EP-4740134-A1 - SYSTEM EVOLVING ARCHITECTURES FOR REFINING MEDIA CONTENT EDITING SYSTEMS

Abstract

Examples are provided relating to system evolving architectures for refining media content editing systems One aspect includes a method of refining a media content editing architecture, the method comprising: editing a media content using a large language model and a back-end tool service comprising a prompt pool and a plurality of application programming interfaces corresponding to a plurality of editing tools; publishing the edited media content; storing contextual information relating to the editing of the media content; and refining the media content editing architecture using the stored contextual information.

Inventors

• CHEN, FAN
• WONG, Kin Chung

Assignees

• Lemon Inc.

Dates

Publication Date

20260513

Application Date

20240628

Claims (20)

1. 1. A method of refining a media content editing architecture, the method comprising: editing a media content using a large language model and a back-end tool service comprising a prompt pool and a plurality of application programming interfaces corresponding to a plurality of editing tools; publishing the edited media content; storing contextual information relating to the editing of the media content; and refining the media content editing architecture using the stored contextual information.
2. 2. The method of claim 1, wherein refining the media content editing architecture comprises refining the large language model and the prompt pool.
3. 3. The method of claim 1, wherein the stored contextual information comprises conversation history that is categorized into user accepted interactions and user rejected interactions, and wherein refining the media content editing architecture comprises refining the prompt pool based on the user accepted interactions and user rejected interactions.
4. 4. The method of claim 1, wherein refining the media content editing architecture comprises refining the large language model using the contextual information and a reward function.
5. 5. The method of claim 4, wherein the reward function is based on one or more viewer engagement indicators associated with the published edited media content.
6. 6. The method of claim 5, wherein the one or more viewer engagement indicators comprise a metric that is one or more of views, likes, shares, or comments.
7. 7. The method of claim 5, wherein refining the large language model comprises refining the large language model using the contextual information when the one or more viewer engagement indicators reach a predetermined threshold.
8. 8. The method of claim 7, wherein the predetermined threshold comprises reaching a predetermined number of views within a predetermined amount of time since publication of the edited media content.
9. 9. The method of claim 1, wherein the contextual information comprises one or more of conversation history, editing context, or editing draft history.
10. 10. The method of claim 1 , wherein the media content is published on a short-form social media platform.
11. 11. A computing device for refining a media content editing architecture, 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: edit a media content using a large language model and a back-end tool service comprising a prompt pool and a plurality of application programming interfaces corresponding to a plurality of editing tools; publish the edited media content; store contextual information relating to the editing of the media content; and refine the media content editing architecture using the stored contextual information.
12. 12. The computing device of claim 11, wherein the stored contextual information comprises conversation history that is categorized into user accepted interactions and user rejected interactions, and wherein refining the media content editing architecture comprises refining the prompt pool based on the user accepted interactions and user rejected interactions.
13. 13. The computing device of claim 11, wherein refining the media content editing architecture comprises refining the large language model using the contextual information and a reward function.
14. 14. The computing device of claim 13, wherein the reward function is based on one or more viewer engagement indicators associated with the published edited media content, and wherein the one or more viewer engagement indicators comprise a metric that is one or more of views, likes, shares, or comments.
15. 15. The computing device of claim 11, wherein the contextual information comprises one or more of conversation history, editing context, or editing draft history.
16. 16. A computing system for refining a media content editing architecture, the computing system comprising: a social media network application comprising a dialog assisted editing interface; memory storing one or more large language models; a processor configured to execute a program using portions of the memory to: edit a media content using the dialog assisted editing interface, the one or more large language models, and a back-end tool service comprising a prompt pool and a plurality of application programming interfaces corresponding to a plurality of editing tools; publish the edited media content using the social media network application; store contextual information in the memory, wherein the contextual information relates to the editing of the media content; and refine the media content editing architecture using the stored contextual information.
17. 17. The computing system of claim 16, wherein the contextual information comprises conversation history that is categorized into user accepted interactions and user rejected interactions, and wherein refining the media content editing architecture comprises refining the prompt pool based on the user accepted interactions and user rejected interactions.
18. 18. The computing system of claim 16, wherein refining the media content editing architecture comprises refining the one or more large language models using the contextual information and a reward function.
19. 19. The computing system of claim 18, wherein the reward function is based on one or more viewer engagement indicators associated with the published edited media content, and wherein the one or more viewer engagement indicators comprise a metric that is one or more of views, likes, shares, or comments.
20. 20. A non-transitory computer readable medium for refining a media content editing architecture, 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.

Description

SYSTEM EVOLVING ARCHITECTURES FOR REFINING MEDIA CONTENT EDITING SYSTEMS CROSS REFERENCE TO RELATED APPLICATIONS [0001] This application claims priority to U S. Application Ser No. 18/346,737, filed July 3, 2023, and titled “SYSTEM EVOLVING ARCHITECTURES FOR REFINING MEDIA CONTENT EDITING SYSTEMS”, the disclosure of which is incorporated herein by reference in its entirety. BACKGROUND [0002] Raw media content in its original recorded form is typically edited before publication to enhance its appeal for better viewer engagement. Editing media content (e g., images, audios, videos, and other modalities) typically involves the use of software with editing capabilities provided in the form of editing tools Edits to media content can include a wide range of manipulations and modifications. For example, in the context of video editing, edits can include trimming segments, re-sequencing segments, adjusting playback speed, embedding content such as special effects and caption text, adjusting audio, cropping, etc. Additionally, the use of powerful editing software enables non-linear editing (NLE) systems where multiple edits are performed on raw media content in a non-destructive process such that the original data can be recovered - i.e., the edits can be reversed. SUMMARY [0003] Examples are provided relating to system evolving architectures for refining media content editing systems. One aspect includes a method of refining a media content editing architecture, the method comprising: editing a media content using a large language model and a back-end tool service comprising a prompt pool and a plurality of application programming interfaces corresponding to a plurality of editing tools, publishing the edited media content; storing contextual information relating to the editing of the media content; and refining the media content editing architecture using the stored contextual information. [0004] This Summary is provided to introduce a selection of concepts in a simplified form that are further described below in the Detailed Description. This Summary is not intended to identify key features or essential features of the claimed subject matter, nor is it intended to be used to limit the scope of the claimed subject matter. Furthermore, the claimed subject matter is not limited to implementations that solve any or all disadvantages noted in any part of this disclosure. BRIEF DESCRIPTION OF THE DRAWINGS [0005] FIG. 1 shows a block diagram model describing a general pipeline and various components of an example technical architecture for implementing a media content editing application. [0006] FIG. 2 is a block diagram model illustrating an example back-end tool service for providing editing tools and editing capabilities, which can be implemented in the general pipeline described in FIG. 1. [0007] FIG. 3 is a block diagram model illustrating an example use of contextual memory 302 in a media content editing architecture, which can be implemented in the general pipeline described in FIG. 1. [0008] FIG. 4 is a block diagram model illustrating an example system evolving and refinement application for a media content editing architecture, which can be implemented in the general pipeline described in FIG. 1. [0009] FIG. 5 is a block diagram model illustrating an example media content editing model architecture with a system evolving and refinement process, which provides a detailed illustration of the general pipeline described in FIG. 1. [0010] FIG. 6 is a flow chart illustrating an example method for a media content editing process using machine learning techniques, which can be implemented using the technical architecture of FIG 1. [0011] FIG. 7 is a flow chart illustrating an example method for refining a media content editing architecture, which can be implemented using the technical architecture of FIG. 1. 100121 FIG. 8 schematically shows a non-limiting embodiment of a computing system that can enact one or more of the methods and processes described above. DETAILED DESCRIPTION [0013] Media content editing software capable of providing powerful editing tools is widely available for commercial and personal uses. Typically, content editing software involves the use of a user interface (UI) with various sections, menus, buttons, etc. for navigating and selecting the desired editing tool. These technologies have grown over time to provide a vast array of tools for performing numerous editing tasks. However, software with more powerful editing capabilities and functionalities will naturally result in more complexity. As a result, many features remain unexplored for the typical user. Complex UI navigation, a lack of knowledge in the software’s capabilities, and difficulty in utilizing said capabilities can all contribute to the underutilization of editing software. For example, a typical user of editing software may be unaware of or lack the ability to use a particular tool or feature of said software to perform the