System, method, and media for identifying top attributes

Patent metadata

Field	Value
Publication number	US-11037226-B2
Application number	US-202016748334-A
Country	US
Kind code	B2
Filing date	Jan 21, 2020
Priority date	Dec 31, 2015
Publication date	Jun 15, 2021
Grant date	Jun 15, 2021

Abstract

In various example embodiments, a system and method for identifying top attributes are presented. Text content from an electronic document describing a product is extracted. A plurality of attributes associated with the product are identified using the extracted text content. A descriptor word proximate to each of the plurality of attributes in the extracted text content is detected. A weight is assigned to each descriptor word proximate to each of the plurality of attributes. The plurality of attributes are ranked based on the weight of the descriptor word proximate to each of the plurality of attributes. A predetermined number of top ranked attributes from the plurality of attributes are caused to be presented. Further, an image associated with each of the top ranked attributes is determined, the image being designated as a visual representation of the corresponding top ranked attribute. The image is caused to be displayed in association with the product on a user interface.

First claim

What is claimed is:

1. A system comprising:
one or more processors; and
computer-readable memory including instructions that when executed by the one or more processors, cause the one or more processors to perform operations comprising:
extracting text content from an electronic document describing a product;
using the extracted text content, identifying a plurality of attributes associated with the product;
ranking the plurality of attributes; and
causing generation of a user interface that includes at least one image, the at least one image being a visual depiction of a top ranked attribute based on the ranking of the plurality of attributes.

2. The system of claim 1 , further comprising detecting descriptor words associated with the plurality of attributes in the extracted text content, wherein the plurality of attributes is ranked based on the descriptor words.

3. The system of claim 1 , wherein the generated user interface comprises a product image of the product, the visual depiction of the top ranked attribute being superimposed over the product image.

4. The system of claim 1 , wherein the generated user interface comprises a product description area for the product, the visual depiction of the top ranked attribute being superimposed over the product description area.

5. The system of claim 1 , wherein the generated user interface comprises content associated with the product, the visual depiction of the top ranked attribute being generated to a side of the content, wherein the visual depiction of the top ranked attribute remains displayed as the content of the user interface is scrolled to different pages.

6. The system of claim 1 , further comprising:
receiving a selection at the visual depiction of the top ranked attribute; and
based on the selection, generating a second user interface comprising a product image associated with a different product, the different product having the top ranked attribute.

7. The system of claim 1 , wherein the electronic document is a webpage associated with the product, and wherein the text content is extracted from a product review provided at the webpage associated with the product.

8. The system of claim 1 , wherein the generated user interface comprises a plurality of images that are visual depictions of top ranked attributes, each image associated with a selectable option, the selectable options configured to allow selection of more than one of the top ranked attributes.

9. A computerized method performed by one or more processors, the method comprising:
extracting text content from product reviews describing a product;
identifying attributes of the product;
ranking the identified attributes based on the extracted text content; and
causing generation of a user interface that includes at least one image that is a visual depiction of a top ranked attribute determined from the ranking.

10. The method of claim 9 , wherein the generated user interface comprises a product image or a product description section for the product, wherein the visual depiction of the top ranked attribute is superimposed over the product image or the product description section.

11. The method of claim 10 , wherein the visual depiction of the top ranked attribute is superimposed to be at least partially transparent to the product image or the product description section.

12. The method of claim 9 , wherein the generated user interface includes a plurality of images that are visual depictions of top ranked attributes, the visual depictions of the top ranked attributes having selectable options configured to allow selection of more than one of the top ranked attributes.

13. The method of claim 12 , further comprising:
receiving a selection of a combination of top ranked attributes, the combination selected from the selectable options of the visual depictions; and
causing generation of another graphical user interface that includes a different product, the different product having attributes matching the selected combination of top ranked attributes.

14. The method of claim 9 , wherein the generated user interface comprises content associated with the product, the visual depiction of the top ranked attribute being generated to a side of the content, wherein the visual depiction of the top ranked attribute remains displayed as the content of the user interface is scrolled to different pages.

15. The method of claim 9 , wherein the text content includes descriptor words proximate to the attributes, and wherein the attributes are ranked based on the descriptor words.

16. One or more non-transitory computer readable media having instructions stored thereon that when executed by one or more processors, cause the one or more processors to perform a method comprising:
extracting text content from a webpage describing a product;
ranking attributes of the product based on the extracted text content; and
causing generation of a user interface that includes at least one image that is a visual depiction of a top ranked attribute determined from the ranking.

17. The media of claim 16 , wherein the text content includes descriptor words proximate to the attributes, and wherein the attributes are ranked based on the descriptor words.

18. The media of claim 16 , wherein the generated user interface comprises a product image or a product description section for the product, wherein the visual depiction of the top ranked attribute is superimposed over the product image or the product description section.

19. The media of claim 18 , wherein the visual depiction of the top ranked attribute is superimposed to be at least partially transparent to the product image or the product description section.

20. The media of claim 16 , wherein the generated user interface includes a plurality of images that are visual depictions of top ranked attributes, the visual depictions of the top ranked attributes having selectable options configured to allow selection of more than one of the top ranked attributes.

Assignees

• Ebay Inc

Inventors

• Vasthimal Deepak Kumar
• Mukherjee Avishek

Classifications

• G06F16/9535

  Search customisation based on user profiles and personalisation · CPC title

• G06F16/24578

  using ranking · CPC title

• G06Q30/0643 Primary

  graphically representing goods, e.g. 3D product representation · CPC title

• G06F16/58 Primary

  Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually · CPC title

• G06Q30/0627

  by specifying product or service characteristics, e.g. product dimensions · CPC title