Cultural heritage display management system and method based on cloud computing

Abstract

The invention provides a cultural heritage display management system and method based on cloud computing, and the system comprises a data collection module which is used for obtaining the multi-modal data of cultural heritage; the preprocessing module is used for carrying out standardization processing on the multi-modal data; the feature extraction module is used for extracting multi-dimensional features of the cultural heritage through an algorithm; the virtual display module is used for generating a dynamic interactive virtual scene; the load balancing module is used for dynamically allocating cloud computing resources; the user analysis module is used for analyzing user behavior data; and the dynamic feedback module is used for adjusting the display content in real time according to the user behavior. According to the invention, user experience and system operation efficiency can be improved, and data integrity and reliability are guaranteed.

Description

Technical Field

[0001] The present invention relates to the field of cultural heritage protection and display, and more specifically, to a cloud computing-based cultural heritage display management system and method. Background Art

[0002] In the field of cultural heritage protection and display, with the rapid development of information technology, digital display has gradually become an important means. Traditional display methods mainly rely on physical exhibitions and static image displays, which are not only limited by time and space, but also difficult to meet the audience's needs for in-depth understanding of cultural heritage. In recent years, although some digital display technologies have begun to be applied, most of them focus on simple image or video displays, lacking interactivity and immersion. At the same time, the collection and processing of cultural heritage data face challenges such as multi-source data fusion, noise interference, and data integrity verification. In addition, when facing large-scale user access, existing systems often have problems such as uneven resource allocation and response delays, which affect user experience.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: insufficient accuracy of data collection and processing, lack of interactivity and immersion in the display method, inflexible allocation of system resources and difficulty in coping with high concurrent user access. These problems limit the further development of the digital display of cultural heritage. Summary of the invention

[0004] The present invention provides a cultural heritage display management system and method based on cloud computing.

[0005] In a first aspect of the present invention, a cloud computing-based cultural heritage display management system is provided, comprising: Data collection module, used to obtain multimodal data of cultural heritage; Preprocessing module, used to standardize multimodal data; Feature extraction module, used to extract multi-dimensional features of cultural heritage through algorithms; A virtual display module, used to generate dynamic interactive virtual scenes; Load balancing module, used to dynamically allocate cloud computing resources; User analysis module, used to analyze user behavior data; Dynamic feedback module, used to adjust display content in real time according to user behavior.

[0006] Furthermore, the data acquisition module includes: Multi-source sensor units for collecting physical parameters of cultural heritage; Environmental parameter unit, used to capture temperature, humidity and light data of the display environment; A data verification unit, used to ensure data integrity through a verification algorithm; Among them, the verification algorithm formula is:

[0007] In the formula, C is the calibration value, is the i-th type of data, is the dynamic weighting factor, is the environmental correction factor, is the timestamp parameter, is the total number of data categories.

[0008] Furthermore, the preprocessing module includes: Noise filtering unit, which uses adaptive filtering algorithm to eliminate data noise; A data alignment unit, used to synchronize the time axis of multimodal data; Format standardization unit, converting data into a unified coding format; The adaptive filtering algorithm formula is:

[0009] In the formula, is the filtered data, is the original signal, is the sliding mean, is the standard deviation, is the attenuation coefficient, is the dynamic gain, is a time-dependent function.

[0010] Furthermore, the feature extraction module includes: Spatial feature unit, extracts spatial structure features through a three-dimensional convolutional network; Texture analysis unit, which uses a multi-scale decomposition algorithm to analyze surface texture; Semantic association unit, constructing the association map between cultural heritage and historical events; The multi-scale decomposition algorithm formula is:

[0011] In the formula, To decompose the results, is the Gaussian kernel of the sth scale, For input data, is the scale weight, is the smoothing factor, is the square of the current decomposition scale.

[0012] Furthermore, the virtual display module includes: A scene generation unit constructs a virtual space topology structure based on feature data; Interaction logic unit, which defines the mapping relationship between user operations and scene responses; Rendering optimization unit, using ray tracing and detail level hybrid rendering technology; The topology structure generation algorithm formula is:

[0013] Where T is the optimal topology, is the feature point, are virtual coordinates, is the constraint coefficient, is the spatial curvature gradient.

[0014] Furthermore, the load balancing module includes: Resource monitoring unit, which monitors the CPU and memory usage of each computing node in real time; Task scheduling unit, using dynamic priority allocation algorithm; Disaster recovery and backup unit, establishing cross-regional data mirroring; The dynamic priority algorithm formula is:

[0015] In the formula, is the CPU utilization, For the task urgency, is the memory usage, is the delay weight, For network delay.

[0016] Furthermore, the user analysis module includes: Behavior collection unit, which records the user's browsing path and duration of stay; Preference modeling unit, constructs interest vectors with multi-dimensional features; Prediction unit, predicts the next behavior through Markov chain; The interest vector calculation formula is:

[0017] In the formula, is the user interest vector, is the behavior type weight, is the frequency of behavior, is the time decay factor, A collection of frequency statistics for all behavior types.

[0018] Furthermore, the dynamic feedback module includes: Content recommendation unit, matching and displaying content according to user interest vectors; Image quality adjustment unit, dynamically adjusts rendering resolution; Path optimization unit, reconstructs the navigation topology of the virtual scene; The formula for dynamically adjusting rendering resolution is:

[0019] In the formula, is the image quality level, is the number of concurrent users, is the network bandwidth, is the terminal screen size, is the base size, is the adaptive coefficient.

[0020] Furthermore, the dynamic weighting factor The calculation methods include: Assign initial weights based on data source reliability scores; Update weight values ​​based on a time decay function; Correct weight bias through feedback mechanism; The formula is:

[0021] In the formula, is the learning rate, is the actual calibration value, To predict the check value, is the dynamic weighting factor of the i-th type of data after the t+1th update, is the dynamic weighting factor of the i-th category data after the t-th update.

[0022] In a second aspect of the present invention, a cloud computing-based cultural heritage display management method is provided, comprising: S1. Collect physical parameters and environmental data of cultural heritage through multi-source sensors; S2. Verify data integrity using a verification algorithm that includes dynamic weighting factors and environmental correction coefficients; S3. Use adaptive filtering algorithm to reduce noise and time align the data; S4. Extract spatial texture features through multi-scale decomposition algorithm; S5. Generate virtual scene structure based on topology optimization algorithm; S6. Allocate cloud computing resources according to a dynamic priority algorithm; S7. Construct user interest vector and predict behavior path; S8. Adjust image quality level and content recommendation strategy in real time.

[0023] The above-mentioned embodiments of the present invention have at least the following beneficial effects: the system can ensure the integrity and reliability of cultural heritage data through a multimodal data acquisition module and a data verification algorithm, and at the same time, by using the adaptive filtering algorithm and data alignment unit of the preprocessing module, it can effectively eliminate data noise and achieve time axis synchronization of multi-source data, providing a high-quality data foundation for subsequent processing. In addition, the feature extraction module combines spatial features, texture analysis and semantic association units to comprehensively extract the multi-dimensional features of cultural heritage and provide rich data support for virtual display. The virtual display module uses topology optimization algorithms and hybrid rendering technology to generate dynamic virtual scenes with strong immersion and interactivity, enhancing users' cognition and experience of cultural heritage.

[0024] The load balancing module can flexibly allocate cloud computing resources through real-time monitoring of resource occupancy and dynamic priority allocation algorithm, ensuring the stability and response speed of the system during high concurrent access. At the same time, the cross-regional data mirroring mechanism of the disaster recovery backup unit can ensure the security and reliability of data. The user analysis module and dynamic feedback module can record user behavior in real time and predict their preferences, so as to dynamically adjust the display content and image quality level according to the user's interest vector, realize personalized display experience, and further improve user satisfaction and the intelligence level of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which: Figure 1 A schematic diagram of the structure of a cloud computing-based cultural heritage display and management system provided by one embodiment of the present invention; Figure 2 A schematic diagram of a process of a cultural heritage display management method based on cloud computing provided by an embodiment of the present invention; Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0026] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0027] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0028] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0029] Reference below Figure 1 , Figure 1 This is a schematic diagram of the structure of a cloud computing-based cultural heritage display management system provided by an embodiment of the present invention. Figure 1 As shown, a cloud computing-based cultural heritage display management system 100 includes: The data acquisition module 101 is used to acquire multimodal data of cultural heritage; A preprocessing module 102, used for standardizing multimodal data; Feature extraction module 103, used to extract multi-dimensional features of cultural heritage through algorithms; A virtual display module 104, used to generate a dynamic interactive virtual scene; A load balancing module 105, for dynamically allocating cloud computing resources; User analysis module 106, used to analyze user behavior data; The dynamic feedback module 107 is used to adjust the display content in real time according to the user behavior.

[0030] It should be noted that the core of this system is to achieve efficient display and management of cultural heritage through the collaborative work of multiple modules. Among them, the data acquisition module is used to obtain multimodal data of cultural heritage, including images, videos, three-dimensional models, etc. Multimodal data refers to various types of data collected by different sensors, such as laser scanners for obtaining three-dimensional point cloud data, high-definition cameras for shooting images and videos, and environmental sensors for recording the temperature, humidity and light intensity of the display environment. The preprocessing module standardizes the collected data to eliminate noise, align the time axis and unify the data format. The feature extraction module extracts the multidimensional features of cultural heritage through algorithms, including spatial structure, texture details and semantic associations. The virtual display module uses the extracted features to generate dynamic interactive virtual scenes to provide users with an immersive experience. The load balancing module dynamically allocates cloud computing resources to ensure the stability and response speed of the system under high concurrent access. The user analysis module records user behavior data, builds a user interest model and predicts user behavior. The dynamic feedback module adjusts the display content and image quality level in real time according to user behavior to achieve personalized display effects.

[0031] Specifically, the multi-source sensor unit in the data acquisition module includes but is not limited to a laser scanner, a high-definition camera, an infrared sensor, and an environmental sensor. For example, a laser scanner can accurately obtain the three-dimensional point cloud data of cultural heritage for building a high-precision three-dimensional model; a high-definition camera is used to capture high-definition images and videos of cultural heritage and record its appearance details; and an environmental sensor is used to monitor the temperature, humidity, and light intensity of the display environment in real time to provide data support for subsequent display optimization. The data verification unit ensures the integrity of the data through a specific verification algorithm. The dynamic weighting factor in the algorithm can be adjusted according to the reliability of the data source, and the environmental correction coefficient corrects the data according to the environmental parameters. The noise filtering unit in the preprocessing module adopts an adaptive filtering algorithm, which dynamically adjusts the filtering parameters through the sliding mean and standard deviation to eliminate noise in the data. The data alignment unit synchronizes the time axis of the multimodal data through the timestamp parameter to ensure data consistency. The format standardization unit converts data of different formats into a unified encoding format for subsequent processing. The spatial feature unit in the feature extraction module uses a three-dimensional convolutional network to extract the spatial structural features of cultural heritage. The texture analysis unit uses a multi-scale decomposition algorithm to analyze surface textures. The semantic association unit constructs a correlation map between cultural heritage and historical events to provide users with richer background information.

[0032] Preferably, the multi-source sensor unit in the data acquisition module can be flexibly configured according to the type of cultural heritage and display requirements. For example, for large cultural heritage such as ancient buildings, drone cameras can be added to obtain panoramic images and videos; for small cultural relics, high-resolution microscopes can be used to obtain microscopic texture details. The verification algorithm in the data verification unit can optimize the dynamic weighting factor and environmental correction factor through machine learning methods to further improve the accuracy of data verification. The adaptive filtering algorithm in the preprocessing module can dynamically adjust the attenuation coefficient and dynamic gain according to the noise level of the data to achieve better noise reduction. The multi-scale decomposition algorithm in the feature extraction module can optimize the accuracy of texture resolution by adjusting the scale weight and smoothing factor. The scene generation unit in the virtual display module can be combined with an artificial intelligence algorithm to dynamically adjust the layout and detail level of the virtual scene according to the user's behavioral preferences. The dynamic priority algorithm in the load balancing module can dynamically adjust the resource allocation strategy according to the real-time network delay and task urgency to ensure the efficient operation of the system.

[0033] In some embodiments, the data acquisition module includes: Multi-source sensor units for collecting physical parameters of cultural heritage; Environmental parameter unit, used to capture temperature, humidity and light data of the display environment; A data verification unit, used to ensure data integrity through a verification algorithm; Among them, the verification algorithm formula is:

[0034] In the formula, C is the calibration value, is the i-th type of data, is the dynamic weighting factor, is the environmental correction factor, is the timestamp parameter, is the total number of data categories.

[0035] It should be noted that the data acquisition module is one of the core components of the cultural heritage display management system, and its main function is to obtain multimodal data of cultural heritage. Multimodal data refers to different types of data collected by multiple sensors, including physical parameters and environmental parameters. Physical parameters refer to information such as the geometric shape, size, material, etc. of the cultural heritage itself, while environmental parameters refer to data such as temperature, humidity, and light intensity in the cultural heritage display environment. The data verification unit ensures the integrity and accuracy of the collected data through a specific verification algorithm. The algorithm performs weighted processing on the data through dynamic weighting factors and environmental correction coefficients, and combines timestamp parameters for comprehensive verification, thereby providing a reliable data basis for subsequent data processing.

[0036] Specifically, the multi-source sensor unit in the data acquisition module may include a laser scanner, a three-dimensional modeling device, a high-definition camera, an infrared imager, a temperature and humidity sensor, and a light sensor. The laser scanner is used to obtain three-dimensional point cloud data of cultural heritage, which can accurately reflect its spatial structure; the high-definition camera is used to take high-definition images of cultural heritage and record its appearance details; the temperature and humidity sensor and the light sensor are used to monitor the temperature, humidity and light intensity of the display environment in real time to provide support for the collection of environmental parameters. The verification algorithm in the data verification unit calculates the verification value through a formula, in which the dynamic weighting factor can be adjusted according to the reliability of the data source. For example, for high-precision laser scanner data, a higher weight can be given; the environmental correction coefficient is adjusted according to the change of environmental parameters to compensate for the impact of environmental factors on data collection. The timestamp parameter is used to mark the time sequence of data collection to ensure the time consistency of the data. For example, when the timestamp of the collected image data does not match the timestamp of the environmental data, the data can be corrected by adjusting the environmental correction coefficient.

[0037] Preferably, the data acquisition module can be flexibly configured according to the specific type and display requirements of the cultural heritage. For large cultural heritage, such as ancient buildings or ruins, high-definition cameras and laser scanners carried by drones can be added to obtain more comprehensive three-dimensional data and panoramic images; for small cultural relics, high-resolution microscopes and photometric stereo vision equipment can be used to obtain micro-texture and material information. The verification algorithm in the data verification unit can optimize the dynamic weighting factor and environmental correction factor through machine learning methods. For example, a neural network trained based on historical data can predict the reliability of different sensor data and dynamically adjust the weights, thereby further improving the accuracy of data verification. In addition, timestamp parameters can be recorded in combination with blockchain technology to ensure the non-tamperability and traceability of the data, providing more reliable protection for the digital protection of cultural heritage.

[0038] In some embodiments, the preprocessing module comprises: Noise filtering unit, which uses adaptive filtering algorithm to eliminate data noise; A data alignment unit, used to synchronize the time axis of multimodal data; Format standardization unit, converting data into a unified coding format; The adaptive filtering algorithm formula is:

[0039] In the formula, is the filtered data, is the original signal, is the sliding mean, is the standard deviation, is the attenuation coefficient, is the dynamic gain, is a time-dependent function.

[0040] It should be noted that the preprocessing module plays a vital role in the cultural heritage display and management system. Its main function is to standardize the collected multimodal data to improve the availability and consistency of the data. The preprocessing module includes a noise filtering unit, a data alignment unit, and a format standardization unit. These units use specific algorithms and techniques to ensure that the data reaches high quality standards before entering the subsequent processing process. Among them, the noise filtering unit adopts an adaptive filtering algorithm, which can dynamically adjust the filtering parameters according to the characteristics of the data, thereby effectively eliminating noise; the data alignment unit is responsible for synchronizing data from different sources on the timeline to ensure data consistency; the format standardization unit converts the data into a unified encoding format for subsequent processing and storage.

[0041] Specifically, the adaptive filtering algorithm in the noise filtering unit is a comprehensive processing based on the sliding mean, standard deviation, attenuation coefficient, dynamic gain and time-related function. The sliding mean is used to smooth short-term fluctuations in the data, the standard deviation is used to measure the discreteness of the data, and the attenuation coefficient and dynamic gain are used to adjust the intensity and response speed of the filter. The time-related function can dynamically adjust the filtering effect according to the temporal characteristics of the data, so as to better adapt to different types of noise. For example, when processing image data of cultural heritage, if there is Gaussian noise in the image, the filtering effect can be optimized by adjusting the attenuation coefficient and dynamic gain. The data alignment unit synchronizes the time axis of multimodal data through the timestamp parameter to ensure that the data collected by different sensors are consistent in time. The format standardization unit converts the data into a unified encoding format, such as converting image data into JPEG or PNG format, and converting three-dimensional point cloud data into PLY or OBJ format, which is convenient for subsequent module processing and storage.

[0042] Preferably, the parameters in the adaptive filtering algorithm can be optimized according to the specific application scenario. For example, when processing video data of cultural heritage, the attenuation coefficient can be set to 0.1 and the dynamic gain can be set to 1.5 to better adapt to the dynamic characteristics of the video data. For high-resolution image data, the window size of the sliding mean can be appropriately increased to improve the effect of noise filtering. The data alignment unit can introduce a time correction algorithm to further optimize the accuracy of time alignment through interpolation or compensation methods. For example, when the sampling frequencies of different sensors are different, the low-frequency data can be time-compensated by interpolation methods to align it with the high-frequency data. In addition, the format standardization unit can support the conversion of multiple encoding formats to meet the needs of different users. For example, for data that needs to be transmitted over the network, a format with a higher compression rate can be selected; for data that needs to be stored locally, a lossless compression format can be selected.

[0043] In some embodiments, the feature extraction module includes: Spatial feature unit, extracts spatial structure features through a three-dimensional convolutional network; Texture analysis unit, which uses a multi-scale decomposition algorithm to analyze surface texture; Semantic association unit, constructing the association map between cultural heritage and historical events; The multi-scale decomposition algorithm formula is:

[0044] In the formula, To decompose the results, is the Gaussian kernel of the sth scale, For input data, is the scale weight, is the smoothing factor, is the square of the current decomposition scale.

[0045] It should be noted that the feature extraction module is a key link in the cultural heritage display management system. Its main function is to extract the multi-dimensional features of cultural heritage from multimodal data through algorithms. These features include spatial structure features, texture features and semantic association features, which can provide rich information support for subsequent virtual display and user interaction. The spatial feature unit uses a three-dimensional convolutional network to extract the spatial structure features of cultural heritage, and can identify the geometric shape and spatial layout of cultural heritage; the texture analysis unit uses a multi-scale decomposition algorithm to analyze the surface texture, and can capture the detailed texture information of cultural heritage; the semantic association unit constructs a correlation map between cultural heritage and historical events, providing users with a deeper cultural background and historical information.

[0046] Specifically, the three-dimensional convolutional network in the spatial feature unit is a deep learning algorithm that can process three-dimensional data and extract its spatial structural features. The network extracts features from the three-dimensional model of cultural heritage through a combination of convolutional layers, pooling layers, and fully connected layers, thereby identifying the geometric shape and spatial layout of cultural heritage. The multi-scale decomposition algorithm in the texture analysis unit is an algorithm based on wavelet transform. It decomposes the input data through Gaussian kernels of different scales and can capture detailed information on the surface texture of cultural heritage. The semantic association unit associates cultural heritage with relevant historical events, cultural background and other information by constructing a knowledge graph, providing users with a richer cultural experience. For example, for an ancient cultural relic, the semantic association unit can be used to associate it with the dynasty, historical figures or major events to which it belongs, thereby enhancing the user's understanding of the cultural relic.

[0047] Preferably, the structure of the three-dimensional convolutional network can be optimized according to the characteristics of the cultural heritage data. For example, the number of convolutional layers can be increased to extract more complex geometric features, or the size of the convolution kernel can be adjusted to adapt to cultural heritage of different scales. The multi-scale decomposition algorithm in the texture analysis unit can optimize the effect of texture extraction by adjusting the scale weight and smoothing factor. For example, for high-resolution image data, the scale weight can be increased to extract finer texture features; for low-resolution data, the scale weight can be appropriately reduced to avoid overfitting. In addition, the semantic association unit can introduce natural language processing technology to further enrich the historical background information of cultural heritage through text mining and semantic analysis. For example, historical documents and archaeological reports can be combined to generate a detailed semantic description for cultural heritage to enhance the user's cultural experience.

[0048] In some embodiments, the virtual display module includes: A scene generation unit constructs a virtual space topology structure based on feature data; Interaction logic unit, which defines the mapping relationship between user operations and scene responses; Rendering optimization unit, using ray tracing and detail level hybrid rendering technology; The topology structure generation algorithm formula is:

[0049] Where T is the optimal topology, is the feature point, are virtual coordinates, is the constraint coefficient, is the spatial curvature gradient.

[0050] It should be noted that the virtual display module is the core part of the cultural heritage display management system to achieve user interaction and immersive experience. Its function is to generate dynamic interactive virtual scenes based on the extracted feature data. This module constructs the topological structure of the virtual space through the scene generation unit, the interactive logic unit defines the mapping relationship between user operations and scene responses, and the rendering optimization unit uses advanced rendering technology to enhance the visual effect of the scene. Among them, the topological structure generation algorithm optimizes the relationship between feature points and virtual coordinates to ensure that the spatial layout of the virtual scene is reasonable and consistent with the real structure of the cultural heritage, thereby providing users with a highly realistic display effect.

[0051] Specifically, the scene generation unit constructs the topological structure of the virtual space based on the characteristic data of the cultural heritage. The topological structure generation algorithm generates the optimal virtual space layout by optimizing the relationship between the feature points and the virtual coordinates, combining the constraint coefficient and the spatial curvature gradient. For example, for the virtual display of ancient buildings, the algorithm will generate a virtual topological structure that is highly consistent with the actual building based on the three-dimensional feature points and spatial structure of the building. The interactive logic unit defines the mapping relationship between user operations and scene responses. For example, users can move, scale and rotate in the virtual scene through gestures or mouse operations, and the system responds to user operations in real time according to the preset interactive logic. The rendering optimization unit uses ray tracing and detail level hybrid rendering technology, combined with the texture and material information of cultural heritage, to generate high-quality visual effects. For example, for cultural relics with complex textures, the rendering optimization unit can dynamically adjust the rendering accuracy through detail level technology to ensure the best visual effects at different viewing distances.

[0052] Preferably, the constraint coefficient in the topology generation algorithm can be adjusted according to the type of cultural heritage and the display requirements. For example, for cultural relics that need to be displayed with high precision, the constraint coefficient can be appropriately increased to ensure the accuracy of the topological structure; for large cultural heritage such as ancient buildings, the constraint coefficient can be appropriately reduced to optimize the computing efficiency. The interactive logic unit can introduce artificial intelligence algorithms to dynamically adjust the interactive response strategy according to the user's operating habits. For example, the user's next operation can be predicted through a machine learning algorithm, and the scene loading and response mechanism can be optimized in advance to improve the user experience. The rendering optimization unit can dynamically adjust the rendering strategy in combination with real-time hardware performance monitoring. For example, full ray tracing technology is enabled on high-performance devices, and switched to simplified rendering mode on low-performance devices to ensure the compatibility and fluency of the system.

[0053] In some embodiments, the load balancing module includes: Resource monitoring unit, which monitors the CPU and memory usage of each computing node in real time; Task scheduling unit, using dynamic priority allocation algorithm; Disaster recovery and backup unit, establishing cross-regional data mirroring; The dynamic priority algorithm formula is:

[0054] In the formula, is the CPU utilization, For the task urgency, is the memory usage, is the delay weight, For network delay.

[0055] It should be noted that the load balancing module is a key component in the cultural heritage display and management system for optimizing cloud computing resource allocation and ensuring stable system operation. Its function is to monitor the resource occupancy of each computing node in real time, and use a dynamic priority allocation algorithm to reasonably schedule tasks, while establishing cross-regional data mirroring to achieve disaster recovery and backup. The resource monitoring unit is responsible for obtaining key indicators such as the CPU and memory occupancy rate of the computing node in real time. The task scheduling unit dynamically allocates task priorities based on these indicators to ensure efficient operation of the system under high concurrent access. The disaster recovery and backup unit uses cross-regional data mirroring technology to ensure data security and reliability, avoiding data loss or service interruption due to single point failures.

[0056] Specifically, the resource monitoring unit collects key indicators such as CPU utilization and memory occupancy in real time through the monitoring program deployed on each computing node. These indicators are reported to the task scheduling unit at a fixed frequency (such as once per second). The task scheduling unit calculates the priority of each task based on the dynamic priority algorithm, combined with factors such as CPU utilization, task urgency, memory usage and network delay. For example, when the CPU utilization of a computing node is high, the algorithm will schedule new tasks to other nodes with lower loads, thereby achieving balanced utilization of resources. The disaster recovery backup unit ensures redundant storage of data by deploying data mirrors in different geographical areas. Once a server in a certain area fails, the system can quickly switch to data mirrors in other areas to ensure service continuity. The parameter settings in the dynamic priority algorithm can be adjusted according to the actual application scenario. For example, the delay weight can be optimized according to the stability of the network environment, and the task urgency can be classified and set according to the type of user request (such as real-time interaction or offline browsing).

[0057] Preferably, the resource monitoring unit can introduce machine learning technology to predict resource usage trends through historical data and adjust resource allocation strategies in advance. For example, based on the time series analysis model, resource demand during peak hours is predicted and computing resources are reserved in advance. The task scheduling unit can combine containerization technology (such as Docker and Kubernetes) to achieve rapid deployment and elastic expansion of tasks. For example, when it is detected that a node is overloaded, the system can automatically start a new container instance to share the task. The disaster recovery backup unit can use distributed storage technology (such as Ceph or GlusterFS) to further improve data reliability and read and write performance. In addition, the dynamic priority algorithm can introduce user behavior analysis to dynamically adjust task priorities based on user activity and behavior patterns. For example, higher priorities can be assigned to requests from high-frequency users or important customers to improve user experience.

[0058] In some embodiments, the user analysis module includes: Behavior collection unit, which records the user's browsing path and duration of stay; Preference modeling unit, constructs interest vectors with multi-dimensional features; Prediction unit, predicts the next behavior through Markov chain; The interest vector calculation formula is:

[0059] In the formula, is the user interest vector, is the behavior type weight, is the frequency of behavior, is the time decay factor, A collection of frequency statistics for all behavior types.

[0060] It should be noted that the user analysis module is an important component of the cultural heritage display management system for improving user experience and realizing personalized display. This module records the user's browsing path, stay time and other behavioral data through the behavior collection unit, constructs the user's multi-dimensional interest vector using the preference modeling unit, and predicts the user's next behavior based on the Markov chain through the prediction unit. These functions enable the system to dynamically adjust the display content and interaction strategy according to the user's interests and behaviors, thereby providing more personalized services. Among them, the calculation of the interest vector combines the behavior type weight, behavior frequency and time decay factor, which can accurately reflect the user's preferences.

[0061] Specifically, the behavior collection unit records the browsing path, dwell time, click behavior and other data of the user in the virtual display scene by deploying monitoring programs on the user terminal and the server. These data are marked with timestamps and stored in the system database. The preference modeling unit constructs the user's multi-dimensional interest vector based on the collected behavior data. For example, the behavior type weight can be assigned according to the user's dwell time and interaction frequency on different categories of content (such as cultural relics, historical background, virtual scenes, etc.). The behavior frequency counts the number of times the user visits a specific content, and the time decay factor is used to reduce the impact of the user's past behavior on the current interest. The prediction unit predicts the user's possible next behavior based on the user's historical behavior sequence based on the Markov chain model. For example, if the user frequently clicks on the relevant historical background information when browsing cultural relics, the system can predict that the user may continue to explore similar content in the next step.

[0062] Preferably, the behavior collection unit can be combined with eye tracking technology to further obtain the user's visual focus data on the displayed content, so as to capture the user's interest more accurately. The preference modeling unit can introduce deep learning algorithms, such as neural networks, to perform more complex feature extraction and modeling on user behavior data to adapt to the behavior patterns of different users. For example, through user profiling technology, users are divided into different interest groups, and personalized display strategies are customized for each group. The prediction unit can be combined with a reinforcement learning algorithm to dynamically adjust the prediction model according to real-time user feedback to improve the accuracy and adaptability of the prediction. In addition, the calculation of the interest vector can introduce more dimensional features, such as the user's social network behavior, geographic location information, etc., to more comprehensively reflect the user's preferences.

[0063] In some embodiments, the dynamic feedback module includes: Content recommendation unit, matching and displaying content according to user interest vectors; Image quality adjustment unit, dynamically adjusts rendering resolution; Path optimization unit, reconstructs the navigation topology of the virtual scene; The formula for dynamically adjusting rendering resolution is:

[0064] In the formula, is the image quality level, is the number of concurrent users, is the network bandwidth, is the terminal screen size, is the base size, is the adaptive coefficient.

[0065] It should be noted that the dynamic feedback module is a key part of the cultural heritage display management system for improving user experience and realizing personalized display. This module dynamically adjusts the display content, image quality level and navigation path of the virtual scene according to the user's behavior and preferences through the content recommendation unit, image quality adjustment unit and path optimization unit. The content recommendation unit matches the display content according to the user's interest vector, the image quality adjustment unit dynamically adjusts the rendering resolution according to the network status and user device, and the path optimization unit reconstructs the navigation topology of the virtual scene to enhance the user interaction experience. These functions enable the system to respond to user needs in real time and provide a more immersive and personalized display effect.

[0066] Specifically, the content recommendation unit matches the displayed content according to the user interest vector, where the user interest vector is a multidimensional feature vector generated by the user analysis module, which reflects the user's interest in different types of cultural heritage. The image quality adjustment unit dynamically adjusts the rendering resolution according to the number of concurrent users, network bandwidth, and user terminal screen size to ensure that the best visual effects can be provided in different network environments. For example, when the network bandwidth is low, the system will automatically reduce the image quality level to reduce jamming; when the user uses a high-resolution screen, the system will increase the image quality level to enhance the visual experience. The path optimization unit reconstructs the navigation topology of the virtual scene by analyzing the user's browsing path and stop points, providing users with a more intuitive and convenient interaction path. For example, if a user stays in a specific area for a long time, the system can automatically adjust the navigation path to guide the user to explore related content.

[0067] Preferably, the content recommendation unit can introduce a collaborative filtering algorithm, combined with the behavioral data of other users, to provide more accurate recommended content for the current user. For example, if the system detects that most users will check the historical background of a certain cultural relic after browsing it, the system can automatically provide a similar recommended path for new users. The image quality adjustment unit can be combined with real-time network monitoring technology to dynamically adjust the adaptive coefficient of the image quality level. For example, by monitoring network latency and packet loss rate, the system can automatically switch to low-quality mode when the network is unstable, and gradually improve the image quality after the network is restored. The path optimization unit can introduce artificial intelligence algorithms, such as reinforcement learning, to dynamically adjust the navigation path based on real-time user feedback to further enhance the user experience. In addition, the image quality adjustment strategy can introduce a user feedback mechanism, allowing users to manually adjust image quality preferences and incorporate these preferences into the system's automatic adjustment strategy.

[0068] In some embodiments, the dynamic weighting factor The calculation methods include: Assign initial weights based on data source reliability scores; Update weight values ​​based on a time decay function; Correct weight bias through feedback mechanism; The formula is:

[0069] In the formula, is the learning rate, is the actual calibration value, To predict the check value, is the dynamic weighting factor of the i-th type of data after the t+1th update, is the dynamic weighting factor of the i-th category data after the t-th update.

[0070] It should be noted that the calculation method of the dynamic weighting factor is an important part of the data verification unit, which is used to ensure data integrity and reliability. The calculation of the dynamic weighting factor combines the reliability score of the data source, the time decay function and the feedback mechanism, and can dynamically adjust the weight value according to the real-time status of the data. The data source reliability score is an assessment of the quality of data collected by different sensors. The time decay function is used to reduce the impact of old data on the current weight. The feedback mechanism corrects the weight deviation by comparing the difference between the actual verification value and the predicted verification value. This method can effectively adapt to the dynamic changes in the data collection process and improve the accuracy and adaptability of data verification.

[0071] Specifically, the initial weight assignment of the dynamic weighting factor is based on the reliability score of the data source. For example, for high-precision laser scanner data, the initial weight can be set to a higher value (such as 0.8), while for data collected by environmental sensors, the initial weight can be set to a lower value (such as 0.5). The time decay function is used to adjust the weight value. As the data collection time goes by, the weight will gradually decay to reduce the impact of old data on the current verification. For example, the time decay function can be set to an exponential decay form, such as ,in is the attenuation coefficient ( ), is the time step. The feedback mechanism corrects the weight deviation by comparing the difference between the actual check value and the predicted check value. For example, if the difference between the actual check value and the predicted check value is large, it means that the current weight setting is unreasonable and needs to be adjusted through the learning rate. Adjust the weights, the formula is:

[0072] in, is the current weight, is the predicted checksum value, is the actual checksum value.

[0073] Preferably, the calculation of dynamic weighting factors can introduce machine learning algorithms, such as linear regression or neural networks, to more accurately predict weight changes. For example, by training the model with historical data, the weight value can be dynamically adjusted to adapt to the reliability changes of different data sources. The time decay function can be adjusted according to the data type and application scenario. For example, for data with higher real-time requirements, a faster decay rate can be used; and for data with higher stability, a slower decay rate can be used. In addition, the learning rate in the feedback mechanism It can be adjusted dynamically according to the system's fault tolerance and the accuracy requirements of data verification. For example, in scenarios where data verification accuracy requirements are high, the learning rate can be set to a higher value to quickly correct weight deviations; while in scenarios where fault tolerance is high, the learning rate can be set to a lower value to avoid over-adjustment.

[0074] The above-mentioned embodiments of the present invention have the following beneficial effects: through the multi-source sensor unit and environmental parameter unit of the data acquisition module, the system can obtain comprehensive multimodal data of cultural heritage, and use the data verification unit to ensure the integrity and accuracy of the data. The noise filtering unit, data alignment unit and format standardization unit of the preprocessing module can effectively eliminate data noise, synchronize the time axis and unify the data format, thereby providing a high-quality data basis for subsequent processing. The spatial feature unit, texture analysis unit and semantic association unit of the feature extraction module can accurately extract the multi-dimensional features of cultural heritage and provide a comprehensive analysis of spatial structure, texture details and historical associations. The scene generation unit, interactive logic unit and rendering optimization unit of the virtual display module can construct an immersive dynamic interactive virtual scene, combining ray tracing with detailed level hybrid rendering technology to improve user experience. The resource monitoring unit, task scheduling unit and disaster recovery backup unit of the load balancing module can monitor resource occupancy in real time, dynamically allocate cloud computing resources, and ensure data security through cross-regional data mirroring, ensuring the stability and reliability of the system during high concurrent access. The behavior acquisition unit, preference modeling unit and prediction unit of the user analysis module can record user behavior in real time, construct user interest vectors and predict the next behavior, providing data support for personalized display. The content recommendation unit, image quality adjustment unit and path optimization unit of the dynamic feedback module can dynamically adjust the display content, image quality level and navigation topology according to user interests, further improving user satisfaction and the intelligence level of the system.

[0075] In addition, the calculation method of dynamic weighting factors can assign initial weights according to the reliability score of the data source, and update the weight values ​​in real time based on the time decay function and feedback mechanism, further improving the accuracy and adaptability of data verification. Overall, this system can achieve efficient collection, accurate processing, immersive display and intelligent management of cultural heritage, while ensuring the integrity of data and the stability of the system, providing comprehensive technical support for the digital protection and display of cultural heritage.

[0076] like Figure 2 As shown, a cultural heritage display management method 200 based on cloud computing in some embodiments includes: S1. Collect physical parameters and environmental data of cultural heritage through multi-source sensors; S2. Verify data integrity using a verification algorithm that includes dynamic weighting factors and environmental correction coefficients; S3. Use adaptive filtering algorithm to reduce noise and time align the data; S4. Extract spatial texture features through multi-scale decomposition algorithm; S5. Generate virtual scene structure based on topology optimization algorithm; S6. Allocate cloud computing resources according to a dynamic priority algorithm; S7. Construct user interest vector and predict behavior path; S8. Adjust image quality level and content recommendation strategy in real time.

[0077] It is understandable that the steps described in the cloud computing-based cultural heritage display management method 200 are similar to those described in the reference Figure 1 Therefore, the modules, features and beneficial effects described above for the cultural heritage display management system based on cloud computing are also applicable to the cultural heritage display management method 200 based on cloud computing and the operations contained therein, and will not be repeated here.

[0078] Reference below Figure 3 , which shows a schematic diagram of the structure of an electronic device 300 suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include but are not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0079] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 to a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0080] Typically, the following devices may be connected to the I / O interface 305: an input device 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 308 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 309. The communication device 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Figure 3The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0081] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0082] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention.

Claims

1. A cultural heritage display management system based on cloud computing, characterized in that: include: Data collection module, used to obtain multimodal data of cultural heritage; Preprocessing module, used to standardize multimodal data; Feature extraction module, used to extract multi-dimensional features of cultural heritage through algorithms; A virtual display module, used to generate dynamic interactive virtual scenes; Load balancing module, used to dynamically allocate cloud computing resources; User analysis module, used to analyze user behavior data; Dynamic feedback module, used to adjust display content in real time according to user behavior.

2. The system according to claim 1, characterized in that The data acquisition module comprises: Multi-source sensor units for collecting physical parameters of cultural heritage; Environmental parameter unit, used to capture temperature, humidity and light data of the display environment; A data verification unit, used to ensure data integrity through a verification algorithm; Among them, the verification algorithm formula is: In the formula, C is the calibration value, is the i-th type of data, is the dynamic weighting factor, is the environmental correction factor, is the timestamp parameter, is the total number of data categories.

3. The system according to claim 1, characterized in that The preprocessing module comprises: Noise filtering unit, which uses adaptive filtering algorithm to eliminate data noise; A data alignment unit, used to synchronize the time axis of multimodal data; Format standardization unit, converting data into a unified coding format; The adaptive filtering algorithm formula is: In the formula, is the filtered data, is the original signal, is the sliding mean, is the standard deviation, is the attenuation coefficient, is the dynamic gain, is a time-dependent function.

4. The system according to claim 1, characterized in that The feature extraction module comprises: Spatial feature unit, extracts spatial structure features through a three-dimensional convolutional network; Texture analysis unit, which uses a multi-scale decomposition algorithm to analyze surface texture; Semantic association unit, constructing the association map between cultural heritage and historical events; The multi-scale decomposition algorithm formula is: In the formula, To decompose the results, is the Gaussian kernel of the sth scale, For input data, is the scale weight, is the smoothing factor, is the square of the current decomposition scale.

5. The system according to claim 1, characterized in that The virtual display module includes: A scene generation unit constructs a virtual space topology structure based on feature data; Interaction logic unit, which defines the mapping relationship between user operations and scene responses; Rendering optimization unit, using ray tracing and detail level hybrid rendering technology; The formula for constructing the virtual space topology structure based on feature data is: Where T is the optimal topology, is the feature point, are virtual coordinates, is the constraint coefficient, is the spatial curvature gradient.

6. The system according to claim 1, characterized in that The load balancing module includes: Resource monitoring unit, which monitors the CPU and memory usage of each computing node in real time; Task scheduling unit, using dynamic priority allocation algorithm; Disaster recovery and backup unit, establishing cross-regional data mirroring; The dynamic priority algorithm formula is: In the formula, is the CPU utilization, For the task urgency, is the memory usage, is the delay weight, For network delay.

7. The system according to claim 1, characterized in that The user analysis module includes: Behavior collection unit, which records the user's browsing path and duration of stay; Preference modeling unit, constructs interest vectors with multi-dimensional features; Prediction unit, predicts the next behavior through Markov chain; The interest vector calculation formula is: In the formula, is the user interest vector, is the behavior type weight, is the frequency of behavior, is the time decay factor, A collection of frequency statistics for all behavior types.

8. The system according to claim 1, characterized in that The dynamic feedback module comprises: Content recommendation unit, matching and displaying content according to user interest vectors; Image quality adjustment unit, dynamically adjusts rendering resolution; Path optimization unit, reconstructs the navigation topology of the virtual scene; The formula for dynamically adjusting rendering resolution is: In the formula, is the image quality level, is the number of concurrent users, is the network bandwidth, is the terminal screen size, is the base size, is the adaptive coefficient.

9. The system according to claim 2, characterized in that The dynamic weighting factor The calculation methods include: Assign initial weights based on data source reliability scores; Update weight values ​​based on a time decay function; Correct weight bias through feedback mechanism; The formula is: In the formula, is the learning rate, is the actual calibration value, To predict the check value, is the dynamic weighting factor of the i-th type of data after the t+1th update, is the dynamic weighting factor of the i-th category data after the t-th update.

10. A cultural heritage display management method based on cloud computing, characterized in that: The following steps are involved: S1. Collect physical parameters and environmental data of cultural heritage through multi-source sensors; S2. Verify data integrity using a verification algorithm that includes dynamic weighting factors and environmental correction coefficients; S3. Use adaptive filtering algorithm to reduce noise and time align the data; S4. Extract spatial texture features through multi-scale decomposition algorithm; S5. Generate virtual scene structure based on topology optimization algorithm; S6. Allocate cloud computing resources according to a dynamic priority algorithm; S7. Construct user interest vector and predict behavior path; S8. Adjust image quality level and content recommendation strategy in real time.

Images