Digital Human Motion Data Processing System

Abstract

This application provides a digital human motion data processing system. The system sends the acquired human body posture data to the server through a communication link via a terminal device, generates a digital human model in the server based on the human body posture data, and determines a target motion posture control model from a preset set of motion posture control models according to the link state of the communication link. Then, the server outputs motion control parameters according to the target motion posture control model and sends the digital human motion data generated according to the motion control parameters to the terminal device for display, thereby realizing a model selection mechanism that adapts to the link state of the communication link, not only improving the adaptability and robustness of the system, but also ensuring stable digital human motion effects can be provided in different network environments.

Description

Technical Field

[0001] This application relates to data processing technologies, and in particular, to a digital human motion data processing system. Background Art

[0002] With the rapid development of digital human technologies, digital humans are increasingly widely used in multiple fields such as entertainment, education, healthcare, and industry. Digital human motion, as an important part of digital human technologies, its realism and smoothness directly affect the user experience and application effects. However, in the process of implementing digital human motion, many technical challenges are faced, and the most critical one is how to ensure the stability and smoothness of digital human motion in different network environments.

[0003] In traditional digital human motion data processing systems, a fixed motion pose control model is usually adopted to process human body pose data and generate digital human motion. However, this fixed-mode method has obvious limitations. On the one hand, due to the variability and uncertainty of the network environment, fixed control models often have difficulty adapting to the data transmission requirements under different network conditions. Especially in low-bandwidth and high-latency network environments, data transmission delays and packet losses will cause digital human motion to freeze, lag, or even interrupt, seriously affecting the user experience.

[0004] On the other hand, different application scenarios have different requirements for digital human motion. For example, in some application scenarios with extremely high requirements for real-time performance and smoothness (such as online games, virtual reality, etc.), digital human motion needs to achieve extremely high update frequencies and fine motion control; while in some application scenarios with relatively low requirements for real-time performance (such as distance education, online meetings, etc.), more attention is paid to the stability and basic continuity of digital human motion. Traditional fixed control models are difficult to meet these diverse requirements simultaneously. Summary of the Invention

[0005] This application provides a digital human motion data processing system to implement a model selection mechanism that adapts to the link state of the communication link to ensure the stability of digital human motion control in different network environments.

[0006] In a first aspect, this application provides a digital human motion data processing system, including: a terminal device and a server;

[0007] The terminal device sends the acquired human body pose data to the server through the communication link;

[0008] The server generates a digital human model based on the human body pose data and determines a target motion pose control model from a preset set of motion pose control models according to the link state of the communication link;

[0009] The server outputs motion control parameters according to the target motion posture control model, and sends the digital human motion data generated according to the motion control parameters to the terminal device for display.

[0010] In the above solution, the human body posture data obtained by the terminal device is sent to the server through the communication link. In the server, a digital human model is generated according to the human body posture data, and a target motion posture control model is determined from the preset motion posture control model set according to the link state of the communication link. Then, the server outputs motion control parameters according to the target motion posture control model, and sends the digital human motion data generated according to the motion control parameters to the terminal device for display, so that the motion posture control model can be dynamically adjusted according to the link state of the communication link. When the link state is good, the system can select a more complex model with higher control accuracy (such as the control model established based on the proportional integral derivative controller) to generate smoother and more natural digital human motion. When the link state is poor, the system will automatically switch to a simpler model with lower requirements for data transmission (such as the control model established based on the proportional derivative controller) to ensure the basic continuity and stability of the digital human motion in an environment with low bandwidth and high latency. This model selection mechanism that adapts to the link state of the communication link not only improves the adaptability and robustness of the system, but also ensures stable digital human motion effects in different network environments.

[0011] Optionally, the preset motion posture control model set includes at least a first motion posture control model and a second motion posture control model, wherein the first motion posture control model is a control model established based on a proportional derivative controller, and the second motion posture control model is a control model established based on a proportional integral derivative controller.

[0012] In the above solution, the first motion posture control model is established based on a proportional derivative controller, and the second motion posture control model is established based on a proportional integral derivative controller. These two models can meet the motion control requirements in different scenarios. Among them, the first motion posture control model realizes the rapid response and stable control of the motion posture through the proportional and derivative links. When the communication link state is poor, such as when there is a delay in data transmission, the first motion posture control model can reduce the data processing volume, thereby achieving a faster control response to ensure the motion smoothness of the digital human model in a poor network state. The second motion posture control model realizes the rapid response and stable control of the motion posture through the proportional, integral, and derivative links. When the communication link state is good, that is, when the data transmission delay is low and the bandwidth is sufficient, the integral link can make the motion posture control accuracy higher to achieve the motion accuracy of the digital human model in a good network state.

[0013] Optionally, if the link state of the communication link is the first link state, the target motion attitude control model is the first motion attitude control model;

[0014] If the link state of the communication link is the second link state, the target motion attitude control model is the second motion attitude control model, where the second link state is better than the first link state.

[0015] In the above solution, when the link state of the communication link is the first link state, the system selects the first motion attitude control model as the target motion attitude control model. The first link state usually represents relatively poor network conditions, and there may be delays in data transmission. In this case, the first motion attitude control model (based on a proportional-derivative controller) is selected because of its simplicity and fast response characteristics to ensure the basic continuity and stability of the digital human motion. When the link state of the communication link is the second link state, the system selects the second motion attitude control model as the target motion attitude control model. The second link state is better than the first link state, usually representing good network conditions, low data transmission delay, and sufficient bandwidth. In this case, the second motion attitude control model (based on a proportional-integral-derivative controller) is selected because of its high precision and strong anti-interference ability to generate a smoother and more natural digital human motion effect.

[0016] Optionally, the default configuration of the target motion attitude control model is the second motion attitude control model.

[0017] In the above solution, setting the default configuration of the target motion attitude control model to the second motion attitude control model enhances the stability of the system in the initial state. The second motion attitude control model, due to its inherent high-precision adjustment ability, can quickly respond and compensate for system deviations through the coordinated action of the proportional, integral, and derivative links, and can maintain the smoothness and accuracy of the digital human motion trajectory.

[0018] In addition, it is worth noting that when switching from a poor network state to a good network state, the integral link in the second motion attitude control model can also be used to adjust the errors in the previous control of the first motion attitude control model, which can gradually adjust the motion attitude to achieve error compensation control of the digital human model and reduce the phenomenon of discontinuous or jittery digital human motion caused by network fluctuations.

[0019] Optionally, the preset set of motion attitude control models only includes the target motion attitude control model. The target motion attitude control model is a control model established based on a proportional-derivative controller, and the gain parameter configuration in the target motion attitude control model is associated with the link state.

[0020] In the above solution, changes in the link state (such as latency, bandwidth fluctuations, etc.) will directly affect the real-time performance and accuracy of the digital human motion data transmission, and thus affect the effect of motion posture control. By dynamically associating the gain parameter configuration in the target motion posture control model with the link state of the communication link, the system can adjust the sensitivity and response speed of the controller in real time to adapt to the motion control requirements in different network environments, and avoid motion posture distortion or interruption caused by network fluctuations.

[0021] Optionally, before the server outputs the motion control parameters according to the target motion posture control model, it further includes:

[0022] If the link state of the communication link is the third link state, configure the first gain parameter for the target motion posture control model, where the first gain parameter includes a first proportional gain parameter and a first differential gain parameter;

[0023] If the link state of the communication link is the fourth link state, configure the second gain parameter for the target motion posture control model, where the second gain parameter includes a second proportional gain parameter and a second differential gain parameter.

[0024] In the above solution, when the communication link is in the third link state, the system configures the first gain parameter (including the first proportional gain parameter and the first differential gain parameter) for the target motion posture control model, which can ensure the accuracy of the controller and achieve a smoother and more accurate digital human motion effect. When the communication link is in the fourth link state, the system configures the second gain parameter (including the second proportional gain parameter and the second differential gain parameter). This configuration is usually for relatively poor network conditions, and the response speed and stability of the controller are optimized by adjusting the proportional gain and differential gain to ensure that the digital human motion posture can still maintain a certain coherence and accuracy under large network fluctuations.

[0025] Optionally, a configuration parameter mapping table is configured in the server, the third link state corresponds to the first gain parameter in the configuration parameter mapping table, and the fourth link state corresponds to the second gain parameter in the configuration parameter mapping table.

[0026] In the above solution, a configuration parameter mapping table is configured in the server. This mapping table directly associates the link states of the communication link (the third link state and the fourth link state) with the gain parameters of the target motion posture control model (the first gain parameter and the second gain parameter), thus significantly improving the convenience and efficiency of system configuration. Through the mapping table, the system can quickly determine the gain parameters to be used in the current link state without complex calculation and reasoning processes, thereby accelerating the configuration speed of the control parameters.

[0027] It should be noted that when the link state is poor, the system can appropriately reduce the proportional gain parameter to reduce the control overshoot caused by network delay and improve the stability of the system. Conversely, when the link state is good, increasing the proportional gain parameter can speed up the response speed of the system and improve the control accuracy. Adjusting the differential gain parameter helps the system predict and compensate for future errors. Especially when the link state fluctuates greatly, by dynamically adjusting the differential gain parameter, oscillations can be effectively suppressed and the robustness of the system can be improved.

[0028] In a second aspect, the present application provides a method for processing digital human motion data, which is applied to a digital human motion data processing system. The system includes: a terminal device and a server;

[0029] The terminal device sends the acquired human body posture data to the server through a communication link;

[0030] The server generates a digital human model based on the human body posture data, and determines a target motion posture control model from a preset set of motion posture control models according to the link state of the communication link;

[0031] The server outputs motion control parameters according to the target motion posture control model, and sends the digital human motion data generated according to the motion control parameters to the terminal device for display.

[0032] In a third aspect, the present application provides an electronic device, including:

[0033] a processor; and,

[0034] a memory for storing executable instructions of the processor;

[0035] wherein, the processor is configured to execute any possible method described in the first aspect by executing the executable instructions.

[0036] In a fourth aspect, the present application provides a computer-readable storage medium, in which computer-executable instructions are stored. When the computer-executable instructions are executed by a processor, they are used to implement any possible method described in the first aspect.

[0037] The digital human motion data processing system provided by this application sends the acquired human body posture data to the server through the terminal device via the communication link. In the server, a digital human model is generated based on the human body posture data, and a target motion posture control model is determined from a preset set of motion posture control models according to the link state of the communication link. Then, the server outputs motion control parameters according to the target motion posture control model and sends the digital human motion data generated according to the motion control parameters to the terminal device for display. Thus, the motion posture control model can be dynamically adjusted according to the link state of the communication link. When the link state is good, the system can select a more complex model with higher control accuracy to generate smoother and more natural digital human motion. When the link state is poor, the system will automatically switch to a simpler model with lower requirements for data transmission to ensure the basic continuity and stability of digital human motion in an environment with low bandwidth and high latency. This model selection mechanism that adapts to the link state of the communication link not only improves the adaptability and robustness of the system but also ensures stable digital human motion effects in different network environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] The accompanying drawings herein are incorporated into the specification and form a part of the specification, showing embodiments consistent with the present application, and are used together with the specification to explain the principles of the present application.

[0039] Figure 1 is a schematic structural diagram of a digital human motion data processing system shown according to an exemplary embodiment of the present application;

[0040] Figure 2 is a schematic flowchart of a digital human motion data processing method shown according to an exemplary embodiment of the present application;

[0041] Figure 3 is a schematic structural diagram of an electronic device shown according to an exemplary embodiment of the present application.

[0042] Through the above accompanying drawings, specific embodiments of the present application have been shown, and there will be more detailed descriptions hereinafter. These drawings and the textual descriptions are not intended to limit the scope of the concept of the present application in any way, but to illustrate the concept of the present application to those skilled in the art by referring to specific embodiments. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0043] Exemplary embodiments will be described in detail herein, and examples thereof are shown in the accompanying drawings. When the following description refers to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present application. On the contrary, they are merely examples of devices and methods consistent with some aspects of the present application as detailed in the appended claims.

[0044] Figure 1 This is a schematic structural diagram of a digital human motion data processing system shown according to an exemplary embodiment of the present application. As Figure 1 shown, the digital human motion data processing system 100 provided in this embodiment includes: a terminal device 110 and a server 120.

[0045] Among them, the terminal device 110 is responsible for collecting human body posture data and sending these data to the server through a communication link. The terminal device 110 can include electronic devices with various sensors, such as cameras, depth sensors, accelerometers, etc., for capturing human motion information. Among them, the above terminal device 110 can be a host device or a user device.

[0046] The server 120 is used to receive the human body posture data sent by the terminal device 110, generate a digital human model based on these data, and determine a target motion posture control model from a preset set of motion posture control models according to the link state of the communication link. The server 120 is also responsible for outputting motion control parameters according to the target motion posture control model and sending the generated digital human motion data back to the terminal device 110 for display.

[0047] In a possible implementation, the preset set of motion posture control models configured in the server includes at least a first motion posture control model and a second motion posture control model. Among them, the first motion posture control model is a control model established based on a proportional derivative controller, and the second motion posture control model is a control model established based on a proportional integral derivative controller.

[0048] The first motion posture control model is a controller based on proportional and derivative links, which can achieve fast response and stable control of the motion posture. The proportional link generates a control action according to the magnitude of the error, and the derivative link generates a control action according to the change rate of the error. The two work together to reduce the error and improve the stability of the system.

[0049] When the communication link state is poor (such as high latency, insufficient bandwidth), the first motion posture control model is selected as the target motion posture control model. This is because the first motion posture control model is relatively simple and has low requirements for data transmission, and can maintain the basic continuity and stability of digital human motion in a poor network environment.

[0050] Specifically, the first motion posture control model can be pre-built in the server, and the corresponding proportional gain and derivative gain parameters can be set. When the link state meets the conditions for selecting the first motion posture control model, the server will start the model and output motion control parameters according to the input human body posture data.

[0051] The second motion posture control model adds an integral link, which can achieve higher-precision control of the motion posture. The integral link generates a control action based on the accumulation of errors, helping to eliminate the steady-state error and improve the control precision of the system.

[0052] When the communication link state is good (such as low latency and sufficient bandwidth), the PID controller model is selected as the target motion posture control model. This is because the PID controller model has higher control precision and anti-interference ability, and can generate a more smooth and natural digital human motion effect in a good network environment.

[0053] Specifically, the second motion posture control model is pre-constructed in the server, and the corresponding proportional gain, integral gain, and derivative gain parameters are set. When the link state meets the conditions for selecting the second motion posture control model, the server will start the model and output motion control parameters according to the input human body posture data.

[0054] The server evaluates the link state by monitoring parameters such as the latency and bandwidth of the communication link. These parameters can be obtained through the interfaces provided by the network protocol stack or measured by dedicated link state monitoring tools. According to the monitored link state, the server selects a suitable target motion posture control model from the preset set of motion posture control models. If the link state is good, the second motion posture control model is selected; if the link state is poor, the first motion posture control model is selected.

[0055] During the motion process, the server may adjust the target motion posture control model according to real-time feedback and monitoring results. For example, if the motion trajectory of the digital human model deviates from the expectation or the link state changes, the server may reselect the control model or adjust the control parameters to improve the stability and accuracy of the motion control.

[0056] Furthermore, the default configuration of the target motion posture control model is the second motion posture control model. Specifically, when the system starts, the model management module loads the second motion posture control model into the memory and sets the default parameters. Then, the link state monitoring module continuously collects the link RTT and packet loss rate.

[0057] If the RTT < 50ms and the packet loss rate < 1%, the second motion posture control model is maintained as the active model. For example, in a local area network environment, the link RTT is stable at 10ms and the packet loss rate is 0%, and the system defaults to using the second motion posture control model to generate a digital human motion effect with high precision and low jitter.

[0058] When the link quality deteriorates and when RTT ≥ 50ms or the packet loss rate ≥ 1%, the model switch is triggered. The model management module preloads the parameters of the first motion posture control model. During the switch, only the control logic pointer needs to be updated, and the switch delay < 5ms.

[0059] When the link quality is restored (RTT < 50ms and the packet loss rate < 1%), the system automatically switches back to the second motion posture control model.

[0060] It should be noted that the above first link state corresponds to the first transmission frame rate, and the second link state corresponds to the second transmission frame rate, and the second transmission frame rate is higher than the first transmission frame rate.

[0061] In the digital human motion data processing system, the transmission frame rate is an important indicator to measure the data transmission efficiency and quality. By dynamically adjusting the transmission frame rate according to the link state, the system can utilize network resources more effectively. When the link state is the first link state (i.e., a relatively poor state), the system selects a lower transmission frame rate (the first transmission frame rate) to reduce the data transmission volume, lower the network burden, and avoid data loss or delay caused by network congestion. On the contrary, when the link state is upgraded to the second link state (i.e., a better state), the system selects a higher transmission frame rate (the second transmission frame rate) to make full use of the network bandwidth and improve the real-time and accuracy of data transmission.

[0062] The increase in the transmission frame rate not only means a faster data transmission speed but also is directly related to the smoothness and realism of the digital human motion. In the first link state, although the lower transmission frame rate may cause slight jerks or delays in the digital human motion, the system can make up for this deficiency to a certain extent by selecting the first motion posture control model based on the proportional derivative controller, ensuring the basic continuity and stability of the digital human motion. In the second link state, the higher transmission frame rate makes the digital human motion more smooth and natural, with richer detail performance, thus greatly enhancing the user's visual experience.

[0063] Associating the transmission frame rate with the link state also enhances the adaptability of the digital human motion data processing system to different network environments. Whether facing an unstable environment with large network fluctuations or a stable environment with good network conditions, the system can ensure the continuity and stability of the digital human motion by dynamically adjusting the transmission frame rate and selecting the corresponding motion posture control model. This adaptive mechanism not only improves the robustness of the system but also enables the system to provide stable digital human motion effects in various network environments.

[0064] In another possible implementation, the above-mentioned preset motion posture control model set only includes the target motion posture control model. The target motion posture control model is a control model established based on a proportional-derivative controller, and the gain parameter configuration in the target motion posture control model is associated with the link state.

[0065] Specifically, after the system is started, initialization operations are first performed, including loading the preset motion posture control model set (only including the target motion posture control model in this embodiment), configuring the initial gain parameters of the PD controller, etc. The terminal device obtains human body posture data through devices such as sensors and sends it to the server through the communication link. The server monitors the link state of the communication link in real time, including key indicators such as delay and bandwidth. According to the monitored link state, the server dynamically adjusts the gain parameters of the PD controller. The server uses the target motion posture control model to generate motion control parameters based on the adjusted gain parameters and the received human body posture data. The server generates digital human motion data based on the motion control parameters and sends it to the terminal device for display.

[0066] Among them, the PD controller realizes the control of the motion posture through the proportional link and the derivative link. The proportional link adjusts the control output according to the current error, while the derivative link predicts and compensates for future errors according to the change rate of the error. This control strategy enables the system to maintain a stable motion effect under different link states. In the PD controller, the configuration of the gain parameters (including the proportional gain and the derivative gain) is crucial for the control effect. In this embodiment, these gain parameters are set to be associated with the link state of the communication link. This means that as the link state changes, the gain parameters will be adjusted accordingly to adapt to different network environments.

[0067] Furthermore, if the link state of the communication link is the third link state, the first gain parameter is configured for the target motion posture control model, where the first gain parameter includes the first proportional gain parameter and the first derivative gain parameter. If the link state of the communication link is the fourth link state, the second gain parameter is configured for the target motion posture control model, where the second gain parameter includes the second proportional gain parameter and the second derivative gain parameter.

[0068] Specifically, if it is determined that it is the third link state, the server configures the first gain parameters for the target motion attitude control model, including setting a relatively high first proportional gain parameter and a first derivative gain parameter. If it is determined that it is the fourth link state, the server configures the second gain parameters for the target motion attitude control model, including setting a relatively low second proportional gain parameter and a second derivative gain parameter. Among them, the first gain parameters and the second gain parameters can also be a dynamic function, so as to achieve dynamic adjustment. After configuring the appropriate gain parameters, the server generates motion control parameters according to the target motion attitude control model and the received human body attitude data.

[0069] In addition, a configuration parameter mapping table is configured in the server. The third link state corresponds to the first gain parameters in the configuration parameter mapping table, and the fourth link state corresponds to the second gain parameters in the configuration parameter mapping table.

[0070] Optionally, the above-mentioned third link state can be better than the fourth link state. The second proportional gain parameter is an adjustment parameter based on the first proportional gain parameter, and the second derivative gain parameter is an adjustment parameter based on the first derivative gain parameter.

[0071] As an adjustment parameter based on the first proportional gain parameter, its value is dynamically adjusted according to the difference between the third link state and the fourth link state. In the third link state, due to the superior network conditions, the system tends to increase the proportional gain to speed up the response speed; while in the fourth link state, in order to reduce the overshoot caused by network fluctuations, the system will appropriately reduce the proportional gain.

[0072] Similarly, as an adjustment parameter based on the first derivative gain parameter, its adjustment logic is similar to that of the proportional gain. In the third link state, the derivative gain is increased to improve the system's prediction and compensation ability for error changes; in the fourth link state, the derivative gain is reduced to reduce the system's sensitivity to noise and improve stability.

[0073] By subdividing the link state into the third link state and the fourth link state and configuring corresponding gain parameters for different states, the system can more finely adapt to different network environments. In the third link state (superior network conditions), the system can respond more quickly to network changes by increasing the proportional gain and the derivative gain, improving the smoothness and accuracy of the digital human motion; while in the fourth link state (poor network conditions), the system reduces the gain parameters to reduce the control overshoot and jitter caused by network fluctuations, ensuring the basic continuity and stability of the digital human motion.

[0074] The adjustment strategy of the gain parameter directly affects the accuracy and stability of the digital human motion control model. Under the design where the second proportional gain parameter and the second derivative gain parameter are adjusted based on the first gain parameter, the system can dynamically balance the control accuracy and stability according to the changes in network conditions. Under excellent network conditions, increasing the gain parameter can enhance the precise control of the digital human motion posture by the system; while under poor network conditions, reducing the gain parameter can avoid over-adjustment of the system caused by network delay or packet loss and maintain the smoothness of the digital human motion.

[0075] By adjusting based on the first gain parameter, the setting of the second gain parameter realizes a smooth transition mechanism. When the network condition gradually improves from the fourth link state to the third link state, the gradual increase of the gain parameter can ensure a smooth transition of the digital human motion control and avoid the phenomenon of discontinuous motion or jitter caused by sudden changes in the gain. Similarly, when the network condition deteriorates, the gradual decrease of the gain parameter can also effectively slow down the change of the control effect and maintain the stability of the digital human motion.

[0076] Ultimately, the above technical effects work together to improve the user experience. Under different network environments, users can all watch smooth and natural digital human motion effects without worrying about problems such as motion jamming, delay, or distortion caused by network fluctuations. This stable digital human motion experience not only enhances users' trust in the system but also improves users' acceptance and satisfaction with digital human interaction technology.

[0077] Optionally, the above third link state corresponds to a third transmission frame rate, the fourth link state corresponds to a fourth transmission frame rate, and the third transmission frame rate is higher than the fourth transmission frame rate.

[0078] Furthermore, the first proportional gain parameter and the first derivative gain parameter in the first gain parameter are preset default configuration parameters in the motion posture control model.

[0079] Specifically, setting the first proportional gain parameter and the first derivative gain parameter as the preset default configuration parameters of the motion posture control model simplifies the system initialization process. When the system starts, the motion posture control model can be quickly put into operation without a complex parameter tuning process. This not only improves the system startup efficiency but also reduces the risk of system anomalies or performance degradation caused by improper parameter configuration.

[0080] The preset default configuration parameters usually go through sufficient testing and optimization and can maintain the stable operation of the system in various network environments. By using these parameters as the first gain parameter, the system can maintain a certain control accuracy and stability under different link states, ensuring the accurate transmission and display of digital human motion data. This stability is crucial for providing a high-quality digital human motion interaction experience.

[0081] Setting the first gain parameter to a preset default configuration parameter also facilitates subsequent parameter adjustment and optimization. During the operation of the system, algorithm experts or system administrators can adjust the first gain parameter according to the actual network environment and user requirements to further optimize the digital human motion control effect. At the same time, this adjustment method based on the preset default configuration parameter also makes the parameter optimization process more intuitive and controllable.

[0082] During the process of dynamically adjusting the gain parameter according to the link state, setting the first gain parameter to a preset default configuration parameter can achieve rapid switching of the gain parameter. When the link state changes, the system can quickly switch from the preset default configuration parameter to the gain parameter applicable to the current link state, thereby ensuring the continuity and stability of digital human motion control. This rapid switching mechanism is of great significance for coping with network fluctuations and improving the system response speed.

[0083] In addition, by setting the first gain parameter to a preset default configuration parameter, the system can maintain consistent performance and stability on different application scenarios and hardware platforms. This versatility and scalability make the system easier to be integrated into a wider range of digital human motion interaction systems, thus promoting the popularization and application of digital human technology.

[0084] Figure 2 is a schematic flow chart of a digital human motion data processing method according to an exemplary embodiment of the present application. As Figure 2 shown, the digital human motion data processing method provided in this embodiment includes:

[0085] S201. The terminal device sends the acquired human body posture data to the server through a communication link.

[0086] Specifically, the terminal device collects human body posture data in real time through built-in sensors. These data can include joint angles, position information, speed information, etc., for describing the motion state of the human body. The collected human body posture data is preprocessed and then sent to the server through a communication link (such as a wireless network, a wired network, etc.). The state of the communication link (such as delay, bandwidth, etc.) will directly affect the real-time performance and accuracy of data transmission.

[0087] S202. The server generates a digital human model according to the human body posture data, and determines a target motion posture control model from a preset set of motion posture control models according to the link state of the communication link.

[0088] Specifically, after receiving the human body posture data sent by the terminal device, the server first generates a digital human model according to these data. The digital human model is a virtual representation of the human body, and its motion state is consistent with that of the real human body.

[0089] Among them, the server first receives the human body posture data sent by the terminal device through the communication link. These data usually include joint angles, position information, speed information, etc., which are used to comprehensively describe the motion state of the human body. The received data will go through a preprocessing stage to eliminate noise, fill in missing values, etc., to ensure the accuracy and integrity of the data. The preprocessed data will be used as the basis for generating the digital human model.

[0090] The server pre-stores the framework of the digital human model, which defines the basic structure of the digital human, including the bone structure, joint connections, muscle distribution, etc. This framework is the basic template for generating the digital human model. The server maps the preprocessed human body posture data onto the framework of the digital human model. This usually involves converting information such as the joint angles and positions of the real human body into corresponding parameters in the digital human model. After the mapping is completed, the server adjusts the digital human model according to these parameters to make its motion state consistent with that of the real human body.

[0091] Then, the server determines the target motion posture control model from the preset set of motion posture control models according to the link state of the communication link. The preset set of motion posture control models includes various motion posture control models, such as the control model established based on the Proportional Derivative (PD) controller, the control model established based on the Proportional Integral Derivative (PID) controller, etc. These models have different complexities and control precisions and are applicable to different network environments.

[0092] When the communication link state is good (such as low latency and sufficient bandwidth), the server selects a model with higher control precision (such as the PID controller model) to generate a more smooth and natural digital human motion.

[0093] When the communication link state is poor (such as high latency and insufficient bandwidth), the server selects a simpler model with lower requirements for data transmission (such as the PD controller model) to ensure the basic continuity and stability of the digital human motion in a low-bandwidth and high-latency environment.

[0094] S203. The server outputs motion control parameters according to the target motion posture control model and sends the digital human motion data generated according to the motion control parameters to the terminal device for display.

[0095] Specifically, the server controls the output of motion control parameters according to the determined target motion posture control model. These parameters may include target joint angles, target positions, target speeds, etc., which describe the motion states that the digital human model should reach, that is, these parameters are used to describe information such as the motion trajectory, speed, and acceleration of the digital human model. According to the motion control parameters, the server generates digital human motion data. These data include information such as the positions and postures of the digital human model at various time points, and are used for real-time display on the terminal device.

[0096] After receiving the digital human motion data sent by the server, the terminal device performs real-time rendering and display. Users can observe the digital human model that is consistent with the real human motion state through the terminal device.

[0097] In this embodiment, the acquired human body posture data is sent to the server through the communication link by the terminal device. In the server, a digital human model is generated according to the human body posture data, and a target motion posture control model is determined from the preset motion posture control model set according to the link state of the communication link. Then, the server outputs motion control parameters according to the target motion posture control model, and sends the digital human motion data generated according to the motion control parameters to the terminal device for display, so that the motion posture control model can be dynamically adjusted according to the link state of the communication link. When the link state is good, the system can select a more complex model with higher control accuracy to generate a more smooth and natural digital human motion. When the link state is poor, the system will automatically switch to a simpler model with lower requirements for data transmission to ensure the basic continuity and stability of the digital human motion in an environment with low bandwidth and high latency. This model selection mechanism that adapts to the link state of the communication link not only improves the adaptability and robustness of the system, but also ensures stable digital human motion effects in different network environments.

[0098] Figure 3 It is a schematic structural diagram of an electronic device shown according to an exemplary embodiment of the present application. As Figure 3 shown, an electronic device 300 provided in this embodiment includes: a processor 301 and a memory 302; wherein:

[0099] The memory 302 is used to store computer programs, and this memory can also be flash (flash memory).

[0100] The processor 301 is used to execute the execution instructions stored in the memory to implement each step in the above method. For specific reference, please refer to the relevant descriptions in the previous method embodiments.

[0101] Optionally, the memory 302 can be either independent or integrated with the processor 301.

[0102] When the memory 302 is a device independent of the processor 301, the electronic device 300 may further include:

[0103] A bus 303 for connecting the memory 302 and the processor 301.

[0104] This embodiment also provides a readable storage medium. A computer program is stored in the readable storage medium. When at least one processor of the electronic device executes the computer program, the electronic device executes the methods provided by the above various embodiments.

[0105] This embodiment also provides a program product. The program product includes a computer program, and the computer program is stored in a readable storage medium. At least one processor of the electronic device can read the computer program from the readable storage medium, and the execution of the computer program by at least one processor enables the electronic device to implement the methods provided by the above various embodiments.

[0106] After considering the specification and practicing the invention disclosed herein, those skilled in the art will readily conceive of other embodiments of the present application. The present application is intended to cover any variations, uses, or adaptations of the present application, which follow the general principles of the present application and include common general knowledge or conventional technical means in the technical field not disclosed in the present application. The specification and examples are only regarded as exemplary, and the true scope and spirit of the present application are pointed out by the claims.

[0107] It should be understood that the present application is not limited to the exact structures described above and shown in the drawings, and various modifications and changes can be made without departing from its scope. The scope of the present application is only limited by the appended claims.

Claims

1. A digital human motion data processing system, characterized in that Including: A terminal device and a server; The terminal device sends the acquired human body posture data to the server through a communication link; The server generates a digital human model based on the human body posture data, and determines a target motion posture control model from a preset set of motion posture control models according to the link state of the communication link. The preset set of motion posture control models at least includes a first motion posture control model established based on a proportional derivative controller and a second motion posture control model established based on a proportional integral derivative controller; The server outputs motion control parameters according to the target motion posture control model, and sends the digital human motion data generated according to the motion control parameters to the terminal device for display; If the link state of the communication link is a first link state, the target motion posture control model is the first motion posture control model; If the link state of the communication link is a second link state, the target motion posture control model is the second motion posture control model, where the second link state is better than the first link state; The first link state corresponds to a first transmission frame rate, the second link state corresponds to a second transmission frame rate, and the second transmission frame rate is higher than the first transmission frame rate.

2. The digital human motion data processing system according to claim 1, wherein, The default configuration of the target motion posture control model is the second motion posture control model.

3. The digital human motion data processing system according to claim 1, wherein The preset set of motion posture control models only includes the target motion posture control model. The target motion posture control model is a control model established based on a proportional derivative controller, and the gain parameter configuration in the target motion posture control model is associated with the link state.

4. The digital human motion data processing system according to claim 3, wherein Before the server outputs motion control parameters according to the target motion posture control model, it further includes: If the link state of the communication link is a third link state, configure a first gain parameter for the target motion posture control model, where the first gain parameter includes a first proportional gain parameter and a first derivative gain parameter; If the link state of the communication link is a fourth link state, configure a second gain parameter for the target motion posture control model, where the second gain parameter includes a second proportional gain parameter and a second derivative gain parameter.

5. The digital human motion data processing system according to claim 4, wherein A configuration parameter mapping table is configured in the server. The third link state corresponds to the first gain parameter in the configuration parameter mapping table, and the fourth link state corresponds to the second gain parameter in the configuration parameter mapping table.

6. A method for processing digital human motion data, characterized in that, Applied to a digital human motion data processing system, the system includes: a terminal device and a server; The terminal device sends the acquired human body posture data to the server through a communication link; The server generates a digital human model based on the human body posture data, and determines a target motion posture control model from a preset set of motion posture control models according to the link state of the communication link. The preset set of motion posture control models at least includes a first motion posture control model established based on a proportional derivative controller and a second motion posture control model established based on a proportional integral derivative controller; The server outputs motion control parameters according to the target motion posture control model, and sends the digital human motion data generated according to the motion control parameters to the terminal device for display; If the link state of the communication link is the first link state, the target motion posture control model is the first motion posture control model; If the link state of the communication link is the second link state, the target motion posture control model is the second motion posture control model, where the second link state is better than the first link state; The first link state corresponds to a first transmission frame rate, the second link state corresponds to a second transmission frame rate, and the second transmission frame rate is higher than the first transmission frame rate.

7. An electronic device, characterized in that, Including: A processor; And, A memory for storing executable instructions of the processor; Wherein, the processor is configured to execute the method according to claim 6 by executing the executable instructions.

8. A computer-readable storage medium, characterized in that, Computer-executable instructions are stored in the computer-readable storage medium, and when the computer-executable instructions are executed by a processor, they are used to implement the method according to claim 6.

Images