Identifying contextual objects from web content

Patent metadata

Field	Value
Publication number	US-12353496-B2
Application number	US-202418760271-A
Country	US
Kind code	B2
Filing date	Jul 1, 2024
Priority date	Jun 21, 2022
Publication date	Jul 8, 2025
Grant date	Jul 8, 2025

Abstract

Systems and methods are provided for determining contextual objects related to web content. Web content may include one or more elements, which may be extracted from the web content and analyzed to identify any contextual objects. The web content elements may be hyperlink elements, and contextual objects may be identified based on the hyperlink elements. A dominant entity may be identified for the web content, and contextual objects relating to the dominant entity may be identified. When a request for web content is received, contextual objects may be provided with the requested content. Personalized contextual objects may be selected from the identified contextual objects based on data associated with the request for web content. Selection of a contextual object may result in navigation to a browsing environment associated with the selected contextual object.

First claim

What is claimed is:

1. A system comprising:
at least one processor; and
memory storing a set of instructions that, when executed by the at least one processor, causes the system to perform a set of operations, the set of operations comprising:
receive web content, wherein the web content comprises a plurality of elements;
extract, based on the plurality of elements, a first dominant entity of the web content;
generate a first confidence score for the first dominant entity;
extract, based on the plurality of elements, a second dominant entity of the web content;
generate a second confidence score for the second dominant entity;
if the first confidence score is above a dominant entity confidence threshold, determine a plurality of primary contextual objects based on the first dominant entity; and
if the first confidence score is below the dominant entity confidence threshold, determine the plurality of primary contextual objects based on the second dominant entity;
in response to receiving a request for the web content, provide the plurality of primary contextual objects with the requested web content; and
in response to receiving a selection of one of the plurality of primary contextual objects, navigate to a browsing context associated with the selected primary contextual object.

2. The system of claim 1 , wherein the set of instructions further comprises:
if the plurality of primary contextual objects is below a contextual object threshold, determine a plurality of secondary contextual objects related to the plurality of primary contextual objects; and
in response to receiving the request for the web content, provide the plurality of secondary contextual objects with the plurality of primary contextual objects and the requested web content.

3. The system of claim 1 , the set of operations further comprising:
determine, from the plurality of primary contextual objects, a plurality of personalized contextual objects based on profile data associated with the request for the web content; and
provide the plurality of personalized contextual objects with the requested web content.

4. The system of claim 1 , wherein the dominant entity confidence threshold is based on a quantity of the plurality of elements used to generate the first dominant entity.

5. The system of claim 1 , wherein the first dominant entity is extracted at a first level of generality and the second dominant entity is extracted at a second level of generality and wherein the second level is higher than the first level.

6. The system of claim 5 , wherein the first dominant entity is a product and wherein the second dominant entity is a product category encompassing the product.

7. The system of claim 6 wherein at least one of the plurality of elements is an image of the product and wherein extracting the first dominant entity comprises determining that the image depicts the product.

8. The system of claim 1 , wherein generating the first confidence score comprises comparing a first quantity of the plurality of elements indicating the first dominant entity to a second quantity of the plurality of elements indicating the second dominant entity.

9. The system of claim 1 , the set of operations further comprising:
parsing the web content;
extracting, based on the parsing, a plurality of hyperlink elements; and
identifying at least one of the plurality of primary contextual objects based on the plurality of hyperlink elements.

10. A computer-implemented method for providing contextual objects with web content, the method comprising:
receiving web content, wherein the web content comprises a plurality of elements;
extracting a first dominant entity of the web content based on the plurality of elements;
generating a first confidence score for the first dominant entity;
extracting a second dominant entity of the web content based on the plurality of elements;
generating a second confidence score for the second dominant entity;
if the first confidence score is above a dominant entity confidence threshold, determining a plurality of primary contextual objects based on the first dominant entity; and
if the first confidence score is below the dominant entity confidence threshold, determining the plurality of primary contextual objects based on the second dominant entity;
in response to receiving a request for the web content, providing the plurality of primary contextual objects with the requested web content; and
in response to receiving a selection of one of the plurality of primary contextual objects, navigating to a browsing context associated with the selected primary contextual object.

11. The method of claim 10 , wherein the method further comprises:
determining, from the plurality of contextual objects, a plurality of personalized contextual objects based on profile data associated with the request for the web content; and
providing the plurality of personalized contextual objects with the requested web content.

12. The method of claim 10 , wherein the dominant entity confidence threshold is based on a quantity of the plurality elements used to generate the first dominant entity.

13. The method of claim 10 , wherein the method further comprises:
parsing the web content;
extracting, based on the parsing, a plurality of hyperlink elements; and
identifying at least one of the plurality of primary contextual objects based on the plurality of hyperlink elements.

14. The method of claim 10 , wherein the first dominant entity is extracted at a first level of generality and the second dominant entity is extracted at a second level of generality and wherein the second level is a higher than the first level.

15. The method of claim 10 , wherein generating the first confidence score comprises comparing a first quantity of the plurality of elements indicating the first dominant entity to a second quantity of the plurality of elements indicating the second dominant entity.

16. The method of claim 10 , wherein the method further comprises:
if the plurality of primary contextual objects is below a contextual object threshold, determining a plurality of secondary contextual objects related to the plurality of primary contextual objects; and
in response to receiving the request for the web content, providing the plurality of secondary contextual objects with the plurality of primary contextual objects and the requested web content.

17. A computer-storage medium encoding computer-executable instructions that, when executed by at least one processor, perform a method comprising:
receiving web content, wherein the web content comprises a plurality of elements;
extracting a first dominant entity of the web content based on the plurality of elements;
generating a first confidence score for the first dominant entity;
extracting a second dominant entity of the web content based on the plurality of elements;
generating a second confidence score for the second dominant entity;
if the first confidence score is above a dominant entity confidence threshold, determining a plurality of primary contextual objects based on the first dominant entity; and
if the first confidence score is below the dominant entity confidence threshold, determining the plurality of primary contextual objects based on the second dominant entity;
determining, from the plurality of primary contextual objects, a plurality of personalized contextual objects based on profile data associated with the request for the web content;
providing the plurality of personalized contextual objects with the requested web conten

Assignees

• Microsoft Technology Licensing Llc

Inventors

• De Barros Marcelo M
• Mittal Manish
• Koduvayoor Subramanian Vinod Krishnan
• Tiwari Prateek
• Banerjee Ayan
• Bathla Samir

Classifications

• G06F16/9538

  Presentation of query results · CPC title

• G06F16/9558 Primary

  Details of hyperlinks; Management of linked annotations · CPC title

• G06F16/9535 Primary

  Search customisation based on user profiles and personalisation · CPC title