Granted Patent B2

US 12,518,439 · App. 18/403,451 · Granted Jan 6, 2026

Inventors: Peter P. Myron (Renton, WA); Michael J. Mitchell (North Bend, WA)

Assignee: T-Mobile USA, Inc.

G06T11/00G06N3/0455G06N3/08G06T3/40H04L41/0686G06F40/205G06F40/30

Abstract

Claims (71)

1 . One or more non-transitory computer-readable media storing computer executable instructions that, when executed, cause one or more processors to perform operations comprising:

receiving report data associated with a notification system;

determining one or more notification subscribers to receive a notification alert for the report data;

determining first context data of context data associated with the one or more notification subscribers, wherein the first context data includes one or more of a user hobby, a job title, and a notification priority;

determining, by using the report data and the context data as input for one or more machine learning (ML) models, image text prompt for an artificial intelligence (AI) image generator, including:

determining, by the one or more ML models, second context data of context data associated with the report data, wherein the second context data includes one or more of a department information, a report type, and a report audience;

determining, by the one or more ML models, an interpreted tone of the report data, wherein the interpreted tone indicates one or more of a positive tone, a negative tone, and a severity level;

generating, using the AI image generator with the image text prompt as input, an emotion-inciting image; and

transmitting the notification alert with the emotion-inciting image.

2 . The one or more non-transitory computer-readable media of claim 1 , wherein determining the second context data comprises:

determining to retrieve a user profile associated with the one or more notification subscribers;

receiving, from a subscriber database, the user profile; and

determining to analyze the user profile for identifying the second context data.

3 . The one or more non-transitory computer-readable media of claim 1 , wherein the operations further comprise:

determining a system policy based on the department information; and

determining, based at least in part on the system policy, to modify the image text prompt.

4 . The one or more non-transitory computer-readable media of claim 1 , wherein the operations further comprise:

receiving user feedback for the emotion-inciting image; and

storing the user feedback with the report data, the image text prompt, and the emotion-inciting image as training data.

5 . The one or more non-transitory computer-readable media of claim 4 , wherein the operations further comprise:

determining to retrain the one or more ML models using the training data.

6 . A method comprising:

receiving report data associated with a notification system;

determining a subscriber account to receive a notification alert for the report data;

determining first context data of context data associated with the subscriber account;

determining, by one or more machine learning (ML) models based at least in part on a content of the report data, second context data of context data;

determining, by the one or more machine learning (ML) models based at least in part on the report data, an interpreted tone of the report data, wherein the interpreted tone indicates one or more of a positive tone, a negative tone, and a severity level;

determining, by the one or more machine learning (ML) models based at least in part on the context data and the interpreted tone, image text prompt for an artificial intelligence (AI) image generator; and

generating, by the AI image generator with the image text prompt as input, an emotion-inciting image.

7 . The method of claim 6 , wherein transmitting the notification alert further comprises:

determining a communication method for the notification alert;

determining, based at least in part on the communication method, to generate a reduced resolution image of the emotion-inciting image; and

transmitting the notification alert with the reduced resolution image.

8 . The method of claim 6 , further comprising:

transmitting the notification alert with the emotion-inciting image;

receiving user feedback for the emotion-inciting image; and

storing the user feedback with the report data, the image text prompt, and the emotion-inciting image as training data.

9 . The method of claim 8 , further comprising:

generating one or more second ML models using the training data, wherein the one or more second ML models adjusts one or more weights associated with one or more context data.

10 . The method of claim 6 , wherein the severity level is determined based at least in part by meeting a predetermined threshold value range.

11 . The method of claim 6 , wherein the severity level is determined based at least in part by exceeding a historical threshold value.

12 . The method of claim 6 , wherein the context data includes one or more of a user hobby, a job title, a notification priority, a department information, a report type, and a report audience.

13 . The method of claim 12 , further comprising:

determining a system policy based on the department information; and

determining, based at least in part on the system policy, to modify the image text prompt.

14 . A system comprising:

one or more processors;

a memory; and

one or more components stored in the memory and executable by the one or more processors to perform operations comprising:

receiving report data associated with a notification system;

determining a subscriber account to receive a notification alert for the report data;

determining first context data of context data associated with the subscriber account, wherein the first context data includes one or more of a user hobby, a job title, and a notification priority;

determining, by an image-generating model based at least in part on the report data, second context data of context data associated with the report data, wherein the second context data includes one or more of a department information, a report type, and a report audience;

determining, by the image-generating model based at least in part on the report data, an interpreted tone of the report data, wherein the interpreted tone indicates one or more of a positive tone, a negative tone, and a severity level;

determining, by the image-generating model based at least in part on the context data and the interpreted tone, image text prompt for an artificial intelligence (AI) image generator; and

generating, by the AI image generator with the image text prompt as input, an emotion-inciting image.

15 . The system of claim 14 , wherein determining the first context data comprises:

determining to retrieve a user profile associated with the subscriber account;

receiving, from a subscriber database, the user profile; and

determining a preferred communication method associated with the subscriber account.

16 . The system of claim 15 , wherein the preferred communication method indicates one of text messaging, email, and notification portal.

17 . The system of claim 16 , the operations further comprising:

determining to modify image quality of the emotion-inciting image based at least in part on the preferred communication method; and

transmitting the notification alert with the emotion-inciting image.

18 . The system of claim 14 , wherein the severity level is determined based at least in part on meeting or exceeding a threshold value.

19 . The system of claim 14 , the operations further comprising:

transmitting the notification alert with the emotion-inciting image;

receiving user feedback for the emotion-inciting image; and

storing the user feedback with the report data, the image text prompt, and the emotion-inciting image as training data.

20 . The system of claim 19 , the operations further comprising:

generating one or more second machine learning (ML) models using the training data, wherein the one or more second ML models adjusts one or more weights associated with one or more context data.

Assignments (1)

Continuity (1)

References Cited (12)