Interaction system of element universe museum

Abstract

The invention discloses an interactive system of a universe museum, and relates to the field of universe technology and museum display technology, and the system comprises the following components: a virtual native digital human module, a digital twinning module of a collection and an exhibition hall, and a virtual symbiosis module of a scene. By integrating the virtual native digital person module, the digital twin module of the collection and exhibition hall and the virtual symbiosis module of the scene, highly immersive and interactive museum experience is realized, the virtual native digital person can adjust the guidance and explanation strategy in real time according to the interactive behavior of the audience, personalized visiting experience is provided, and meanwhile, the intellectual property of the virtual native digital person is improved. The digital twin module utilizes a multi-modal data fusion three-dimensional reconstruction algorithm to accurately copy details of collections and exhibition halls, so that audiences can view and research the exhibits in a close range in a virtual environment, and the interactive system not only enriches the exhibition means of the museum, but also improves the participation degree and satisfaction degree of the audiences.

Description

Technical Field

[0001] The present invention relates to the technical fields of the metaverse technology and museum display technology, and specifically to an interactive system for a metaverse museum. Background Art

[0002] With the rapid development of technology, the metaverse technology has gradually become the new favorite in the digital age. The metaverse is a virtual world parallel to the real world, which provides users with an immersive and interactive digital environment. Against this background, museums, as important carriers of culture and history, have also begun to explore how to apply the metaverse technology to exhibitions and displays to provide a more rich visiting experience. The interactive system of the metaverse museum has emerged as the times require. It combines virtual reality and artificial intelligence technologies, aiming to create a brand-new and highly immersive museum experience for users.

[0003] Traditional technologies have deficiencies. On the one hand, they cannot provide a highly immersive and interactive museum experience and cannot adjust their guiding and explaining strategies in real time according to the interactive behaviors of the audience to provide a personalized visiting experience. On the other hand, they cannot enable the audience to closely observe and study exhibits in the virtual environment. Therefore, it is particularly important to develop an interactive system for a metaverse museum. Summary of the Invention

[0004] The purpose of the present invention is to make up for the deficiencies of the existing technology, and provide an interactive system for a metaverse museum, which can break the limitations of traditional museums by integrating virtual native digital humans, digital twins and virtual symbiosis modules, and bring a more rich, personalized and immersive visiting experience to the audience.

[0005] To solve the above technical problems, the present invention provides the following technical solutions: An interactive system for a metaverse museum, the system includes the following components: a virtual native digital human module, a digital twin module of collections and exhibition halls, and a virtual symbiosis module of the scene;

[0006] The virtual native digital human module: Construct a virtual native digital human, and the algorithm formula is: N = φ(∑ i-1 (ω i ×A i ) + β), where N represents the final behavior output of the digital human, A i is the i-th feature vector extracted from the interactive behavior of the audience, n is the number of feature vectors, ω iLet \(w\) be the weight, \(\beta\) be the bias term, \(\varphi\) be the activation function, and a piecewise function is used as the non - linear activation function, which performs different mappings according to the urgency and content depth of the audience interaction. This neural network has a unique inter - layer connection structure, and the inter - layer connection weights are adjusted according to the complexity and importance of the exhibits in different areas of the museum. The knowledge storage of the digital human is based on the knowledge fusion graph algorithm. This algorithm first performs semantic analysis on knowledge data from various sources, extracts knowledge entities and relationships. The algorithm formula is: where \(K\) represents the result after knowledge fusion, \(E\) j is the feature vector of the \(j\) - th knowledge entity, \(m\) is the number of knowledge entities, and the weight \(\lambda\) j is determined by evaluating the credibility of knowledge from different sources. The basis for credibility evaluation is the authority of the knowledge - publishing institution, the citation frequency of research results, etc. \(\mu\) is the initial knowledge bias, obtained by counting the knowledge related to the core exhibits of the museum, and \(Y\) is the fusion function;

[0007] The digital twin module of the collection and exhibition hall: The digital replication of the collection and exhibition hall adopts a multi - modal data fusion three - dimensional reconstruction algorithm. The algorithm formula is: where \(T\) is the generated three - dimensional model, \(D\) k is the feature of the \(k\) - th data point obtained by multi - modal means such as laser scanning, photogrammetry, and infrared imaging, \(p\) is the number of data points, \(\sigma\) k is the weight, \(\tau\) is the initial model parameter, and \(\theta\) is the fusion function. For the blockchain management of digital collections, an adaptive blockchain consensus algorithm is adopted. The algorithm formula is: where \(C\) is the consensus result of the blockchain, \(V\) l is the voting vector of the \(l\) - th node, \(q\) is the number of nodes, \(\rho\) l is the weight, \(\xi\) is the initial consensus parameter, and \(\in\) is the consensus function:

[0008] The virtual symbiosis module of the scene: The construction of the virtual scene adopts a physical - behavior coupling rendering algorithm. The algorithm formula is: where \(S\) is the generated virtual scene, \(F\) r is the physical - behavior feature vector of the \(r\) - th scene element, \(s\) is the number of scene elements, \(\eta\) r is the weight, \(\omega\) is the initial scene parameter, and \(\zeta\) is the rendering function.

[0009] Furthermore, in the emotion - perception neural network algorithm of the virtual native digital human module, the dynamic adjustment mechanism of the weight \(\omega\) i is as follows: During the operation of the system, as the audience interaction data accumulates continuously, an incremental weight update algorithm is used to adjust the weight in real - time. The algorithm formula is: where \(\omega\) i , \(t + 1\) and \(\omega\) i, t are the weights at times t + 1 and t respectively, α is the learning rate, G is the number of samples of audience interaction data collected within the time interval, R g is the weight update factor of the g-th sample, determined according to the time freshness of the sample and the importance of the interaction, A i，g is the value of the i-th feature vector in the g-th sample, is the historical average of the feature vector A i Through this dynamic adjustment mechanism, the digital human can timely adapt to the changes in the audience's behavior patterns. When a new exhibition is launched and the audience's attention and inquiry directions for exhibits change, the digital human can quickly adjust its guiding and explanation strategies according to the new data to better meet the needs of the audience.

[0010] Furthermore, in the multi-modal data fusion three-dimensional reconstruction algorithm of the digital twin module of the collection and exhibition hall, for the model optimization methods of different types of collections and exhibition hall structures: when dealing with collections with complex textures, when determining the weight σ k , in addition to correlation analysis, a texture detail enhancement coefficient is also introduced. For the texture data features obtained through high-resolution photogrammetry, its weight calculation formula is: where σ k，tex is the weight after considering texture details, K is the texture detail enhancement coefficient, T k is the texture detail measurement value corresponding to the k-th data point. For the exhibition hall structure with irregular geometry, during the model fusion process, a shape adaptive fusion algorithm is adopted, and a shape adaptive factor is added to the θ function. The algorithm formula is where e new is the adjusted fusion function, λ is the shape adaptive coefficient, S k is the geometric shape feature value corresponding to the k-th data point, and S is the average value of the geometric shape feature values of all data points. Through these optimization methods, the details of complex texture collections and the shapes of irregular exhibition hall structures can be better presented in the digital twin model.

[0011] Furthermore, in the adaptive blockchain consensus algorithm of the digital twin module of the collection and exhibition hall, the supplementary method for node performance evaluation: also consider the stability and anti-attack ability of the node. For the stability evaluation of the node, by monitoring the running state of the node within a certain period of time, the node stability weight ρ l , the calculation formula of stab is: where M h，l is the value of the h-th performance index of the l-th node, is the average value of the h-th performance metric for all nodes, and H is the number of performance metrics. For the evaluation of the node's anti-attack ability, a simulated attack test is adopted. By comprehensively considering the stability and anti-attack ability of the node, the reliability of the blockchain network can be further improved, ensuring the secure management of digital collections in a more complex network environment.

[0012] Furthermore, in the physical-behavior coupling rendering algorithm of the virtual symbiosis module of the scenario, for the physical-behavior feature vector F of the scenario elements r The extension method: When constructing a virtual scene with a cultural ritual scene, add the cultural symbol element features to F r Among them, for the sacrificial utensils and ritual action elements in the scene, the cultural symbol element feature vector C r is determined by semantic analysis of relevant historical documents and archaeological research. The calculation formula for the new physical-behavior feature vector F of the scene elements is: F r，new =[F r，new , C r , C r . In the rendering function ζ, the "cultural symbol rendering enhancement algorithm" is adopted, and the algorithm formula is: Where ζ new is the adjusted rendering function, C d is the importance weight of the d-th cultural symbol element, and I d is the rendering intensity of the d-th cultural symbol element in the current scene. Through this method, the connotation and characteristics of the cultural ritual can be presented more prominently in the virtual scene, enhancing the audience's understanding of ancient culture.

[0013] Furthermore, the interactive system also includes a user experience feedback analysis module that adopts a multi-dimensional user experience evaluation algorithm. The algorithm formula is: U = Π(∑ c＝1 (φ e ×X e ) + ψ), where U is the user experience evaluation result, X e is the feature vector of the e-th user experience dimension, o is the number of user experience dimensions, including but not limited to visual perception, interaction fluency, and knowledge acquisition satisfaction. The weight φ e is determined by factor analysis of the experience feedback data of a large number of users in different types of metaverse scenarios. ψ is the initial experience bias, and Π is the evaluation function. According to the user experience feedback analysis result, the system can optimize each module specifically. When it is found that the interaction fluency of users in the virtual scene is low, the performance of the virtual symbiosis module of the scene can be optimized.

[0014] Furthermore, the interactive system also includes a cross-museum interaction and collaboration module that realizes the interaction and collaboration between different metaverse museums based on a distributed knowledge sharing algorithm. The algorithm formula is: K = λ(∑n＝1 (μ n ×Y n ) + ν), where K is the result of cross - museum knowledge sharing, Y n is the knowledge feature vector of the nth museum, r is the number of meta - universe museums participating in interactive collaboration, the weight μ n is determined based on the authority and uniqueness of each museum in a specific knowledge field, v is the initial knowledge sharing bias, λ is the sharing function, and a distributed computing method based on privacy protection is adopted to achieve knowledge sharing and communication without revealing the core data of each museum. When a historical museum has unique achievements in the research of ancient ceramics, it can share research methods and exhibition experience with other relevant museums through this module, promoting the development of the entire meta - universe museum industry.

[0015] Furthermore, the interaction system also includes a system adaptive configuration module that uses an environment - aware adaptive configuration algorithm. The algorithm formula is: where A is the result of system configuration adjustment, Z s is the s - th environment - aware parameter vector, t is the number of environment - aware parameters, the weight ξ s is determined by regression analysis of experimental data on the impact of different environmental parameters on system performance, η is the initial configuration bias, ω is the configuration function, and an adaptive configuration method based on a rule engine is adopted to automatically adjust the parameters of each module of the system according to the real - time changes of environment - aware parameters, such as the response strategy of virtual native digital humans, the rendering resolution of the digital twin module, and the complexity of the scene virtual symbiosis module, ensuring that the system can provide a good user experience in different environments.

[0016] Compared with the prior art, the interaction system of this meta - universe museum has the following beneficial effects:

[0017] First, by integrating the virtual native digital human module, the digital twin module of collections and exhibition halls, and the virtual symbiosis module of the scene, the system realizes a highly immersive and interactive museum experience. The virtual native digital human can adjust its guiding and explanation strategies in real - time according to the interaction behaviors of the audience, providing a personalized visit experience. At the same time, the digital twin module uses a multi - modal data fusion three - dimensional reconstruction algorithm to accurately replicate the details of collections and exhibition halls, enabling the audience to closely observe and study exhibits in a virtual environment. This kind of interaction system not only enriches the display means of the museum but also improves the audience's participation and satisfaction.

[0018] Second, through the distributed knowledge sharing algorithm, knowledge sharing and communication can be achieved among different metaverse museums, promoting the overall development of the museum industry. In addition, the system adaptive configuration module can automatically adjust the parameters of each module of the system according to the real-time changes of the environmental perception parameters, ensuring that the system can provide a good user experience in different environments. This flexibility and scalability enable the interactive system to meet the needs of future museum development and bring a richer and more diverse visiting experience to the audience.

[0019] Other advantages, objectives, and features of the present invention will be described to some extent in the subsequent specification, and to some extent, will be obvious to those skilled in the art based on the study of the following text, or can be learned from the practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or in the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings based on these drawings without creative efforts.

[0021] Figure 1 It is a flowchart of the operation of an interactive system for a metaverse museum. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention objective, the following will, in conjunction with the accompanying drawings and preferred embodiments, describe in detail the specific embodiments, structures, features, and their effects of the present invention as follows.

[0023] Embodiment 1

[0024] This embodiment describes that the metaverse museum focuses on displaying the historical cultures of ancient civilizations, including the cultural relics and scenes of different civilizations in ancient Egypt, ancient Greece, and ancient China. Users can freely shuttle through different exhibition halls in the virtual space, interact with virtual native digital humans, and deeply understand the development process and cultural characteristics of ancient civilizations.

[0025] According to the algorithm formula Construct virtual native digital humans. For example, when a user asks a question about the construction of the ancient Egyptian pyramids, the system extracts relevant feature vectors from the user's interactive behaviors such as voice and text inputs, such as question keywords and questioning tones. Suppose the extracted keyword feature vector A1 (corresponding to "pyramid construction") has a relatively high weight ω1 because this is an important knowledge point in ancient civilizations. The digital human answers through the knowledge stored by the knowledge fusion graph algorithm, and its knowledge fusion algorithm Among them, the knowledge entity feature vector E regarding the construction of the pyramid j (such as building materials, construction techniques, etc.) has a relatively large weight λ1 (such as building materials, construction techniques, etc.) because these knowledge sources are authoritative and have a large number of citations. The digital human finally outputs accurate and detailed answers, such as "The ancient Egyptian pyramids were mainly built with huge stones and used techniques such as slope transportation. Emotional perception and weight adjustment: During the communication between the user and the digital human, an incremental weight update algorithm is used to adjust the weights. For example, when the user expresses satisfaction with the digital human's answer about the construction of the pyramid and delves deeper into relevant details, the system determines the weight update factor R based on the time freshness of the sample (this interaction occurred recently) and the importance of the interaction (involving core knowledge points and high user interest). g is relatively high. Through the formula: The weight ω1 of the feature vector related to the pyramid construction is updated in real time, enabling the digital human to provide more accurate relevant knowledge in subsequent similar interactions.

[0026] For collections with complex textures such as ancient Egyptian mummy coffins, in the multi-modal data fusion three-dimensional reconstruction algorithm, in addition to the conventional correlation analysis to determine the weight σ, a texture detail enhancement coefficient K is introduced, and the texture data feature T is obtained through high-resolution photogrammetry k (such as the details of the mysterious patterns on the coffin), and the weight considering texture details is calculated Thereby generating a more realistic three-dimensional model. Users can clearly see the pattern textures on the coffin, as if they were in an ancient Egyptian tomb. For the structure of the ancient Greek temple exhibition hall with irregular geometric shapes, a shape adaptive fusion algorithm is adopted during the model fusion process. According to the geometric shape eigenvalue S corresponding to the data points of the exhibition hall structure k (such as the shape and layout of the temple columns, etc.) and the average value The difference is adjusted through the shape adaptive factor λ in the fusion function θ, that is So that the generated exhibition hall model can more accurately restore the architectural style of the ancient Greek temple. In the blockchain management of digital collections, an adaptive blockchain consensus algorithm is adopted. For the nodes participating in the consensus, in addition to the conventional performance evaluation, the stability and anti-attack ability of the nodes are also considered. By monitoring the running state of the nodes over a period of time, the node stability weight is calculated For example, if a certain node has small fluctuations in performance indicators during operation, its stability weight is relatively high, and its influence in the consensus process increases accordingly, ensuring the reliability of the blockchain management of digital collections.

[0027] When constructing an ancient sacrificial ceremony scene, in the physical-behavior coupling rendering algorithm, for the sacrificial utensils (such as the tripod in ancient China) and ritual action elements in the scene, the cultural symbol element feature vector, vector C, is determined through semantic analysis of relevant historical documents and archaeological researchr , add it to the physical-behavior feature vector F of the scene element r to obtain a new feature vector F r，new = [F r , C r . In the rendering function ζ, adopt the "Cultural Symbol Rendering Enhancement Algorithm". According to the importance weight C d (such as the high importance weight of the tripod in the sacrificial ceremony) and the rendering intensity I d , through the formula to make the scene rendering more cultural, and users can deeply feel the solemnity and sacredness of the ancient sacrificial ceremony.

[0028] The above is only a preferred embodiment of the present invention, and it is not a limitation of the present invention in any form. Although the present invention has been disclosed above with a preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments by using the disclosed technical content within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments based on the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An interactive system for a metaverse museum, characterized in that: The system includes the following components: virtual native digital human module, digital twin module of collections and exhibition halls, and virtual symbiosis module of scenes; The virtual native digital human module: constructs a virtual native digital human, and the algorithm formula is: N = φ (∑ i-1 (ω i ×A i )+β), where N represents the final behavior output of the digital human, A i is the i-th feature vector extracted from the audience interaction behavior, n is the number of feature vectors, ω i is the weight, β is the bias term, φ is the activation function, and a nonlinear activation function of a piecewise function is used. Different mappings are performed according to the urgency of the audience's interaction and the depth of the content. The neural network has a unique inter-layer connection structure, and the inter-layer connection weights are adjusted according to the complexity and importance of the exhibits in different areas of the museum. The knowledge storage of digital humans is based on the knowledge fusion graph algorithm. The algorithm first performs semantic analysis on knowledge data from various sources and extracts knowledge entities and relationships. The algorithm formula is: Where K represents the result of knowledge fusion, E j is the feature vector of the jth knowledge entity, m is the number of knowledge entities, and the weight λ j It is determined by evaluating the credibility of knowledge from different sources. The credibility evaluation is based on the authority of the knowledge publishing organization, the number of citations of research results, etc. μ is the initial knowledge bias, which is obtained by statistics on the knowledge related to the core exhibits of the museum, and γ is the fusion function; Digital twin modules of the collections and exhibition halls: The digital reproduction of the collections and exhibition halls adopts a multimodal data fusion 3D reconstruction algorithm, and the algorithm formula is: Where T is the generated 3D model, D k is the feature of the kth data point obtained by multimodal means of laser scanning, photogrammetry, and infrared imaging, p is the number of data points, and σ k is the weight, τ is the initial model parameter, θ is the fusion function, and for the blockchain management of digital collections, an adaptive blockchain consensus algorithm is used, and the algorithm formula is: Where C is the consensus result of the blockchain, V l is the voting vector of the lth node, q is the number of nodes, ρ l is the weight, ξ is the initial consensus parameter, ∈ is the consensus function; The virtual symbiosis module of the scene: The construction of the virtual scene adopts the physical behavior coupling rendering algorithm, and the algorithm formula is: Where S is the generated virtual scene, F r is the physical-behavioral feature vector of the rth scene element, s is the number of scene elements, η r is the weight, ω is the initial scene parameter, and ζ is the rendering function.

2. The interactive system of the Metaverse Museum according to claim 1, characterized in that: In the emotion perception neural network algorithm of the virtual native digital human module, the weight ω i The dynamic adjustment mechanism is as follows: During the operation of the system, as the audience interaction data continues to accumulate, an incremental weight update algorithm is used to adjust the weight in real time. The algorithm formula is: where ω i , t+1 and ω i , t are the weights at time t+1 and t respectively, α is the learning rate, G is the number of audience interaction data samples collected in the time interval, R g is the weight update factor of the g-th sample, which is determined according to the temporal freshness of the sample and the importance of the interaction. i，g is the value of the i-th eigenvector in the g-th sample, is the eigenvector A i historical average.

3. The interactive system of the Metaverse Museum according to claim 1, characterized in that: In the multimodal data fusion 3D reconstruction algorithm of the digital twin module of the collection and the exhibition hall, the model optimization method for different types of collections and exhibition hall structures is as follows: when processing collections with complex textures, in determining the weight σ k In addition to the correlation analysis, the texture detail enhancement coefficient is also introduced. For the texture data features obtained by high-resolution photogrammetry, the weight calculation formula is: where σ k，tex is the weight after considering texture details, κ is the texture detail enhancement coefficient, T k is the texture detail metric corresponding to the kth data point. For the pavilion structure with irregular geometric shapes, the shape adaptive fusion algorithm is used in the model fusion process. The shape adaptive factor is added to the θ function. The algorithm formula is: where θ new is the adjusted fusion function, λ is the shape adaptation coefficient, S k is the geometric shape eigenvalue corresponding to the kth data point, is the average of the geometric eigenvalues ​​of all data points.

4. The interactive system of the Metaverse Museum according to claim 1, characterized in that: In the adaptive blockchain consensus algorithm of the digital twin module of the collection and the exhibition hall, a supplementary method for node performance evaluation is described: the stability and anti-attack ability of the node are also considered. For the stability evaluation of the node, by monitoring the running status of the node within a certain period of time, the calculation formula of the node stability weight ρ1,stab is: Among them, M h，l is the hth performance indicator value of the lth node, It is the average value of the hth performance index of all nodes, H is the number of performance indicators, and for the evaluation of the node's anti-attack capability, a simulated attack test is used.

5. The interactive system of the metaverse museum according to claim 1, characterized in that: In the physical-behavior coupling rendering algorithm of the virtual symbiosis module of the scene, the physical-behavior feature vector F of the scene element is r Extension method: When constructing a virtual scene with a cultural ritual scene, in F r The cultural symbolic element features are added to the scene. For the sacrificial utensils and ritual action elements in the scene, the cultural symbolic element feature vector C r The new scene element physical-behavioral feature vector F is determined by semantic analysis of relevant historical documents and archaeological research. r，new The calculation formula is: r，new =[F r , C r ], in the rendering function ζ, the "cultural symbol rendering enhancement algorithm" is used, and the algorithm formula is: where ζ new is the adjusted rendering function, C d is the importance weight of the dth cultural symbolic element, I d is the rendering intensity of the dth cultural symbol element in the current scene.

6. The interactive system of the Metaverse Museum according to claim 1, characterized in that: The interactive system also includes a user experience feedback analysis module that uses a multi-dimensional user experience evaluation algorithm. The algorithm formula is: U = π (∑ c＝1 (φ e ×X e )+ψ), where U is the user experience evaluation result, X e is the feature vector of the e-th user experience dimension, o is the number of user experience dimensions, including but not limited to visual perception, interaction fluency, knowledge acquisition satisfaction, and weight φ e It is determined by factor analysis of the experience feedback data of a large number of users in different types of metaverse scenarios. ψ is the initial experience bias and π is the evaluation function.

7. The interactive system of the Metaverse Museum according to claim 1, characterized in that: The interactive system also includes a cross-museum interactive collaboration module that implements interactive collaboration between different metaverse museums based on a distributed knowledge sharing algorithm. The algorithm formula is: Where K is the result of cross-library knowledge sharing, Y n is the knowledge feature vector of the nth museum, r is the number of metaverse museums participating in the interactive collaboration, and the weight μ n The basis for determining is the authority and uniqueness of each library in a specific knowledge field, v is the initial knowledge sharing bias, and λ is the sharing function.

8. The interactive system of the Metaverse Museum according to claim 1, characterized in that: The interactive system also includes a system adaptive configuration module that uses an environment-aware adaptive configuration algorithm, and the algorithm formula is: Where A is the result of system configuration adjustment, Z s is the sth environmental perception parameter vector, t is the number of environmental perception parameters, and the weight ξ s It is determined by regression analysis of experimental data on the impact of different environmental parameters on system performance. η is the initial configuration bias and ω is the configuration function.

Images