Granted Patent B2

US 12,394,443 · App. 18/346,727 · Granted Aug 19, 2025

Inventors: Fan Chen (Los Angeles, CA); Kin Chung Wong (Los Angeles, CA)

Assignee: Lemon Inc.

G11B27/02G06F16/3329G06F40/35

Abstract

Claims (59)

1. A method for media content editing, the method comprising:

receiving a media content from a user;

receiving an editing request for the media content from the user through a dialog-assisted editing interface;

editing the media content based on the editing request to generate edited media content by:

retrieving a prompt from a prompt pool, wherein the retrieved prompt is selected based on the editing request;

parsing the retrieved prompt and the editing request using a large language model to generate one or more editing actions to be performed on the media content; and

performing the one or more editing actions on the media content to generate the edited media content;

storing conversation history between the user and the large language model; and

determining from a conversation history that a plurality of rounds of edits performed by the user on the media content have been performed, and in response prompting the user to publish the edited media content.

2. The method of claim 1 , wherein performing the one or more editing actions comprises performing application programming interface calls provided by a back-end tool service comprising a plurality of editing tools, wherein each application programming interface call corresponds to a respective editing tool in the plurality of editing tools.

3. The method of claim 2 , wherein each editing tool in the plurality of editing tools corresponds to one or more prompts in the prompt pool.

4. The method of claim 2 , wherein the plurality of editing tools is organized into a plurality of groupings, and wherein the prompt pool is generated based at least in part on the plurality of groupings.

5. The method of claim 1 , further comprising rendering and displaying the edited media content to the user; and receiving a second editing request.

6. The method of claim 5 , wherein the second editing request comprises a request to revert the performed one or more editing actions.

7. The method of claim 1 , further comprising storing contextual information relating to the editing of the media content.

8. The method of claim 7 , wherein the contextual information comprises one or more of the conversation history, an editing context, or an editing draft history.

9. The method of claim 8 , further comprising refining the prompt pool based on the contextual information.

10. The method of claim 1 , wherein editing the media content further comprises:

providing a dialog reply to the user, wherein the dialog reply is generated by the large language model in response to the retrieved prompt and the editing request; and

receiving a dialog response from the user in response to the dialog reply.

11. A computing device for media content editing, the computing device comprising:

a processor and memory of a computing device, the processor being configured to execute a program using portions of the memory to:

receive a media content from a user:

receive an editing request for the media content from the user through a dialog-assisted editing interface;

edit the media content based on the editing request to generate edited media content by:

retrieving a prompt from a prompt pool, wherein the retrieved prompt is selected based on the editing request;

parsing the retrieved prompt and the editing request using a large language model to generate one or more editing actions to be performed on the media content; and

performing the one or more editing actions on the media content to generate the edited media content;

store conversation history between the user and the large language model; and

determine from a conversation history that a plurality of rounds of edits performed by the user on the media content have been performed, and in response prompt the user to publish the edited media content.

12. The computing device of claim 11 , wherein performing the one or more editing actions comprises performing application programming interface calls provided by a back-end tool service comprising a plurality of editing tools, wherein each application programming interface call corresponds to a respective editing tool in the plurality of editing tools.

13. The computing device of claim 12 , wherein:

each editing tool in the plurality of editing tools corresponds to one or more prompts in the prompt pool;

the plurality of editing tools is organized into a plurality of groupings; and

the prompt pool is generated based at least in part on the plurality of groupings.

14. The computing device of claim 11 , wherein the processor is further configured to store contextual information relating to the editing of the media content, wherein the contextual information comprises one or more of the conversation history, an editing context, or an editing draft history.

15. The computing device of claim 11 , wherein editing the media content further comprises:

providing a dialog reply to the user, wherein the dialog reply is generated by the large language model in response to the retrieved prompt and the editing request; and

receiving a dialog response from the user in response to the dialog reply.

16. A computing system for media content editing, the computing system comprising:

a display;

a back-end tool service comprising a prompt pool, a plurality of editing tools, and a plurality of application programming interfaces, each application programming interface corresponding to an editing tool in the plurality of editing tools;

a processor and memory of a computing device, the processor being configured to execute a program using portions of the memory to:

receive a media content from a user:

receive an editing request for the media content from the user through a dialog-assisted editing interface;

edit the media content based on the editing request to generate edited media content by:

retrieving a prompt from the prompt pool, wherein the retrieved prompt is selected based on the editing request;

parsing the retrieved prompt and the editing request using one or more large language models to generate one or more editing actions to be performed on the media content; and

performing the one or more editing actions on the media content by calling at least one application programming interface in the plurality of application programming interfaces to generate the edited media content;

render and display the edited media content using the display through the dialog-assisted editing interface;

store conversation history between the user and the large language model; and

determine from a conversation history that a plurality of rounds of edits performed by the user on the media content have been performed, and in response prompt the user to publish the edited media content.

17. The computing system of claim 16 , wherein the one or more large language models comprises a plurality of large language models, each trained for at least one task, and wherein the processor is configured to select a large language model from the plurality of large language models to parse the retrieved prompt and the editing request.

18. The computing system of claim 16 , wherein:

each editing tool in the plurality of editing tools corresponds to one or more prompts in the prompt pool;

the plurality of editing tools is organized into a plurality of groupings; and

prompts in the prompt pool are generated based at least in part on the plurality of groupings.

19. The computing system of claim 16 , wherein the processor is further configured to store contextual information relating to the editing of the media content, wherein the contextual information comprises one or more of the conversation history, an editing context, or an editing draft history.

20. A non-transitory computer readable medium for media content editing, the non-transitory computer readable medium comprising instructions that, when executed by a computing device, cause the computing device to implement the method of claim 1 .

Assignments (2)

Continuity (1)

References Cited (46)