3D exhibition hall effect visualization experience platform

Abstract

The present invention discloses a 3D exhibition hall effect visualization experience platform, which relates to the field of exhibition hall effect visualization experience technology, including a motion data acquisition module, a delay and jamming prediction module, an urgency information evaluation module, a hierarchical rendering processing module and a real-time optimization monitoring module; the delay and jamming prediction module analyzes the pre-processed user motion data to predict whether the degree of user's rapid movement will cause delays and jams in the picture; the urgency information evaluation module obtains the urgency information of all rendering data that need to be processed when it is predicted that the degree of user's rapid movement will cause delays and jams in the picture, and analyzes after acquisition to evaluate the urgency of each rendering data. The present invention can effectively solve the problem that when the user of the virtual exhibition hall moves quickly, the system cannot update the user's perspective in real time, resulting in delays and jams in the picture, thereby improving the user's immersion experience and satisfaction.

Description

Technical Field

[0001] The present invention relates to the technical field of exhibition hall effect visualization experience, and in particular to a 3D exhibition hall effect visualization experience platform. Background Art

[0002] 3D exhibition hall effect visualization is to use three-dimensional modeling and rendering technology to realistically restore the layout, exhibits and display effects of the actual exhibition hall on the computer, so that users can experience the overall effect of the exhibition hall in a virtual environment. 3D exhibition hall effect visualization experience refers to the use of interactive interfaces, motion capture and virtual reality technologies to enable users to browse freely in the virtual exhibition hall and interact with exhibits, thereby gaining an immersive exhibition experience. Existing 3D exhibition hall effect visualization experience technologies usually include high-precision 3D modeling, real-time rendering, virtual reality equipment (such as VR headsets), motion capture equipment (such as somatosensory gloves) and intelligent interactive systems. Users can use these technical means to truly feel the spatial layout, exhibit details and display effects of the exhibition hall in a virtual environment, and even conduct virtual guided tours, information inquiries and interactive operations, making the exhibition process more vivid, convenient and interesting.

[0003] The existing 3D exhibition hall effect visualization experience technology uses high-precision 3D modeling to digitally reproduce the exhibition hall and its exhibits, and then uses real-time rendering technology to generate realistic visual effects. Users wear virtual reality devices (such as VR headsets) to enter the virtual exhibition hall, and use motion capture devices (such as somatosensory gloves, cameras) to capture the user's body movements, allowing users to move freely and interact in the virtual space. The intelligent interactive system uses the interface and voice recognition technology to enable users to choose to view different exhibits, query exhibit information, and participate in interactive displays. The entire process is supported by high-performance computing equipment and software platforms to ensure a real-time, smooth and immersive experience.

[0004] The prior art has the following deficiencies:

[0005] When users move quickly in a virtual exhibition hall, the system sometimes cannot update the user's perspective in real time, resulting in delays and freezes in the screen. This is especially obvious when displaying complex, multi-layered 3D models, because the system needs to process a large amount of rendering data in a short period of time. This delay and freeze will seriously affect the user's immersive experience and make the user feel dizzy and uncomfortable. Since the existing technology cannot effectively solve the problems of real-time rendering and fast perspective updates, users will miss important display content or be unable to interact smoothly during the browsing process, which will ultimately affect the effect of the exhibition and the user's overall impression of the virtual exhibition hall.

[0006] The above information disclosed in this Background section is only for enhancement of understanding of the background of the present disclosure and therefore it may contain information that does not constitute the prior art that is already known to one of ordinary skill in the art. Summary of the invention

[0007] The purpose of the present invention is to provide a 3D exhibition hall effect visualization experience platform to solve the problems in the above-mentioned background technology.

[0008] In order to achieve the above-mentioned object, the present invention provides the following technical solutions: a 3D exhibition hall effect visualization experience platform, including a motion data acquisition module, a delay and freeze prediction module, an urgent information evaluation module, a hierarchical rendering processing module and a real-time optimization monitoring module;

[0009] The motion data acquisition module acquires the user's motion data in real time during the user's rapid movement and performs preprocessing after acquisition;

[0010] The delay and freeze prediction module analyzes the pre-processed user motion data to predict whether the user's fast movement will cause delays and freezes in the picture;

[0011] An urgency information evaluation module, when predicting that the user's fast movement will cause delays and freezes in the screen, obtains the urgency information of all rendering data that need to be processed, analyzes it after acquisition, evaluates the urgency of each rendering data, and divides each rendering data into high-urgency rendering data and low-urgency rendering data according to the evaluation results;

[0012] A hierarchical rendering processing module is used to process high-urgency rendering data first, and then process low-urgency rendering data after the high-urgency rendering data is processed.

[0013] Real-time optimization monitoring module, real-time monitoring of rendering effects, use machine learning algorithms to continuously optimize motion prediction models and rendering strategies, and continuously adjust rendering parameters based on user feedback and system performance data.

[0014] Preferably, the pre-processed user motion data is analyzed to predict whether the degree of rapid movement of the user will cause delay and freeze in the picture, which specifically includes the following steps:

[0015] Extracting velocity information and acceleration information from the preprocessed user motion data;

[0016] Analyze the extracted speed information and acceleration information to generate speed variation coefficient and acceleration fluctuation coefficient respectively;

[0017] The generated speed variation coefficient and acceleration fluctuation coefficient are used to construct a dynamic load prediction model to generate a smoothness prediction coefficient;

[0018] Determining a pre-set threshold value for the fluency prediction coefficient;

[0019] The generated fluency prediction coefficient is compared with the pre-set fluency prediction coefficient threshold, and based on the comparison result, it is predicted whether the degree of fast movement of the user will cause delay and freeze in the picture.

[0020] Preferably, the acquisition logic of the speed variation coefficient and the acceleration fluctuation coefficient is as follows:

[0021] Extract speed information from the preprocessed user motion data, including the actual speed of the user at different times during a period of fast movement and the corresponding time points, and use the function to convert the actual speed of the user at different times during a period of fast movement into a time series. To express, is a time point, and the time period is defined as ;

[0022] Calculate the speed change coefficient. The specific calculation formula is as follows:

[0023]

[0024] In the formula, is the speed variation coefficient, is the rate of change of speed;

[0025] Extract acceleration information from the preprocessed user motion data, including the actual acceleration of the user at different times during a period of rapid movement and the corresponding time points, and use the function to convert the actual acceleration of the user at different times during a period of rapid movement into a time series. To express, is a time point, and the time period is defined as ;

[0026] Calculate the acceleration fluctuation coefficient. The specific calculation formula is as follows:

[0027]

[0028] In the formula, is the acceleration fluctuation coefficient, is the rate of change of acceleration.

[0029] Preferably, the generated speed variation coefficient and acceleration fluctuation coefficient are used to construct a dynamic load prediction model, a fluency prediction coefficient is generated, a preset fluency prediction coefficient threshold is determined, the generated fluency prediction coefficient is compared with the preset fluency prediction coefficient threshold, and whether the degree of rapid movement of the user will cause delay and freeze in the screen is predicted according to the comparison result, which specifically includes the following steps:

[0030] Collect several speed change coefficients, several acceleration fluctuation coefficients and corresponding fluency prediction coefficients of users in the past period of time, and calibrate them as , and , Indicates the numbers of several speed change coefficients, several acceleration fluctuation coefficients and corresponding fluency prediction coefficients of the user in the past period of time. , is a positive integer, and the data collected in the past period of time forms a historical data set;

[0031] Select the multivariate regression model as the dynamic load prediction model, and train it through the historical data set to determine the value of the regression coefficient according to the formula:

[0032] In the formula, , and is the regression coefficient;

[0033] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and finally determined. , and The value of

[0034] Using the final regression coefficient, the speed change coefficient obtained by real-time detection is input into the constructed dynamic load prediction model. and acceleration fluctuation coefficient , generate fluency prediction coefficients in real time ;

[0035] Determine the pre-set fluency prediction coefficient threshold ;

[0036] The fluency prediction coefficient generated in real time The fluency prediction coefficient threshold was set Compare and predict whether the user's fast movement will cause delays and freezes in the screen based on the comparison results. The specific comparison analysis is as follows:

[0037] like , the user's fast movement will not cause delays and freezes in the picture;

[0038] like , the degree to which the user moves quickly can cause delays and freezes in the picture.

[0039] Preferably, when it is predicted that the degree of rapid movement of the user will cause delay and freeze in the screen, the urgency information of all rendering data to be processed is obtained, and after the acquisition, the urgency of each rendering data is evaluated, and the rendering data is divided into high-urgency rendering data and low-urgency rendering data according to the evaluation result, which specifically includes the following steps:

[0040] When it is predicted that the user's fast movement will cause delays and freezes in the picture, obtain urgent information about all the rendering data that needs to be processed, including the number of polygons, texture resolution, rendering time and data transmission time of each rendering data;

[0041] Preprocessing the polygon quantity, texture resolution, rendering time and data transmission time of each acquired rendering data;

[0042] Analyze the number of polygons, texture resolution, rendering time, and data transmission time of each pre-processed rendering data to generate a rendering complexity index and a real-time processing requirement coefficient for each rendering data;

[0043] An urgency assessment model is constructed based on the rendering complexity index and real-time processing requirement coefficient of each generated rendering data, and an urgency coefficient of each rendering data is generated. The urgency coefficient of each generated rendering data is compared with a preset urgency coefficient threshold, and the urgency of each rendering data is evaluated based on the comparison result. According to the evaluation result, each rendering data is divided into high-urgency rendering data and low-urgency rendering data.

[0044] Preferably, the logic for obtaining the rendering complexity index and the real-time processing requirement coefficient of each rendering data is as follows:

[0045] Obtain the urgent information of all rendering data that need to be processed, including the number of polygons, texture resolution, rendering time, and data transmission time of each rendering data, and calibrate the number of polygons, texture resolution, rendering time, and data transmission time of each rendering data as , , and , Indicates The number of polygons in the rendering data, Indicates The texture resolution of the rendered data, Indicates The rendering time of the rendered data, Indicates The data transmission time of the rendering data, , is a positive integer;

[0046] Calculate the rendering complexity index and real-time processing requirement coefficient of each rendering data. The specific calculation formula is as follows:

[0047]

[0048]

[0049] In the formula, For the The rendering complexity index of the rendering data, For the The real-time processing requirement factor of the rendering data.

[0050] Preferably, the rendering complexity index of each generated rendering data is and real-time processing demand factor Construct an urgency assessment model and generate the urgency coefficient of each rendering data through weighted summation , the urgency coefficient of each rendered data generated With the pre-set urgency factor threshold A comparison is performed, and the urgency of each rendering data is evaluated according to the comparison results. According to the evaluation results, each rendering data is divided into high-urgency rendering data and low-urgency rendering data. The specific analysis is as follows:

[0051] like , No. If the urgency of a rendering data is low, the rendering data is classified as low-urgency rendering data;

[0052] like , No. If the urgency of a rendering data is high, the rendering data is classified as high-urgency rendering data.

[0053] Preferably, high urgency rendering data is processed first, and after the high urgency rendering data is processed, low urgency rendering data is processed, which specifically includes the following steps:

[0054] According to the urgency evaluation result, the high-urgency rendering data and the low-urgency rendering data are stored in the high-urgency rendering queue and the low-urgency rendering queue respectively;

[0055] Extract rendering data from the high-urgency rendering queue and call the rendering engine to process the high-urgency rendering data;

[0056] Real-time monitoring of the processing status of high-urgency rendering data. After all high-urgency rendering data is processed, the system automatically switches to low-urgency rendering data processing;

[0057] After the high-urgency rendering data is processed, the rendering data is extracted from the low-urgency rendering queue, and the rendering engine is called to process the low-urgency rendering data;

[0058] After each rendering cycle, update the high-urgency rendering queue and the low-urgency rendering queue;

[0059] Dynamically adjust the processing priority of high-urgency and low-urgency rendering data based on system resource usage and rendering data processing progress.

[0060] In the above technical solution, the technical effects and advantages provided by the present invention are:

[0061] 1. The present invention significantly improves the performance of the virtual exhibition hall when the user moves quickly through the collaborative work of multiple modules. First, through the motion data acquisition module and the delay and jamming prediction module, the system can collect the user's motion data in real time and predict possible delays and jamming. This foresight allows the system to take measures in advance to avoid performance bottlenecks caused by a large number of rendering tasks, thereby ensuring the smoothness and real-time performance of the user's picture during fast movement.

[0062] 2. The present invention performs detailed urgency analysis and classification processing on rendering data through an urgency information evaluation module and a hierarchical rendering processing module. By analyzing the number of polygons, texture resolution, rendering time, and data transmission time, the system can prioritize high-urgency rendering data to ensure that critical tasks are completed first. In this way, not only the delays and freezes caused by the rendering of complex 3D models are effectively reduced, but also the utilization of system resources is optimized and the overall rendering efficiency is improved. The hierarchical processing mechanism enables the system to ensure real-time processing of important tasks when resources are tight, thereby enhancing the user's immersive experience.

[0063] 3. The present invention uses machine learning algorithms and real-time monitoring data to continuously optimize motion prediction models and rendering strategies. According to user feedback and system performance data, the rendering parameters are dynamically adjusted to ensure that the system can maintain optimal performance in various usage scenarios. Through this adaptive optimization mechanism, the system can flexibly respond to the challenges brought by the rapid movement of users, ensure the stability and smoothness of the picture, reduce the user's dizziness and discomfort, and improve the user's overall satisfaction and interactive experience with the virtual exhibition hall. In short, the comprehensive application of these technical solutions has achieved efficient, stable and smooth operation of the virtual exhibition hall in a high-dynamic environment. DETAILED DESCRIPTION

[0064] Example embodiments will now be described more fully. However, example embodiments can be implemented in a variety of forms and should not be construed as limited to the examples set forth herein; rather, these example embodiments are provided so that the description of the present disclosure will be more comprehensive and complete, and the concept of the example embodiments will be fully conveyed to those skilled in the art.

[0065] The present invention provides a 3D exhibition hall effect visualization experience platform, including a motion data acquisition module, a delay and freeze prediction module, an emergency information evaluation module, a hierarchical rendering processing module and a real-time optimization monitoring module;

[0066] The motion data acquisition module acquires the user's motion data in real time during the user's rapid movement and performs preprocessing after acquisition;

[0067] To determine when a user is moving quickly, you can analyze the speed and acceleration parameters in the user's motion data. When the system detects that the user's speed or acceleration exceeds a set threshold, the user is considered to be in a state of rapid movement. This threshold can be determined through experiments and statistical analysis to ensure that it can accurately identify when the user is moving quickly. The system will continue to monitor these parameters, and when the speed or acceleration exceeds the threshold for a period of time, the system will mark it as a period of rapid movement.

[0068] The user's motion data can be obtained in real time through a variety of sensors and devices, including embedded IMU (inertial measurement unit) sensors, accelerometers, gyroscopes, etc. These sensors can be installed in devices worn by users (such as VR helmets, handheld controllers, etc.). The sensor transmits data to the system through wireless communication methods such as Bluetooth and Wi-Fi. The specific process of obtaining motion data includes: the sensor samples regularly (for example, 50 times per second), and sends the collected raw data to the central processing unit through the wireless communication module. The central processing unit receives, buffers and stores the data to ensure the continuity and real-time nature of the data.

[0069] Preprocessing after acquiring motion data is to ensure the accuracy and availability of the data. Preprocessing includes steps such as denoising, filtering, data calibration and synchronization. First, the raw data is denoised using a low-pass filter or Kalman filter to remove noise caused by sensor errors or environmental interference. Secondly, the data is calibrated using a sensor calibration algorithm to correct the sensor's deviation and drift. Then, the data collected by different sensors is time synchronized to ensure that each data point is consistent at the same timestamp. The preprocessed data is smoother and more accurate, providing a reliable basis for subsequent analysis and prediction.

[0070] The delay and freeze prediction module analyzes the pre-processed user motion data to predict whether the user's fast movement will cause delays and freezes in the picture;

[0071] In this implementation example, the pre-processed user motion data is analyzed to predict whether the degree of rapid movement of the user will cause delay and freeze in the picture, which specifically includes the following steps:

[0072] Extracting velocity information and acceleration information from the preprocessed user motion data;

[0073] Extracting velocity information and acceleration information from preprocessed user motion data can be achieved in the following ways: First, by reading the preprocessed data stream, the data is synchronized using the timestamp. The specific method of extracting velocity information includes calculating the instantaneous velocity from the position sensor data, or directly reading the value provided by the velocity sensor. The method of extracting acceleration information includes directly reading the data of the acceleration sensor, or obtaining the acceleration value by differentiating the velocity data. After data synchronization, the system uses a data parsing algorithm to extract velocity and acceleration information from the synchronized data stream, and stores this information in the corresponding data structure for subsequent analysis.

[0074] Analyze the extracted speed information and acceleration information to generate speed variation coefficient and acceleration fluctuation coefficient respectively;

[0075] The generated speed variation coefficient and acceleration fluctuation coefficient are used to construct a dynamic load prediction model to generate a smoothness prediction coefficient;

[0076] Determining a pre-set threshold value for the fluency prediction coefficient;

[0077] Determining a pre-set fluency prediction coefficient threshold can be achieved by analyzing a large amount of historical records of user motion data and rendering performance data. The specific methods include: first, collecting and storing the user's motion data under different movement speeds and accelerations and their corresponding rendering performance data. Then, use statistical analysis software to perform cluster analysis and regression analysis on these data to identify the relationship between different fluency prediction coefficients and rendering performance. Next, test different thresholds through experiments to select the optimal threshold that can accurately reflect the delays and freezes caused by the user's rapid movement. Finally, use a machine learning algorithm to further optimize and verify the threshold to ensure that it is suitable for various usage scenarios and is preset as a standard parameter in the software system.

[0078] The generated fluency prediction coefficient is compared with the pre-set fluency prediction coefficient threshold, and based on the comparison result, it is predicted whether the degree of fast movement of the user will cause delay and freeze in the picture.

[0079] In this embodiment, the acquisition logic of the velocity variation coefficient and the acceleration fluctuation coefficient is as follows:

[0080] Extract speed information from the preprocessed user motion data, including the actual speed of the user at different times during a period of fast movement and the corresponding time points, and use the function to convert the actual speed of the user at different times during a period of fast movement into a time series. To express, is a time point, and the time period is defined as ;

[0081] Extracting speed information from preprocessed user motion data can be achieved in the following ways: First, ensure the time synchronization of the data by reading the preprocessed data stream containing timestamps. Specific methods for extracting speed information include: 1) directly reading the user's speed data at different time points from the speed sensor, which is usually marked with timestamps; 2) if the position sensor data is used, the instantaneous speed is calculated by numerically differentiating the position data, and the formula is ,in For location data, The system uses a data parsing algorithm to extract the speed value of each time point from the synchronous data stream and stores the speed data in a data structure for subsequent analysis and calculation. In this way, the extracted speed information can be ensured to be accurate and time consistent.

[0082] Calculate the speed change coefficient. The specific calculation formula is as follows:

[0083]

[0084] In the formula, is the speed variation coefficient, is the rate of change of velocity, that is, the absolute value of the derivative of velocity with respect to time;

[0085] The size of the speed change coefficient directly affects the prediction of whether the degree of rapid movement of the user will cause delays and freezes in the picture. Specifically, a higher speed change coefficient indicates that the user's movement speed changes greatly, which means that the system needs to process a large amount of rendering data in a short period of time, which may exceed the system's processing capacity, resulting in delays and freezes in the picture. On the contrary, a lower speed change coefficient means that the user's movement speed changes less, and the system can perform rendering processing more calmly, reducing the risk of delays and freezes. Therefore, by monitoring the speed change coefficient, it is possible to effectively predict and prevent screen delays and freezes that may be caused by users moving quickly.

[0086] Extract acceleration information from the preprocessed user motion data, including the actual acceleration of the user at different times during a period of rapid movement and the corresponding time points, and use the function to convert the actual acceleration of the user at different times during a period of rapid movement into a time series. To express, is a time point, and the time period is defined as ;

[0087] Extracting acceleration information from preprocessed user motion data can be achieved in the following ways: First, ensure the time synchronization of the data by reading the preprocessed data stream. The specific methods for extracting acceleration information include: 1) directly reading the user's acceleration data at different time points from the acceleration sensor, which is usually marked with a timestamp; 2) if the velocity sensor data is used, the instantaneous acceleration is calculated by numerically differentiating the velocity data, and the formula is ,in is the speed data, The system uses a data parsing algorithm to extract the acceleration value of each time point from the synchronous data stream and stores the acceleration data in a data structure for subsequent analysis and calculation. In this way, the extracted acceleration information can be ensured to be accurate and time-consistent.

[0088] Calculate the acceleration fluctuation coefficient. The specific calculation formula is as follows:

[0089]

[0090] In the formula, is the acceleration fluctuation coefficient, is the rate of change of acceleration, that is, the absolute value of the second-order derivative of velocity with respect to time.

[0091] The size of the acceleration fluctuation coefficient is directly related to the prediction of whether the degree of rapid movement of the user will cause delays and freezes in the picture. Specifically, a higher acceleration fluctuation coefficient indicates that the user's motion acceleration changes greatly, which means that the user's motion state is unstable, and the system needs to frequently adjust the rendering calculation to adapt to this rapid change, which may exceed the system's processing capacity, causing delays and freezes in the picture. On the contrary, a lower acceleration fluctuation coefficient means that the user's motion acceleration changes less, and the system can perform rendering processing more stably, reducing the risk of delays and freezes. Therefore, by monitoring the acceleration fluctuation coefficient, it is possible to effectively predict and prevent screen delays and freezes that may be caused by users moving quickly.

[0092] In this embodiment, the generated speed variation coefficient and acceleration fluctuation coefficient are used to construct a dynamic load prediction model, a fluency prediction coefficient is generated, a preset fluency prediction coefficient threshold is determined, the generated fluency prediction coefficient is compared with the preset fluency prediction coefficient threshold, and whether the degree of rapid movement of the user will cause delay and freeze in the screen is predicted according to the comparison result, which specifically includes the following steps:

[0093] Collect several speed change coefficients, several acceleration fluctuation coefficients and corresponding fluency prediction coefficients of users in the past period of time, and calibrate them as , and , Indicates the numbers of several speed change coefficients, several acceleration fluctuation coefficients and corresponding fluency prediction coefficients of the user in the past period of time. , is a positive integer, and the data collected in the past period of time forms a historical data set;

[0094] Several speed change coefficients, acceleration fluctuation coefficients, and corresponding fluency prediction coefficients of users in the past period of time can be collected in the following ways: First, the user's motion data, including speed and acceleration information, is continuously monitored and recorded through the software system. The speed change coefficient and acceleration fluctuation coefficient are calculated in real time using sensor data, and these data are marked with timestamps. Then, by recording the fluency prediction coefficient generated in real time, the speed change coefficient, acceleration fluctuation coefficient, and fluency prediction coefficient are saved in the database. These historical data are regularly sorted and summarized to form a complete data set for subsequent model training and analysis. In this way, the collected data is ensured to be time consistent and accurate, which is convenient for the construction of a dynamic load prediction model.

[0095] The value of is set to be greater than or equal to 3 to ensure that the collected speed variation coefficient, acceleration fluctuation coefficient and corresponding fluency prediction coefficient can provide enough data points to accurately calculate the three regression coefficients in the multiple regression model. In regression analysis, at least three data points are required to solve the three unknowns to ensure that the model equation has a solution, so as to determine the regression coefficients. , and By using at least 3 sets of data, the complex relationship between user movement and rendering performance can be captured, improving the accuracy and reliability of the model. More data points not only help smooth out accidental fluctuations and outliers, but also enhance the stability and robustness of the model prediction. Therefore, The value of is set to be greater than or equal to 3 to ensure that the dynamic load prediction model has sufficient data support during the training process, can accurately calculate the regression coefficient, and ensure the effectiveness and accuracy of the model in practical applications.

[0096] In the formula, , and is the regression coefficient;

[0097] The reason for choosing the multiple regression model as the dynamic load prediction model is that the multiple regression model can simultaneously consider the impact of multiple independent variables and reveal the relationship between them and the dependent variables. By analyzing the joint effect of the speed change coefficient and the acceleration fluctuation coefficient on the smoothness prediction coefficient, the multiple regression model can provide more accurate and comprehensive prediction results. In addition, the multiple regression model has good explanatory power and can quantify the contribution of each independent variable to the dependent variable, thereby providing guidance for optimizing system performance.

[0098] Three regression coefficients , and Represent different meanings: is a constant term, which represents the baseline value of the fluency prediction coefficient when all independent variables (speed variation coefficient and acceleration fluctuation coefficient) are zero; is the regression coefficient of the speed change coefficient, indicating the degree of influence of speed change on the prediction of fluency; is the regression coefficient of the acceleration fluctuation coefficient, which indicates the degree of influence of acceleration fluctuation on the smoothness prediction. By determining these regression coefficients, the impact of speed change and acceleration fluctuation on system performance can be accurately quantified, thereby optimizing the rendering strategy and improving the user experience.

[0099] By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and finally determined. , and The value of

[0100] The purpose of optimizing the regression coefficient by minimizing the error between the predicted value and the actual value is to ensure the accuracy and reliability of the dynamic load prediction model. The specific method is to use the least squares method to calculate the regression coefficient. , and The least squares method ensures that the model can best fit the historical data by solving the regression coefficient combination that minimizes the sum of squared errors between the predicted value and the actual value. The optimization process includes the following steps: collecting enough historical data, building a regression equation, calculating the sum of squared errors, and iteratively adjusting the regression coefficients until the sum of squared errors reaches the minimum. This method can effectively improve the model's ability to predict new data, thereby more accurately predicting the rendering load when users move quickly.

[0101] Using the final regression coefficient, the speed change coefficient obtained by real-time detection is input into the constructed dynamic load prediction model. and acceleration fluctuation coefficient , generate fluency prediction coefficients in real time ;

[0102] Determine the pre-set fluency prediction coefficient threshold ;

[0103] The fluency prediction coefficient generated in real time The fluency prediction coefficient threshold was set Compare and predict whether the user's fast movement will cause delays and freezes in the screen based on the comparison results. The specific comparison analysis is as follows:

[0104] like , the user's fast movement will not cause delays and freezes in the picture, which means that the user's fast movement will not cause delays and freezes in the picture. In this case, the system can calmly respond to the user's movement changes within the existing rendering strategy and processing capabilities, keep the picture smooth and stable, and the user experience will not be negatively affected. The system can continue to render according to the normal strategy without additional optimization or adjustment, ensuring efficient use of resources;

[0105] like The degree of rapid movement of the user will cause delays and freezes in the picture, which means that the user's rapid movement may cause delays and freezes in the picture. In this case, the system's existing rendering strategy and processing capabilities may not be sufficient to cope with the user's movement changes, resulting in delayed picture updates and a poor user experience. To avoid this situation, the system needs to take corresponding measures, such as adjusting the rendering strategy, prioritizing key rendering tasks, or allocating more resources to reduce the impact of picture delays and freezes, and ensure the smoothness and continuity of the user experience.

[0106] An urgency information evaluation module, when predicting that the user's fast movement will cause delays and freezes in the screen, obtains the urgency information of all rendering data that need to be processed, analyzes it after acquisition, evaluates the urgency of each rendering data, and divides each rendering data into high-urgency rendering data and low-urgency rendering data according to the evaluation results;

[0107] In this embodiment, when it is predicted that the degree of rapid movement of the user will cause delay and freeze in the screen, the urgency information of all rendering data to be processed is obtained, and after the acquisition, the urgency of each rendering data is evaluated, and the rendering data is divided into high-urgency rendering data and low-urgency rendering data according to the evaluation result, which specifically includes the following steps:

[0108] When it is predicted that the user's fast movement will cause delays and freezes in the picture, obtain urgent information about all the rendering data that needs to be processed, including the number of polygons, texture resolution, rendering time and data transmission time of each rendering data;

[0109] When it is predicted that the user's rapid movement will cause delays and freezes in the screen, the software system can monitor the data processing in the rendering engine in real time to obtain the urgency information of all the rendering data that needs to be processed. The specific methods include: using the rendering engine's API interface to extract the number of polygons and texture resolution of each rendering data in the rendering task queue, recording the time to render each data block, and measuring the data transmission time through network monitoring tools. By calling these API interfaces and monitoring tools, the software system collects the number of polygons, texture resolution, rendering time and data transmission time of each rendering data in real time, and stores this data in the database for subsequent urgency assessment. In this way, the collected data is ensured to be accurate, real-time, and consistent.

[0110] Preprocessing the polygon quantity, texture resolution, rendering time and data transmission time of each acquired rendering data;

[0111] The number of polygons, texture resolution, rendering time, and data transmission time of each rendered data are preprocessed to ensure the consistency, integrity, and accuracy of the data for subsequent analysis and calculation. Preprocessing includes the following steps: first, clean the data, remove outliers and noise, and ensure the authenticity of the data; second, standardize the data, convert data of different dimensions to a unified scale for comparison and calculation; finally, fill in missing values, use interpolation or average methods to complete the data, and ensure the integrity of the data set. By implementing preprocessing through software, you can call the algorithm library for data cleaning and standardization, batch process the collected rendering data, and store the preprocessed data in the database to ensure the accuracy and reliability of subsequent analysis.

[0112] Analyze the number of polygons, texture resolution, rendering time, and data transmission time of each pre-processed rendering data to generate a rendering complexity index and a real-time processing requirement coefficient for each rendering data;

[0113] An urgency assessment model is constructed based on the rendering complexity index and real-time processing requirement coefficient of each generated rendering data, and an urgency coefficient of each rendering data is generated. The urgency coefficient of each generated rendering data is compared with a preset urgency coefficient threshold, and the urgency of each rendering data is evaluated based on the comparison result. According to the evaluation result, each rendering data is divided into high-urgency rendering data and low-urgency rendering data.

[0114] In this embodiment, the logic for obtaining the rendering complexity index and the real-time processing requirement coefficient of each rendering data is as follows:

[0115] Obtain the urgent information of all rendering data that need to be processed, including the number of polygons, texture resolution, rendering time, and data transmission time of each rendering data, and calibrate the number of polygons, texture resolution, rendering time, and data transmission time of each rendering data as , , and , Indicates The number of polygons in the rendering data, Indicates The texture resolution of the rendered data, Indicates The rendering time of the rendered data, Indicates The data transmission time of the rendering data, , is a positive integer;

[0116] No. The number of polygons in the rendering data Indicates the number of basic geometric figures used to constitute the rendering data. The number of polygons is one of the important indicators to measure the complexity of rendering, because more polygons mean more computing resources are required for rendering. The more polygons there are, the more vertices, edges, and faces the rendering engine needs to process, which increases the rendering time and computing complexity. Therefore, accurately obtaining and calculating the number of polygons for each rendering data is crucial to evaluating its rendering complexity.

[0117] No. Texture resolution of the rendered data Represents the clarity and detail level of image textures attached to polygonal surfaces. Texture resolution is usually measured in pixels, such as 1024x1024 or 2048x2048. High-resolution textures can provide richer visual details, but also increase the rendering and processing burden. Higher texture resolutions require more storage space and bandwidth, and increase rendering time. Therefore, evaluating the texture resolution of each rendered data is very important to determine its demand on system resources and rendering complexity.

[0118] No. Rendering time for each rendered data Indicates the time required to complete rendering of the data. Rendering time is affected by multiple factors such as the number of polygons, texture resolution, lighting calculations, and shadow processing. A longer rendering time indicates that the rendering data requires more computing resources and time to process, which may cause delays and freezes. Accurately recording and analyzing the rendering time of each rendering data can help optimize the rendering process and ensure that the system can maintain a smooth user experience under high load conditions.

[0119] No. Data transfer time for rendering data Indicates the time required to transfer rendering data from the storage device or network to the rendering engine. Data transfer time is affected by factors such as data size, network bandwidth, and transmission path. Long data transfer time may delay the start of rendering and affect overall rendering performance. By monitoring and optimizing data transfer time, you can reduce transmission bottlenecks, improve rendering efficiency, and ensure that the screen can be updated in time when the user moves quickly, avoiding delays and freezes.

[0120] Calculate the rendering complexity index and real-time processing requirement coefficient of each rendering data. The specific calculation formula is as follows:

[0121]

[0122]

[0123] In the formula, For the The rendering complexity index of the rendering data, For the The real-time processing requirement factor of the rendering data.

[0124] No. The rendering complexity index of the rendering data The size of the rendering complexity index directly affects the evaluation of the urgency of the rendering data. The larger the rendering complexity index, the more polygons and higher texture resolution the rendering data contains, and thus more computing resources are required for rendering. A higher complexity index means that the rendering data is more likely to cause an increase in system load during the rendering process, increasing the risk of delays and freezes. Therefore, data with a larger rendering complexity index is usually evaluated as high urgency and needs to be processed first to ensure that the system can respond to the user's fast movements in a timely manner and keep the picture smooth and stable.

[0125] No. Real-time processing requirement factor for rendering data The size of is an important indicator for evaluating the urgency of the rendering data. The larger the real-time processing demand coefficient, the longer the rendering data requires, which may cause bottlenecks in the system when processing the data, increasing the possibility of delays and freezes. A higher real-time processing demand coefficient means that the rendering data has a higher demand for system resources under high load conditions, and is therefore assessed as high urgency. In order to ensure the smoothness and real-time nature of the picture when the user moves quickly, the system will give priority to processing these high-urgency rendering data to prevent performance degradation and poor user experience.

[0126] In this embodiment, the rendering complexity index of each rendering data generated is and real-time processing demand factor Construct an urgency assessment model and generate the urgency coefficient of each rendering data through weighted summation , the urgency coefficient of each rendered data generated With the pre-set urgency factor threshold A comparison is performed, and the urgency of each rendering data is evaluated according to the comparison results. According to the evaluation results, each rendering data is divided into high-urgency rendering data and low-urgency rendering data. The specific analysis is as follows:

[0127] like , No. If the urgency of a rendering data is low, the rendering data is classified as low-urgency rendering data, which means that the complexity and processing requirements of the rendering data are within the acceptable range of the system. At this time, the rendering data will not cause significant pressure on the rendering performance of the system and can be classified as low-urgency rendering data. Low-urgency rendering data can be processed later if the system resources are sufficient, so as to give priority to ensuring the real-time and smoothness of high-urgency rendering data. This can optimize the allocation of system resources and ensure that important rendering data can be processed in time when the user moves quickly, so as to maintain the smoothness and stability of the overall picture;

[0128] like , No. If the urgency of a rendering data is high, the rendering data is classified as high-urgency rendering data, which means that the complexity and processing requirements of the rendering data exceed the normal processing capabilities of the system, and may cause great pressure on the rendering performance of the system. At this time, the rendering data is evaluated as high-urgency rendering data and needs to be processed with priority to ensure the smoothness and real-time nature of the picture when the user moves quickly. Prioritizing the processing of high-urgency rendering data can effectively reduce picture delays and freezes, improve user experience, and prevent visual discomfort and decreased interactivity caused by rendering delays.

[0129] The urgency evaluation model is constructed by converting the rendering complexity index of each generated rendering data into and real-time processing demand factor Perform weighted summation to generate the urgency coefficient of each rendering data The specific steps are as follows: First, determine the weight coefficient and , which are used to measure the impact of rendering complexity and real-time processing requirements on urgency. These two weight coefficients can be adjusted according to system performance testing and actual application requirements to ensure that the model can accurately reflect the urgency of different rendering data. Then, the urgency coefficient of each rendering data is calculated by the following formula:

[0130]

[0131] In the formula, Indicates The rendering complexity index of the rendering data, Indicates The real-time processing requirement coefficient of the rendering data, and is a pre-set weight coefficient. In this way, the complexity and processing requirements of the rendering data are comprehensively considered to generate the urgency coefficient of each rendering data. , used to assess its urgency.

[0132] The pre-set urgency coefficient threshold can be determined in the following way: First, collect a large number of rendering data samples under different situations, including their rendering complexity index and real-time processing demand coefficient, as well as the corresponding system performance indicators, such as rendering delay and jamming. Then, through data analysis and statistical methods, determine at what urgency coefficient the system performance begins to decline significantly. Specifically, software tools can be used for regression analysis or cluster analysis, to associate the urgency coefficient with system performance indicators, and find an urgency coefficient value that can minimize delays and jamming as a threshold. Then, the model is trained and verified through software, and the applicability and reliability of the threshold in different scenarios are finally determined to ensure that it can effectively evaluate the urgency of rendering data in practical applications.

[0133] A hierarchical rendering processing module is used to process high-urgency rendering data first, and then process low-urgency rendering data after the high-urgency rendering data is processed.

[0134] In this embodiment, high urgency rendering data is processed first, and after the high urgency rendering data is processed, low urgency rendering data is processed, which specifically includes the following steps:

[0135] According to the urgency evaluation result, the high-urgency rendering data and the low-urgency rendering data are stored in the high-urgency rendering queue and the low-urgency rendering queue respectively;

[0136] According to the urgency evaluation results, high-urgency rendering data and low-urgency rendering data are stored in the high-urgency rendering queue and the low-urgency rendering queue respectively. This can be achieved in the following way: the software system first calls the urgency evaluation module to determine the urgency of each rendering data according to its urgency coefficient. Data with high urgency is marked as high-urgency rendering data and stored in the high-urgency rendering queue, and data with low urgency is stored in the low-urgency rendering queue. The specific approach is to manage the rendering data through the queue data structure, classify the data using high and low priority tags, and push it to the corresponding queue to ensure that the rendering data can be extracted and processed according to the urgency order during subsequent processing.

[0137] Extract rendering data from the high-urgency rendering queue, call the rendering engine to process the high-urgency rendering data, and ensure that the high-urgency rendering data is rendered first;

[0138] Extracting rendering data from the high-urgency rendering queue and calling the rendering engine to process the high-urgency rendering data can be achieved in the following way: the software system checks the high-urgency rendering queue first in the rendering loop, and uses queue operations to extract the rendering data that enters the queue earliest. Then, the system calls the rendering function of the rendering engine and passes the extracted high-urgency rendering data to the rendering engine for processing. In order to ensure that the high-urgency rendering data is rendered first, the rendering engine can allocate more computing resources and priorities when processing the high-urgency rendering data to ensure that the data can be rendered as soon as possible.

[0139] Real-time monitoring of the processing status of high-urgency rendering data. After all high-urgency rendering data is processed, the system automatically switches to low-urgency rendering data processing;

[0140] Real-time monitoring of the processing status of high-urgency rendering data. After all high-urgency rendering data has been processed, the system automatically switches to low-urgency rendering data processing. This can be achieved in the following ways: The software system includes a monitoring module that continuously monitors the status of the high-urgency rendering queue. By periodically checking whether the queue is empty, the monitoring module can determine whether all high-urgency rendering data has been processed. When it is detected that the high-urgency rendering queue is empty, the monitoring module will trigger the system to switch to low-urgency rendering data processing mode to ensure that the system can start processing low-urgency rendering data in a timely manner.

[0141] After the high-urgency rendering data is processed, the rendering data is extracted from the low-urgency rendering queue, and the rendering engine is called to process the low-urgency rendering data to ensure that the low-urgency rendering data is rendered in time if system resources allow;

[0142] After the high-urgency rendering data is processed, the rendering data is extracted from the low-urgency rendering queue, and the rendering engine is called to process the low-urgency rendering data. This can be achieved in the following way: when the high-urgency rendering queue is empty, the system automatically switches to the low-urgency rendering queue. Through queue operations, the rendering data that enters the queue earliest is extracted from the low-urgency rendering queue. The system calls the rendering function of the rendering engine and passes the extracted low-urgency rendering data to the rendering engine for processing. Although the processing priority of low-urgency rendering data is lower, after the high-urgency data is processed, these data will be processed in time to ensure the completion of the overall rendering task of the system.

[0143] After each rendering cycle, update the high-urgency rendering queue and the low-urgency rendering queue to ensure that the newly added rendering data is correctly classified according to its urgency assessment results and added to the corresponding queue;

[0144] After each rendering cycle, the high-urgency rendering queue and the low-urgency rendering queue are updated to ensure that the newly added rendering data is correctly classified according to its urgency evaluation results and added to the corresponding queues. This can be achieved in the following way: the software system calls the data update module at the end of each rendering cycle to perform urgency evaluation on the newly generated rendering data. Based on the evaluation results, the system classifies these new data and pushes them to the corresponding rendering queues. The specific operations include calling the urgency evaluation function to calculate the urgency coefficient, adding high-urgency data to the high-urgency rendering queue, and adding low-urgency data to the low-urgency rendering queue, ensuring that the data in the queue is always classified and stored according to the latest urgency evaluation results.

[0145] Dynamically adjust the processing priority of high-urgency and low-urgency rendering data based on system resource usage and rendering data processing progress, ensuring that the system prioritizes high-urgency rendering data when resources are tight, thereby improving overall rendering efficiency.

[0146] According to the system resource usage and the rendering data processing progress, the processing priority of high-urgency and low-urgency rendering data is dynamically adjusted to ensure that the system prioritizes high-urgency rendering data when resources are tight and improve the overall rendering efficiency. This can be achieved in the following ways: the software system includes a resource management module, which monitors the system resource usage (such as CPU and GPU load, memory usage, etc.) and the rendering data processing progress in real time. According to the monitoring results, the resource management module can dynamically adjust the processing priority of high-urgency and low-urgency rendering data. When system resources are tight, resources are allocated to high-urgency rendering data first; when resources are relatively abundant, low-urgency rendering data can be properly processed. Through this dynamic adjustment, the system can efficiently manage rendering tasks under different load conditions to ensure that important rendering tasks are processed in a timely manner.

[0147] Real-time optimization monitoring module, real-time monitoring of rendering effects, use of machine learning algorithms to continuously optimize motion prediction models and rendering strategies, based on user feedback and system performance data, continuous adjustment of rendering parameters to ensure the smoothness and real-time nature of the picture.

[0148] The real-time optimization monitoring module can be implemented in the following ways: First, the system collects rendering effect data, user feedback and system performance data in real time through monitoring tools embedded in the rendering engine and user devices. These data include frame rate, delay, number of freezes, user operation response time, etc. Then, the machine learning algorithm is used to analyze and process the data collected in real time, and the motion prediction model and rendering strategy optimization model are constructed using regression analysis, cluster analysis and other technologies. Based on these models, the system predicts the user's motion trajectory and perspective changes, and optimizes the rendering strategy, such as adjusting rendering priority, allocating computing resources, and dynamically changing resolution. After each rendering cycle, the system automatically adjusts the rendering parameters according to the latest analysis results and user feedback, and continuously optimizes the rendering effect and system performance. For example, the system can reduce the texture resolution of certain scenes to increase the frame rate, or increase the priority of key rendering tasks when the user moves quickly to ensure the smoothness and real-time performance of the picture. Through this continuous and automated optimization process, the system can adaptively adjust the rendering strategy, improve the user experience, and ensure the best rendering effect in different usage environments.

[0149] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0150] The above embodiments can be implemented in whole or in part by software, hardware, firmware or any other combination. When implemented by software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions can be transmitted from one website, computer, server or data center to another website, computer, server or data center by wired or wireless (such as infrared, wireless, microwave, etc.). The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that contains one or more available media sets. The available medium can be a magnetic medium (for example, a floppy disk, a hard disk, a tape), an optical medium (for example, a DVD), or a semiconductor medium. The semiconductor medium can be a solid-state hard disk.

[0151] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0152] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0153] In the several embodiments provided in the present application, it should be understood that the disclosed systems and methods can be implemented in other ways. For example, the embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms.

[0154] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0155] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0156] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. 3D exhibition hall effect visualization experience platform, It is characterized in that It includes motion data acquisition module, delay and freeze prediction module, urgent information evaluation module, hierarchical rendering processing module and real-time optimization monitoring module; The motion data acquisition module acquires the user's motion data in real time during the user's rapid movement and performs preprocessing after acquisition; The delay and freeze prediction module analyzes the pre-processed user motion data to predict whether the user's fast movement will cause delays and freezes in the picture; The pre-processed user motion data is analyzed to predict whether the user's fast movement will cause delays and freezes in the picture, including the following steps: Extracting velocity information and acceleration information from the preprocessed user motion data; Analyze the extracted speed information and acceleration information to generate speed variation coefficient and acceleration fluctuation coefficient respectively; The generated speed variation coefficient and acceleration fluctuation coefficient are used to construct a dynamic load prediction model to generate a smoothness prediction coefficient; Determining a pre-set threshold value for the fluency prediction coefficient; The generated fluency prediction coefficient is compared with a preset fluency prediction coefficient threshold, and whether the degree of the user's fast movement will cause delay and freeze in the screen is predicted based on the comparison result; An urgency information evaluation module, when predicting that the user's fast movement will cause delays and freezes in the screen, obtains the urgency information of all rendering data that need to be processed, analyzes it after acquisition, evaluates the urgency of each rendering data, and divides each rendering data into high-urgency rendering data and low-urgency rendering data according to the evaluation results; In the case where it is predicted that the user's fast movement will cause delays and freezes in the screen, the urgency information of all rendering data to be processed is obtained, and after the acquisition, the urgency of each rendering data is evaluated, and each rendering data is divided into high-urgency rendering data and low-urgency rendering data according to the evaluation result, which specifically includes the following steps: When it is predicted that the user's fast movement will cause delays and freezes in the picture, obtain urgent information about all the rendering data that needs to be processed, including the number of polygons, texture resolution, rendering time and data transmission time of each rendering data; Preprocessing the polygon quantity, texture resolution, rendering time and data transmission time of each acquired rendering data; Analyze the number of polygons, texture resolution, rendering time, and data transmission time of each pre-processed rendering data to generate a rendering complexity index and a real-time processing requirement coefficient for each rendering data; Constructing an urgency assessment model based on the rendering complexity index and real-time processing requirement coefficient of each generated rendering data, generating an urgency coefficient of each rendering data, comparing the generated urgency coefficient of each rendering data with a preset urgency coefficient threshold, evaluating the urgency of each rendering data according to the comparison result, and dividing each rendering data into high-urgency rendering data and low-urgency rendering data according to the evaluation result; A hierarchical rendering processing module is used to process high-urgency rendering data first, and then process low-urgency rendering data after the high-urgency rendering data is processed. Real-time optimization monitoring module, real-time monitoring of rendering effects, use machine learning algorithms to continuously optimize motion prediction models and rendering strategies, and continuously adjust rendering parameters based on user feedback and system performance data.

2. The 3D exhibition hall effect visualization experience platform according to claim 1, It is characterized in that The acquisition logic of the speed variation coefficient and the acceleration fluctuation coefficient is as follows: Extract speed information from the preprocessed user motion data, including the actual speed of the user at different times during a period of fast movement and the corresponding time points, and use the function to convert the actual speed of the user at different times during a period of fast movement into a time series. To express, is a time point, and the time period is defined as ; Calculate the speed change coefficient. The specific calculation formula is as follows: In the formula, is the speed variation coefficient, is the rate of change of speed; Extract acceleration information from the preprocessed user motion data, including the actual acceleration of the user at different times during a period of rapid movement and the corresponding time points, and use the function to convert the actual acceleration of the user at different times during a period of rapid movement into a time series. To express, is a time point, and the time period is defined as ; Calculate the acceleration fluctuation coefficient. The specific calculation formula is as follows: In the formula, is the acceleration fluctuation coefficient, is the rate of change of acceleration.

3. The 3D exhibition hall effect visualization experience platform according to claim 2, It is characterized in that The generated speed variation coefficient and acceleration fluctuation coefficient are used to construct a dynamic load prediction model, a fluency prediction coefficient is generated, a preset fluency prediction coefficient threshold is determined, the generated fluency prediction coefficient is compared with the preset fluency prediction coefficient threshold, and whether the degree of user's fast movement will cause delay and freeze in the screen is predicted according to the comparison result, specifically including the following steps: Collect several speed change coefficients, several acceleration fluctuation coefficients and corresponding fluency prediction coefficients of users in the past period of time, and calibrate them as , and , Indicates the numbers of several speed change coefficients, several acceleration fluctuation coefficients and corresponding fluency prediction coefficients of the user in the past period of time. , is a positive integer, and the data collected in the past period of time forms a historical data set; Select the multivariate regression model as the dynamic load prediction model, and train it through the historical data set to determine the value of the regression coefficient according to the formula: In the formula, , and is the regression coefficient; By minimizing the error between the predicted value and the actual value, the regression coefficient is optimized and finally determined. , and The value of Using the final regression coefficient, the speed change coefficient obtained by real-time detection is input into the constructed dynamic load prediction model. and acceleration fluctuation coefficient , generate fluency prediction coefficients in real time ; Determine the pre-set fluency prediction coefficient threshold ; The fluency prediction coefficient generated in real time The fluency prediction coefficient threshold was set Compare and predict whether the user's fast movement will cause delays and freezes in the screen based on the comparison results. The specific comparison analysis is as follows: like , the user's fast movement will not cause delays and freezes in the picture; like , the degree to which the user moves quickly can cause delays and freezes in the picture.

4. The 3D exhibition hall effect visualization experience platform according to claim 3, It is characterized in that The logic for obtaining the rendering complexity index and real-time processing requirement coefficient of each rendering data is as follows: Obtain the urgent information of all rendering data that need to be processed, including the number of polygons, texture resolution, rendering time, and data transmission time of each rendering data, and calibrate the number of polygons, texture resolution, rendering time, and data transmission time of each rendering data as , , and , Indicates The number of polygons in the rendering data, Indicates The texture resolution of the rendered data, Indicates The rendering time of the rendered data, Indicates Data transfer time for rendering data, , is a positive integer; Calculate the rendering complexity index and real-time processing requirement coefficient of each rendering data. The specific calculation formula is as follows: In the formula, For the The rendering complexity index of the rendering data, For the The real-time processing requirement factor of the rendering data.

5. The 3D exhibition hall effect visualization experience platform according to claim 4, It is characterized in that The rendering complexity index of each rendering data generated and real-time processing demand factor Construct an urgency assessment model and generate the urgency coefficient of each rendering data through weighted summation , the urgency coefficient of each rendered data generated With the pre-set urgency factor threshold A comparison is performed, and the urgency of each rendering data is evaluated according to the comparison results. According to the evaluation results, each rendering data is divided into high-urgency rendering data and low-urgency rendering data. The specific analysis is as follows: like , No. If the urgency of a rendering data is low, the rendering data is classified as low-urgency rendering data; like , No. If the urgency of a rendering data is high, the rendering data is classified as high-urgency rendering data.

6. The 3D exhibition hall effect visualization experience platform according to claim 5, It is characterized in that Prioritize high-urgency rendering data, and after the high-urgency rendering data is processed, process the low-urgency rendering data, specifically including the following steps: According to the urgency evaluation result, the high-urgency rendering data and the low-urgency rendering data are stored in a high-urgency rendering queue and a low-urgency rendering queue respectively; Extract rendering data from the high-urgency rendering queue and call the rendering engine to process the high-urgency rendering data; Real-time monitoring of the processing status of high-urgency rendering data. After all high-urgency rendering data is processed, the system automatically switches to low-urgency rendering data processing; After the high-urgency rendering data is processed, the rendering data is extracted from the low-urgency rendering queue, and the rendering engine is called to process the low-urgency rendering data; After each rendering cycle, update the high-urgency rendering queue and the low-urgency rendering queue; Dynamically adjust the processing priority of high-urgency and low-urgency rendering data based on system resource usage and rendering data processing progress.

Images