Multi-split-mirror structured short video batch mixing and cutting method with material controllable repeatability

Abstract

The invention relates to a multi-sub-mirror structured short video batch mixing and cutting method with controllable repetition degree of materials, which comprises the following steps of: separately managing sub-mirrors and the materials, establishing a mapping relation between the materials and the videos, introducing a control value of an allowable maximum repetition sub-mirror number during calculation and combination, and performing gradient repetition degree operation from low to high. Through tracking and statistics of historical materials, a material minimum usage priority principle is applied, and video library repetition comparison is converted into material repetition comparison; the method has the advantages that the historical use records of the materials are persistent, and the use condition of each material can be tracked; the output video combinations are output according to the gradient of the repetition degree from low to high, the material repetition index of the material combination of each video is visualized, and the risk of preferential release is reduced to the minimum; the situation that all combinations are compared with all videos in a video library one by one is effectively avoided, and the time and space complexity of a combination calculation algorithm is reduced.

Description

Technical Field

[0001] The present invention belongs to the technical field of batch remixing of short videos, and in particular relates to a batch remixing method of multi-storyboard structured short videos with controllable repetition of materials. Background Art

[0002] At present, short video editing technology has made significant progress in automation and intelligence. With the help of artificial intelligence and machine learning algorithms, short video editing tools can automatically identify and edit highlights, important scenes and key clips in videos. The application of computer vision technology enables these tools to accurately identify people, objects and backgrounds in videos, and automatically switch scenes and optimize content. Natural language processing technology performs semantic analysis on dialogues and audio in videos to select the most attractive clips. Template and style applications further improve the efficiency of batch production. Users only need to select preset templates or styles, and the tools can automatically batch edit and generate high-quality short videos that meet the requirements. In addition, the application of cloud computing and distributed processing technology makes video rendering and processing faster and more efficient, and supports large-scale simultaneous processing of multiple videos. In general, the combination of automation and intelligent technology has significantly improved the efficiency and quality of short video editing, providing content creators with more convenient and powerful tools.

[0003] In the field of short video matrix, the demand for batch editing and synthesis of short video content is increasing. Many content creators use multiple platforms and multiple accounts to distribute short video content in batches, and a large number of short video batch remix creation tool platforms have emerged in the market, such as Huaer Duoduo and Super Editor. These platforms have begun to use AIGC (artificial intelligence generated content) technology combined with intelligent marketing to produce a large amount of content through batch editing and synthesis of materials and distribute them to various short video platforms.

[0004] Although the short video content batch creation platforms on the market have made certain progress in automation and intelligence, there are still significant deficiencies in controlling the duplication of video material content. Many current systems lack effective means to control the reuse of video materials, which not only leads to a decrease in the quality of the generated video content, but may even fail to pass the original high-quality content detection methods of major content platforms due to content duplication. For example, the platform cannot accurately identify the reuse rate of materials in the overall video library and material library, resulting in a high degree of similarity in many films. This not only affects the user experience, but may also hinder the dissemination and recommendation of videos on the platform.

[0005] In addition, existing platforms also face challenges in managing and optimizing large-scale material libraries. The reuse of materials and the frequent generation of highly similar videos make it difficult for content to remain fresh and unique, which directly affects the creator's content creation efficiency and the user's viewing experience. More seriously, the platform's poor control of repetition and similarity may also cause infringement disputes and copyright issues. Therefore, how to effectively identify and control the reuse rate of materials and video similarity has become a key issue that short video batch remixing technology needs to solve.

[0006] Most platforms directly use simple calculations of permutations and combinations to mix and combine materials, lacking precise control of repetition. For example, a certain platform uses the following method to calculate repetition: for a batch of structured videos, they can be split into 10 storyboards, each storyboard provides 6 different material clips, and 1 material is taken from each storyboard, and a total of 10 materials are spliced ​​into 1 video. It can be calculated that the number of videos with a repetition rate of no more than 20% in the film is 44. The specific calculation method is to generate an ordered combination of the Cartesian product of the material clips, and then randomly select a combination and put it into the film library, and then randomly select the next combination, and compare the repetition with all the videos in the film library one by one. If the repetition of all videos is less than 20%, they will be put into the library, otherwise they will be discarded until all combinations are randomly selected.

[0007] This calculation method can quickly produce results when processing videos with low shot counts and low material counts, but as the number of shots increases, the algorithm's spatial complexity and time complexity increase exponentially, and it is difficult for ordinary computers to complete the calculation in a short period of time. Therefore, the existing defects are not only reflected in the poor control of repetition, but also in the efficiency of the algorithm under high complexity conditions.

[0008] Based on this, this case is brought forward. Summary of the invention

[0009] The purpose of the present invention is to provide an improved algorithm for controlling the repetition of materials in the batch mixing technology of multi-storyboard structured short video materials.

[0010] In order to achieve the above object, the technical solution of the present invention is as follows:

[0011] A method for batch mixing of multi-storyboard structured short videos with controllable repetition of materials, comprising the following steps:

[0012] S10. Create a storyboard directory. Each product can be decomposed into multiple storyboards according to the video content structure, and a directory for storing materials is created according to the storyboard sequence;

[0013] S20. Put the filmed materials into the storyboard catalog at any time in the form of putting them in batches, and track and accumulate the materials used in the past, record the sequence number, usage frequency and weight of the materials, and initialize the frequency and weight of the newly put materials to 0;

[0014] S30. Selecting storyboards. For all storyboards under a certain product, any number of storyboards are selected each time a video of the product is synthesized;

[0015] S40. Enter the maximum number of repeated shots allowed, which value is greater than or equal to 0 and does not exceed the number of shots selected in step S30 for synthesizing the video;

[0016] S50. Input the number of videos required this time;

[0017] S60. Select materials for each storyboard to generate a combination. When selecting storyboard materials, the principle of minimum use priority is adopted according to the frequency of use and weight of the materials under each storyboard. If the frequency of use and weight are equal, the principle of minimum material number priority is adopted, and the current generated video number needs to be recorded, and the frequency of use and weight of the selected materials need to be updated, and the association between the material and the video number needs to be recorded;

[0018] Before selecting the material for the next storyboard, filter out the materials whose use frequency exceeds the maximum allowed number of repeated storyboards among the used materials, and find out all the video serial number lists associated with them. Then, when selecting the material for the next storyboard, exclude the material associated with the video serial number list, until the material selection for each storyboard of a structured video is completed;

[0019] S70. Repeat step S60 to continue matching the next combination that meets the conditions until no available material can be selected for a certain storyboard, and then output all available combinations;

[0020] S80. Perform subsequent single-piece intelligent editing based on the materials selected according to each combination information.

[0021] Furthermore, the step S10 also includes the following process: allowing the user to increase or decrease the number of mirrors, or adjust the order of mirrors during the synthesis of any batch.

[0022] Furthermore, the step S20 also includes the following process: each time the material is added, the user can provide a different amount of material for each storyboard, or some storyboards may not need to add new material.

[0023] Furthermore, the step S30 also includes the following process: customizing the marked materials, excluding certain materials marked by human intervention from participating in the task synthesis.

[0024] Compared with the prior art, the advantages of the present invention are: the historical usage records of materials are persisted, and the usage of each material can be tracked; the output video combination will be output in a gradient from low to high repetition, and the material repetition index of each video material combination can be visualized; if the video is distributed according to the gradient, the risk of priority release will be minimized; at the same time, the present invention effectively avoids comparing all combinations with all videos in the video library one by one, reducing the time and space complexity of the combination calculation algorithm. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] Figure 1 Schematic diagram of the process of batch mixing and cutting of short videos in the embodiment. DETAILED DESCRIPTION

[0026] The present invention is further described in detail below with reference to the embodiments.

[0027] The present invention is further described in detail below in conjunction with the embodiments. It should be understood that the directions or positional relationships indicated by the terms "upper", "lower", "front", "back", "left", "right", "top", "bottom", "inside" and "outside" herein are based on the directions or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention.

[0028] This embodiment proposes a method for batch mixing of multi-storyboard structured short videos with controllable repetition of materials, such as Figure 1 As shown, the following steps are included.

[0029] S10. Create a storyboard directory. Each product can be decomposed into multiple storyboards according to the video content structure, and a directory for storing materials is created according to the storyboard sequence. This embodiment allows the user to increase or decrease the number of storyboards or adjust the sequence of storyboards during the synthesis of any batch, which will not affect the combination repetition calculation result of this embodiment.

[0030] S20. Add materials in batches. The material shooting of batch remixed videos is usually not completed in one go. This method supports the form of adding materials in batches, allowing the filmed materials to be placed in the storyboard catalog at any time. Each time the material is added, the user can provide a different number of materials for each storyboard, or some storyboards do not need to add new materials. This embodiment will track and accumulate the materials used in the history, record the serial number, frequency of use and weight of the materials, and select the most suitable materials for the combination based on these attributes in the subsequent material selection. The frequency and weight of the new materials added here are initialized to 0.

[0031] S30. Select storyboards and custom marked materials. For all storyboards under a certain product, you can select any number of storyboards each time you synthesize the video of the product, and support custom marking of materials, that is, you can exclude some materials marked by manual intervention from participating in the synthesis of this task.

[0032] S40. Input the maximum allowed number of repeated shots. The value of the maximum allowed number of repeated shots is greater than or equal to 0, and does not exceed the number of shots selected in step S30 for synthesizing the video. This embodiment will increase the maximum allowed number of repeated shots from 0 until it is equal to the value input by the user, and gradually calculate all material combinations that meet the repeated shot number condition.

[0033] S50. Enter the number of videos required this time. The user can control the maximum number of videos generated this time. If the material is not enough to meet the duplication condition, the actual number of videos generated will be lower than the number of videos required this time. If you need to continue to produce videos that meet the duplication condition, just put new materials into some storyboards.

[0034] S60. Select materials for each storyboard and generate combinations.

[0035] When selecting storyboard materials, the principle of minimum usage priority is adopted according to the usage frequency and weight of the materials under each storyboard. If the usage frequency and weight are equal, the principle of minimum material number priority is adopted. In addition, it is necessary to record the current generated video number, update the usage frequency and weight of the selected materials, and record the association between the material and video number.

[0036] Before selecting the material for the next storyboard, filter out the materials that have been used and whose usage frequency exceeds the maximum allowed number of repeated storyboards, and find out all the video serial number lists associated with them. Then, when selecting the material for the next storyboard, exclude the material associated with the video serial number list, until the material selection for each storyboard of a structured video is completed.

[0037] S70: Repeat step S60 to continue matching the next combination that meets the conditions until no available materials can be selected for a certain storyboard, and then output all available combinations.

[0038] S80: Perform subsequent single-piece intelligent editing based on the materials selected according to each combination information.

[0039] Each time the video synthesis for the product is repeated according to the above steps. The following is an example of the implementation of the above steps. For the production of a marketing promotion video for a certain brand of safe, the video content is structured and broken down into the following 10 display scenes (the number in the brackets indicates the total number of materials put into this scene, and all of them are put in for the first time):

[0040] 1. Overall appearance (11);

[0041] 2. Brand Logo (10);

[0042] 3. Put money into the counter (10);

[0043] 4. Lock the bolt door (13);

[0044] 5. Password panel (11);

[0045] 6. Tap the box (10);

[0046] 7. Open the cabinet door (11);

[0047] 8. Surrounding environment (10);

[0048] 9. Close-up of the cabinet details (10);

[0049] 10. The whole process ends and freezes (11).

[0050] In this task, all the shots and materials are selected, and the maximum number of repeated shots is set to 2. The number of videos required is 10. If the material is described as a 2-digit hexadecimal number, the low digit represents the material number, and the high digit represents the shot number, the number of all the materials can be obtained as follows (for example: 11 represents the first shot, the first material, 1A represents the tenth material of the first shot, that is, A, B, and C represent 10, 11, and 12 respectively):

[0051] 11, 12, 13, 14, 15, 16, 17, 18, 19, 1A, 1B;

[0052] 21, 22, 23, 24, 25, 26, 27, 28, 29, 2A;

[0053] 31, 32, 33, 34, 35, 36, 37, 38, 39, 3A;

[0054] 41, 42, 43, 44, 45, 46, 47, 48, 49, 4A, 4B, 4C, 4D;

[0055] 51, 52, 53, 54, 55, 56, 57, 58, 59, 5A, 5B;

[0056] 61, 62, 63, 64, 65, 66, 67, 68, 69, 6A;

[0057] 71, 72, 73, 74, 75, 76, 77, 78, 79, 7A, 7B;

[0058] 81, 82, 83, 84, 85, 86, 87, 88, 89, 8A;

[0059] 91, 92, 93, 94, 95, 96, 97, 98, 99, 9A;

[0060] A1, A2, A3, A4, A5, A6, A7, A8, A9, AA, AB;

[0061] According to the storyboard material selection logic of steps S50 and S60 of this solution, the following video combinations will be output in sequence:

[0062] 11, 21, 31, 41, 51, 61, 71, 81, 91, A1;

[0063] 12, 22, 32, 42, 52, 62, 72, 82, 92, A2;

[0064] 13, 23, 33, 43, 53, 63, 73, 83, 93, A3;

[0065] 14, 24, 34, 44, 54, 64, 74, 84, 94, A4;

[0066] 15, 25, 35, 45, 55, 65, 75, 85, 95, A5;

[0067] 16, 26, 36, 46, 56, 66, 76, 86, 96, A6;

[0068] 17, 27, 37, 47, 57, 67, 77, 87, 97, A7;

[0069] 18, 28, 38, 48, 58, 68, 78, 88, 98, A8;

[0070] 19, 29, 39, 49, 59, 69, 79, 89, 99, A9;

[0071] 1A, 2A, 3A, 4A, 5A, 6A, 7A, 8A, 9A, AA.

[0072] The above embodiments are only used to explain the concept of the present invention, rather than to limit the protection of the rights of the present invention. Any non-substantial changes to the present invention using this concept shall fall within the protection scope of the present invention.

Claims

1. A method for batch mixing of multi-storyboard structured short videos with controllable repetition of materials, characterized in that: The following steps are involved: S10. Create a storyboard directory. Each product can be decomposed into multiple storyboards according to the video content structure, and a directory for storing materials is created according to the storyboard sequence; S20. Put the filmed materials into the storyboard catalog at any time in the form of putting them in batches, and track and accumulate the materials used in the past, record the sequence number, usage frequency and weight of the materials, and initialize the frequency and weight of the newly put materials to 0; S30. Selecting storyboards. For all storyboards under a certain product, any number of storyboards are selected each time a video of the product is synthesized; S40. Enter the maximum number of repeated shots allowed, which value is greater than or equal to 0 and does not exceed the number of shots selected in step S30 for synthesizing the video; S50. Input the number of videos required this time; S60. Select materials for each storyboard to generate a combination. When selecting storyboard materials, the principle of minimum use priority is adopted according to the frequency of use and weight of the materials under each storyboard. If the frequency of use and weight are equal, the principle of minimum material number priority is adopted, and the current generated video number needs to be recorded, and the frequency of use and weight of the selected materials need to be updated, and the association between the material and the video number needs to be recorded; Before selecting the material for the next storyboard, filter out the materials whose use frequency exceeds the maximum allowed number of repeated storyboards among the used materials, and find out all the video serial number lists associated with them. Then, when selecting the material for the next storyboard, exclude the material associated with the video serial number list, until the material selection for each storyboard of a structured video is completed; S70. Repeat step S60 to continue matching the next combination that meets the conditions until no available material can be selected for a certain storyboard, and then output all available combinations; S80. Perform subsequent single-piece intelligent editing based on the materials selected according to each combination information.

2. A method for batch mixing of multi-screen structured short videos with controllable repetition of materials as claimed in claim 1, characterized in that: In step S10, Includes the following process: allowing the user to increase or decrease the number of mirrors, or adjust the order of mirrors during the synthesis of any batch.

3. A method for batch mixing of multi-screen structured short videos with controllable repetition of materials as claimed in claim 1, characterized in that: The step S20 also includes the following process: each time the material is added, the user can provide a different amount of material for each storyboard, or some storyboards do not need to add new materials.

4. A method for batch mixing of multi-screen structured short videos with controllable repetition of materials as claimed in claim 1, characterized in that: In step S30, The process includes: customizing the marked materials and excluding some materials marked by manual intervention from participating in the synthesis of this task.

Images