Automatic electronic message filtering method and apparatus

Patent metadata

Field	Value
Publication number	US-12034529-B2
Application number	US-202117152277-A
Country	US
Kind code	B2
Filing date	Jan 19, 2021
Priority date	May 7, 2019
Publication date	Jul 9, 2024
Grant date	Jul 9, 2024

Abstract

Disclosed are systems and methods for improving interactions with and between computers in electronic messaging and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The disclosed systems and methods provide systems and methods for generating electronic message filters and for using electronic message filters comprising item category filtering criteria and having an automatically-determined expiration. The discloses systems and methods filter electronic messages using the item category filtering criteria while an electronic message filter remains active as determined using the automatically-determined expiration information.

First claim

The invention claimed is:

1. A method comprising:
extracting, by a computing device, information from a first electronic message directed to a user;
generating, by the computing device, an electronic message filter using the information extracted from the first electronic message, the electronic message filter having an associated filter action;
automatically determining, by the computing device, expiration information indicating a time frame for applicability of the electronic message filter, the determining comprising using a trained machine model and feature data corresponding to the user as input to the trained machine model, the trained machine model being trained using feature data generated using a corpus of electronic messages corresponding to a plurality of users;
using, by the computing device, the electronic message filter in a time frame in accordance with the determined expiration information, the using comprising:
identifying a second electronic message directed to the user, the identifying comprising determining, using information extracted from the second electronic message, that the second electronic message comprises second information satisfying the electronic message filter; and
performing the filtering action with the second electronic message.

2. The method of claim 1 , further comprising:
identifying, by the computing device, a first information item using the extracted information;
determining, by the computing device, an information category for the identified first item; and
using the determined information category in generating the electronic message filter.

3. The method of claim 2 , determining an item category further comprising:
using the identified first information item to search a data store to identify the item category.

4. The method of claim 2 , wherein the trained machine model is trained for use with the identified information category.

5. The method of claim 4 , the trained machine model is trained for the user using training data generated from the data extracted from the corpus of electronic messages retrieved from a store of the user's messages.

6. The method of claim 4 , the trained machine model is generated for a plurality of users, including the user, using training data generated from the data extracted from the corpus of electronic messages retrieved from messages stored for the plurality of users.

7. The method of claim 1 , further comprising:
automatically making, by the computing device, a determination that the time frame for applicability of the electronic messaging filter is expired; and
prohibiting, by the computing device, use of the electronic messaging filter based on the determination.

8. The method of claim 1 , further comprising:
using the information extracted from the second message to search a store of filters to locate the electronic message filter prior to determining that the second information satisfies the electronic message filter.

9. The method of claim 1 , further comprising:
prior to using the electronic message filter, requesting, by the computing device, approval of the electronic message filter from the user.

10. The method of claim 9 , requesting approval of the user further comprising requesting the user's approval of the time frame determined for the electronic message filter using the trained machine model.

11. The method of claim 9 , requesting approval of the user further comprising requesting the user's approval of the filtering action.

12. The method of claim 9 , further comprising:
using the electronic messaging filter in accordance with input received from the user in response to the request.

13. The method of claim 1 , further comprising:
initiating, by the computing device, generation of the electronic message filter in response to input from the user.

14. The method of claim 13 , further comprising:
using, by the computing device, the user input in identifying the first electronic message as one of a plurality of electronic messages used in generating the electronic message filter.

15. The method of claim 13 , the user input comprising one or more search criteria used in a search of the user's electronic messages to identify at least the first electronic message satisfying the search criteria.

16. The method of claim 13 , the input of the user comprising selection of at least the first electronic message by the user.

17. A non-transitory computer-readable storage medium tangibly encoded with computer-executable instructions that when executed by a processor associated with a computing device perform a method comprising:
extracting information from a first electronic message directed to a user;
generating an electronic message filter using the information extracted from the first electronic message, the electronic message filter having an associated filter action;
automatically determining expiration information indicating a time frame for applicability of the electronic message filter, the determining comprising using a trained machine model and feature data corresponding to the user as input to the trained machine model, the trained machine model being trained using feature data generated using a corpus of electronic messages corresponding to a plurality of users;
using the electronic message filter in a time frame in accordance with the determined expiration information, the using comprising:
identifying a second electronic message directed to the user, the identifying comprising determining, using information extracted from the second electronic message, that the second electronic message comprises second information satisfying the electronic message filter; and
performing the filtering action with the second electronic message.

18. The non-transitory computer-readable storage medium of claim 17 , further comprising:
identifying a first information item using the extracted information;
determining an information category for the identified first item; and
using the determined information category in generating the electronic message filter.

19. The non-transitory computer-readable storage medium of claim 18 , determining an item category further comprising:
using the identified first information item to search a data store to identify the item category.

20. A computing device comprising:
a processor;
a non-transitory storage medium for tangibly storing thereon program logic for execution by the processor, the program logic comprising:
extracting logic executed by the processor for extracting information from a first electronic message directed to a user;
generating logic executed by the processor for generating an electronic message filter using the information extracted from the first electronic message, the electronic message filter having an associated filter action;
determining logic executed by the processor for automatically determining expiration information indicating a time frame for applicability of the electronic message filter, the determining comprising using a trained machine model and feature data corresponding to the user as input to the trained machine model, the trained machine model being trained using feature data generated using a corpus of electronic messages corresponding to a plurality of users;
using logic executed by the processor for using the electronic message filter in a time frame in accordance with the determined expiration information, the using logic comprising:
identifying logic executed by the processor for identifying a second electronic m

Assignees

• Yahoo Assets Llc

Inventors

• Raviv Ariel
• Pelleg Dan
• Wolff Ran
• Lalouche Gal
• Avigdor-Elgrabli Noa

Classifications

• H04L51/42

  Mailbox-related aspects, e.g. synchronisation of mailboxes · CPC title

• H04L51/212 Primary

  using filtering or selective blocking · CPC title