Generation media output method and generation media output system

The system addresses limitations in audio-video processing by separating and aligning tracks using AI, enabling automatic generation and mixing of new media content for various applications.

JP7953935B2Active Publication Date: 2026-11-19呉建州
View PDF 5 Cites 0 Cited by

Patent Information

Application Number
JP2025077982
Authority / Receiving Office
JP · JP
Patent Type
Patents
Current Assignee / Owner
Priority Date
2024-06-19
Filing Date
2025-05-08
Publication Date
2026-11-19
Estimated Expiration
2045-05-08

AI Technical Summary

Technical Problem

Conventional methods fail to automatically generate matching audio tracks, cannot perform object identification and edge detection on audio-video sources, and lack the ability to autonomously create new content based on selected audio tracks.

Method used

A method and system utilizing a feedforward neural network and object identification model to separate and align audio-video information, generating new media by combining split track information with artificial intelligence, and mixing it with selected audio tracks.

Benefits of technology

Facilitates automatic generation of new media content, supports smooth system communication, and enables diverse applications in entertainment, education, and creative works.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure 0007953935000001
    Figure 0007953935000001
  • Figure 0007953935000002
    Figure 0007953935000002
  • Figure 0007953935000003
    Figure 0007953935000003
Patent Text Reader

Abstract

To provide a generated media output method and a generated media output system.SOLUTION: The method for acquiring network audio and video information, performing track segmentation processing and outputting production media in combination with artificial intelligence according to the present invention comprises the following steps: the device server 11 or the production artificial intelligence server 3 acquires network audio and video information, separates a plurality of segment track information and then combines at least one production information into production media, and the device server 11 plays the production media in the playback interface 12. Thus, the production media are outputted at a high speed based on the network audio video information and the production information.SELECTED DRAWING: Figure 1
Need to check novelty before this filing date? Find Prior Art

Description

TECHNICAL FIELD

[0001] The present invention relates to a method and system for performing track separation processing on network audio and video information, generating generation information in combination with artificial intelligence, and further outputting generated media. Hereinafter, in the present specification, "audio and video" is abbreviated as "audio-video". BACKGROUND ART

[0002] In conventional patent documents, for example, the following Patent Document 1 discloses a music matching method. The apparatus, electronic device, and computer are capable of reading stored media, and mainly perform audio track separation on to-be-matched music to obtain a target audio track of the to-be-matched music. The target audio track includes a target person's voice audio track, a target accompaniment audio track, a target bass audio track, and a target drum audio track, and the first target drum sequence and the second target drum sequence are obtained based on the target drum audio track. Finally, at least one target music piece is selected from candidate music pieces, and a to-be-matched video containing the target music piece is set as the target video. PRIOR ART DOCUMENTS PATENT DOCUMENTS

[0003] PATENT DOCUMENT 1 Chinese Patent Application Publication No. 116939323A Specification SUMMARY OF THE INVENTION PROBLEMS TO BE SOLVED BY THE INVENTION

[0004] However, the aforementioned Patent Document 1 has the following limitations. 1. Matching of target music and target video is performed based on the target drum audio track. 2. It is not possible to automatically generate a generated audio track that matches the target audio track. 3. Multiple target audio tracks can be separated only for music awaiting matching, and operations such as object identification, edge detection, and subject capture cannot be performed on audio-video sources that include video. 4. It is not possible to autonomously generate new matching videos, footage, or other content based on the selected target audio track.

[0005] Therefore, the inventors believed that the above-mentioned shortcomings could be improved, and after diligent research, they developed the present invention, which effectively improves the above-mentioned problems through rational design. Network audio and video information We proposed a method and system for acquiring data, performing track splitting processing, and outputting generated media by combining it with artificial intelligence. [Means for solving the problem]

[0006] To solve the above objective, one aspect of the present invention is Network audio and video informationA method for acquiring and performing track splitting processing and outputting generated media in combination with artificial intelligence includes the steps of: an audio-video playback device server, or a generated artificial intelligence server to which a signal is connected, acquiring network audio-video information from a streaming platform; the device server or the generated artificial intelligence server separating a plurality of split track information from the network audio-video information using a sampling module; the generated artificial intelligence server selecting some or all of the split track information, positioning the selected split track information so that it aligns on the time axis; the generated artificial intelligence server generating at least one generated information based on the selected split track information, and positioning the generated information so that it aligns on the time axis with the split track information; the generated artificial intelligence server mixing the selected split track information and the generated information, outputting it as generated media, and feeding it back to the device server; and the device server playing the generated media in the playback interface of the audio-video playback device. The sampling module includes a feedforward neural network, samples the segmented track information from the network audio-video information based on frequency characteristics, and captures the main subject's video from the network audio-video information using an object identification model and an edge detection algorithm.

[0007] Furthermore, in order to achieve the above objective, another aspect of the present invention is Network audio and video informationThe system, which acquires network audio-video information, performs track splitting, and outputs generated media by combining it with artificial intelligence, has a signal connected to a streaming platform. The system, which acquires network audio-video information, performs track splitting, and outputs generated media by combining it with artificial intelligence, comprises an audio-video playback device having a device server and a playback interface to which a signal is connected to the device server, a sampling module to which a signal is connected to the device server, and a generating artificial intelligence server to which signals are connected to the device server and the sampling module. The device server or the generating artificial intelligence server acquires network audio-video information from the streaming platform, and then the device server or the generating artificial intelligence server separates a plurality of split track pieces from the network audio-video information using the sampling module. The generating artificial intelligence server selects some or all of the split track pieces, positions the selected split track pieces so that they are aligned on the time axis, generates at least one generated piece of information based on the selected split track pieces, and positions the generated piece of information so that it is aligned on the time axis with the split track pieces. The generating artificial intelligence server mixes the selected split track pieces and the generated piece of information, outputs it as generated media, and also provides feedback to the device server. The device server plays the generated media during the playback interface. The sampling module includes a feedforward neural network, which samples the segmented track information from the network audio-video information based on frequency characteristics, and captures the main subject's video from the network audio-video information using an object identification model and an edge detection algorithm. [Effects of the Invention]

[0008] As the present invention is configured as described above, it produces the following effects. 1. Application Programming Interface (API) technology is used to facilitate communication between different systems or application programs. Furthermore, APIs can be modularized and configured based on different capture targets, making operations smoother and maintenance easier. 2. The generation AI server automatically generates one or more matching generated pieces of information on the time axis based on the input segmented track information. All generated pieces of information generated by the generation AI server are selectable independent items. The generation AI server superimposes the selected generated pieces of information onto the input segmented track information to rapidly generate a completely new generated medium, which can be widely applied to entertainment, education, creative works, and other uses.

[0009] The following information will be clear from the description and drawings described later. Note that "YouTube," "Netflix," "Spotify," and "KKBOX" in Figures 3 and 4 are all registered trademarks. [Brief explanation of the drawing]

[0010] [Figure 1] This is a block diagram showing a system according to one embodiment of the present invention that acquires network audio video information, performs track splitting processing, and outputs generated media by combining it with artificial intelligence. [Figure 2] This flowchart shows a method and system according to one embodiment of the present invention for acquiring network audio-video information, performing track splitting processing, and outputting generated media by combining it with artificial intelligence. [Figure 3] This is a schematic diagram (1) of a search sort interface according to one embodiment of the present invention, which has a single search mode and an integrated search mode. [Figure 4] This is a schematic diagram (2) showing how search results are displayed in a search sort interface according to one embodiment of the present invention. [Figure 5]FIG. 3 is a schematic diagram (Part 3) in a case where audio-only network audio-video information is divided into separate tracks according to an embodiment of the present invention. [Figure 6] FIG. 4 is a schematic diagram (Part 4) in a case where generation information is mixed based on audio-only network audio-video information and output as generated media according to an embodiment of the present invention. [Figure 7] FIG. 5 is a schematic diagram (Part 5) in a case where network audio-video information including audio and pictures is divided into separate tracks according to an embodiment of the present invention. [Figure 8] FIG. 6 is a schematic diagram (Part 6) in a case where generation information is mixed based on network audio-video information including audio and pictures and output as generated media according to an embodiment of the present invention. [Figure 9] FIG. 7 is a schematic diagram (Part 7) in a case where generation information is mixed based on network audio-video information including audio and pictures and output as other generated media according to an embodiment of the present invention. [Mode for Carrying Out the Invention]

[0011] Hereinafter, embodiments of the present invention will be described in detail. However, the present invention is not limited thereto, and various modifications are possible within the described scope, and embodiments obtained by appropriately combining technical means respectively disclosed in different embodiments are also included in the technical scope of the present invention.

[0012] FIG. 1 shows a system according to the present invention Network audio and video information that acquires data, executes track division processing, and outputs generated media in combination with artificial intelligence (hereinafter referred to as the present system) is used to execute a method according to the present invention Network audio and video information that acquires data, executes track division processing, and outputs generated media in combination with artificial intelligence (hereinafter referred to as the present method).

[0013] In this system, signals are connected to a plurality of streaming platforms A, such as YouTube (registered trademark), Netflix (registered trademark) and the like that play audio-video, and Spotify (registered trademark), KKBOX (registered trademark) and the like that play music. Each of the streaming platforms A is all provided with an API server A1.

[0014] This system includes the following configurations. Each of them will be described below.

[0015] <Audio-video playback device 1> It has a device server 11, and a playback interface 12, a search and sorting interface 13, an open interface 14, and a database 15, each of which is signal-connected to the device server 11.

[0016] The device server 11 is signal-connected to all the API servers A1 respectively, and a plurality of open interfaces 14 corresponding one-to-one to the streaming platforms A may be provided based on the number of the streaming platforms A. The database 15 may be a physical hard disk, a storage area network, a cloud hard disk, or the like.

[0017] <Sampling module 2> A signal is connected to the device server 11. Preferably, the sampling module 2 includes a feedforward neural network, an item identification model, and an edge detection algorithm. The feedforward neural network is one of the following: multi-source separation model (UMX), speech frequency separation network (TasNet), speech separation model (Looking to listen), speech separation model (Demucs), and dual path transformation network (DPTNet); the item identification model is one of the following: YOLO8, Vision Master, Vision AI, and Amazon Rekognition®; and the edge detection algorithm is one of the following: Canny edge detection algorithm, Laplacian edge detection algorithm, and Sobel edge detection algorithm.

[0018] <Generating Artificial Intelligence Server 3> The signal is connected to the device server 11 via the sampling module 2.

[0019] Refer to Figures 1 and 2. This method comprises the following steps. First, the system is installed. For example, an audio-video playback device 1 is purchased, and the audio-video playback device 1 is connected to the cloud-based sampling module 2 and the generating artificial intelligence server 3. Alternatively, the application program deployed by this system is loaded onto a playback device or PC that the user already owns, and the processing unit of the playback device or PC itself is used as the device server 11 to execute this method.

[0020] Refer to Figures 3 and 4. Also refer to Figures 1 and 2. The user searches for network audio-video information B, such as audio-video or music, that they want to play using the single search mode or integrated search mode of the search sort interface 13 (see Figure 5 for network audio-video information B).

[0021] In single search mode, different streaming platforms A, as shown in Figure 3, select the corresponding search option based on whether the music you want to play has no video, or whether the audio-video has video.

[0022] The user selects a single search mode for one of the streaming platforms A, then enters the keyword they want to search for, and the device server 11 sends an audio-video search request to the selected API server A1 using Application Programming Interface (API) technology based on the keyword.

[0023] API server A1 performs a search based on an audio-video search request and retrieves search results corresponding to the keywords. Device server 11 obtains multiple link codes of the search results from API server A1 via the API, and each link code corresponds to a different network audio-video information B. The search sort interface 13 first removes link codes corresponding to network audio-video information B that are in an invalid state, then arranges the link codes in the search sort interface 13 and displays the search results.

[0024] Taking YouTube (registered trademark) as an example, after YouTube (registered trademark) receives an audio-video search request, YouTube's API server A1 performs a search using YouTube's own search engine, and the retrieved search results include multiple audio-videos.

[0025] This invention links information such as the address, name, and creator of these audio and video files as a link code, while eliminating invalid link codes that have copyright issues, playback rights issues, or violations of streaming platform A's policies. It also allows users to fully view YouTube® search results using the search and sort interface 13 without having to open the YouTube® webpage or the YouTube® application program screen. Playback is not interrupted due to invalid link codes, and the user's audio and video viewing experience is not affected.

[0026] In the integrated search mode, as shown in Figure 3, for example, when the user enters the keyword they want to search for, the device server 11 sends an audio-video search request to all the API servers A1 of the streaming platform A, and each API server A1 performs the search independently and retrieves its own search results.

[0027] The device server 11 integrates multiple network audio video information B from different streaming platforms A that have the same name or creator into a single data set, or it also integrates multiple network audio video information B from the same creator that have the same keywords but not exactly the same name into a single data set, and in the search sort interface 13 it indicates that this data has sources from different streaming platforms A, and displays the search results for all streaming platforms A in a single search sort interface 13, allowing the user to make a selection (see Figure 4).

[0028] The user clicks on the corresponding source icon to add the link code of the specific source to the playlist. The user can then delete, rearrange, etc., the link codes using the playlist options shown in Figure 3. This is an intuitive operation method that users will quickly become familiar with.

[0029] The device server 11 or the generating artificial intelligence server 3 sequentially retrieves link codes from the playlist, parses the link codes using the API, and then retrieves network audio video information B from the API server A1. Similarly, there is no need to jump to the web pages of other streaming platforms A, use application programs, or download network audio video information B.

[0030] Directly downloading network audio-video information B from streaming platform A without employing an API is also a possible embodiment of the present invention.

[0031] Preferably, the device server 11 or the generating artificial intelligence server 3 first verifies whether the streaming platform A is open. For example, it verifies whether the user is logged in, whether the paid mode is open, etc.

[0032] If streaming platform A is not open, the device server 11 displays an open interface 14 corresponding to streaming platform A in the audio-video playback device 1, opens it to the user, then retrieves network audio-video information B, and restores the source of network audio-video information B to a normal state.

[0033] Next, the feedforward neural network of the sampling module 2 separates the network audio-video information B into multiple split-track information C1, C2, and C3 for sampling based on frequency characteristics (see Figure 5). The split-track information C1, C2, and C3 include the audio data of the split-track, the video of the split-track, the main subject's video, lyrics, outlined text, narration, etc. The main subject's video is preferably acquired by capturing it using an object identification model and an edge detection algorithm.

[0034] The generating artificial intelligence server 3 randomly or based on user commands selects partial or all of the divided track information C1, C2, and C3, and positions the selected divided track information C1, C2, and C3 so that their positions are aligned on the time axis. For example, all the divided track information C1, C2, and C3 start from the same playback time of 0 seconds during the sampling process, and the starting point of the playback time is marked as the starting point of each divided track information C1, C2, and C3 on the time axis. The positioning of the divided track information C1, C2, and C3 is completed by aligning the positions of the starting points of each selected divided track information C1, C2, and C3.

[0035] The generation artificial intelligence server 3 generates at least one generation information D1, D2, and D3 based on the selected split track information C1, C2, and C3 (see Figure 6), and positions the generation information D1, D2, and D3 so as to align with the split track information C1, C2, and C3 on the time axis. The generation information D1, D2, and D3 include generated audio data, static generated video, dynamically sequential generated video, generated text, etc.

[0036] The generating artificial intelligence server 3 automatically or based on user commands performs additional modifications such as changes in musical style, rhythm, melody, volume, and tone on selected partial segmented track information C1, C2, and C3, thereby meeting the diverse needs of each user for a wide range of applications including entertainment, education, and creative work.

[0037] Finally, the generation artificial intelligence server 3 mixes the selected split track information C1, C2, C3 and generation information D1, D2, D3, outputs it as generated media E, and feeds it back to the device server 11 (see Figure 6). The device server 11 then plays the generated media E into the playback interface 12 for the user to enjoy.

[0038] Refer to Figures 5 and 6. Also refer to Figures 1 and 2. In one embodiment, network audio video information B contains only voice. The split track information C1, C2, and C3 after track splitting contains only audio data for the split tracks, such as drum sounds, violin sounds, and piano sounds. The generating artificial intelligence server 3 can generate generated information D1, D2, and D3, such as generated images, generated videos, and generated text, such as static seaside buildings and continuously changing sailing ships. The generating artificial intelligence server 3 mixes the split track information C1, C2, and C3 and the generated information D1, D2, and D3 and outputs it as generated media E.

[0039] Refer to Figures 7 to 9. Refer to Figures 1 and 2 together. In another embodiment, the network audio-video information B' has both audio and video simultaneously, and the split track information C1', C2', C3', C4' after track splitting has, in addition to the audio data of the split track, the video of the split track of the main subject, for example. The generating artificial intelligence server 3 is capable of generating the generated information D1', D2', and mixes the split track information C1', C2', C3', C4' and the generated information D1', D2' to output the generated media E1'.

[0040] Only the split track information C1', C2', and C3', which will be used as audio data for the split tracks, is selected and mixed with the generated information D3', D4', and D5', such as generated video, generated animation, and generated text, and output as a different generated media E2' (see Figure 9).

[0041] Alternatively, one may select only the audio data and video of a partially split track and combine them with generated text, or select only the audio data of a partially split track and combine it with generated audio data and generated video, or remove the sailboat from the main video, select the waves in the split track video and combine them with the generated audio data, etc. The method of selection and combination is not limited.

[0042] Returning to Figure 6, we refer to Figures 1 and 2 together. The present invention has many more applications. For example, if the user is a violinist, they can separate the audio tracks of the violin, piano, trumpet, etc., from a Spotify® music band performance. Next, they can remove the violin audio track and combine the remaining separated track information C1, C2, and C3 with sheet music or a favorite generated video to output as generated media E. The user can then play generated media E while simultaneously practicing the violin, thereby further improving their technique for the piece.

[0043] Alternatively, a user can upload a recording of a company meeting to YouTube (registered trademark), separate the voices of different colleagues into tracks, amplify the voices of colleagues with quieter voices individually, and have the generating artificial intelligence server 3 combine the identified dialogue content and translations to output it as generated media E, creating a multilingual meeting transcript.

[0044] For link codes whose acquisition count reaches a threshold, the device server 11 further stores these link codes in the database 15, making them readily available for the next time the user plays them, either by the device server 11 or the generating artificial intelligence server 3. Furthermore, the device server 11 collects statistics on link codes frequently used by users of different regions, ages, and genders, and provides personalized recommendations based on the user's region, age, gender, etc.

[0045] The present invention is not limited to the embodiments described above, and various modifications are possible within the scope of the claims. Embodiments obtained by appropriately combining the technical means disclosed in different embodiments are also included in the technical scope of the present invention. [Explanation of symbols]

[0046] 1. Audio-video playback device 11. Device Server 12 Playback Interface 13 Search and Sort Interface 14 Open Interface 15 Databases 2. Sampling Module 3. Generating artificial intelligence server A streaming platform A1 API Server B Network audio and video information B' Network Audio & Video Information C1 Split Track Information C2 Split Track Information C3 Split Track Information C1' Split Track Information C2' Split Track Information C3' Split Track Information C4' Split Track Information D1 generation information D2 generation information D3 generation information D1' Generation information D2' generation information D3' Generation Information D4' Generation Information D5' Generation information E Generation Media E1' Generation media E2' Generation Media

Claims

1. A method for acquiring network audio video information, performing track splitting processing, and outputting generated media by combining it with artificial intelligence, The process involves an audio-video playback device server, or a generating artificial intelligence server to which a signal is connected, acquiring network audio-video information from a streaming platform, and the device server or the generating artificial intelligence server separating multiple split track information from the network audio-video information using a sampling module. The generation artificial intelligence server selects some or all of the divided track information, positions the selected divided track information so that it aligns with the time axis, and generates at least one generated piece of information based on the selected divided track information, and positions the generated piece of information so that it aligns with the divided track information on the time axis. The generation artificial intelligence server mixes the selected divided track information and the generation information, outputs it as the generation medium, and provides feedback to the device server. The device server includes the step of playing the generated media in the playback interface of the audio-video playback device, The sampling module includes a feedforward neural network, samples the segmented track information from the network audio-video information based on frequency characteristics, and captures the main subject video from the network audio-video information using an object identification model and an edge detection algorithm, thereby enabling a generated media output method.

2. The generated media output method according to claim 1, characterized in that the audio-video playback device has a search sort interface to which a signal is connected to the device server, the device server sends an audio-video search request to the API server of the streaming platform using application programming interface technology based on a keyword, the API server performs a search based on the audio-video search request and obtains a search result corresponding to the keyword, the device server then obtains a plurality of link codes of the search result from the API server using application programming interface technology, each link code corresponds to a different network audio-video information, the device server obtains one of the link codes, the device server or the generating artificial intelligence server analyzes one of the link codes and obtains the corresponding network audio-video information from the API server, and the search sort interface displays the search result by arranging the link codes from the audio-video playback device.

3. The generated media output method according to claim 2, wherein the audio-video playback device has a database to which signals are connected to the device server, the search results are displayed on the search sort interface, the user selects at least one of the link codes, the search sort interface adds the selected link code to a playlist, the device server or the generating artificial intelligence server sequentially retrieves the link codes from the playlist, and when the number of times one of the link codes has been retrieved reaches a threshold, the device server saves that one of the link codes to the database.

4. The generated media output method according to claim 2, wherein the method has a plurality of streaming platforms, each of which has its own API server to which signals are connected to the device server, the search sort interface includes a single search mode and an integrated search mode, and when the search sort interface is operated in the single search mode, the device server sends the audio video search request to the API server of one of the streaming platforms and displays the search results of that one of the streaming platforms in the audio video playback device, and when the search sort interface is operated in the integrated search mode, the device server sends the audio video search request to the API servers of all of the streaming platforms and displays the search results of all of the streaming platforms in the audio video playback device, and the device server displays the link codes corresponding to the same network audio video information from different streaming platforms in an integrated manner.

5. The generated media output method according to claim 2, characterized in that, before displaying the search results in the search sort interface, the device server first removes the link code corresponding to the network audio video information in which an invalid status exists, and before the device server or the generating artificial intelligence server obtains the network audio video information from the streaming platform, first verify whether the streaming platform is open.

6. The method for outputting generated media according to claim 1, characterized in that, before the generating artificial intelligence server outputs the generated media, it first performs an additional change on the selected at least partial divided track information, including a change in musical style, rhythm, melody, volume, and tone.

7. A system that acquires network audio-video information from a signal connected to a streaming platform, performs track splitting processing, and outputs generated media by combining it with artificial intelligence, An audio-video playback device having a device server and a playback interface to which signals are connected to the device server, A sampling module to which the signal is connected to the aforementioned device server, The system comprises the aforementioned device server and a generation artificial intelligence server to which signals are connected to the sampling module, The device server or the generating artificial intelligence server acquires network audio video information from the streaming platform, and then separates multiple split track information from the network audio video information using the sampling module. The generating artificial intelligence server selects some or all of the divided track information, positions the selected divided track information so that it aligns with the time axis, generates at least one generated piece of information based on the selected divided track information, and positions the generated piece of information so that it aligns with the divided track information on the time axis. The generation artificial intelligence server mixes the selected segmented track information and the generation information, outputs it as the generation medium, and also feeds it back to the device server. The device server plays the generated media during the playback interface. The sampling module includes a feedforward neural network and, based on frequency characteristics, samples the segmented track information from the network audio-video information, and captures the main subject video from the network audio-video information using an object identification model and an edge detection algorithm, thereby creating a media output system.

8. The generating media output system according to claim 7, wherein the streaming platform has an API server, the device server has a signal connected to the API server, the audio-video playback device has a search sort interface to which a signal is connected to the device server, the device server sends an audio-video search request to the API server by application programming interface technology based on a keyword, the API server performs a search and obtains search results corresponding to the keyword, the device server then obtains a plurality of link codes from the API server corresponding to the search results by application programming interface technology, each link code corresponds to different network audio-video information, the device server obtains one of the link codes, the device server or the generating artificial intelligence server analyzes the one of the link codes by application programming interface technology, and then obtains the corresponding network audio-video information from the API server by application programming interface technology based on the one of the link codes, and the search sort interface arranges the link codes in the audio-video playback device and displays the search results.

9. The generated media output system according to claim 8, wherein the audio-video playback device has a database to which signals are connected to the device server, displays the search results on the search sort interface, the user selects at least one of the link codes, the search sort interface adds the selected link code to a playlist, the device server or the generating artificial intelligence server sequentially retrieves the link codes from the playlist, and when the number of times one of the link codes has been retrieved reaches a threshold, the device server stores that one of the link codes in the database.

10. The generated media output system according to claim 8, comprising a plurality of streaming platforms, each of which has its own API server to which signals are connected to the device server, the search sort interface having a single search mode and an integrated search mode, the device server sending the audio video search request to the API server of one of the streaming platforms and displaying the search results of that one of the streaming platforms in the audio video playback device, the device server sending the audio video search request to the API servers of all the streaming platforms and displaying the search results of all the streaming platforms in the audio video playback device, and the device server integrally displaying the link codes corresponding to the same network audio video information from different streaming platforms.

11. The generated media output system according to claim 8, characterized in that, before displaying the search results in the search sort interface, the device server first eliminates the link code corresponding to the network audio video information in which an invalid status exists, and before the device server or the generating artificial intelligence server obtains the network audio video information from the streaming platform, the device server first verifies whether the streaming platform is open.

12. The generated media output system according to claim 7, characterized in that, before the generating artificial intelligence server outputs the generated media, it first performs an additional change on the selected at least partial divided track information, including a change in musical style, rhythm, melody, volume, and tone.

Citation Information

Patent Citations

  • Music matching method and device, electronic equipment and computer readable storage medium

    CN116939323A

  • Receiving device, query generation method and program

    JP2014160503A

  • Systems and methods for immersive audio experiences

    JP2024522251A

  • Unified playlist

    US20160241922A1

  • Music streaming, playlist creation and streaming architecture

    US20230185846A1