Extracting and populating content from an email link

Patent metadata

Field	Value
Publication number	US-11899734-B2
Application number	US-202117142112-A
Country	US
Kind code	B2
Filing date	Jan 5, 2021
Priority date	Jan 5, 2021
Publication date	Feb 13, 2024
Grant date	Feb 13, 2024

Abstract

Systems and methods are described for extracting and populating content from an email link. In an example, a machine learning (“ML”) model can be trained based on user interactions with emails. When an email is received for the user, the ML model can be applied to score the email. An application can extract a link in the email. The application can retrieve a web page with the link and store it locally. The application can create a card for the email that includes the link and insert the card into a graphical user interface (“GUI”). A user can access the GUI and select the card. The web page can be retrieved from the local storage and displayed in the GUI.

First claim

What is claimed is:

1. A method for extracting and populating content from an email link, comprising:
detecting links in a plurality of emails addressed to an email account of a user;
extracting the links from the plurality of emails;
based on a machine learning model that analyzes user interactions with email links to determine patterns, calculating an importance score for each of the plurality of links;
retrieving a plurality of web pages corresponding to a subset of the plurality of links, the importance score for each of the subset of links exceeding a threshold;
storing the retrieved plurality of web pages in a cache;
for each of the subset of links, creating a plurality of tiles, each of the plurality of tiles displaying at least one link from the subset of links and content information related to an email from which the one link was extracted;
presenting the plurality of tiles in a graphical user interface (“GUI”);
receiving a selection of a first link in its corresponding tile; and
displaying a first web page corresponding to the first link from the cache.

2. The method of claim 1 , further comprising:
dynamically rearranging the tiles in the GUI based on learned behavior of the user, the rearranging including prioritizing tiles with links that the learned behavior indicates the user is most likely to interact with based on the current time.

3. The method of claim 1 , further comprising:
receiving a selection of a first tile; and
responsive to the selection of the first tile, displaying additional information corresponding to a first email associated with the first tile.

4. The method of claim 1 , wherein the content information related to the email includes a sender of the email, a subject of the email, and a snippet of content from a body of the email.

5. The method of claim 1 , wherein the machine learning model determines patterns based on user interactions with the tiles.

6. The method of claim 1 , wherein extracting the link includes performing a backend credential check to determine whether the link is accessible to the user.

7. The method of claim 1 , wherein extracting the link includes comparing the link to a list to determine whether the link is allowed or prohibited.

8. A non-transitory, computer-readable medium containing instructions that, when executed by a hardware-based processor, performs stages for extracting and populating content from an email link, the stages comprising:
detecting links in a plurality of emails addressed to an email account of a user;
extracting the links from the plurality of emails;
based on a machine learning model that analyzes user interactions with email links to determine patterns, calculating an importance score for each of the plurality of links;
retrieving a plurality of web pages corresponding to a subset of the plurality of links, the importance score for each of the subset of links exceeding a threshold;
storing the retrieved plurality of web pages in a cache;
for each of the subset of links, creating a plurality of tiles, each of the plurality of tiles displaying at least one link from the subset of links and content information related to an email from which the one link was extracted;
presenting the plurality of tiles in a graphical user interface (“GUI”);
receiving a selection of a first link in its corresponding tile; and
displaying a first web page corresponding to the first link from the cache.

9. The non-transitory, computer-readable medium of claim 8 , the stages further comprising:
dynamically rearranging the tiles in the GUI based on learned behavior of the user, the rearranging including prioritizing tiles with links that the learned behavior indicates the user is most likely to interact with based on the current time.

10. The non-transitory, computer-readable medium of claim 8 , the stages further comprising:
receiving a selection of a first tile; and
responsive to the selection of the first tile, displaying additional information corresponding to a first email associated with the first tile.

11. The non-transitory, computer-readable medium of claim 8 , wherein the content information related to the email includes a sender of the email, a subject of the email, and a snippet of content from a body of the email.

12. The non-transitory, computer-readable medium of claim 8 , wherein the machine learning model determines patterns based on user interactions with the tiles.

13. The non-transitory, computer-readable medium of claim 8 , wherein extracting the link includes performing a backend credential check to determine whether the link is accessible to the user.

14. The non-transitory, computer-readable medium of claim 8 , wherein extracting the link includes comparing the link to a list to determine whether the link is allowed or prohibited.

15. A system for extracting and populating content from an email link, comprising:
a memory storage including a non-transitory, computer-readable medium comprising instructions; and
a computing device including a hardware-based processor that executes the instructions to carry out stages comprising:
detecting links in a plurality of emails addressed to an email account of a user;
extracting the links from the plurality of emails;
based on a machine learning model that analyzes user interactions with email links to determine patterns, calculating an importance score for each of the plurality of links;
retrieving a plurality of web pages corresponding to a subset of the plurality of links, the importance score for each of the subset of links exceeding a threshold;
storing the retrieved plurality of web pages in a cache;
for each of the subset of links, creating a plurality of tiles, each of the plurality of tiles displaying at least one link from the subset of links and content information related to an email from which the one link was extracted;
presenting the plurality of tiles in a graphical user interface (“GUI”);
receiving a selection of a first link in its corresponding tile; and
displaying a first web page corresponding to the first link from the cache.

16. The system of claim 15 , the stages further comprising:
dynamically rearranging the tiles in the GUI based on learned behavior of the user, the rearranging including prioritizing tiles with links that the learned behavior indicates the user is most likely to interact with based on the current time.

17. The system of claim 15 , the stages further comprising:
receiving a selection of a first tile; and
responsive to the selection of the first tile, displaying additional information corresponding to a first email associated with the first tile.

18. The system of claim 15 , wherein the content information related to the email includes a sender of the email, a subject of the email, and a snippet of content from a body of the email.

19. The system of claim 15 , wherein the machine learning model determines patterns based on user interactions with tiles.

20. The system of claim 15 , wherein extracting the link includes performing a backend credential check to determine whether the link is accessible to the user.

Assignees

• VMware LLC
• Vmware Inc

Inventors

• Shetty Rohit Pradeep
• Stuntebeck Erich
• Xuan Chaoting
• Samuel Sharun Varghese

Classifications

• G06F16/9577 Primary

  Optimising the visualization of content, e.g. distillation of HTML documents · CPC title

• G06F16/9558 Primary

  Details of hyperlinks; Management of linked annotations · CPC title

• G06N20/00

  Machine learning · CPC title

• H04L5/18

  Automatic changing of the traffic direction · CPC title

• H04L51/066

  Format adaptation, e.g. format conversion or compression · CPC title