Three-dimensional animation creative design and networked cooperation device and method

Abstract

The invention discloses a three-dimensional animation creative design and networked cooperation device and method, and relates to the technical field of cross-domain intelligent cooperation systems.The three-dimensional animation creative design and networked cooperation device comprises a figure data acquisition module, a figure data analysis module, a figure data processing module and a local database; skeleton parameters and operation instructions are captured in real time and at high precision through the figure data acquisition module, accurate data are provided for analysis, the problem that acquisition is not timely and inaccurate is solved, the data analysis module identifies anti-physical motion, evaluates innovation indexes, calculates key parameters, balances creativity and specifications, solves the problems that physical rules are out of control, the skeleton is disordered and the like, and is high in practicability. The data processing module carries out grading risk response, assists targeted processing, improves cooperation efficiency, promotes an industrialization process, effectively solves the existing defects through cooperation of the three parts, and guarantees the animation production quality and efficiency.

Description

Technical Field

[0001] The present invention relates to the technical field of cross-domain intelligent collaborative systems, and in particular to a three-dimensional animation creative design and networked collaborative device and method. Background Art

[0002] There are generally serious technical defects in the existing 3D animation production field: the loss of control of physical rules leads to the inability to block anti-physical actions in real time, the fragmentation of the collaboration mechanism causes confusion in skeleton proportions and data silos, which is time-consuming and hinders the industrial process. Therefore, creative design and networked collaboration of 3D animation are very necessary.

[0003] Existing technologies such as the invention patent application with announcement number: CN115426273B discloses a dynamic measurement method for the aggregation and collaborative elasticity of network platform services. The method includes: multi-level and multi-dimensional indicator extraction, quantification and comprehensive evaluation, supporting analysis and regulation of industrial Internet, etc. Existing technologies such as the invention patent application with announcement number: CN114640179A discloses a networked command interaction system for distribution networks. The system includes: distribution network control including the factory end, operation and maintenance end, dispatching end and network commanding end. The dispatching instructions are issued through the commanding end and executed by the factory end, which can improve the control efficiency.

[0004] With regard to the above scheme, it can be seen that the current technical collaboration mechanism is fragmented, causing confusion in skeleton proportions, lacking scientific evaluation of innovation indexes, and unable to reasonably balance creativity and standards. Either excessive restrictions stifle creativity, or unreasonable movements are mixed in due to the lack of standards. Skeleton difference analysis is missing, making it difficult to accurately compare with reference characters, and the character's body parts are prone to imbalance. The construction of motion feature vectors is incomplete, and there is a lack of risk level division and response mechanism. As a result, problems in production are difficult to deal with in a timely manner, which is time-consuming and hinders the advancement of industrial processes. Summary of the Invention

[0005] The purpose of the present invention is to provide a three-dimensional animation creative design and networked collaboration device and method, which solves the problems existing in the background technology.

[0006] In order to solve the above technical problems, the present invention adopts the following technical solutions: The first aspect of the present invention provides a three-dimensional animation creative design and networked collaboration device, including: a character data acquisition module: used to capture the skeleton parameters and operation instructions of each character in the three-dimensional animation in real time, the skeleton parameters including: the total number of skeletal joints, the skeletal joint rotation axis data, the operation instructions including: joint displacement vector, operation timestamp.

[0007] The character data analysis module is used for outputting the anti-physical motion set and the regular physical motion set of each character in the three-dimensional cartoon, evaluating the innovation index of each character in the three-dimensional cartoon, returning the three-dimensional cartoon if the innovation index of the character does not meet the requirement, calculating the joint constraint satisfaction rate of each character in the three-dimensional cartoon if the innovation index of the character meets the requirement, analyzing the skeleton difference of each character in the three-dimensional cartoon, constructing the motion feature vector of each character in the three-dimensional cartoon, and calculating the conflict probability of each character in the three-dimensional cartoon.

[0008] The character data processing module is used for dividing the risk level of each character in the three-dimensional cartoon and responding according to the risk level.

[0009] The second aspect of the present application provides a three-dimensional cartoon creative design and networked collaboration method, which comprises the following steps: 1. character data acquisition: real-time capture of skeleton parameters and operation instructions of each character in the three-dimensional cartoon, wherein the skeleton parameters comprise total number of skeletal joints and skeletal joint rotation axis data, and the operation instructions comprise joint displacement vector and operation timestamp.

[0010] 2. Character data analysis: used for outputting the anti-physical motion set and the regular physical motion set of each character in the three-dimensional cartoon, evaluating the innovation index of each character in the three-dimensional cartoon, returning the three-dimensional cartoon if the innovation index of the character does not meet the requirement, calculating the joint constraint satisfaction rate of each character in the three-dimensional cartoon if the innovation index of the character meets the requirement, analyzing the skeleton difference of each character in the three-dimensional cartoon, constructing the motion feature vector of each character in the three-dimensional cartoon, and calculating the conflict probability of each character in the three-dimensional cartoon.

[0011] 3. Character data processing: used for dividing the risk level of each character in the three-dimensional cartoon and responding according to the risk level.

[0012] The present application has the following advantages: (1) The character data acquisition module of the present application can capture skeleton parameters and operation instructions in real time with high precision, provide accurate and comprehensive raw data support for subsequent analysis, ensure that subsequent analysis of character motion has a reliable data basis, and solve the problem of analysis deviation caused by untimely and inaccurate data collection in the prior art.

[0013] (2) The character data analysis module of the present application can identify anti-physical motion to avoid unreasonable action, scientifically evaluate the innovation index to balance creativity and standardization, calculate the joint constraint satisfaction rate and analyze the skeleton difference to ensure reasonable character shape, construct the motion feature vector and calculate the conflict probability to provide basis for risk judgment, and solve the problems of out-of-control physical rules, unbalanced creativity and standardization, and chaotic skeleton proportion in the prior art.

[0014] (3) The character data processing module of the present application: by dividing the risk level and pushing the corresponding character set, the designer can target the problem and improve the collaboration efficiency, avoid the problem accumulation in production, promote the smooth progress of the three-dimensional animation production industrialization process, solve the problem of problem processing lag and process block in the prior art. BRIEF DESCRIPTION OF DRAWINGS

[0015] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.

[0016] Figure 1 The system module schematic diagram of the present application.

[0017] Figure 2 The method flowchart of the present application. DETAILED DESCRIPTION

[0018] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0019] Referring to Figure 1 The present application provides a three-dimensional animation creative design and networked collaboration device, which comprises a character data acquisition module, a character data analysis module, a character data processing module and a local database.

[0020] It should be noted that the character data acquisition module is connected with the character data analysis module, the character data analysis module is connected with the character data processing module, and the local database is connected with the character data acquisition module, the character data analysis module and the character data processing module.

[0021] It should be further noted that the local database is used to store the constraint interval of each joint at the relative rotation angle, the length L xz of each body part of each character in the three-dimensional animation, the length of each body part of the corresponding reference character in the three-dimensional animation, the standard frame interval time length in the three-dimensional animation, the motion feature vector of each character in the three-dimensional animation in the safe state, the distance threshold value of the motion feature vector of each character in the three-dimensional animation to the safe state, the first risk threshold value and the second risk threshold value of the conflict probability of each character in the three-dimensional animation.

[0022] The character data acquisition module is used for real-time capturing of skeleton parameters and operation instructions of each character in the three-dimensional cartoon, wherein the skeleton parameters comprise total number of skeleton joints and skeleton joint rotation axis data, and the operation instructions comprise joint displacement vector and operation time stamp.

[0023] In one specific embodiment, the real-time capturing of skeleton parameters and operation instructions of each character in the three-dimensional cartoon comprises total number of skeleton joints, skeleton joint rotation axis data, joint displacement vector and operation time stamp, and the specific capturing method is as follows: real-time acquisition of motion data of each character in the three-dimensional cartoon by an optical motion capture device, automatic analysis of rotation angle, position offset and operation instruction of the skeleton joint by combining an image recognition algorithm and an inverse dynamics solver, acquisition of the operation instruction from the cartoon, and synchronous recording of the millisecond time stamp by a high-precision system clock.

[0024] The character data acquisition module of the present application provides accurate and comprehensive raw data support for subsequent analysis by real-time high-precision capturing of skeleton parameters and operation instructions, ensures reliable data basis for subsequent analysis of character motion, and solves the problem of analysis deviation caused by untimely and inaccurate data acquisition in the prior art.

[0025] The character data analysis module is used for outputting anti-physical motion set and regular physical motion set of each character in the three-dimensional cartoon, evaluating innovation index of each character in the three-dimensional cartoon, returning the three-dimensional cartoon if the innovation index of the character does not meet the requirement, and calculating joint constraint satisfaction rate of each character in the three-dimensional cartoon, analyzing skeleton difference degree of each character in the three-dimensional cartoon, constructing motion feature vector of each character in the three-dimensional cartoon and calculating conflict probability of each character in the three-dimensional cartoon if the innovation index of the character meets the requirement.

[0026] In the specific embodiment of the present application, the outputting of the anti-physical motion set and the regular physical motion set of each character in the three-dimensional cartoon is achieved by reading skeleton joint rotation axis data of each character in the three-dimensional cartoon to obtain relative rotation angle of each character at the i joint in the p frame x,i,p , and calculating rotation angle of all joints of each character from the p frame to the p+1 frame in the three-dimensional cartoon wherein x represents the number of the character, x=1, 2, …, m, m is a positive integer greater than 2, i represents the number of each joint of the character, i=1, 2, …, n, n is a positive integer greater than 2.

[0027] The outputting of the anti-physical motion set and the regular physical motion set of each character in the three-dimensional cartoon is achieved by reading joint displacement vector of each character in the three-dimensional cartoon to obtain relative joint displacement of each character at the i joint in the p frame , and calculating relative distance of all joints of each character from the p frame to the p+1 frame in the three-dimensional cartoon

[0028] If the rotation angle of a joint of a character in a 3D animation from the p-th frame to the p+1-th frame exceeds the standard rotation angle threshold or the relative distance exceeds the standard relative distance threshold, the physical movement of the character from the p-th frame to the p+1-th frame is recorded as anti-physical movement; otherwise, the physical movement of the character from the p-th frame to the p+1-th frame is recorded as normal physical movement.

[0029] By analogy, several anti-physical motions and several conventional physical motions of each character in the three-dimensional animation are identified, thereby constructing a set of anti-physical motions and a set of conventional physical motions of each character in the three-dimensional animation.

[0030] It should be noted that the rotation angle specifically refers to the rotation angle between a joint and the connected joint.

[0031] It should also be noted that the relative distance specifically refers to the relative distance between a joint and the center point of the character modeling.

[0032] For example, anti-physics movements include weightless suspension, out-of-bounds joint rotation, and unsupported positions.

[0033] In a specific embodiment of the present invention, the method for evaluating the character innovation index in the three-dimensional animation is as follows: based on the conventional physical movement set of each character in the three-dimensional animation, the number of conventional physical movements of each character is obtained by counting γ x , by image recognition, the 3D posture models of several conventional physical movements of each character in the 3D animation are compared with the 3D posture models of each physical movement of each character in the 3D animation preset in the database. Through the action similarity evaluation model, the action similarity of the 3D posture models of several conventional physical movements of each character and the 3D posture model of each physical movement is output. If the 3D posture model of a conventional physical movement and the 3D posture model of each movement are less than the preset similarity threshold, the conventional physical movement is recorded as an innovative physical movement, thereby obtaining several innovative conventional physical movements of each character, and the number μ of innovative conventional physical movements of each character is obtained by counting. x .

[0034] Based on the anti-physics movement set of each character in the 3D animation, the number of anti-physics movements of each character is obtained. If the number of anti-physics movements of a character in the 3D animation exceeds a certain limit, the innovation index of the character in the 3D animation is recorded as 0. If the number of anti-physics movements of each character in the 3D animation does not exceed a certain limit, the innovation index of the character in the 3D animation is evaluated as

[0035] It should be noted that action similarity is an existing technology and is relatively mature, so it will not be described in detail here.

[0036] It should be noted that the three-dimensional posture model refers to the posture model of a character in a three-dimensional cartoon in an environment, not only a motion posture of the character.

[0037] In one embodiment, if the innovation index of the character in the three-dimensional cartoon is lower than the set innovation index threshold, the three-dimensional cartoon is returned, for example, if the innovation index of the character in the three-dimensional cartoon is 0, the innovation index of the character in the three-dimensional cartoon is not qualified, and the three-dimensional cartoon is returned.

[0038] In an embodiment of the present application, the joint constraint satisfaction rate of each character in the three-dimensional cartoon is calculated, and the specific method is as follows: the constraint interval of each joint in the relative rotation angle is obtained from the local database The joint constraint satisfaction rate of each character in the three-dimensional cartoon is calculated The determination function is

[0039] In one embodiment, the single-joint constraint interval of each character in the three-dimensional cartoon is obtained from the local database, and the specific obtaining method is as follows: the preset rotation range of each joint of the three-dimensional cartoon character pre-stored in the database is called, for example, the x-axis rotation limit of the shoulder joint is-30 degrees to 90 degrees, the corresponding constraint data is loaded in real time by matching the bone in the current cartoon frame with the joint name.

[0040] It should be noted that δ(θ x,i,p ,A i ) is a determination function, which is 1 when the roll joint rotation of each character in the three-dimensional cartoon is in compliance, and 0 when it is out of compliance.

[0041] In an embodiment of the present application, the skeleton difference degree of each character in the three-dimensional cartoon is analyzed, and the specific method is as follows: the length L xz of each body part of each character in the three-dimensional cartoon is obtained from the local database xz , the length L' of each body part of the corresponding reference character in the three-dimensional cartoon is obtained from the local database, and the skeleton standardization difference value of each body part of each character and the corresponding reference character is calculated The skeleton difference degree of each character in the three-dimensional cartoon is analyzed Where j is the total number of body parts.

[0042] It should be noted that each character in the three-dimensional cartoon has a reference character at the set time, and the reference character is historical character data stored in the database, which meets the industry experience and is similar in size to each character in the three-dimensional cartoon, so that the character in the three-dimensional cartoon is more realistic.

[0043] In the embodiment of the present application, the motion feature vector of each character in the three-dimensional animation is constructed, and the specific method is as follows: the action fluency of each character in the three-dimensional animation from the pth frame to the (p+1)th frame is judged according to the anti-physical motion type, if the action of a certain character in the three-dimensional animation from the pth frame to the (p+1)th frame is a regular physical motion, the first fluency of the character in the three-dimensional animation from the pth frame to the (p+1)th frame is recorded as D x,p , and the first fluency of each character in the three-dimensional animation is obtained by statistics x,p

[0044] The standard frame interval time t' of the three-dimensional animation is obtained from the local database x , and the time interval of each character in the three-dimensional animation from the pth frame to the (p+1)th frame is introduced into the second fluency evaluation model, and the second fluency of each character in the three-dimensional animation is evaluated as

[0045] The overall action fluency F of each character in the three-dimensional animation is determined according to the first fluency and the second fluency x x x , and the motion feature vector of each character in the three-dimensional animation is constructed as

[0046] It should be noted that the standard frame interval time is a parameter set based on industry specifications.

[0047] In the embodiment of the present application, the conflict probability of each character in the three-dimensional animation is calculated, and the specific method is as follows: the motion feature vector of each character in the three-dimensional animation in the safe state is obtained from the local database The covariance matrix between the motion feature vector of each character and the motion feature vector in the safe state is calculated, and the distance from the motion feature vector of each character to the safe state is obtained as σ x The distance threshold σ of the motion feature vector of each character to the safe state in the three-dimensional animation is obtained from the local database x The distance from the motion feature vector of each character to the safe state is uniformly processed The dimensionless distance from the motion feature vector of each character to the safe state is obtained , and is recorded as the conflict probability of each character in the three-dimensional animation.

[0048] It should be noted that the covariance matrix technology is mature at present, and will not be repeated here.

[0049] ​​​Exemplarily, the motion characteristic vector of each character in the three-dimensional animation in a safe state is obtained from a local database, and a specific obtaining method is as follows: similar characters in 30 days are screened out, the average value of joint satisfaction rate, action fluency, and standardized skeleton difference under the same frame rate configuration is calculated as the motion characteristic vector of each character in the safe state.

[0050] The character data analysis module of the present application can identify anti-physical motion to avoid unreasonable action, scientifically evaluate innovation index to balance creativity and standardization, calculate joint constraint satisfaction rate and analyze skeleton difference to ensure reasonable character shape, construct motion characteristic vector and calculate conflict probability to provide basis for risk judgment, and solve the problems of uncontrolled physical rules, unbalanced creativity and standardization, and chaotic skeleton proportion in the prior art.

[0051] The character data processing module is used to divide the risk level of each character in the three-dimensional animation and respond according to the risk level.

[0052] In the specific embodiment of the present application, the specific method for dividing the risk level of each character in the three-dimensional animation is as follows: the first-level risk threshold and the second-level risk threshold of the conflict probability of each character in the three-dimensional animation are obtained from the local database, if the conflict probability of a certain character in the three-dimensional animation is less than the first-level risk threshold, the character in the three-dimensional animation is marked as low risk, if the conflict probability of a certain character in the three-dimensional animation is greater than or equal to the first-level risk threshold and less than the second-level risk threshold, the character in the three-dimensional animation is marked as medium risk, and if the conflict probability of a certain character in the three-dimensional animation is greater than or equal to the second-level risk threshold, the character in the three-dimensional animation is marked as high risk.

[0053] In the specific embodiment of the present application, the specific method for grading response according to the risk level is as follows: a low-risk character set, a medium-risk character set, and a high-risk character set in the three-dimensional animation are generated and sent to the designer of the three-dimensional animation.

[0054] The character data processing module of the present application: by dividing the risk level and pushing the corresponding character set, the designer can deal with the problem specifically, improve the cooperation efficiency, avoid the problem accumulation in the production, promote the smooth progress of the industrialization process of three-dimensional animation production, and solve the problem of lagging problem processing and process blocking in the prior art.

[0055] Referring to Figure 2 The second aspect of the present application provides a three-dimensional animation creative design and networked collaboration method, which comprises the following steps: step 1, character data acquisition, step 2, character data analysis, and step 3, character data processing.

[0056] Step 1. Character data acquisition: real-time capture of the skeleton parameters and operation instructions of each character in the three-dimensional animation, the skeleton parameters including: total number of skeleton joints, skeleton joint rotation axis data, the operation instructions including: joint displacement vector, operation timestamp.

[0057] Step 2. Character data analysis: used for outputting the anti-physical motion set and the conventional physical motion set of each character in the three-dimensional animation, evaluating the innovation index of each character in the three-dimensional animation, if the innovation index of the character does not meet the requirements, returning the three-dimensional animation, if the innovation index of the character meets the requirements, calculating the joint constraint satisfaction rate of each character in the three-dimensional animation, analyzing the skeleton difference degree of each character in the three-dimensional animation, constructing the motion feature vector of each character in the three-dimensional animation, and calculating the conflict probability of each character in the three-dimensional animation.

[0058] Step 3. Character data processing: used for dividing the risk level of each character in the three-dimensional animation, and responding according to the risk level.

[0059] The above is only an example and description of the concept of the present application, and those skilled in the art can make various modifications or supplements to the described specific embodiments or use similar ways to replace, as long as the modifications or supplements do not deviate from the concept of the present application or exceed the scope defined by the present application, and should belong to the protection scope of the present application.

Claims

1. 3D animation creative design and network collaboration device, characterized by: include: Character data acquisition module: used to capture the skeleton parameters and operation instructions of each character in 3D animation in real time. The skeleton parameters include: the total number of skeleton joints and the rotation axis data of the skeleton joints. The operation instructions include: joint displacement vectors and operation timestamps. Character Data Analysis Module: This module is used to output the anti-physics motion set and conventional physical motion set of each character in the 3D animation, evaluate the innovation index of each character in the 3D animation, return the 3D animation if the character innovation index does not meet the requirements, and calculate the joint constraint satisfaction rate of each character in the 3D animation if the character innovation index meets the requirements, analyze the skeleton differences of each character in the 3D animation, construct the motion feature vector of each character in the 3D animation, and calculate the collision probability of each character in the 3D animation; Character data processing module: used to classify the risk level of each character in 3D animation and respond according to the risk level.

2. The 3D animation creative design and network collaboration device according to claim 1, characterized in that: The specific method of outputting the anti-physics motion set and the conventional physical motion set of each character in the three-dimensional animation is as follows: By reading the skeletal joint rotation axis data of each character in the 3D animation, the relative rotation angle θ of each character at the i-th joint in the p-th frame is obtained. x,i,p , calculate the rotation angles of all joints of each character in the 3D animation from the pth frame to the p+1th frame Where x represents the character number, x = 1, 2, ..., m, m is a positive integer greater than 2, i represents the number of each joint of the character, i = 1, 2, ..., n, n is a positive integer greater than 2; By reading the joint displacement vectors of each character in the 3D animation, the relative joint displacement of each character at the i-th joint in the p-th frame is obtained. Calculate the relative distances of all joints of each character in a 3D animation from the pth frame to the p+1th frame If the rotation angle of a joint of a character in a 3D animation from the p-th frame to the p+1-th frame exceeds the standard rotation angle threshold or the relative distance exceeds the standard relative distance threshold, the physical movement of the character from the p-th frame to the p+1-th frame is recorded as anti-physical movement. Otherwise, the physical movement of the character from the p-th frame to the p+1-th frame is recorded as normal physical movement. By analogy, several anti-physical motions and several conventional physical motions of each character in the three-dimensional animation are identified, thereby constructing a set of anti-physical motions and a set of conventional physical motions of each character in the three-dimensional animation.

3. The 3D animation creative design and network collaboration device according to claim 2, characterized in that: The specific method for evaluating the character innovation index in three-dimensional animation is as follows: Based on the set of regular physical movements of each character in 3D animation, the number of regular physical movements of each character is obtained by counting γ x , by image recognition, the 3D posture models of several conventional physical movements of each character in the 3D animation are compared with the 3D posture models of each physical movement of each character in the 3D animation preset in the database. Through the action similarity evaluation model, the action similarity of the 3D posture models of several conventional physical movements of each character and the 3D posture model of each physical movement is output. If the 3D posture model of a conventional physical movement and the 3D posture model of each physical movement are less than the preset similarity threshold, the conventional physical movement is recorded as an innovative physical movement, thereby obtaining several innovative conventional physical movements of each character, and the number μ of innovative conventional physical movements of each character is obtained by counting. x ; Based on the anti-physics movement set of each character in the 3D animation, the number of anti-physics movements of each character is obtained. If the number of anti-physics movements of a character in the 3D animation exceeds a certain limit, the innovation index of the character in the 3D animation is recorded as 0. If the number of anti-physics movements of each character in the 3D animation does not exceed a certain limit, the innovation index of the character in the 3D animation is evaluated as 4. The 3D animation creative design and network collaboration device according to claim 3, characterized in that: The specific method for calculating the joint constraint satisfaction rate of each character in the three-dimensional animation is as follows: Obtain the constraint range of each joint in the relative rotation angle from the local database Calculate the joint constraint satisfaction rate of each character in 3D animation The decision function 5. The 3D animation creative design and network collaboration device according to claim 4, characterized in that: The specific method for analyzing the skeleton differences of the characters in the 3D animation is as follows: Get the length L of each body part of each character in the 3D animation from the local database xz , the length L′ of each body part of the reference character corresponding to each character in the 3D animation xz , where z is the number of each body part, z = 1, 2, ..., j, j is a positive integer greater than 2, calculate the standardized difference value of each body part of each character and the corresponding reference character Analyze the skeleton differences of characters in 3D animation where j is the total number of body parts.

6. The 3D animation creative design and network collaboration device according to claim 5, characterized in that: The specific method of constructing the motion feature vector of each character in the three-dimensional animation is as follows: The smoothness of the movements of each character in the 3D animation from the pth frame to the p+1th frame is determined based on the anti-physics motion type. If the movement of a character from the pth frame to the p+1th frame in the 3D animation is a regular physical movement, the first smoothness of the character from the pth frame to the p+1th frame in the 3D animation is recorded as D x,p , so that the first smoothness of each character in the 3D animation from the pth frame to the p+1th frame is D x,p , the first fluency of each character in the 3D animation is obtained by statistics: Get the standard frame interval duration t′ in 3D animation from the local database x The duration from the pth frame to the p+1th frame of each character in the 3D animation is imported into the second fluency evaluation model, and the second fluency of each character in the 3D animation is evaluated as The overall action fluency F of each character in the 3D animation is determined based on the first fluency and the second fluency. x =ζ x +D x ′, then the motion feature vectors of each character in the three-dimensional animation are constructed as 7. The 3D animation creative design and network collaboration device according to claim 6, characterized in that: The specific method for calculating the collision probability of each character in the three-dimensional animation is as follows: Obtain the motion feature vectors of each character in the 3D animation in a safe state from the local database By calculating the covariance matrix between the motion feature vector of each character and the motion feature vector in the safe state, the distance from the motion feature vector of each character to the safe state is obtained as σ x , obtain the distance threshold σ from the motion feature vector of each character in the 3D animation to the safe state from the local database x ′, the distance between each character's motion feature vector and the safe state is normalized Get the dimensionless distance of each character's motion feature vector to the safe state Denote the conflict probability of each character in the 3D animation.

8. The 3D animation creative design and network collaboration device according to claim 7, characterized in that: The specific method for classifying the risk level of each character in the three-dimensional animation is as follows: The first-level risk threshold and the second-level risk threshold of the conflict probability of each character in the three-dimensional animation are obtained from the local database. If the conflict probability of a character in the three-dimensional animation is less than the first-level risk threshold, the character in the three-dimensional animation is marked as low risk. If the conflict probability of a character in the three-dimensional animation is greater than or equal to the first-level risk threshold and less than the second-level risk threshold, the character in the three-dimensional animation is marked as medium risk. If the conflict probability of a character in the three-dimensional animation is greater than or equal to the second-level risk threshold, the character in the three-dimensional animation is marked as high risk.

9. The 3D animation creative design and network collaboration device according to claim 8, characterized in that: The specific method of performing graded response according to risk level is as follows: Generate a low-risk character set, a medium-risk character set, and a high-risk character set for the three-dimensional animation, and send the result to the three-dimensional animation designer.

10. A networked collaboration method for executing the three-dimensional animation creative design and networked collaboration device according to any one of claims 1 to 9, characterized in that: include: Step 1. Character data collection: real-time capture of skeleton parameters and operation instructions of each character in the 3D animation. The skeleton parameters include: the total number of skeletal joints and skeletal joint rotation axis data; the operation instructions include: joint displacement vectors and operation timestamps; Step 2. Character Data Analysis: This is used to output the anti-physics motion set and conventional physical motion set of each character in the 3D animation, evaluate the innovation index of each character in the 3D animation, return the 3D animation if the character innovation index does not meet the requirements, and calculate the joint constraint satisfaction rate of each character in the 3D animation if the character innovation index meets the requirements. The skeleton differences of each character in the 3D animation are analyzed, the motion feature vector of each character in the 3D animation is constructed, and the collision probability of each character in the 3D animation is calculated. Step 3. Character data processing: used to classify the risk level of each character in the 3D animation and respond according to the risk level.

Images