Granted Patent B2

US 12,634,252 · App. 18/586,221 · Granted May 19, 2026

Inventor: Chingming Chao (Bellevue, WA)

Assignee: T-Mobile USA, Inc.

H04L51/10H04L51/04

Abstract

Claims (55)

1 . A method for generating and transmitting a generative artificial intelligence (AI) multimedia content via a mobile telecommunications network comprising:

receiving, from an input device processor associated with an input device, a request to transmit a text message to a terminating mobile device, wherein the request comprises an invocation key indicating a user request to generate multimedia content, wherein the invocation key contains a predetermined special character, and wherein the request is input using a text messaging application of the input device;

parsing the request to identify the invocation key indicating the user request to generate the multimedia content;

parsing the request to identify a set of descriptors for generating the multimedia content;

generating, based on the set of descriptors, a prompt for providing to a generative AI model;

transmitting, to the generative AI model, the generated prompt, wherein the generative AI model generates the multimedia content, wherein the generated prompt is transmitted to the generative AI model by a multimedia messaging service center of the mobile telecommunications network via an MM7 interface;

receiving, by the multimedia messaging service center from the generative AI model, the generated multimedia content;

generating, by the multimedia messaging service center, the text message including the generated multimedia content; and

transmitting, to the terminating mobile device using the multimedia messaging service center, the text message comprising the generated multimedia content.

2 . The method of claim 1 , wherein the invocation key comprises a string of predetermined characters indicating the user request for generating multimedia content.

3 . The method of claim 1 , wherein the multimedia content comprises at least one of: an image, a video, or an audio.

4 . The method of claim 1 , further comprising, prior to transmitting the multimedia content to the terminating mobile device:

transmitting, to the input device, the multimedia content;

receiving, from the input device, an indication to send the generated multimedia content to the terminating mobile device.

5 . The method of claim 1 , wherein the request includes an indication of a reference image for generating the multimedia content, and wherein transmitting the generated prompt comprises transmitting the reference image.

6 . The method of claim 5 , wherein the reference image is selected from one of: a local storage of the input device or a connected cloud service of a user of the input device.

7 . The method of claim 1 , further comprising, prior to generating the prompt:

determining one or more enrichments based on information about a user of the input device, the information including one or more of: an age of the user, a location of the user, a current weather at the location of the user, a forecasted weather at the location of the user, or an upcoming event of the user.

8 . The method of claim 1 , wherein the request further comprises a request to translate a message, wherein the method further comprises translating the message.

9 . The method of claim 1 , further comprising, prior to transmitting the text message to the terminating mobile device:

determining that a user of the input device has received at least a minimum number of messages from a receiving user.

10 . The method of claim 1 , wherein transmitting the text message to the terminating mobile device comprises transmitting the text message to a second, different multimedia messaging service center than a multimedia messaging service center involved in receiving the request from the input device processor.

11 . A system for generating and transmitting a generative artificial intelligence (AI) multimedia content via a mobile telecommunications network comprising:

a processor; and

a non-transitory memory, wherein the non-transitory memory has instructions encoded thereon that, when executed by the processor, cause the system to:

receive, from an input device processor associated with an input device, a request to transmit a text message to a terminating mobile device, wherein the request comprises an invocation key indicating a user request to generate multimedia content, wherein the invocation key contains a predetermined special character, and wherein the request is input using a text messaging application of the input device;

parse the request to identify the invocation key indicating the user request to generate the multimedia content;

parse the request to identify a set of descriptors for generating the multimedia content;

generate, based on the set of descriptors, a prompt for providing to a generative AI model;

transmit, to the generative AI model, the generated prompt, wherein the generative AI model generates the multimedia content, wherein the generated prompt is transmitted to the generative AI model using a multimedia messaging service center of the system via an MM7 interface;

receive, by the multimedia messaging service center of the system, from the generative AI model, the generated multimedia content;

generate, by the multimedia messaging service center of the system the text message including the generated multimedia content; and

transmit, to the terminating mobile device using the multimedia messaging service center of the system, the text message comprising the generated multimedia content.

12 . The system of claim 11 , wherein the invocation key comprises a string of predetermined characters indicated the user request for generating multimedia content.

13 . The system of claim 11 , wherein the multimedia content comprises at least one of: an image, a video, or an audio.

14 . The system of claim 11 , wherein the instructions, when executed by the processor, further cause the system to, prior to transmitting the generated multimedia content to the terminating mobile device:

transmit, to the input device, the generated multimedia content;

receive, from the input device, an indication to send the generated multimedia content to the terminating mobile device.

15 . The system of claim 11 , wherein the request includes an indication of a reference image for generating the multimedia content, and wherein transmitting the generated prompt comprises transmitting the reference image.

16 . The system of claim 15 , wherein the reference image is selected from one of: a local storage of the input device or a connected cloud service of a user of the input device.

17 . The system of claim 11 , wherein the request further comprises a request to translate a message, wherein the instructions, when executed by the processor, further cause the system to:

translate the message.

18 . The system of claim 11 , wherein the instructions, when executed by the processor, further cause the system to prior to transmitting the text message to the terminating mobile device:

determine that a user of the input device has received at least a minimum number of messages from a receiving user.

19 . The system of claim 11 , further comprising, prior to generating the prompt:

determining one or more enrichments based on information about a user of the input device, the information including one or more of: an age of the user, a location of the user, a current weather at the location of the user, a forecasted weather at the location of the user, or an upcoming event of the user.

20 . A non-transitory, computer-readable storage medium comprising instructions recorded thereon, wherein the instructions when executed by at least one processor of a system, cause the system to:

receive, from an input device processor, a request to transmit a text message to a terminating mobile device, wherein the request comprises an invocation key indicating a user request to generate multimedia content, wherein the invocation key contains a predetermined special character, and wherein the request is input using a text messaging application of the input device;

parse the request to identify the invocation key indicating the user request to generate the multimedia content;

parse the request to identify a set of descriptors for generating the multimedia content;

generate, based on the set of descriptors, a prompt for providing to a generative AI model;

transmit, to the generative AI model using a multimedia messaging service center of a mobile telecommunications network associated with the system, via an MM7 interface, the generated prompt, wherein the generative AI model generates the multimedia content;

receive, using the multimedia messaging service center, from the generative AI model, the generated multimedia content;

generate, using the multimedia messaging service center, the text message including the generated multimedia content; and

transmit, to the terminating mobile device using the multimedia messaging service center, the text message comprising the generated multimedia content.

Assignments (2)

Continuity (1)

References Cited (28)