Interactive painting exhibition system based on VR (virtual reality) technology

Abstract

The invention belongs to the technical field of image rendering, and discloses a painting interactive exhibition system based on a VR technology. Comprising the following steps: acquiring high-precision painting original data and exhibition environment information, and constructing an exhibition space feature map; performing spatial attribute feature recognition on the exhibition space feature map, and constructing a virtual exhibition space holographic model; performing painting interaction rendering processing on the virtual exhibition space holographic model to generate a painting interaction experience network; performing visual experience simulation on the virtual exhibition space holographic model to generate high-immersion visual experience data; performing dynamic ray tracing processing on the painting interactive experience network by utilizing the high-immersion visual experience data to obtain an interactive experience change track; performing multi-dimensional exhibition effect comprehensive evaluation on the interactive experience change track; according to the method, highly immersive painting interaction experience can be realized, the method has accurate visual restoration capability, and the exhibition experience quality of a user and the exhibition space utilization efficiency are improved.

Description

Technical Field

[0001] This invention relates to the field of image rendering technology, and more specifically, to an interactive exhibition system for paintings based on VR technology. Background Technology

[0002] Art exhibitions serve as a vital vehicle for cultural inheritance and innovation, attracting hundreds of millions of visitors worldwide each year. With the rapid development of digital technology and the growing public demand for immersive experiences, traditional art exhibition models face challenges of innovation and transformation. Therefore, constructing highly immersive and intelligently interactive digital art exhibition systems is of great significance for enhancing cultural dissemination and the visitor experience.

[0003] Compared with existing technologies, traditional art exhibition systems mainly have the following problems:

[0004] Traditional art exhibitions typically employ static displays, limiting interaction between viewers and artworks. The exhibition experience offered is often monotonous and fails to meet the personalized needs of diverse audiences. Existing methods for evaluating exhibition effectiveness are largely based on subjective impressions or simple questionnaires, lacking quantitative analysis of viewer behavior and experience. Traditional exhibition design often relies on curators' experience and intuition, lacking systematic collection and analysis of data such as viewer flow paths and dwell time. Exhibition environment design (e.g., lighting, spatial layout) often follows fixed patterns, failing to dynamically optimize based on the characteristics of different artworks and viewer needs. These exhibition design methods lack scientific basis, environmental parameter settings are largely based on experiential judgment, and different types of artworks often employ similar display methods, resulting in low personalization and precision in exhibition effectiveness.

[0005] In view of this, the present invention proposes an interactive painting exhibition system based on VR technology to solve the above problems. Summary of the Invention

[0006] To overcome the aforementioned deficiencies of the prior art and to achieve the above objectives, the present invention provides the following technical solution:

[0007] An interactive art exhibition system based on VR technology includes:

[0008] The data acquisition module is used to acquire high-precision original data of paintings and exhibition environment information; it performs spatial feature mining on the exhibition environment information and constructs an exhibition space feature map.

[0009] The space construction module is used to identify spatial attribute features of the exhibition space feature map, reconstruct the three-dimensional space, and build a holographic model of the virtual exhibition space.

[0010] The interactive rendering module performs interactive rendering processing on the holographic model of the virtual exhibition space based on high-precision original painting data, and fits the user's perspective distribution to generate an interactive painting experience network.

[0011] The visual optimization module is used to simulate the visual experience of the holographic model of the virtual exhibition space to obtain dynamic visual simulation data; the lighting effect is optimized on the dynamic visual simulation data to generate highly immersive visual experience data.

[0012] The ray tracing module uses highly immersive visual experience data to perform dynamic ray tracing processing on the artwork interaction experience network and detects the artwork interaction effect to obtain the trajectory of interaction experience changes.

[0013] The analysis and feedback module performs an interaction network integrity analysis on the trajectory of changes in the interactive experience and conducts a comprehensive evaluation of the exhibition effect from multiple dimensions to generate an exhibition effect evaluation result.

[0014] Furthermore, the implementation process of the data acquisition module includes:

[0015] High-precision original data of the paintings to be exhibited were collected from multiple sources, including art galleries, art databases, and museum digital resources. Simultaneously, exhibition environment information related to the original data was collected and organized, including venue layout, lighting conditions, and visitor routes. Various characteristic indicators describing the spatial flow were extracted, including visitor movement paths, dwell time, and distribution of points of interest. Using spatial modeling and cluster analysis techniques, the corresponding spatial flow characteristics were systematically mined and depicted. Based on the dynamic flow characteristics of the exhibition space, a visual representation was created in the form of a graph. In the graph, different nodes represent spatial points where visitors participate in interactive activities, and lines represent the paths and intensity of visitor flow. This constructed a comprehensive visual model reflecting the current dynamic characteristics of the exhibition space, providing a foundation for further in-depth analysis.

[0016] Furthermore, the implementation process of the space building module includes:

[0017] By deeply analyzing the spatial attribute characteristics of each node and connection, including multiple dimensions such as node type (e.g., exhibition hall, passageway, rest area), connection type (e.g., main path, auxiliary path), and node / connection weight (e.g., visitor flow, dwell time), and using deep learning, spatial clustering, and other technologies, rich attribute features describing the entire exhibition space are automatically extracted. Based on these attribute features, the data is reorganized and integrated to construct a more complete virtual exhibition space model. This model includes not only the topological information of nodes and connections but also the rich spatial attributes of each element. Through this holographic modeling method, the actual spatial state of the current exhibition environment can be more accurately reflected. In this holographic model, various nodes and connections are given rich attribute annotations, forming a three-dimensional and dynamic description of the virtual exhibition space.

[0018] Furthermore, the implementation process of the interactive rendering module includes:

[0019] High-precision original data of the paintings are input into a holographic model of the virtual exhibition space. Through global rendering, the presentation and interaction of these paintings in the virtual exhibition space are displayed and recorded. The acquired painting rendering and display information is analyzed in depth to extract various statistical indicators describing the distribution characteristics of user perspectives, including the distribution of perspective dwell time among different paintings, gaze preferences, attention duration, and other dimensions. Using mathematical modeling techniques such as probability statistics and eye tracking, these perspective distribution characteristics are accurately fitted and modeled. Based on the holographic model, a network structure describing the interactive experience of the paintings in the entire virtual exhibition space is further extracted. This painting interaction experience network can comprehensively reflect the actual situation of audience interaction with the paintings in the current exhibition environment, providing a basic support for subsequent exhibition effect analysis.

[0020] Furthermore, the implementation process of the visual optimization module includes:

[0021] A thorough visual experience evaluation and analysis of the entire virtual exhibition environment was conducted. Using technologies such as visual engines and rendering pipelines, key nodes affecting the visual experience within the virtual exhibition space were identified. Based on these identified key viewpoint nodes, combined with actual visual perception data and light propagation statistics, the visual immersion of each node was calculated. These immersion values ​​quantitatively characterize the visual experience level of each key point in the virtual exhibition space. The calculated node visual immersion was used as input for dynamic visual experience simulation. Through methods such as ray tracing simulation, various visual activities occurring in the virtual exhibition space were simulated. Deep learning was used to learn and extract various texture features from high-precision original painting data, including brushstroke structure, color distribution, and artistic style, generating a complete set of dynamic visual simulation data. This provides a foundation for subsequent lighting effect optimization. Through lighting rendering, material mapping, and other technologies, the dynamic visual simulation data was finely optimized to generate a set of highly immersive visual experience data.

[0022] Furthermore, the implementation process of the ray tracing module includes:

[0023] The generated highly immersive visual experience data is input into the constructed painting interaction experience network model to simulate the dynamic presentation and propagation of this visual data in the virtual exhibition space. Its impact on the entire network structure is observed, and in-depth analysis of the painting interaction ray tracing data is conducted to extract various indicators describing the realistic rendering response characteristics in the virtual exhibition space. These indicators include visual response characteristics across multiple dimensions such as frame rate changes, rendering quality, and material representation. Based on the realistic rendering data of the paintings, Monte Carlo simulation and other methods are used to predict and simulate the optimization process of visual effects in the virtual exhibition space, identifying the main paths of visual presentation and optimization, and extracting the complete visual optimization path. This visual optimization path information provides crucial support for subsequent interaction effect analysis. The acquired visual optimization path information is then compared and analyzed with the painting interaction experience network to identify the trajectory of changes in the painting interaction effects in the virtual exhibition space during the visual optimization process.

[0024] Furthermore, the implementation process of the analysis feedback module includes:

[0025] By combining the acquired interactive experience change trajectories, the resulting experience effects are analyzed, considering factors such as interaction fluency and visual realism. An experience quantification model is used to calculate the user experience quantification value for each trajectory. These interactive experience quantification values ​​are summarized and sorted to provide a reference for subsequent overall evaluation. The structural changes of the entire painting's interactive experience network are analyzed in depth, and the integrity of the interactive network is evaluated, including indicators such as key node response and key interaction fluency. The effect of painting detail reproduction under different visual conditions is analyzed, considering factors such as texture clarity, color reproduction, and brushstroke expression. A quantitative model is used to calculate the painting detail reproduction degree. Through weighted summation and fuzzy comprehensive evaluation methods, a comprehensive evaluation result reflecting the exhibition effect of the virtual exhibition space is generated. This evaluation result can provide a reliable basis and decision support for the formulation of subsequent exhibition optimization strategies.

[0026] The technical effects and advantages of the VR-based interactive painting exhibition system of this invention are as follows:

[0027] This invention ensures the high authenticity of data used in the exhibition system by acquiring high-precision original data of paintings and exhibition environment information, promptly presenting the fine details of the paintings. The collection of exhibition environment information allows subsequent analysis to be based on actual exhibition needs, enhancing the relevance and artistic expression of the viewing experience. By mining spatial flow characteristics, an exhibition space feature map is constructed, providing a clear view to help identify audience flow patterns and focal points. Identifying spatial attribute characteristics allows for a detailed understanding of the characteristics of various exhibition spaces, facilitating the formulation of subsequent display strategies. Holographic model reconstruction integrates multi-dimensional information of the virtual exhibition space, forming a comprehensive spatial holographic model, providing a rich visual foundation for subsequent interactions. Through global tracking and processing of user interactions, real-time monitoring of user interactions in various exhibition areas is possible, quickly identifying changes in interest and generating... The interactive experience network for paintings helps understand how users interact between different paintings, providing data support for subsequent visual optimization. Through visual experience simulation, it tests the system's immersion and realism, identifies potential areas for visual optimization, and generates highly immersive visual experience data to help evaluate the system's visual reproduction capabilities, enhancing the immersive experience of the exhibition. Through dynamic ray tracing, it can evaluate the system's visual performance under different viewing conditions in real time, providing a basis for optimizing the display effect. The trajectory of interactive experience changes can quickly identify the impact of visual optimization on the experience, helping to adjust display strategies in a timely manner and improve the quality of the experience. Through multi-dimensional comprehensive evaluation of exhibition effects, it can comprehensively evaluate the effect of the exhibition system, ensuring the integrity and smoothness of the viewing experience. The generated exhibition effect evaluation results provide exhibition designers with clear optimization directions and enable them to formulate more effective exhibition strategies. Attached Figure Description

[0028] Figure 1This is a schematic diagram of the VR-based interactive painting exhibition system of the present invention. Detailed Implementation

[0029] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0030] Example 1

[0031] Please see Figure 1 As shown in this embodiment, the interactive painting exhibition system based on VR technology includes:

[0032] The data acquisition module is used to acquire high-precision original data of paintings and exhibition environment information; it performs spatial feature mining on the exhibition environment information and constructs an exhibition space feature map.

[0033] In this embodiment, high-precision original data of the paintings to be exhibited are collected from multiple channels, including art galleries, art databases, and museum digital resources. Simultaneously, exhibition environment information related to the original painting data is collected and organized, including venue layout, lighting conditions, and visitor routes. Various feature indicators describing the spatial flow characteristics are extracted, including visitor movement paths, dwell time, and distribution of points of interest. Using spatial modeling and cluster analysis techniques, the corresponding spatial flow characteristics are systematically mined and characterized. Based on the dynamic flow characteristics of the exhibition space, a visual representation is presented in the form of a graph. In the graph, different nodes represent spatial points participating in the exhibition interaction, and connecting lines represent the paths and intensity of visitor flow, constructing a comprehensive visualization model that reflects the current dynamic characteristics of the exhibition space, providing a foundation for subsequent in-depth analysis.

[0034] The space construction module is used to identify spatial attribute features of the exhibition space feature map, reconstruct the three-dimensional space, and build a holographic model of the virtual exhibition space.

[0035] In this embodiment, the spatial attribute characteristics of each node and connection are analyzed in depth, including multiple dimensions such as node type (e.g., exhibition hall, passageway, rest area, etc.), connection type (e.g., main path, auxiliary path, etc.), and node / connection weight (e.g., visitor flow, dwell time, etc.). Using deep learning, spatial clustering and other technologies, rich attribute characteristics describing the entire exhibition space are automatically extracted. Based on the exhibition space attribute characteristics, the data are reorganized and integrated to construct a more complete virtual exhibition space model. This model includes not only the topological information of nodes and connections but also the rich spatial attributes of each element. Through this holographic modeling method, the actual spatial state of the current exhibition environment can be reflected more accurately. In this holographic model, various nodes and connections are given rich attribute labels, forming a three-dimensional and dynamic virtual exhibition space description.

[0036] The interactive rendering module performs interactive rendering processing on the holographic model of the virtual exhibition space based on high-precision original painting data, and fits the user's perspective distribution to generate an interactive painting experience network.

[0037] In this embodiment, high-precision original painting data is input into a holographic model of the virtual exhibition space. Through global rendering, the presentation effect and interaction process of these paintings in the virtual exhibition space are displayed and recorded. The obtained painting rendering and display information is analyzed in depth, and various statistical indicators describing the distribution characteristics of user perspectives are extracted, including the distribution of perspective dwell time among various paintings, gaze preference, attention duration, and other dimensions. Using mathematical modeling methods such as probability statistics and eye tracking, these perspective distribution characteristics are accurately fitted and modeled. Based on the holographic model, a network structure describing the interactive experience of the paintings in the entire virtual exhibition space is further extracted. This painting interactive experience network can comprehensively reflect the actual situation of audience interaction with paintings in the current exhibition environment, providing basic support for subsequent exhibition effect analysis.

[0038] The visual optimization module is used to simulate the visual experience of the holographic model of the virtual exhibition space to obtain dynamic visual simulation data; the lighting effect is optimized on the dynamic visual simulation data to generate highly immersive visual experience data.

[0039] In this embodiment, an in-depth visual experience evaluation and analysis of the entire virtual exhibition environment is conducted. Using technologies such as visual engines and rendering pipelines, key nodes affecting the visual experience in the virtual exhibition space are identified. Based on the identified key viewpoint nodes, combined with actual visual perception data and light propagation statistics, the visual immersion of each node is calculated. These immersion values ​​can quantitatively characterize the visual experience level of each key point in the virtual exhibition space. The calculated node visual immersion is used as input conditions for dynamic visual experience simulation. Through methods such as ray tracing simulation, various visual activities occurring in the virtual exhibition space are simulated. Deep learning is used to learn and extract various texture features of the paintings from high-precision original data, including brushstroke structure, color distribution, artistic style, and other multi-dimensional feature descriptions, generating a complete set of dynamic visual simulation data. This provides a foundation for subsequent lighting effect optimization. Through lighting rendering, material mapping, and other technologies, the dynamic visual simulation data is finely optimized to generate a set of highly immersive visual experience data.

[0040] The ray tracing module uses highly immersive visual experience data to perform dynamic ray tracing processing on the artwork interaction experience network and detects the artwork interaction effect to obtain the trajectory of interaction experience changes.

[0041] In this embodiment, the generated highly immersive visual experience data is input into the constructed painting interaction experience network model to simulate the dynamic presentation and propagation of this visual data in the virtual exhibition space. The impact on the entire network structure is observed, and the painting interaction ray tracing data is analyzed in depth. Various indicators describing the realistic rendering response characteristics in the virtual exhibition space are extracted, including visual response characteristics across multiple dimensions such as frame rate changes, rendering quality, and material representation. Based on the realistic rendering data of the paintings, Monte Carlo simulation and other methods are used to predict and simulate the optimization process of visual effects in the virtual exhibition space, identifying the main paths of visual presentation and optimization, and extracting the complete visual optimization path. This visual optimization path information provides important support for subsequent interaction effect analysis. The obtained visual optimization path information is compared and analyzed with the painting interaction experience network to identify the trajectory of changes in the painting interaction effects in the virtual exhibition space during the visual optimization process.

[0042] The analysis and feedback module performs an interaction network integrity analysis on the trajectory of changes in the interactive experience and conducts a comprehensive evaluation of the exhibition effect from multiple dimensions to generate exhibition effect evaluation results.

[0043] In this embodiment, the resulting experience effects are analyzed by combining the acquired interactive experience change trajectories. Considering factors such as interaction fluency and visual realism, an experience quantification model is used to calculate the user experience quantification value for each trajectory. These interactive experience quantification values ​​are summarized and sorted to provide a reference for subsequent overall evaluation. The structural changes of the entire painting interaction experience network are analyzed in depth to evaluate the integrity of the interaction network, including indicators such as key node response and key interaction fluency. The effect of painting detail restoration under different visual conditions is analyzed, considering factors such as texture clarity, color restoration, and brushstroke expression. A quantitative model is used to calculate the painting detail restoration degree. Through weighted summation, fuzzy comprehensive evaluation, and other methods, a comprehensive evaluation result reflecting the exhibition effect of the virtual exhibition space is generated. This evaluation result can provide a reliable basis and decision support for the formulation of subsequent exhibition optimization strategies.

[0044] It should be further explained that, in the specific implementation process, the data acquisition module includes the following steps:

[0045] Acquire high-precision original data of the paintings and information about the exhibition environment;

[0046] Deeply analyze the spatial semantic features of the exhibition environment information to generate exhibition space semantic features; and identify key display areas based on the exhibition space semantic features to obtain key display area data.

[0047] Based on data from key display areas, spatial flow characteristics of the exhibition environment are mined to construct an exhibition space feature map.

[0048] In this embodiment, high-precision original data of paintings is collected by connecting to various art museum systems, including indicators such as painting texture, color information, and brushstroke details. At the same time, relevant information about the current exhibition environment is obtained, such as venue space layout, lighting conditions, and audience flow. The high-precision original data of paintings and exhibition environment information are integrated to form a complete dynamic snapshot of the art exhibition environment. The exhibition environment information is subjected to semantic-level deep analysis to extract various keywords, spatial concepts, and semantic relationships describing the exhibition space, and a semantic feature library of the exhibition space is constructed. This semantic feature can comprehensively reflect the spatial context of the current exhibition environment, providing support for subsequent key area identification. Spatial analysis technology is used to intelligently identify the display area. Combined with exhibition standards, various key display areas in the current exhibition environment are identified, such as core exhibition areas, interactive experience areas, and transition areas. The identified key display area information is labeled and stored to provide targeted spatial support for subsequent effect evaluation. The flow patterns of key areas in the exhibition space are analyzed, including audience gathering, movement paths, and dwell time, to uncover the flow trajectory, flow changes, and visit behavior of key areas in the current exhibition space, and to construct a feature map of the exhibition space.

[0049] In one embodiment of the present invention, the process of constructing an exhibition space feature map by mining spatial flow characteristics of exhibition environment information based on key display area data includes:

[0050] Based on key exhibition area data, audience flow path analysis is performed on exhibition environment information to extract audience flow paths within the exhibition.

[0051] Path aggregation point analysis was performed on the visitor flow path within the exhibition to obtain the flow path aggregation points;

[0052] Spatial flow characteristics are mined from the aggregation points of the flow paths to obtain the current flow characteristics of the exhibition space;

[0053] The exhibition environment information is analyzed to obtain audience type classification; and the viewing behavior of the audience type classification is identified to obtain viewing behavior data for each audience type classification.

[0054] Based on the viewing behavior data of the corresponding audience types, the current exhibition space flow characteristics are fitted to a map to construct an exhibition space characteristic map.

[0055] In this embodiment, by analyzing key exhibition areas, the flow paths of visitors in the exhibition space are identified, including the entrance, viewing process, and exit. These identified flow paths are visualized to form a visitor flow path map, showing the movement of visitors between different exhibition areas. Detailed information about the visitor flow paths is compiled into records, including dwell time, attention level, and interactive behavior in each area. Heatmap analysis is used to monitor clustering phenomena in the visitor flow paths, identifying cluster points. These cluster points are marked, and their occurrence time, location, and possible causes are recorded. The visitor flow near the cluster points is analyzed, and relevant features are extracted, such as dwell time, interaction frequency, and interest level. The correlation between cluster points and other spatial flow features is studied to identify potential causal relationships. The extracted features are organized into flow characteristic data of the exhibition space, forming structured information for subsequent use. This data is then used to collect information related to visitor flow. Relevant data, including audience demographics, interests, and visiting history, is collected. Based on audience behavior and visiting patterns, audiences are categorized into different types (e.g., art professionals, leisure visitors, student groups, etc.). The characteristics of each audience type are organized to form an audience type classification dataset. Based on audience type, the viewing behavior of different audience types is analyzed, including visiting routes, dwell time, and interaction preferences. Audience types are mapped to their viewing behaviors to establish a correspondence between audience types and behaviors. Using viewing behavior data and flow characteristic information, an exhibition space feature map is constructed. This map can be used to display the relationship between audience types and spatial flow characteristics. Map fitting techniques are used to associate audience viewing behavior with spatial flow characteristics, forming a dynamic visualization map. The feature map is regularly updated and optimized based on actual usage to ensure it reflects the latest spatial characteristics and viewing behaviors.

[0056] It should be further explained that, in the specific implementation process, the spatial construction module includes the following steps:

[0057] Based on the exhibition environment information, the original data of the high-precision paintings are analyzed to determine the exhibition requirements.

[0058] Spatial attribute features are identified from the exhibition environment information to obtain multiple spatial attribute features;

[0059] Multiple spatial attribute characteristics are analyzed for inter-attribute correlation to generate attribute relationships. Furthermore, quantitative spatial topology analysis is performed using exhibition demand data to generate exhibition space topology demand data.

[0060] Based on the topological requirements data of the exhibition space, the feature map of the exhibition space is reconstructed in three dimensions to build a holographic model of the virtual exhibition space.

[0061] It should be noted that the process involves analyzing information from the current exhibition environment to identify display needs, such as the presentation of artworks, audience interaction, and space utilization. This includes reviewing high-precision original artwork data to assess its suitability for the exhibition, identifying potential display challenges and technical bottlenecks, and summarizing the analysis results to form an exhibition needs dataset. This dataset includes specific display requirements, interactive design, and spatial planning. Spatial analysis and feature extraction are performed on the exhibition environment information to identify various attribute characteristics describing the current exhibition space. These attributes include venue type, space size, lighting conditions, acoustic characteristics, and other dimensions. The spatial attribute relationships are combined with the exhibition needs data to construct a topological model of the exhibition space. Quantitative analysis of the topological model is conducted using mathematical models or computational methods to assess the impact of different attributes on the exhibition effect. The analysis results are integrated to generate exhibition space topological needs data, clarifying the specific requirements of each attribute for the exhibition space. Based on the topological needs data, a holographic model of the virtual exhibition space is designed, including a three-dimensional dynamic display of each attribute and its relationships. Three-dimensional modeling technology is used to reconstruct the exhibition space feature map, ensuring that it can realistically reflect the relationships between spatial attributes and exhibition needs within the virtual environment. The holographic model is tested and verified to ensure its accuracy and reliability, providing support for subsequent applications.

[0062] It should be further explained that, in the specific implementation process, the interactive rendering module includes the following steps:

[0063] High-precision original data of the painting is input into the holographic model of the virtual exhibition space to perform 3D rendering of the painting in order to obtain the rendering and display information of the painting.

[0064] Perform interactive behavior feature analysis on the rendering and display information of paintings to generate interactive behavior feature data;

[0065] Perform global user interaction tracking processing on interactive behavior feature data to generate multiple interactive experience paths;

[0066] The user perspective distribution of multiple interactive experience paths is fitted to generate an interactive experience network for paintings.

[0067] It should be noted that the high-precision original data of the painting is imported into the constructed holographic model of the virtual exhibition space, ensuring that the data format and structure are compatible with the model. Through 3D rendering, the visual effects and artistic expression of the painting are reproduced in the holographic model. Key visual features and states during the rendering process are recorded, generating rendering display information, including rendering quality and material representation. Characteristic indicators of interactive behaviors, such as interaction methods, response times, and user experience smoothness, are determined. Corresponding feature data is extracted from the rendering display information to ensure coverage of all key interactive behaviors. The extracted interactive behavior features are organized into a structured dataset for subsequent analysis and use. Eye-tracking and other technologies are employed to analyze the entire... The system tracks user interaction behavior globally within the virtual exhibition space. Based on features such as gaze focus and interaction touchpoints, related interactions are linked into complete interactive experience paths, generating multiple experience path information describing the user interaction process within the virtual exhibition space. User perspective distribution analysis is performed on multiple interactive experience paths, using probability distribution models (such as heatmaps and attention distribution) to describe the distribution characteristics of user perspectives. Based on the perspective distribution results, an interactive experience network of paintings is constructed, treating the experience paths as nodes and edges in the network to form a network structure. The effectiveness and stability of the interactive experience network of paintings are verified, and by analyzing indicators such as network connectivity and clustering, it is ensured that it reflects the real interactive experience mode.

[0068] In one embodiment of the present invention, the process of performing interactive behavior feature analysis on the rendering and display information of a painting to generate interactive behavior feature data includes:

[0069] Calculate the interactive response speed of the painting rendering and display information, and generate user interaction response speed parameters;

[0070] Extracting key interactive nodes based on information displayed through artwork rendering;

[0071] The interaction frequency of key interaction nodes is statistically analyzed to generate the interaction frequency between nodes;

[0072] The system identifies the user's gaze focus by analyzing the rendered and displayed information of the artwork.

[0073] Based on the frequency of interaction between nodes, user interest trend analysis is performed on user gaze focus data to generate user interest change trends;

[0074] Analyze user interaction response speed parameters and user interest change trends to generate interactive behavior feature data.

[0075] In this embodiment, the user's response speed at various interaction nodes is analyzed, and various quantitative indicators describing the interaction response speed, such as average response time and fastest response time, are calculated. These interaction response speed parameters are organized and stored to provide basic data for subsequent interaction behavior analysis. The definition of key interaction nodes is clarified, which are usually important links in the user interaction process (such as viewing details of an artwork, changing perspectives, zooming in and out, etc.). Identifiers and related information of each key interaction node are extracted from the rendered display information. The identified key interaction nodes are organized into a dataset to ensure the uniqueness and completeness of each node. The interaction frequency of the extracted key interaction nodes is statistically analyzed, and the number of interactions between each pair of nodes is calculated. The statistical results are organized into a frequency matrix. Rows and columns represent different nodes, and matrix elements represent interaction frequencies. The generated interaction frequency data is saved in a structured format for easy subsequent analysis. The distribution of users' gaze focus in the virtual exhibition space is analyzed, and various characteristic indicators describing users' gaze focus, such as gaze duration and gaze frequency, are extracted. Based on interaction frequency and gaze focus, a user interest trend analysis model is established. Statistical and predictive analysis methods are used to identify the changing trends of user interests, such as enhancement, weakening, or stabilization. The analysis results are compiled into a user interest change trend report, including trend type and change magnitude. The response speed parameter is combined with the interest change trend to analyze its impact on interactive behavior, identify key features, and organize the generated interactive behavior feature data to form a structured feature set.

[0076] It should be further explained that, in the specific implementation process, the visual optimization module includes the following steps:

[0077] Dynamic perspective transition recognition is performed on the holographic model of the virtual exhibition space to obtain key perspective transition nodes;

[0078] Visual immersion is calculated for key viewpoint transition nodes to generate the node visual immersion corresponding to each key viewpoint transition node;

[0079] Visual experience simulation is performed based on node visual immersion to obtain dynamic visual simulation data;

[0080] The texture features of the painting are learned from the original data of the high-precision painting to obtain the texture feature parameters of the painting.

[0081] Based on the texture feature parameters of the painting, the dynamic visual simulation data is optimized for lighting effects to generate highly immersive visual experience data.

[0082] It should be noted that in-depth perspective analysis and experience evaluation of the entire virtual exhibition environment are conducted. Using techniques such as viewpoint computation and user experience modeling, key perspective transition nodes in the virtual exhibition space are identified. Combined with actual experience data and visual perception statistics, the visual immersion of each node is calculated. Node visual immersion refers to a quantitative indicator of the degree of visual immersion experienced by the user at a specific viewing position (node) in the virtual exhibition space. It can quantitatively characterize the visual experience level of each key point in the virtual exhibition space. Different visual experience models (such as ray tracing, real-time rendering, etc.) are defined and combined with node immersion. The calculated node visual immersion is used as... Input conditions are used to simulate a dynamic visual experience. High-precision samples of original painting data are collected to ensure coverage of various types and artistic styles. Through methods such as ray tracing simulation, various visual experiences occurring in a virtual exhibition space are simulated, generating a complete set of dynamic visual simulation data. Using technologies such as deep learning, various texture features of the paintings are extracted, including multi-dimensional feature descriptions such as brushstroke structure, color distribution, and material expression, constructing a complete painting texture feature parameter library. Through lighting rendering, material mapping, and other techniques, the dynamic visual simulation data is finely optimized to generate a set of highly immersive visual experience data to enhance the realism of the exhibition experience.

[0083] It should be further explained that, in the specific implementation process, the ray tracing module includes the following steps:

[0084] Dynamic ray tracing processing is performed on the painting interaction experience network based on highly immersive visual experience data to obtain painting interaction ray tracing data;

[0085] Perform realistic rendering response analysis on the interactive ray tracing data of the painting to generate realistic rendering data of the painting;

[0086] Visual effects are optimized from the realistic rendering data of the painting, thereby extracting the visual optimization path;

[0087] Based on the visual optimization path, the interaction effect of the artwork is detected by the artwork interaction experience network, and the trajectory of interaction experience change is obtained.

[0088] In this embodiment, highly immersive visual experience data is input into the constructed painting interaction experience network model to simulate the dynamic presentation and propagation process of this visual data in the virtual exhibition space, observe its impact on the entire network structure, deeply analyze the painting interaction ray tracing data, extract various indicators describing the realistic rendering response characteristics in the virtual exhibition space, including visual response characteristics in multiple dimensions such as frame rate changes, rendering quality, and material performance, and use visual optimization algorithms to predict and simulate the optimization process of visual effects in the virtual exhibition space, identify the main paths of visual presentation and optimization, extract the complete visual optimization path, identify the change trajectory of the painting interaction effect in the virtual exhibition space during the visual optimization process, organize the detected interaction experience changes into trajectory data, and record the change time, change nature, etc. of each trajectory.

[0089] It should be further explained that, in the specific implementation process, the analysis and feedback module includes the following steps:

[0090] The user experience is quantified by analyzing the trajectory of changes in the interactive experience to generate a quantitative value for the user experience.

[0091] Based on the trajectory of changes in interactive experience, an interactive network integrity analysis is performed on the interactive experience network of the artwork, and an interactive network integrity assessment value is generated.

[0092] The painting detail reproduction rate is calculated based on the realistic rendering data of the painting to generate a painting detail reproduction rate value;

[0093] A multi-dimensional comprehensive evaluation of the exhibition effect is conducted based on the quantitative value of user experience, the evaluation value of the integrity of the interactive network, and the value of the reproduction of the details of the painting, so as to generate the exhibition effect evaluation results;

[0094] In this embodiment, quantitative indicators of interactive experience are defined, considering factors such as interaction fluency, response time, and operational intuition. The impact of changes in the interactive experience trajectory on user experience is analyzed, taking into account factors such as interaction interruption and visual delay. The user experience value of each trajectory is calculated using an experience quantification model. The structural changes of the entire painting's interactive experience network are analyzed in depth, and the integrity of the interactive network is evaluated, including indicators such as key node response and key interaction fluency. The reproduction effect of painting details under different visual conditions is analyzed, considering factors such as texture clarity, color reproduction, and brushstroke expression. The reproduction degree of painting details is calculated using a quantitative model. A comprehensive evaluation model is established, combining the user experience quantification value, the interactive network integrity evaluation value, and the painting detail reproduction degree value. Weights are assigned to each indicator according to the actual situation to ensure that the evaluation results reflect the true exhibition effect. Through weighted calculation, the various indicators are integrated to generate the final exhibition effect evaluation result, which is then compiled into a report.

[0095] This invention acquires high-precision original data of paintings and exhibition environment information to understand the current exhibition environment and art display needs, providing a foundation for subsequent exhibition effect evaluation. It constructs an exhibition space feature map to reveal user flow characteristics in different exhibition spaces, gaining a deeper understanding of the visiting logic and viewing habits behind the audience experience. By identifying spatial attribute features and reconstructing three-dimensional space from the exhibition space feature map, a holographic model of the virtual exhibition space is established, more comprehensively describing the characteristics and relationships of the space. The holographic model of the virtual exhibition space integrates spatial associations and attribute features, providing a detailed spatial foundation for subsequent interactive rendering of paintings. Through interactive rendering of paintings and fitting of user perspective distribution on the holographic model of the virtual exhibition space, a comprehensive display and interaction of high-precision original data of paintings is achieved. An interactive experience network is generated to analyze user interaction behavior, identify audience interest focuses and dwell patterns, and provide a basis for subsequent exhibition effect evaluation. The system provides data support by simulating the visual experience of a holographic model of a virtual exhibition space and generating highly immersive visual experience data. This evaluates the system's display capabilities under different viewing methods. Dynamic visual simulation data verifies the system's visual realism and stability, providing visual experience and optimization strategies for subsequent exhibition effect evaluation. High-immersive visual experience data is used to perform dynamic ray tracing processing on the artwork's interactive experience network to evaluate the system's performance and image effects under different lighting conditions. The resulting interactive experience change trajectory reveals potential visual optimization points and display technology bottlenecks, providing improvement directions and strategies for the system's display effect. Finally, interactive network integrity analysis and multi-dimensional comprehensive evaluation of the exhibition effect comprehensively assess the system's display effect and immersive experience, generating exhibition effect evaluation results, identifying experience risks, and proposing display improvement suggestions, providing support for visual optimization and interactive response.

[0096] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art can still modify the technical solutions described in the foregoing embodiments or make equivalent substitutions for some of the technical features. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

[0097] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0098] In the description of this invention, it should be understood that the terms "first," "second," etc., are used only for distinguishing descriptions and should not be construed as indicating or implying relative importance.

[0099] In the description of this invention, unless otherwise stated, "a plurality of" means two or more.

[0100] In the description of this invention, "several" means one or more, and "a large number" means two or more.

[0101] In the description of this specification, references to terms such as "one embodiment," "some embodiments," "example," "specific example," or "some examples," etc., indicate that a specific feature, structure, material, or characteristic described in connection with that embodiment or example is included in at least one embodiment or example of the invention. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0102] All formulas in this manual are dimensionless and calculated numerically. The formulas are derived from software simulations based on a large amount of collected data to obtain the most recent real-world results. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0103] Although embodiments of the invention have been shown and described, those skilled in the art will understand that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.

Claims

1. An interactive painting exhibition system based on VR technology, characterized in that, include: The data acquisition module is used to acquire high-precision original data of the paintings and information about the exhibition environment. Spatial feature mining of exhibition environment information to construct exhibition space feature map; The space construction module is used to identify spatial attribute features of the exhibition space feature map, reconstruct the three-dimensional space, and build a holographic model of the virtual exhibition space. The interactive rendering module performs interactive rendering processing on the holographic model of the virtual exhibition space based on high-precision original painting data, and fits the user's perspective distribution to generate an interactive painting experience network. The visual optimization module is used to simulate the visual experience of the holographic model of the virtual exhibition space to obtain dynamic visual simulation data; the lighting effect is optimized on the dynamic visual simulation data to generate highly immersive visual experience data. The ray tracing module uses highly immersive visual experience data to perform dynamic ray tracing processing on the artwork interaction experience network and detects the artwork interaction effect to obtain the trajectory of interaction experience changes. The analysis and feedback module performs an interaction network integrity analysis on the trajectory of changes in the interactive experience and conducts a comprehensive evaluation of the exhibition effect from multiple dimensions to generate an exhibition effect evaluation result.

2. The interactive painting exhibition system based on VR technology according to claim 1, characterized in that, The process of spatial feature mining of exhibition environment information includes: Acquire high-precision original data of paintings and exhibition environment information; perform deep analysis of spatial semantic features of exhibition environment information to generate exhibition space semantic features; identify key display areas based on exhibition space semantic features to obtain key display area data; and mine spatial flow features of exhibition environment information based on key display area data to construct exhibition space feature map.

3. The interactive painting exhibition system based on VR technology according to claim 2, characterized in that, The process of mining spatial flow characteristics of exhibition environment information based on key display area data and constructing an exhibition space feature map includes: Based on key exhibition area data, audience flow path analysis is performed on exhibition environment information to extract audience flow paths within the exhibition. Path aggregation point analysis was performed on the visitor flow path within the exhibition to obtain the flow path aggregation points; Spatial flow characteristics are mined from the aggregation points of the flow paths to obtain the current flow characteristics of the exhibition space; The exhibition environment information is analyzed to obtain audience type classification; and the viewing behavior of the audience type classification is identified to obtain viewing behavior data for each audience type classification. Based on the viewing behavior data of corresponding audience types, the flow characteristics of the current exhibition space are fitted to a map to construct an exhibition space feature map.

4. The interactive painting exhibition system based on VR technology according to claim 3, characterized in that, The process of constructing a holographic model of a virtual exhibition space includes: Based on the exhibition environment information, the original data of the high-precision paintings are analyzed to determine the exhibition requirements. Spatial attribute features are identified from the exhibition environment information to obtain multiple spatial attribute features; Multiple spatial attribute characteristics are analyzed for inter-attribute correlation to generate attribute relationships. Furthermore, quantitative spatial topology analysis is performed using exhibition demand data to generate exhibition space topology demand data. Based on the topological requirements of the exhibition space, the feature map of the exhibition space is reconstructed in three dimensions to build a holographic model of the virtual exhibition space.

5. The interactive painting exhibition system based on VR technology according to claim 4, characterized in that, The process of acquiring the interactive experience network for artwork includes: High-precision original data of the painting is input into the holographic model of the virtual exhibition space to perform 3D rendering of the painting in order to obtain the rendering and display information of the painting. Perform interactive behavior feature analysis on the rendering and display information of paintings to generate interactive behavior feature data; Perform global user interaction tracking processing on interactive behavior feature data to generate multiple interactive experience paths; We fit the user perspective distribution to multiple interactive experience paths to generate an interactive experience network for paintings.

6. The interactive painting exhibition system based on VR technology according to claim 5, characterized in that, The process of acquiring interactive behavior feature data includes: Calculate the interactive response speed of the painting rendering and display information, and generate user interaction response speed parameters; Extracting key interactive nodes based on information displayed through artwork rendering; The interaction frequency of key interaction nodes is statistically analyzed to generate the interaction frequency between nodes; The system identifies the user's gaze focus by analyzing the rendered and displayed information of the artwork. Based on the frequency of interaction between nodes, user interest trend analysis is performed on user gaze focus data to generate user interest change trends; Interaction behavior feature analysis is performed on user interaction response speed parameters and user interest change trends to generate interaction behavior feature data.

7. The interactive painting exhibition system based on VR technology according to claim 5, characterized in that, The process of acquiring data for highly immersive visual experiences includes: Dynamic perspective transition recognition is performed on the holographic model of the virtual exhibition space to obtain key perspective transition nodes; Visual immersion is calculated for key viewpoint transition nodes to generate the node visual immersion corresponding to each key viewpoint transition node; Visual experience simulation is performed based on node visual immersion to obtain dynamic visual simulation data; The texture features of the painting are learned from the original data of the high-precision painting to obtain the texture feature parameters of the painting. The lighting effects of the dynamic visual simulation data are optimized based on the texture feature parameters of the painting to generate highly immersive visual experience data.

8. The interactive painting exhibition system based on VR technology according to claim 7, characterized in that, The process of obtaining the trajectory of changes in interactive experience includes: Dynamic ray tracing processing is performed on the painting interaction experience network based on highly immersive visual experience data to obtain painting interaction ray tracing data; Perform realistic rendering response analysis on the interactive ray tracing data of the painting to generate realistic rendering data of the painting; Visual effects are optimized from the realistic rendering data of the painting, thereby extracting the visual optimization path; Based on the visual optimization path, the interaction effect of the artwork is detected by the artwork interaction experience network, and the trajectory of interaction experience changes is obtained.

9. The interactive painting exhibition system based on VR technology according to claim 8, characterized in that, The process of obtaining exhibition effectiveness evaluation results includes: The user experience is quantified by analyzing the trajectory of changes in the interactive experience to generate a quantitative value for the user experience. Based on the trajectory of changes in interactive experience, an interactive network integrity analysis is performed on the interactive experience network of the artwork, and an interactive network integrity assessment value is generated. The painting detail reproduction rate is calculated based on the realistic rendering data of the painting to generate a painting detail reproduction rate value; A multi-dimensional comprehensive evaluation of the exhibition effect is conducted based on the quantitative value of user experience, the evaluation value of the integrity of the interactive network, and the value of the reproduction of the details of the painting, so as to generate the exhibition effect evaluation results.

10. The interactive painting exhibition system based on VR technology according to claim 2, characterized in that, The exhibition environment information includes venue layout, lighting conditions, and visitor routes; high-precision original data of the paintings, including painting textures, color information, and brushstroke details.

Images