IP Library › Granted Patent US 12,671,665
Granted Patent B2
US 12,671,665 · App. 18/436,466 · Granted Jun 30, 2026

Automatically generating and targeting communications using artificial intelligence techniques

Inventors: Abhishek Mishra (Bangalore, IN); Vivek Bhargava (Bangalore, IN); Piyush Goswami (Bangalore, IN); Ajith Navada (Davangere District, IN)
Assignee: Dell Products L.P.
H04L51/043H04L41/16H04L41/5019
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,671,665
App. No.
18/436,466
Granted
Jun 30, 2026
Kind
B2
Abstract

Methods, apparatus, and processor-readable storage media for automatically generating and targeting communications using artificial intelligence techniques are provided herein. An example computer-implemented method includes obtaining notification data associated with one or more software applications and/or one or more processing devices; determining at least one issue and one or more actions for resolving at least a portion of the issue(s) by processing at least a portion of the notification data using one or more artificial intelligence techniques; identifying at least one recipient of communication data related to the at least one issue by processing user-related data, across multiple users, in connection with the issue(s) and/or the action(s); generating the communication data including identification of the issue(s) and a recommendation for performing the action(s); and transmitting at least a portion of the communication data to the at least one recipient.

Claims (40)

1 . A computer-implemented method comprising:

obtaining notification data associated with at least one of one or more software applications and one or more processing devices;

determining at least one issue and one or more actions for resolving at least a portion of the at least one issue by processing at least a portion of the notification data using one or more large language models (LLMs), wherein determining at least one issue and one or more actions for resolving at least a portion of the at least one issue comprises determining one or more temporal constraints applicable to carrying out at least a portion of the one or more actions by processing, at least in part in the one or more LLMs, service level agreement data associated with at least one of the one or more software applications and the one or more processing devices;

identifying at least one recipient of communication data related to the at least one issue by processing user-related data, across multiple users, in connection with one or more of the at least one issue and the one or more actions;

generating the communication data related to the at least one issue, wherein the communication data comprises identification of the at least one issue and a recommendation for performing the one or more actions for resolving at least a portion of the at least one issue, wherein the recommendation includes identification of at least one of the one or more temporal constraints applicable to carrying out the at least a portion of the one or more actions; and

transmitting at least a portion of the communication data to the at least one recipient;

wherein the method is performed by at least one processing device comprising a processor coupled to a memory.

2 . The computer-implemented method of claim 1 , wherein determining at least one issue and one or more actions for resolving at least a portion of the at least one issue comprises processing the at least a portion of the notification data using one or more natural language processing (NLP) techniques.

3 . The computer-implemented method of claim 1 , wherein identifying at least one recipient comprises processing availability-related data associated with at least a portion of the multiple users.

4 . The computer-implemented method of claim 1 , wherein identifying at least one recipient comprises identifying one or more of the multiple users who have previously performed at least a portion of the one or more actions by processing historical records associated with at least a portion of the multiple users.

5 . The computer-implemented method of claim 1 , wherein identifying at least one recipient comprises identifying one or more of the multiple users associated with a domain of work related to the one or more actions.

6 . The computer-implemented method of claim 1 , wherein generating the communication data comprises generating the recommendation for performing the one or more actions in a given sequence.

7 . The computer-implemented method of claim 1 , wherein transmitting at least a portion of the communication data to the at least one recipient comprises using at least one foreground application in use on a user device associated with the at least one recipient.

8 . The computer-implemented method of claim 1 , further comprising:

performing one or more automated actions based at least in part on feedback related to transmitting the at least a portion of the communication data to the at least one recipient.

9 . The computer-implemented method of claim 8 , wherein performing one or more automated actions comprises automatically training at least a portion of the one or more LLMs using at least a portion of the feedback related to transmitting the at least a portion of the communication data to the at least one recipient.

10 . The computer-implemented method of claim 1 , wherein generating the communication data comprises generating at least one request for the at least one recipient to approve or reject with respect to performing the one or more actions.

11 . The computer-implemented method of claim 10 , further comprising:

training at least one artificial intelligence-based classifier to calculate a probability of a given recipient approving a given request using feedback from the at least one recipient in response to the at least one request.

12 . The computer-implemented method of claim 11 , wherein identifying at least one recipient comprises ranking at least a portion of the multiple users based at least in part on probability values generated using the at least one artificial intelligence-based classifier.

13 . A non-transitory processor-readable storage medium having stored therein program code of one or more software programs, wherein the program code when executed by at least one processing device causes the at least one processing device:

to obtain notification data associated with at least one of one or more software applications and one or more processing devices;

to determine at least one issue and one or more actions for resolving at least a portion of the at least one issue by processing at least a portion of the notification data using one or more large language models (LLMs), wherein determining at least one issue and one or more actions for resolving at least a portion of the at least one issue comprises determining one or more temporal constraints applicable to carrying out at least a portion of the one or more actions by processing, at least in part in the one or more LLMs, service level agreement data associated with at least one of the one or more software applications and the one or more processing devices;

to identify at least one recipient of communication data related to the at least one issue by processing user-related data, across multiple users, in connection with one or more of the at least one issue and the one or more actions;

to generate the communication data related to the at least one issue, wherein the communication data comprises identification of the at least one issue and a recommendation for performing the one or more actions for resolving at least a portion of the at least one issue, wherein the recommendation includes identification of at least one of the one or more temporal constraints applicable to carrying out the at least a portion of the one or more actions; and

to transmit at least a portion of the communication data to the at least one recipient.

14 . The non-transitory processor-readable storage medium of claim 13 , wherein determining at least one issue and one or more actions for resolving at least a portion of the at least one issue comprises processing the at least a portion of the notification data using one or more NLP techniques.

15 . The non-transitory processor-readable storage medium of claim 13 , wherein generating the communication data comprises generating the recommendation for performing the one or more actions in a given sequence.

16 . The non-transitory processor-readable storage medium of claim 13 , wherein transmitting at least a portion of the communication data to the at least one recipient comprises using at least one foreground application in use on a user device associated with the at least one recipient.

17 . An apparatus comprising:

at least one processing device comprising a processor coupled to a memory;

the at least one processing device being configured:

to obtain notification data associated with at least one of one or more software applications and one or more processing devices;

to determine at least one issue and one or more actions for resolving at least a portion of the at least one issue by processing at least a portion of the notification data using one or more large language models (LLMs), wherein determining at least one issue and one or more actions for resolving at least a portion of the at least one issue comprises determining one or more temporal constraints applicable to carrying out at least a portion of the one or more actions by processing, at least in part in the one or more LLMs, service level agreement data associated with at least one of the one or more software applications and the one or more processing devices;

to identify at least one recipient of communication data related to the at least one issue by processing user-related data, across multiple users, in connection with one or more of the at least one issue and the one or more actions;

to generate the communication data related to the at least one issue, wherein the communication data comprises identification of the at least one issue and a recommendation for performing the one or more actions for resolving at least a portion of the at least one issue, wherein the recommendation includes identification of at least one of the one or more temporal constraints applicable to carrying out the at least a portion of the one or more actions; and

to transmit at least a portion of the communication data to the at least one recipient.

18 . The apparatus of claim 17 , wherein determining at least one issue and one or more actions for resolving at least a portion of the at least one issue comprises processing the at least a portion of the notification data using one or more NLP techniques.

19 . The apparatus of claim 17 , wherein generating the communication data comprises generating the recommendation for performing the one or more actions in a given sequence.

20 . The apparatus of claim 17 , wherein transmitting at least a portion of the communication data to the at least one recipient comprises using at least one foreground application in use on a user device associated with the at least one recipient.