AI-based intelligent interactive animation collaborative production management method and system

Abstract

The present invention specifically relates to an AI-based intelligent interactive animation collaborative production management method and system, the method comprising real-time collection of morphological data, determination of initial morphological data, and generation of a skeleton binding data set; acquisition of color combination data and scene requirement data; substitution of the color combination data, scene requirement data, morphological data, and skeleton binding data set into an animation generation module, automatic generation of multiple visual animation scene models and a visual report corresponding to each visual animation scene model, and uploading the same to the collaborative production module; and in response to the operation instructions of each management terminal on the multiple visual animation scene models, real-time recording and display of the latest status of each visual animation scene model. This method realizes the collaborative production management of automatically generated animation scene models by multiple management terminals, improves the intelligence level of animation production, improves the efficiency and quality of the intelligent interactive animation collaborative production management method, and reduces production costs and time costs.

Description

Technical Field

[0001] The present invention relates to the field of image data processing technology, specifically to the field of interactive animation collaborative production management technology, and specifically to an AI-based intelligent interactive animation collaborative production management method and system. Background Art

[0002] Traditional animation production often requires significant manpower and time for design, editing, and other tasks. Furthermore, different people may have different aesthetic preferences and understandings of the work, resulting in varying quality in the final product. To address this issue, with the rapid development of artificial intelligence technology in recent years, researchers have begun experimenting with its application in animation production, aiming to leverage the power of AI to improve both efficiency and quality.

[0003] However, current animation production methods still face several challenges. For example, the animation process often requires manual effort to determine the animation's scenes, characters, and actions. This is not only time-consuming and labor-intensive, but also susceptible to subjective influences from the production staff. Furthermore, the lack of effective communication and management between different team members during the collaborative production process also impacts work efficiency and the quality of the final product.

[0004] Therefore, this field needs a new AI-based intelligent interactive animation collaborative production management solution to solve the above problems. Summary of the Invention

[0005] Based on this, the present invention proposes an AI-based intelligent interactive animation collaborative production management method and system, which solves the problem that in the animation production process of the existing technology, the animation scene, role, action and other information need to be manually determined, which is time-consuming and labor-intensive, and easily affected by the personal subjective factors of the production staff. In addition, in the collaborative production process, there is a lack of timely communication and management synchronization between different team members, which directly affects the work efficiency and the quality of the final work.

[0006] According to a first aspect of the present invention, there is provided an AI-based intelligent interactive animation collaborative production management method, which collects morphological data in real time, determines initial morphological data, and generates a skeletal binding data set, wherein the skeletal binding data set includes at least the skeletal structures corresponding to each capture point in the initial morphological data and the association relationship between each skeletal structure;

[0007] Obtain color combination data and scene requirement data;

[0008] According to the color combination data, scene requirement data, morphological data and bone binding data set, the animation generation module automatically generates multiple visual animation scene models and the corresponding visual report of each visual animation scene model and uploads them to the collaborative production module;

[0009] In response to the operation instructions of each management terminal on multiple visual animation scene models, the latest status of each visual animation scene model is recorded and displayed in real time.

[0010] According to an embodiment of the present invention, the real-time acquisition of morphological data, determination of initial morphological data, and generation of a skeleton binding data set includes:

[0011] Collect morphological data in real time and select the morphological data at any moment as the initial morphological data;

[0012] According to the initial morphological data, acquiring morphological data of a frame preceding the initial morphological data and morphological data of a frame following the initial morphological data;

[0013] Determining a capture point set in the initial morphological data according to the initial morphological data, morphological data of a frame preceding the initial morphological data, and morphological data of a frame following the initial morphological data, wherein the capture point set includes at least fixed capture points and auxiliary capture points;

[0014] A skeleton binding data set is generated according to the capture point set in the initial morphological data, wherein the skeleton binding data set at least includes the skeleton structures corresponding to the respective capture points in the initial morphological data and the association relationship between the respective skeleton structures.

[0015] According to an embodiment of the present invention, determining the capture point set in the morphological initial data according to the morphological initial data, the morphological data of a previous frame of the morphological initial data, and the morphological data of a subsequent frame of the morphological initial data includes:

[0016] Determining a first set of capture points in the initial morphological data according to the initial morphological data and morphological data of a previous frame of the initial morphological data;

[0017] Determining a second set of capture points in the initial morphological data according to the initial morphological data and morphological data of a subsequent frame of the initial morphological data;

[0018] Performing cluster analysis on the first group of capture points in the initial morphological data and the second group of capture points in the initial morphological data to obtain a plurality of fixed capture points and a plurality of auxiliary capture points in the initial morphological data;

[0019] selectively generating a plurality of auxiliary capture points according to the plurality of fixed capture points and the plurality of auxiliary capture points in the initial morphological data;

[0020] The plurality of fixed capture points and all auxiliary capture points in the initial morphological data constitute a capture point set in the initial morphological data.

[0021] According to an embodiment of the present invention, obtaining color combination data and obtaining scene requirement data includes:

[0022] Acquire color combination data, wherein the color combination data includes at least a plurality of colors, at least one reference position of each color, a reference quantity of color usage, and at least one hue requirement parameter;

[0023] Obtaining user scenario information sent by the management terminal, wherein the user scenario information at least includes scenario introduction information required by the user and the user's identity information;

[0024] Determine the user profile corresponding to the user's identity information based on the user scenario information sent by the management terminal;

[0025] Generate multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter based on the user portrait corresponding to the user's identity information and the scene introduction information required by the user;

[0026] Based on the user profile corresponding to the user's identity information, multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter are simulated and screened to obtain multiple sets of screened scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter;

[0027] The scene requirement data is composed of the screened multiple groups of scene style parameters and the screened multiple color tone requirement parameters corresponding to each scene style parameter.

[0028] According to an embodiment of the present invention, the animation generation module stores a preset history database and a preset history morphology database;

[0029] Before substituting the color combination data, scene requirement data, morphology data, and skeleton binding data set into the animation generation module, the method further trains the animation generation module through the following steps:

[0030] Generate training data sets corresponding to different numbers of management terminals and test data sets corresponding to the training data sets according to a preset historical database and a preset historical morphology database;

[0031] Obtaining a behavior profile of each management terminal corresponding to each training data set based on at least one management terminal corresponding to each training data set;

[0032] Generating, based on each training data set, a plurality of animation scene models corresponding to each training data set, wherein each animation scene model includes a colored animation frame pose corresponding to the morphological data in the training data set;

[0033] According to the behavior profile of each management terminal corresponding to each training data set, multiple animation scene models corresponding to each training data set are screened to obtain multiple screened animation scene models corresponding to each training data set;

[0034] Performing visualization processing on the filtered multiple animation scene models corresponding to each training data set to obtain multiple visualized animation scene models corresponding to each training data set;

[0035] Generate a visualization report corresponding to each visualization animation scene model according to each visualization animation scene model corresponding to each training data set;

[0036] According to the test data set corresponding to each training data set, multiple visual animation scene models corresponding to each training data set and the visual report corresponding to each visual animation scene model are tested to obtain the training result of the animation generation module.

[0037] According to an embodiment of the present invention, the preset historical database stores behavioral portraits of multiple management terminals, multiple sets of historical scene demand data corresponding to each user issued by each management terminal, and multiple sets of historical color combination data; the preset historical morphological database stores multiple sets of morphological data and a skeletal binding data set corresponding to each set of morphological data;

[0038] The step of generating, based on a preset history database and a preset history morphology database, training data sets corresponding to different numbers of management terminals and test data sets corresponding to the training data sets includes:

[0039] Select multiple management terminals based on the preset historical morphology database;

[0040] Combining multiple management terminals according to a preset historical database and multiple selected management terminals to obtain management terminal combinations with different numbers of management terminals;

[0041] According to each management terminal combination, a preset historical morphology database, and a preset historical database, a training data set corresponding to each management terminal combination is obtained, wherein the training data set includes a set of historical scene requirement data, a set of historical color combination data matching the historical scene requirement data, a set of morphology data, and a skeletal binding data set corresponding to the morphology data;

[0042] Randomly selecting at least one historical operation instruction feedback of each management terminal and a feedback trigger rate of each historical operation instruction feedback based on the selected multiple management terminals and a preset history database;

[0043] Based on multiple management terminal combinations, the training data set corresponding to each management terminal combination, at least one historical operation instruction feedback of each management terminal, and the feedback trigger rate of each historical operation instruction feedback, a verification data set corresponding to each training data set is generated, wherein the verification data set at least includes the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the training data set and the feedback trigger rate of the historical operation instruction feedback.

[0044] According to an embodiment of the present invention, generating a plurality of animation scene models corresponding to each training data set according to each training data set includes:

[0045] Based on the morphological data and skeletal binding data set in each training dataset, generate the animation frame pose corresponding to each morphological data;

[0046] Automatically coloring each animation frame posture corresponding to each morphological data according to the animation frame posture corresponding to each morphological data and the color combination data in the training data set to obtain multiple groups of colored animation frame postures corresponding to each morphological data;

[0047] According to the multiple groups of colored animation frame postures corresponding to each morphological data, the color combination data in the training data set and the scene requirement data, multiple animation scene models matching each group of colored animation frame postures are generated.

[0048] According to an embodiment of the present invention, the plurality of animation scene models corresponding to each training data set are screened based on the behavior profile of each management terminal corresponding to each training data set, and the screened plurality of animation scene models corresponding to each training data set include:

[0049] Based on the behavioral profile of each management terminal corresponding to each training data set, a multi-dimensional score is performed on multiple animation scene models corresponding to each training data set, and a multi-dimensional score of each animation scene model corresponding to each training data set is obtained by each management terminal corresponding to each training data set;

[0050] According to the multi-dimensional scoring of each animation scene model corresponding to each training data set by each management terminal corresponding to each training data set, multiple animation scene models corresponding to each training data set are screened to obtain multiple screened animation scene models corresponding to each training data set.

[0051] According to an embodiment of the present invention, the step of testing the multiple visualization animation scene models corresponding to each training data set and the visualization report corresponding to each visualization animation scene model based on the test data set corresponding to each training data set to obtain the training result of the animation generation module includes:

[0052] According to the test data set corresponding to each training data set, selectively triggering the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the training data set;

[0053] According to the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the selectively triggered training data set, the historical operation instruction is executed on the multiple visual animation scene models corresponding to the training data set and the visual report corresponding to each visual animation scene model, to obtain the multiple visual animation scene models corresponding to the training data set and the visual report corresponding to each visual animation scene model after execution;

[0054] According to each training data set, multiple types of scoring are performed on the multiple visual animation scene models corresponding to the training data set and the visual reports corresponding to each visual animation scene model after execution, to obtain multiple types of test scores corresponding to each training data set;

[0055] The training result of the animation generation module is obtained according to the multiple types of test scores corresponding to each training data set.

[0056] According to a second aspect of the present invention, there is provided an AI-based intelligent interactive animation collaborative production management system, the system comprising a data acquisition device, an animation generation module, a collaborative production module and a control device, wherein the data acquisition device interacts with the morphology acquisition device, multiple management terminals and the collaborative production module to realize respective data collection of the morphology acquisition device and the multiple management terminals, the animation generation module stores a preset historical database and a preset historical morphology database, the collaborative production module comprises a visualization display device for recording and displaying the latest status of each visualization animation scene model in real time, the control device comprises a processor and a memory, the memory is suitable for storing multiple program codes, the program codes are suitable for being loaded and run by the processor to execute the AI-based intelligent interactive animation collaborative production management method described in any one of the technical solutions of the above-mentioned AI-based intelligent interactive animation collaborative production management method.

[0057] From the above technical solutions, it can be seen that the AI-based intelligent interactive animation collaborative production management method provided by the present invention has the following beneficial effects:

[0058] The AI-based intelligent interactive animation collaborative production management method provided by the present invention realizes the automatic generation of a skeleton binding data set by collecting morphological data in real time, determining the initial morphological data and generating a skeleton binding data set, thereby ensuring the true restoration of the collected morphological data, and thus realizing the accurate expression of the animation posture. Then, by obtaining color combination data and scene requirement data, timely acquisition of animation production needs is realized. By substituting the obtained data into the animation generation module, a plurality of visual animation scene models and a visual report corresponding to each visual animation scene model are automatically generated and uploaded to the collaborative production module, thereby realizing the automatic generation of a plurality of visual animation scene models. The management terminal can intuitively feel the design elements of the animation scene model through the collaborative production module, and understand and grasp the style of the animation scene model, thereby improving the intelligence level of animation production. Moreover, by responding to the operation instructions of each management terminal on the plurality of visual animation scene models, each visual animation scene model is recorded and displayed in real time. The latest status of the scene model is realized, and the collaborative production management of the automatically generated visual animation scene model by multiple management terminals is realized, ensuring that each management terminal can grasp the animation production progress in real time, process the details of the animation scene model in time, improve the production efficiency of the animation scene model, and ensure the information synchronization and consistency of each management terminal by real-time recording and tracking changes in the production process. Moreover, by recording the visual report of each visual animation scene model in real time, it is convenient for the management terminal to find and recover lost or erroneous data in time, thereby improving the efficiency and quality of the intelligent interactive animation collaborative production management method, reducing production costs and time costs, and avoiding the need to manually determine the animation scene, role, action and other information in the animation production process of the existing technology, which is time-consuming and labor-intensive, and is easily affected by the personal subjective factors of the production staff. Moreover, in the collaborative production process, there is a lack of timely communication and management synchronization between different team members, which directly affects the work efficiency and the technical problems of the final work quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] The disclosure of the present invention will be more easily understood with reference to the accompanying drawings. Those skilled in the art will readily appreciate that these drawings are for illustrative purposes only and are not intended to limit the scope of protection of the present invention. Furthermore, similar numbers in the drawings represent similar components, wherein:

[0060] Figure 1 This is a flowchart of the main steps of an AI-based intelligent interactive animation collaborative production management method according to one embodiment of the present invention;

[0061] Figure 2 This is a flowchart of the main steps of a training animation generation module of an AI-based intelligent interactive animation collaborative production management method according to an embodiment of the present invention;

[0062] Figure 3 It is a schematic diagram of the main structural block diagram of an animation collaborative production management system according to an embodiment of the present invention.

[0063] List of reference numerals:

[0064] 300: Animation collaborative production management system; 301: Control device; 3011: Processor; 3012: Memory; 3013: Program code; 302: Animation generation module; 3021: Historical database; 3022: Historical morphology database; 303: Data acquisition device; 304: Collaborative production module. DETAILED DESCRIPTION

[0065] Some embodiments of the present invention are described below with reference to the accompanying drawings. Those skilled in the art should understand that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0066] In the description of the present invention, "module" and "processor" may include hardware, software, or a combination of both. A module may include hardware circuitry, various suitable sensors, communication ports, and memory. It may also include software components, such as program code, or a combination of software and hardware. A processor may be a central processing unit, a microprocessor, an image processor, a digital signal processor, or any other suitable processor. A processor has data and / or signal processing capabilities. A processor may be implemented in software, hardware, or a combination of both. Non-transitory computer-readable storage media include any suitable medium capable of storing program code, such as magnetic disks, hard disks, optical disks, flash memory, read-only memory, random access memory, and the like. The term "A and / or B" refers to all possible combinations of A and B, such as only A, only B, or both A and B. The terms "at least one of A or B" or "at least one of A and B" have similar meanings to "A and / or B" and may include only A, only B, or both A and B. The singular forms "one" and "the" may also include the plural forms.

[0067] See attached Figure 1 , Figure 1 This is a flow chart of the main steps of an AI-based intelligent interactive animation collaborative production management method according to an embodiment of the present invention. Figure 1 As shown, an AI-based intelligent interactive animation collaborative production management method in an embodiment of the present invention mainly includes the following steps S101 to S104.

[0068] Step S101: collecting morphological data in real time, determining initial morphological data, and generating a skeleton binding data set, wherein the skeleton binding data set at least includes the skeletal structures corresponding to each capture point in the initial morphological data and the association relationship between each skeletal structure;

[0069] In some embodiments, the real-time acquisition of morphological data, determination of initial morphological data, and generation of a skeletal binding data set includes:

[0070] Collect morphological data in real time and select the morphological data at any moment as the initial morphological data;

[0071] According to the initial morphological data, acquiring morphological data of a frame preceding the initial morphological data and morphological data of a frame following the initial morphological data;

[0072] Determining a capture point set in the initial morphological data according to the initial morphological data, morphological data of a frame preceding the initial morphological data, and morphological data of a frame following the initial morphological data, wherein the capture point set includes at least fixed capture points and auxiliary capture points;

[0073] A skeleton binding data set is generated according to the capture point set in the initial morphological data, wherein the skeleton binding data set at least includes the skeleton structures corresponding to the respective capture points in the initial morphological data and the association relationship between the respective skeleton structures.

[0074] In some embodiments, determining the capture point set in the morphological initial data based on the morphological initial data, the morphological data of a previous frame of the morphological initial data, and the morphological data of a subsequent frame of the morphological initial data includes:

[0075] Determining a first set of capture points in the initial morphological data according to the initial morphological data and morphological data of a previous frame of the initial morphological data;

[0076] Determining a second set of capture points in the initial morphological data according to the initial morphological data and morphological data of a subsequent frame of the initial morphological data;

[0077] Performing cluster analysis on the first group of capture points in the initial morphological data and the second group of capture points in the initial morphological data to obtain a plurality of fixed capture points and a plurality of auxiliary capture points in the initial morphological data;

[0078] selectively generating a plurality of auxiliary capture points according to the plurality of fixed capture points and the plurality of auxiliary capture points in the initial morphological data;

[0079] The plurality of fixed capture points and all auxiliary capture points in the initial morphological data constitute a capture point set in the initial morphological data.

[0080] In some embodiments, the method for determining the capture points in the morphological initial data can use a trained neural network model or a trained machine learning model. The choice of determination method here is only an exemplary explanation. In actual testing, those skilled in the art can make a choice according to actual needs. As long as it is possible to determine the first group of capture points in the morphological initial data based on the morphological initial data and the morphological data of the previous frame of the morphological initial data, and to determine the second group of capture points in the morphological initial data based on the morphological initial data and the morphological data of the next frame of the morphological initial data, it will be sufficient. No further details will be given here.

[0081] In some embodiments, each auxiliary point in the first group of capture points and each auxiliary point in the second group of capture points corresponds to at least one skeletal structure, and cluster analysis is performed on the first group of capture points in the initial morphological data and the second group of capture points in the initial morphological data to obtain multiple fixed capture points and multiple auxiliary capture points in the initial morphological data, including:

[0082] Performing cluster analysis on the first group of capture points in the initial morphological data and the second group of capture points in the initial morphological data to obtain a plurality of clustered capture points, and using the plurality of capture points as a plurality of fixed capture points;

[0083] The multiple capture points screened out by cluster analysis are used as multiple auxiliary capture points;

[0084] In order to obtain multiple fixed capture points and multiple auxiliary capture points in the initial morphological data.

[0085] In some embodiments, selectively generating a plurality of auxiliary capture points according to the plurality of fixed capture points and the plurality of auxiliary capture points in the initial morphological data includes:

[0086] Determining, based on the plurality of fixed capture points and the plurality of auxiliary capture points in the initial morphological data, a skeletal structure corresponding to each fixed capture point in the initial morphological data;

[0087] Determining, based on the skeletal structure corresponding to each fixed capture point in the initial morphological data, structural data of each skeletal structure and the number and position of auxiliary capture points in each skeletal structure, wherein the structural data of the skeletal structure includes at least bone length, bone position, and bone operation parameters;

[0088] Determining a preset capture point quantity range and a preset distribution threshold range corresponding to each skeletal structure based on the structural data of each skeletal structure;

[0089] According to the preset capture point quantity range and the preset distribution threshold range corresponding to each skeletal structure, a plurality of auxiliary capture points corresponding to each skeletal structure are selectively generated.

[0090] In some embodiments, selectively generating a plurality of auxiliary capture points corresponding to each skeletal structure according to a preset capture point quantity range and a preset distribution threshold range corresponding to each skeletal structure includes:

[0091] If the number of auxiliary capture points in the skeletal structure is lower than the preset capture point number range corresponding to the skeletal structure, and the positions of the auxiliary capture points in the skeletal structure do not meet the preset distribution threshold range corresponding to the skeletal structure, it is determined that additional auxiliary capture points are needed, and at least one auxiliary capture point corresponding to the skeletal structure is generated;

[0092] If the number of auxiliary capture points in the skeletal structure reaches a preset range of capture point numbers corresponding to the skeletal structure, and the positions of the auxiliary capture points in the skeletal structure do not conform to a preset distribution threshold range corresponding to the skeletal structure, it is determined that the positions of the auxiliary capture points need to be adjusted, and a plurality of auxiliary capture points corresponding to the skeletal structure are regenerated, and the auxiliary capture points in the skeletal structure are replaced with the regenerated plurality of auxiliary capture points;

[0093] If the number of auxiliary capture points in the skeletal structure reaches a preset capture point number range corresponding to the skeletal structure, and the positions of the auxiliary capture points in the skeletal structure meet a preset distribution threshold range corresponding to the skeletal structure, it is determined that the auxiliary capture points in the skeletal structure do not need to be adjusted, and the generation of multiple auxiliary capture points is not performed;

[0094] If the number of auxiliary capture points in the skeletal structure exceeds the preset capture point number range corresponding to the skeletal structure, and the number of capture points in the positions of the auxiliary capture points in the skeletal structure that do not conform to the preset distribution threshold range corresponding to the skeletal structure exceeds the preset elimination threshold, it is determined that the multiple auxiliary capture points corresponding to the skeletal structure need to be screened, and the multiple auxiliary capture points corresponding to the skeletal structure are screened to obtain the multiple auxiliary capture points corresponding to the screened skeletal structure and re-execute "selectively generate multiple auxiliary capture points corresponding to the skeletal structure according to the preset capture point number range and the preset distribution threshold range corresponding to the skeletal structure."

[0095] In some embodiments, the preset distribution threshold range can be set by comprehensively considering different bone lengths, bone positions and bone motion parameters, or it can be set using a trained machine learning model. The choice of setting method for the preset distribution threshold range here is only an example. In actual testing, those skilled in the art can make a choice according to actual needs, as long as it is possible to determine the preset distribution threshold range corresponding to each bone structure based on the structural data of each bone structure, and selectively generate multiple auxiliary capture points corresponding to each bone structure based on the preset distribution threshold range corresponding to each bone structure, it will not be repeated here.

[0096] In some embodiments, the setting method of the preset capture point number range can be independently set by those skilled in the art, or it can be set using a trained neural network model. The selection of the setting method of the preset capture point number range here is only an exemplary description. In actual tests, those skilled in the art can make a selection based on actual needs. As long as it is possible to determine the preset capture point number range corresponding to each skeletal structure based on the structural data of each skeletal structure, and selectively generate multiple auxiliary capture points corresponding to each skeletal structure based on the preset capture point number range corresponding to each skeletal structure, it will not be repeated here.

[0097] In the above embodiment, by collecting morphological data in real time and selecting morphological data at any moment as initial morphological data, the initial morphological data is determined, and the capture point set in the initial morphological data is determined through the initial morphological data, and a skeleton binding data set is generated, thereby realizing the automatic determination of the capture point set of the initial morphological data, improving the matching degree between the capture point set and the morphological data, and thereby improving the accuracy and authenticity of the skeleton binding data set.

[0098] Step S102: Acquire color combination data and scene requirement data;

[0099] In some embodiments, obtaining color combination data and obtaining scene requirement data includes:

[0100] Acquire color combination data, wherein the color combination data includes at least a plurality of colors, at least one reference position of each color, a reference quantity of color usage, and at least one hue requirement parameter;

[0101] Obtaining user scenario information sent by the management terminal, wherein the user scenario information at least includes scenario introduction information required by the user and the user's identity information;

[0102] Determine the user profile corresponding to the user's identity information based on the user scenario information sent by the management terminal;

[0103] Generate multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter based on the user portrait corresponding to the user's identity information and the scene introduction information required by the user;

[0104] Based on the user profile corresponding to the user's identity information, multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter are simulated and screened to obtain multiple sets of screened scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter;

[0105] The scene requirement data is composed of the screened multiple groups of scene style parameters and the screened multiple color tone requirement parameters corresponding to each scene style parameter.

[0106] In some embodiments, the simulation method for simulating and screening multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter can be the user portrait simulation method in the prior art, or it can be a trained neural network model to simulate the user's selection based on the user portrait. The choice of simulation method here is only an exemplary explanation. In actual testing, those skilled in the art can make a choice according to actual needs. As long as it is possible to simulate and screen multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter based on the user portrait corresponding to the user's identity information, and obtain multiple sets of scene style parameters after screening and multiple color tone requirement parameters corresponding to each scene style parameter after screening, it will not be repeated here.

[0107] In the above embodiment, multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter are generated based on the user scene information sent by the management terminal, and then the multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter are screened through the user portrait of the user to form scene requirement data, thereby realizing the automatic generation of scene requirement data, ensuring the matching degree between the scene requirement data and the user, and thus improving the accuracy of the subsequently generated animation scene model in expressing the user's actual needs.

[0108] Step S103: Substituting the color combination data, scene requirement data, morphology data, and skeleton binding data set into the animation generation module, automatically generating multiple visual animation scene models and a visual report corresponding to each visual animation scene model, and uploading them to the collaborative production module;

[0109] like Figure 2As shown, in some embodiments, the animation generation module stores a preset history database and a preset history morphology database;

[0110] Before substituting the color combination data, scene requirement data, morphology data, and skeleton binding data set into the animation generation module, the method further trains the animation generation module through the following steps:

[0111] Generate training data sets corresponding to different numbers of management terminals and test data sets corresponding to the training data sets according to a preset historical database and a preset historical morphology database;

[0112] Obtaining a behavior profile of each management terminal corresponding to each training data set based on at least one management terminal corresponding to each training data set;

[0113] Generating, based on each training data set, a plurality of animation scene models corresponding to each training data set, wherein each animation scene model includes a colored animation frame pose corresponding to the morphological data in the training data set;

[0114] According to the behavior profile of each management terminal corresponding to each training data set, multiple animation scene models corresponding to each training data set are screened to obtain multiple screened animation scene models corresponding to each training data set;

[0115] Performing visualization processing on the filtered multiple animation scene models corresponding to each training data set to obtain multiple visualized animation scene models corresponding to each training data set;

[0116] Generate a visualization report corresponding to each visualization animation scene model according to each visualization animation scene model corresponding to each training data set;

[0117] According to the test data set corresponding to each training data set, multiple visual animation scene models corresponding to each training data set and the visual report corresponding to each visual animation scene model are tested to obtain the training result of the animation generation module.

[0118] In some embodiments, the preset historical database stores behavioral portraits of multiple management terminals, multiple sets of historical scene demand data corresponding to each user issued by each management terminal, and multiple sets of historical color combination data; the preset historical morphological database stores multiple sets of morphological data and a skeletal binding data set corresponding to each set of morphological data;

[0119] The step of generating, based on a preset history database and a preset history morphology database, training data sets corresponding to different numbers of management terminals and test data sets corresponding to the training data sets includes:

[0120] Select multiple management terminals based on the preset historical morphology database;

[0121] Combining multiple management terminals according to a preset historical database and multiple selected management terminals to obtain management terminal combinations with different numbers of management terminals;

[0122] According to each management terminal combination, a preset historical morphology database, and a preset historical database, a training data set corresponding to each management terminal combination is obtained, wherein the training data set includes a set of historical scene requirement data, a set of historical color combination data matching the historical scene requirement data, a set of morphology data, and a skeletal binding data set corresponding to the morphology data;

[0123] Randomly selecting at least one historical operation instruction feedback of each management terminal and a feedback trigger rate of each historical operation instruction feedback based on the selected multiple management terminals and a preset history database;

[0124] Based on multiple management terminal combinations, the training data set corresponding to each management terminal combination, at least one historical operation instruction feedback of each management terminal, and the feedback trigger rate of each historical operation instruction feedback, a verification data set corresponding to each training data set is generated, wherein the verification data set at least includes the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the training data set and the feedback trigger rate of the historical operation instruction feedback.

[0125] In some embodiments, generating a plurality of animation scene models corresponding to each training data set according to each training data set includes:

[0126] Based on the morphological data and skeletal binding data set in each training dataset, generate the animation frame pose corresponding to each morphological data;

[0127] Automatically coloring each animation frame posture corresponding to each morphological data according to the animation frame posture corresponding to each morphological data and the color combination data in the training data set to obtain multiple groups of colored animation frame postures corresponding to each morphological data;

[0128] According to the multiple groups of colored animation frame postures corresponding to each morphological data, the color combination data in the training data set and the scene requirement data, multiple animation scene models matching each group of colored animation frame postures are generated.

[0129] In some embodiments, the generation method of the animation frame posture corresponding to each morphological data and the generation of multiple animation scene models that match each group of colored animation frame postures can adopt a trained neural network model or a trained machine learning model. The choice of generation method here is only an exemplary explanation. In actual testing, those skilled in the art can make a choice according to actual needs. As long as it is possible to generate the animation frame posture corresponding to each morphological data according to the morphological data and the bone binding data set in each training data set, and generate multiple animation scene models that match each group of colored animation frame postures according to the multiple groups of colored animation frame postures corresponding to each morphological data, the color combination data in the training data set, and the scene requirement data, it will be sufficient. No further details will be given here.

[0130] In some embodiments, the plurality of animation scene models corresponding to each training data set are screened based on the behavior profile of each management terminal corresponding to each training data set, and the screened plurality of animation scene models corresponding to each training data set include:

[0131] Based on the behavioral profile of each management terminal corresponding to each training data set, a multi-dimensional score is performed on multiple animation scene models corresponding to each training data set, and a multi-dimensional score of each animation scene model corresponding to each training data set is obtained by each management terminal corresponding to each training data set;

[0132] According to the multi-dimensional scoring of each animation scene model corresponding to each training data set by each management terminal corresponding to each training data set, multiple animation scene models corresponding to each training data set are screened to obtain multiple screened animation scene models corresponding to each training data set.

[0133] In some embodiments, the step of testing the multiple visual animation scene models corresponding to each training data set and the visual report corresponding to each visual animation scene model based on the test data set corresponding to each training data set to obtain the training result of the animation generation module includes:

[0134] According to the test data set corresponding to each training data set, selectively triggering the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the training data set;

[0135] According to the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the selectively triggered training data set, the historical operation instruction is executed on the multiple visual animation scene models corresponding to the training data set and the visual report corresponding to each visual animation scene model, to obtain the multiple visual animation scene models corresponding to the training data set and the visual report corresponding to each visual animation scene model after execution;

[0136] According to each training data set, multiple types of scoring are performed on the multiple visual animation scene models corresponding to the training data set and the visual reports corresponding to each visual animation scene model after execution, to obtain multiple types of test scores corresponding to each training data set;

[0137] The training result of the animation generation module is obtained according to the multiple types of test scores corresponding to each training data set.

[0138] In some embodiments, the multiple types include at least scene requirement completion, scene color completion, gesture color completion, and gesture accuracy.

[0139] In some embodiments, based on each training data set, multiple types of scoring are performed on the multiple visual animation scene models corresponding to the training data set after execution and the visual report corresponding to each visual animation scene model, and the multiple types of test scores corresponding to each training data set are obtained, including:

[0140] According to each visual animation scene model, scene color data, posture color data and posture data of each visual animation scene model are obtained;

[0141] The scene color data, posture color data and posture data of any visual animation scene model are respectively compared with the historical scene requirement data, historical color combination data and morphological data in the training data set corresponding to the visual animation scene model, and various types of test scores for the scene requirement completion, scene color completion, posture color completion and posture accuracy corresponding to the visual animation scene model are obtained.

[0142] In some embodiments, the scene color data of any visual animation scene model is compared with a plurality of color tone requirement parameters in the scene requirement data in the training data set corresponding to the visual animation scene model to obtain a ratio of the scene color data of the visual animation scene model to the plurality of color tone requirement parameters in the scene requirement data in the training data set corresponding to the visual animation scene model;

[0143] The ratio of the scene color data of the visual animation scene model to the multiple color tone requirement parameters in the scene requirement data in the training data set corresponding to the visual animation scene model is used as the test score of the scene requirement completion degree corresponding to the visual animation scene model;

[0144] By analogy, various types of test scores are obtained for the scene requirement completion, scene color completion, posture color completion, and posture accuracy corresponding to the visual animation scene model.

[0145] In some embodiments, obtaining the training results of the animation generation module according to the multiple types of test scores corresponding to each training data set includes:

[0146] Determine the number of successful training and failed training of the animation generation module in this module training based on the multiple types of test scores corresponding to each training data set;

[0147] If the ratio of the number of successful training times of the animation generation module to the total number of training times reaches a preset training success ratio threshold, the training result of the animation generation module is determined to be successful;

[0148] Otherwise, determining that the training result of the animation generation module is a training failure, adjusting the animation generation module, and re-executing the training of the animation generation module;

[0149] This is to continuously improve the performance of the generated animation scene model by adjusting the module.

[0150] Among them, the preset training success rate threshold can be 90% or 85%. The setting of the preset training success rate threshold here is only an example. In actual testing, those skilled in the art can set it according to actual needs, which will not be repeated here.

[0151] In the above embodiment, during module training, multiple sets of training data sets and their corresponding test data sets are generated through a preset historical database and a preset historical morphology database, and then multiple animation scene models corresponding to each training data set are generated based on each training data set. According to at least one management terminal corresponding to the training data set, a behavioral portrait of each management terminal corresponding to each training data set is obtained, thereby screening the multiple animation scene models corresponding to each training data set, obtaining the screened multiple animation scene models corresponding to each training data set and performing visualization processing, thereby achieving optimized training of the animation scene model to generate high-quality animation scene models, obtaining multiple visualized animation scene models corresponding to each training data set, and generating a visualization report corresponding to each visualized animation scene model, thereby achieving the retention of information on each visualized animation scene model to facilitate the updating and maintenance of the model, and then testing the training results through the test data set corresponding to each training data set to facilitate further optimization and improvement, thereby improving the intelligence level of the animation generation module for animation production.

[0152] In some embodiments, the color combination data, scene requirement data, morphology data, and skeletal binding data set are substituted into the animation generation module to automatically generate multiple visual animation scene models and a visual report corresponding to each visual animation scene model and upload them to the collaborative production module, including:

[0153] Generate multiple animation scene models based on the color combination data, the scene requirement data, the morphological data, and the skeletal binding data set, wherein each animation scene model includes a colored animation frame pose corresponding to the morphological data;

[0154] Obtaining a behavior profile of each management terminal according to at least one management terminal corresponding to the scenario requirement data;

[0155] According to the behavior profile of each management terminal, multiple animation scene models are screened to obtain multiple screened animation scene models;

[0156] Performing visualization processing on the filtered multiple animation scene models to obtain multiple visualized animation scene models;

[0157] Generate a visualization report corresponding to each visualization animation scene model according to each visualization animation scene model;

[0158] And upload multiple visual animation scene models and the visual report corresponding to each visual animation scene model to the collaborative production module.

[0159] Step S104: In response to the operation instructions of each management terminal on the multiple visual animation scene models, the latest status of each visual animation scene model is recorded and displayed in real time to achieve collaborative production management of the automatically generated visual animation scene models by multiple management terminals.

[0160] In some embodiments, the types of the operation instructions include at least modification and deletion. In response to the operation instructions of each management terminal on multiple visual animation scene models, real-time recording and displaying the latest status of each visual animation scene model includes:

[0161] In response to the operation instructions of each management terminal on the multiple visual animation scene models, obtaining the sending time of the multiple operation instructions corresponding to each visual animation scene model;

[0162] Sorting the multiple operation instructions corresponding to each visual animation scene model according to the sending time of the multiple operation instructions corresponding to each visual animation scene model to obtain the execution order of the multiple operation instructions corresponding to each visual animation scene model;

[0163] According to the execution order of the multiple operation instructions corresponding to the visual animation scene model, the multiple operation instructions corresponding to the visual animation scene model are executed in sequence:

[0164] The collaborative production module performs an operation corresponding to the operation instruction on the visual animation scene model corresponding to the operation instruction to obtain a visual animation scene model after execution;

[0165] The executed visual animation scene model is visually displayed in real time, and the operation of the executed visual animation scene model is recorded in real time, and the latest status of each visual animation scene model is displayed on the visual display device in the collaborative production module.

[0166] Based on the above steps S101-S104, by collecting morphological data in real time, determining the initial morphological data and generating a skeleton binding data set, the skeleton binding data set is automatically generated, and then by obtaining color combination data and scene requirement data, the timely acquisition of animation production needs is achieved. By substituting the obtained data into the animation generation module, multiple visual animation scene models and a visual report corresponding to each visual animation scene model are automatically generated and uploaded to the collaborative production module, thereby automatically generating multiple visual animation scene models. By responding to the operation instructions of each management terminal on multiple visual animation scene models, the latest status of each visual animation scene model is recorded and displayed in real time, and the collaborative production management of the automatically generated visual animation scene models by multiple management terminals is achieved, ensuring that each management terminal can grasp the animation production progress in real time, process the details of the animation scene model in time, improve the production efficiency of the animation scene model, improve the efficiency and quality of the intelligent interactive animation collaborative production management method, and reduce production costs and time costs.

[0167] It should be pointed out that although the various steps in the above embodiments are described in a specific order, those skilled in the art will understand that in order to achieve the effects of the present invention, different steps do not have to be performed in such an order. They can be performed simultaneously (in parallel) or in other orders. These changes are within the scope of protection of the present invention.

[0168] Furthermore, the present invention also provides an animation collaborative production management system.

[0169] See attached Figure 3 , Figure 3 This is a main structural diagram of an animation collaborative production management system according to an embodiment of the present invention. Figure 3As shown, an animation collaborative production management system 300 in an embodiment of the present invention mainly includes a data acquisition device 303, an animation generation module 302, a collaborative production module 304 and a control device 301. The data acquisition device 303 interacts with the morphology acquisition device, multiple management terminals and the collaborative production module 304 to realize data collection for the morphology acquisition device and multiple management terminals. The animation generation module 302 stores a preset historical database 3021 and a preset historical morphology database 3022. The collaborative production module 304 includes a visualization display device for recording and displaying the latest status of each visualization animation scene model in real time. The control device 301 includes a processor 3011 and a memory 3012. The memory 3012 can be configured to store a program code 3013 for executing the AI-based intelligent interactive animation collaborative production management method of the above-mentioned method embodiment. The processor 3011 can be configured to execute the program code 3013 in the memory 3012. The program code 3013 includes but is not limited to the program code 3013 for executing the AI-based intelligent interactive animation collaborative production management method of the above-mentioned method embodiment. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The control device 301 can be a control device device formed by various electronic devices.

[0170] In some embodiments, the data acquisition device 303 can be various communication devices or data acquisition devices with different communication types. The selection of the data acquisition device 303 here is only an example. In actual testing, technical personnel in this field can make a selection according to actual needs. As long as information interaction can be achieved between the data acquisition device 303 and the morphological acquisition device, multiple management terminals and the collaborative production module 304, it will not be repeated here.

[0171] In some embodiments, the morphological acquisition device can be a morphological acquisition device in the prior art, or it can be a multi-angle camera device. The selection of the morphological acquisition device here is only an exemplary explanation. In actual testing, technical personnel in this field can make a selection according to actual needs, as long as the morphological data can be collected through the morphological acquisition device. No further details will be given here.

[0172] In some embodiments, the visualization display device of the collaborative production module 304 can be a display device respectively set on the management terminal, or it can be any one or more display devices in the prior art, such as a display screen. The selection of the visualization display device here is only an exemplary explanation. In actual testing, those skilled in the art can make a selection according to actual needs. As long as the visualization display of the visualization animation scene model and the visualization report can be achieved through the visualization display device, it will not be repeated here.

[0173] In some embodiments, the preset historical database 3021 stores behavioral portraits of multiple management terminals, multiple sets of historical scene demand data corresponding to each user issued by each management terminal, and multiple sets of historical color combination data, and the preset historical morphological database 3022 stores multiple sets of morphological data and the bone binding data sets corresponding to each set of morphological data.

[0174] In one embodiment, the description of the specific implementation functions can refer to steps S101 to S104.

[0175] The above animation collaborative production management system 300 is used to execute Figure 1 The embodiment of the AI-based intelligent interactive animation collaborative production management method shown in the figure has similar technical principles, technical problems solved and technical effects produced. Technical personnel in this technical field can clearly understand that for the convenience and conciseness of description, the specific working process and related instructions of the animation collaborative production management system 300 can refer to the contents described in the embodiment of the AI-based intelligent interactive animation collaborative production management method, and will not be repeated here.

[0176] Those skilled in the art will appreciate that all or part of the process steps in the method of the above embodiment of the present invention can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When executed by the processor 3011, the computer program can implement the steps of each of the above method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable storage medium can include: any entity or device, medium, USB flash drive, mobile hard drive, magnetic disk, optical disk, computer memory, read-only memory, random access memory, electric carrier signal, telecommunication signal, and software distribution medium that can carry the computer program code. It should be noted that the content of the computer-readable storage medium can be appropriately increased or decreased based on the requirements of legislation and patent practice in a jurisdiction. For example, in some jurisdictions, based on legislation and patent practice, computer-readable storage media do not include electric carrier signals and telecommunication signals.

[0177] Furthermore, the animation collaborative production management system 300 of the present invention also includes a computer-readable storage medium. In a computer-readable storage medium embodiment according to the present invention, the computer-readable storage medium can be configured to store a program code 3013 for executing the animation collaborative production management method based on big data analysis of the above-mentioned method embodiment. The program code 3013 can be loaded and run by the processor 3011 to implement the above-mentioned animation collaborative production management method based on big data analysis. For ease of explanation, only the parts related to the embodiment of the present invention are shown. For specific technical details not disclosed, please refer to the method part of the embodiment of the present invention. The computer-readable storage medium can be a memory device formed by various electronic devices. Optionally, the computer-readable storage medium in the embodiment of the present invention is a non-temporary computer-readable storage medium.

[0178] Furthermore, it should be understood that since the configuration of each module is merely for illustrating the functional units of the apparatus of the present invention, the physical devices corresponding to these modules may be the processor 3011 itself, or a portion of the software, a portion of the hardware, or a combination of software and hardware in the processor 3011. Therefore, the number of modules in the figure is merely illustrative.

[0179] Those skilled in the art will appreciate that the various modules in the device can be adaptively split or merged. Such splitting or merging of specific modules does not cause the technical solution to deviate from the principles of the present invention. Therefore, the technical solutions after splitting or merging will fall within the scope of protection of the present invention.

[0180] Thus far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art may make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will fall within the scope of protection of the present invention.

Claims

1. An AI-based intelligent interactive animation collaborative production management method, characterized by: The method comprises the following steps: Collecting morphological data in real time, determining initial morphological data, and generating a skeleton binding data set, wherein the skeleton binding data set at least includes the skeletal structures corresponding to each capture point in the initial morphological data and the association relationship between each skeletal structure; Obtain color combination data and scene requirement data; According to the color combination data, scene requirement data, morphological data and bone binding data set, the animation generation module automatically generates multiple visual animation scene models and the corresponding visual report of each visual animation scene model and uploads them to the collaborative production module; In response to the operation instructions of each management terminal on multiple visual animation scene models, the latest status of each visual animation scene model is recorded and displayed in real time; The animation generation module stores a preset history database and a preset history morphology database; Before substituting the color combination data, scene requirement data, morphology data, and skeleton binding data set into the animation generation module, the method further trains the animation generation module through the following steps: Generate training data sets corresponding to different numbers of management terminals and test data sets corresponding to the training data sets according to a preset historical database and a preset historical morphology database; Obtaining a behavior profile of each management terminal corresponding to each training data set based on at least one management terminal corresponding to each training data set; Generating, based on each training data set, a plurality of animation scene models corresponding to each training data set, wherein each animation scene model includes a colored animation frame pose corresponding to the morphological data in the training data set; According to the behavior profile of each management terminal corresponding to each training data set, multiple animation scene models corresponding to each training data set are screened to obtain multiple screened animation scene models corresponding to each training data set; Performing visualization processing on the filtered multiple animation scene models corresponding to each training data set to obtain multiple visualized animation scene models corresponding to each training data set; Generate a visualization report corresponding to each visualization animation scene model according to each visualization animation scene model corresponding to each training data set; According to the test data set corresponding to each training data set, multiple visual animation scene models corresponding to each training data set and the visual report corresponding to each visual animation scene model are tested to obtain the training result of the animation generation module.

2. The AI-based intelligent interactive animation collaborative production management method according to claim 1 is characterized in that: The real-time acquisition of morphological data, determination of initial morphological data, and generation of a skeleton binding data set includes: Collect morphological data in real time and select the morphological data at any moment as the initial morphological data; According to the initial morphological data, acquiring morphological data of a frame preceding the initial morphological data and morphological data of a frame following the initial morphological data; Determining a capture point set in the initial morphological data according to the initial morphological data, morphological data of a frame preceding the initial morphological data, and morphological data of a frame following the initial morphological data, wherein the capture point set includes at least fixed capture points and auxiliary capture points; A skeleton binding data set is generated according to the capture point set in the initial morphological data, wherein the skeleton binding data set at least includes the skeleton structures corresponding to the respective capture points in the initial morphological data and the association relationship between the respective skeleton structures.

3. The AI-based intelligent interactive animation collaborative production management method according to claim 2 is characterized in that: Determining the capture point set in the morphological initial data according to the morphological initial data, the morphological data of a previous frame of the morphological initial data, and the morphological data of a subsequent frame of the morphological initial data includes: Determining a first set of capture points in the initial morphological data according to the initial morphological data and morphological data of a previous frame of the initial morphological data; Determining a second set of capture points in the initial morphological data according to the initial morphological data and morphological data of a subsequent frame of the initial morphological data; Performing cluster analysis on the first group of capture points in the initial morphological data and the second group of capture points in the initial morphological data to obtain a plurality of fixed capture points and a plurality of auxiliary capture points in the initial morphological data; selectively generating a plurality of auxiliary capture points according to the plurality of fixed capture points and the plurality of auxiliary capture points in the initial morphological data; The plurality of fixed capture points and all auxiliary capture points in the initial morphological data constitute a capture point set in the initial morphological data.

4. The AI-based intelligent interactive animation collaborative production management method according to claim 3 is characterized in that: The obtaining of color combination data and scene requirement data includes: Acquire color combination data, wherein the color combination data includes at least a plurality of colors, at least one reference position of each color, a reference quantity of color usage, and at least one hue requirement parameter; Obtaining user scenario information sent by the management terminal, wherein the user scenario information at least includes scenario introduction information required by the user and the user's identity information; Determine the user profile corresponding to the user's identity information based on the user scenario information sent by the management terminal; Generate multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter based on the user portrait corresponding to the user's identity information and the scene introduction information required by the user; Based on the user profile corresponding to the user's identity information, multiple sets of scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter are simulated and screened to obtain multiple sets of screened scene style parameters and multiple color tone requirement parameters corresponding to each scene style parameter; The scene requirement data is composed of the screened multiple groups of scene style parameters and the screened multiple color tone requirement parameters corresponding to each scene style parameter.

5. The AI-based intelligent interactive animation collaborative production management method according to claim 4 is characterized in that: The preset historical database stores behavioral portraits of multiple management terminals, multiple sets of historical scene demand data corresponding to each user issued by each management terminal, and multiple sets of historical color combination data. The preset historical morphological database stores multiple sets of morphological data and a skeleton binding data set corresponding to each set of morphological data. The step of generating, based on a preset history database and a preset history morphology database, training data sets corresponding to different numbers of management terminals and test data sets corresponding to the training data sets includes: Select multiple management terminals based on the preset historical morphology database; Combining multiple management terminals according to a preset historical database and multiple selected management terminals to obtain management terminal combinations with different numbers of management terminals; According to each management terminal combination, a preset historical morphology database, and a preset historical database, a training data set corresponding to each management terminal combination is obtained, wherein the training data set includes a set of historical scene requirement data, a set of historical color combination data matching the historical scene requirement data, a set of morphology data, and a skeletal binding data set corresponding to the morphology data; Randomly selecting at least one historical operation instruction feedback of each management terminal and a feedback trigger rate of each historical operation instruction feedback based on the selected multiple management terminals and a preset history database; Based on multiple management terminal combinations, the training data set corresponding to each management terminal combination, at least one historical operation instruction feedback of each management terminal, and the feedback trigger rate of each historical operation instruction feedback, a verification data set corresponding to each training data set is generated, wherein the verification data set at least includes the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the training data set and the feedback trigger rate of the historical operation instruction feedback.

6. The AI-based intelligent interactive animation collaborative production management method according to claim 5 is characterized in that: Generating a plurality of animation scene models corresponding to each training data set according to each training data set includes: Based on the morphological data and skeletal binding data set in each training dataset, generate the animation frame pose corresponding to each morphological data; Automatically coloring each animation frame posture corresponding to each morphological data according to the animation frame posture corresponding to each morphological data and the color combination data in the training data set to obtain multiple groups of colored animation frame postures corresponding to each morphological data; According to the multiple groups of colored animation frame postures corresponding to each morphological data, the color combination data in the training data set and the scene requirement data, multiple animation scene models matching each group of colored animation frame postures are generated.

7. The AI-based intelligent interactive animation collaborative production management method according to claim 6 is characterized in that: The plurality of animation scene models corresponding to each training data set are screened according to the behavior portrait of each management terminal corresponding to each training data set, and the screened plurality of animation scene models corresponding to each training data set include: Based on the behavioral profile of each management terminal corresponding to each training data set, a multi-dimensional score is performed on multiple animation scene models corresponding to each training data set, and a multi-dimensional score of each animation scene model corresponding to each training data set is obtained by each management terminal corresponding to each training data set; According to the multi-dimensional scoring of each animation scene model corresponding to each training data set by each management terminal corresponding to each training data set, multiple animation scene models corresponding to each training data set are screened to obtain multiple screened animation scene models corresponding to each training data set.

8. The AI-based intelligent interactive animation collaborative production management method according to claim 7 is characterized in that: The step of testing the multiple visual animation scene models corresponding to each training data set and the visual report corresponding to each visual animation scene model based on the test data set corresponding to each training data set to obtain the training results of the animation generation module includes: According to the test data set corresponding to each training data set, selectively triggering the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the training data set; According to the historical operation instruction feedback corresponding to any one or more management terminals corresponding to the selectively triggered training data set, the historical operation instruction is executed on the multiple visual animation scene models corresponding to the training data set and the visual report corresponding to each visual animation scene model, to obtain the multiple visual animation scene models corresponding to the training data set and the visual report corresponding to each visual animation scene model after execution; According to each training data set, multiple types of scoring are performed on the multiple visual animation scene models corresponding to the training data set and the visual reports corresponding to each visual animation scene model after execution, to obtain multiple types of test scores corresponding to each training data set; The training result of the animation generation module is obtained according to the multiple types of test scores corresponding to each training data set.

9. An AI-based intelligent interactive animation collaborative production management system, characterized by: The system includes a data acquisition device, an animation generation module, a collaborative production module and a control device. The data acquisition device interacts with the morphology acquisition device, multiple management terminals and the collaborative production module to realize data acquisition of the morphology acquisition device and the multiple management terminals. The animation generation module stores a preset historical database and a preset historical morphology database. The collaborative production module includes a visualization display device for recording and displaying the latest status of each visualization animation scene model in real time. The control device includes a processor and a memory. The memory is suitable for storing multiple program codes. The program code is suitable for being loaded and run by the processor to execute an AI-based intelligent interactive animation collaborative production management method according to any one of claims 1 to 8.

Images