webpage is rendered.

16. The method of claim 9 , wherein the value of the feature is size of anchor text of the hyperlink on the first webpage when the first webpage is rendered.

17. A computer-readable storage medium comprising instructions that, when executed by a processor, cause the processor to perform acts comprising:
receiving a query from a client computing device;
identifying a plurality of webpages as being germane to the query; and
ordering the plurality of webpages into a ranked list, wherein a first webpage is positioned in the ranked list based upon a static score assigned to the first webpage, wherein the static score is based upon a weight assigned to a hyperlink in a second webpage, the hyperlink points to the first webpage, wherein the weight is assigned to the hyperlink based upon a value of a feature of the hyperlink, wherein the value of the feature indicates whether a named entity in anchor text of the hyperlink matches a named entity in text of the second webpage, and further wherein the second webpage comprises several hyperlinks with different weights assigned thereto.

18. The computer-readable storage medium of claim 17 , wherein the weight is assigned to the hyperlink based upon a value of a sec

Assignees

• Microsoft Technology Licensing Llc

Inventors

• Li Ziliu
• Ahmed Junaid
• Overwijk Arnold
• Xiong Li

Classifications

• G06F16/9558

  Details of hyperlinks; Management of linked annotations · CPC title

• G06F40/279 Primary

  Recognition of textual entities · CPC title

• G06F16/9538

  Presentation of query results · CPC title

• G06F40/134

  Hyperlinking · CPC title

• G06F16/24578 Primary

  using ranking · CPC title