Intangible cultural heritage digitization method and system

By establishing a standard library of intangible cultural heritage characteristics and a dynamic three-dimensional display model, combined with the LSTM neural network algorithm, dynamically adjusting the display of intangible cultural heritage, the problem of lack of multimodal interaction in the existing technology is solved, and the effect of multi-sensory fusion experience and deep cognition is achieved.

CN120353946AActive Publication Date: 2025-07-22SHISHENG CULTURAL DEVELOPMENT (SHANGHAI) CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Application Number
CN202510833640.9
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-06-20
Publication Date
2025-07-22
Estimated Expiration
2045-06-20

AI Technical Summary

Technical Problem

The existing digital technology of intangible cultural heritage lacks a multimodal interaction mechanism for spatial audio capture feedback and behavioral trajectory capture feedback, which makes it difficult for users to receive information in one direction, making it difficult to form cultural resonance and deep cognition through active participation, which weakens the attractiveness and educational effectiveness of display.

Method used

By extracting spatial audio and behavioral trajectory characteristics in intangible cultural heritage, establishing a feature standard library, using Autodesk Maya three-dimensional modeling software to build a dynamic three-dimensional display model, combining spatial audio acquisition devices and multi-view camera arrays for data acquisition, and quantitative evaluation of imitation behavior consistency based on LSTM neural network algorithm, dynamically adjusting the demonstration process and speed, and comprehensively assessing the viewer's acceptance level.

Benefits of technology

Multimodal human-computer interaction is realized, breaking through the interactive limitations of traditional static display, providing a dynamic imitation experience of multi-sensory fusion, and improving the viewer's sense of participation and cognition of intangible cultural heritage.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN120353946A_ABST
    Figure CN120353946A_ABST
Patent Text Reader

Abstract

The invention discloses an intangible cultural heritage digitization method and system, and relates to the field of intangible cultural heritage digitization, and the method comprises the steps: extracting spatial audio and behavior trajectory features in intangible cultural heritage, and building an intangible cultural heritage feature standard library; constructing an intangible cultural heritage dynamic three-dimensional display model fused with multi-modal data through three-dimensional modeling software; dynamically capturing spatial audio information and behavior tracks of the audience; through data comparison and analysis, performing quantitative evaluation on intangible cultural heritage imitation behavior consistency; dynamically adjusting the dynamic demonstration process of the intangible cultural heritage according to the consistency quantitative evaluation result; and comprehensively evaluating the acceptance level of the audience on the intangible cultural heritage imitation behavior according to the dynamic demonstration result. A three-dimensional dynamic modeling and real-time interaction technology is adopted to construct an intangible cultural heritage digital model, multi-sensory fusion dynamic simulation experience is achieved through man-machine interaction, and the interaction limitation of traditional static display is broken through.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the field of digitalization of intangible cultural heritage, and specifically to a method and system for digitalizing intangible cultural heritage. Background Art

[0002] Intangible cultural heritage is the carrier of national cultural genes, such as traditional music, dance, handicrafts, etc. Its inheritance depends on the oral instruction and personal guidance of the skill holders. However, due to the aging of inheritors, the gap in the audience, and geographical restrictions, there is a risk of the loss of skills. Traditional protection methods such as written records and static image archiving are difficult to completely preserve the dynamic characteristics of intangible cultural heritage such as spatial audio rhythm and behavioral trajectories, and lack interactivity, making it difficult to stimulate the interest of the younger generation.

[0003] Digitalization of intangible cultural heritage refers to the process of using digital technology to record, preserve, disseminate, innovate, and inherit intangible cultural heritage projects. With the development of digital technology, digital technology provides new opportunities for the protection of intangible cultural heritage. Through three-dimensional modeling, multi-modal data collection and analysis, three-dimensional recording, standardized inheritance, and multi-sensory integrated dissemination of intangible cultural heritage can be realized. Currently, the research on digitalization of intangible cultural heritage is gradually shifting from single-modal recording to multi-modal integration. However, existing technologies mostly focus on static display (such as 3D scanning of cultural relics), lacking interactive presentation of the dynamic process of intangible cultural heritage, resulting in users being able to only receive information unidirectionally, which is not conducive to the dissemination and inheritance of intangible cultural heritage.

[0004] Existing digital technologies for intangible cultural heritage mainly adopt static display and single-touch interaction. However, such technologies lack a multi-modal interaction mechanism for spatial audio capture feedback and behavioral trajectory capture feedback, as well as the adaptability of dynamic content to adjust the presentation rhythm according to the viewer's behavior, resulting in users being able to only receive information unidirectionally, making it difficult to form cultural resonance and in-depth understanding through active participation, thereby weakening the attractiveness and educational effectiveness of the display of intangible cultural heritage. Summary of the Invention

[0005] To solve the above technical problems, a method and system for digitalizing intangible cultural heritage are provided. The present technical solution solves the problem that the lack of a multi-modal interaction mechanism for spatial audio capture feedback and behavioral trajectory capture feedback, as well as the adaptability of dynamic content to adjust the presentation rhythm according to the viewer's behavior, results in users being able to only receive information unidirectionally, making it difficult to form cultural resonance and in-depth understanding through active participation, thereby weakening the attractiveness and educational effectiveness of the display of intangible cultural heritage as described in the above background art.

[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:

[0007] A method for digitalizing intangible cultural heritage, comprising: Based on the standard data of intangible cultural heritage projects, extract the spatial audio and behavioral trajectory features in intangible cultural heritage, and establish a standard library of intangible cultural heritage features; Based on the standard library of intangible cultural heritage features, use Autodesk Maya 3D modeling software to construct a dynamic 3D display model of intangible cultural heritage that integrates multi-modal data; Use a spatial audio acquisition device and a multi-view camera array to collect simultaneous sequential data, and realize the dynamic capture of the spatial audio information and behavioral trajectory of viewers; Based on the standard library of intangible cultural heritage features and the spatial audio and behavioral trajectory data of viewers, through data comparison and analysis, realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors; According to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors, dynamically adjust the process of dynamic demonstration of intangible cultural heritage; According to the results of the dynamic demonstration of intangible cultural heritage, comprehensively evaluate the acceptance level of viewers' imitation behaviors of intangible cultural heritage.

[0008] Preferably, the realizing the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors based on the standard library of intangible cultural heritage features and the spatial audio and behavioral trajectory data of viewers through data comparison and analysis specifically includes: Form input pairs by taking each sample in the test data set and the historical samples before and after the simultaneous sequential points in the target data set, and control the length of the target data window by adjusting the sliding window; Adopt a FIFO queue to dynamically adjust the length of the target data window, maintain the time continuity of the data in the window, and always retain the most recent standard sequential data; According to the length of the target data window, based on the DTW algorithm, calculate the DTW distance between the current observation value and each standard value in the window; Take the DTW distance values between each current observation value and each standard value in the window as input quantities, and the quantitative evaluation value of the consistency of intangible cultural heritage imitation behaviors as the output quantity; According to the attention mechanism, dynamically weight the contributions of the DTW distance values of the spatial audio and behavioral trajectory features in each intangible cultural heritage; Based on the LSTM neural network algorithm, establish a quantitative evaluation model for the consistency of intangible cultural heritage imitation behaviors, and dynamically evaluate the consistency of intangible cultural heritage imitation behaviors.

[0009] Preferably, the dynamically adjusting the process of dynamic demonstration of intangible cultural heritage according to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors specifically includes: According to the non-material cultural heritage imitation behavior consistency quantification evaluation model, obtain the non-material cultural heritage imitation behavior consistency quantification evaluation result and the DTW distance between the current observation value and each standard value within the window; According to the requirements of non-material cultural heritage imitation behavior consistency, set the boundary threshold of the DTW distance between the current observation value and each standard value within the window; Obtain the number of continuous occurrences of the DTW distance between the current observation value and each standard value within the window length within the boundary threshold; According to the number of continuous occurrences of the DTW distance for each standard value within each window length, dynamically adjust the process of non-material cultural heritage dynamic demonstration; According to the matching positions of the DTW distances for each standard value within each window length, establish a non-material cultural heritage dynamic demonstration speed adjustment model to dynamically adjust the non-material cultural heritage dynamic demonstration speed; The specific process of the above-mentioned dynamic adjustment of the non-material cultural heritage dynamic demonstration includes: The DTW distances for each standard value within each window length are divided into the first frames, the current frame, and the subsequent frames; If the continuity of each window length is within the first frames, it indicates that the non-material cultural heritage imitation behavior has temporal delay, and the speed of the non-material cultural heritage dynamic demonstration needs to be reduced; If the continuity of each window length is at the current frame, it indicates that the non-material cultural heritage imitation behavior has temporal consistency, and the non-material cultural heritage dynamic demonstration proceeds normally; If the continuity of each window length is within the subsequent frames, it indicates that the non-material cultural heritage imitation behavior has temporal lead, and the speed of the non-material cultural heritage dynamic demonstration needs to be increased; The expression of the non-material cultural heritage dynamic demonstration speed adjustment model is: ; In the formula, is the non-material cultural heritage dynamic demonstration speed adjustment value, , are the coefficients of the linear term and the quadratic term respectively, which can be obtained by the least squares method, is the average value of the DTW distance values of the window standard values, is the DTW distance value of the th window standard value, is the number of windows of the DTW distance values of the standard values, where takes a value of 1 or , is the sign selection function. ​

[0010] Preferably, the comprehensive evaluation of the acceptance level of the viewer's imitation behavior of intangible cultural heritage according to the dynamic demonstration results of intangible cultural heritage specifically includes: Obtain the evaluation results of the consistency of the imitation behavior of intangible cultural heritage and the adjustment results of the dynamic demonstration speed of intangible cultural heritage at the same time sequence, and establish a list of imitation behaviors at different time sequences; According to the list of imitation behaviors at different time sequences, based on the weighted formula, establish an evaluation model for the acceptance level of the viewer's imitation behavior of intangible cultural heritage; Through the evaluation model of the acceptance level of the viewer's imitation behavior of intangible cultural heritage, comprehensively evaluate the acceptance level of the viewer's imitation behavior of intangible cultural heritage; The expression of the evaluation model for the acceptance level of the viewer's imitation behavior of intangible cultural heritage is: ; In the formula, is the evaluation value of the acceptance level of the viewer's imitation behavior of intangible cultural heritage, , , are the weights of the evaluation results of the consistency of the imitation behavior of intangible cultural heritage, the adjustment value of the dynamic demonstration speed of intangible cultural heritage, and the adjustment frequency of the dynamic demonstration speed of intangible cultural heritage respectively, is the th evaluation value of the consistency of the imitation behavior of intangible cultural heritage, is the weight of the th adjustment of the dynamic demonstration speed of intangible cultural heritage, is the th adjustment value of the dynamic demonstration speed of intangible cultural heritage, is the average adjustment frequency of the dynamic demonstration speed of intangible cultural heritage, is the number of evaluation results of the consistency of the imitation behavior of intangible cultural heritage, is the number of adjustments of the dynamic demonstration speed of intangible cultural heritage.

[0011] Furthermore, this solution proposes a digital system for intangible cultural heritage, which is used to implement the digital method of intangible cultural heritage as described above, including: A standard library module, which is used to extract the spatial audio and behavior trajectory features in intangible cultural heritage based on the standard data of intangible cultural heritage projects, and establish a standard library of intangible cultural heritage features; A three-dimensional display module, which is used to construct a dynamic three-dimensional display model of intangible cultural heritage integrating multi-modal data through Autodesk Maya three-dimensional modeling software based on the standard library of intangible cultural heritage features; Dynamic capture environment module, which is used to collect simultaneous sequence data by using a spatial audio acquisition device and a multi-view camera array, so as to realize the dynamic capture of the spatial audio information and behavior trajectory of the viewer; Comprehensive evaluation module, which is used to realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors based on the intangible cultural heritage feature standard library and the viewer's spatial audio and behavior trajectory data through data comparison and analysis; dynamically adjust the process of the dynamic demonstration of intangible cultural heritage according to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors; comprehensively evaluate the acceptance level of the viewer's imitation behaviors of intangible cultural heritage according to the dynamic demonstration results of intangible cultural heritage.

[0012] Preferably, the comprehensive evaluation module includes: Consistency evaluation unit, which is used to realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors based on the intangible cultural heritage feature standard library and the viewer's spatial audio and behavior trajectory data through data comparison and analysis; Dynamic demonstration unit, which is used to dynamically adjust the process of the dynamic demonstration of intangible cultural heritage according to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors; Acceptance evaluation unit, which is used to comprehensively evaluate the acceptance level of the viewer's imitation behaviors of intangible cultural heritage according to the dynamic demonstration results of intangible cultural heritage.

[0013] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention provides a method for digitizing intangible cultural heritage. By extracting the spatial audio and behavioral trajectory features in intangible cultural heritage, a feature standard library of intangible cultural heritage is constructed. Secondly, according to the feature standard library of intangible cultural heritage and the spatial audio and behavioral trajectory data of viewers, through data comparison and analysis, based on the LSTM neural network algorithm, a quantitative evaluation model for the consistency of intangible cultural heritage imitation behavior is established to realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behavior. And according to the DTW distance of each standard value and the number of consecutive windows of each window length, the process of dynamic demonstration of intangible cultural heritage is dynamically adjusted. Thus, according to the matching position of the DTW distance of each standard value and the window length, a dynamic demonstration speed adjustment model of intangible cultural heritage is established to dynamically adjust the dynamic demonstration speed of intangible cultural heritage. Finally, according to the evaluation result of the consistency of intangible cultural heritage imitation behavior and the dynamic demonstration speed adjustment result of intangible cultural heritage at the same time series, based on the weighted formula, an evaluation model for the acceptance level of viewers' imitation behavior of intangible cultural heritage is established. Through the evaluation model, the acceptance level of viewers' imitation behavior of intangible cultural heritage is comprehensively evaluated, so as to achieve the purpose of constructing a digital model of intangible cultural heritage by using three-dimensional dynamic modeling and real-time interaction technology, and realizing a multi-sensory fusion dynamic imitation experience through multi-modal human-computer interaction, breaking through the interactive limitations of traditional static displays. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] Figure 1 is a flowchart of a method for digitizing intangible cultural heritage according to the present invention; Figure 2 is a flowchart of realizing the quantitative evaluation of the consistency of intangible cultural heritage imitation behavior according to the feature standard library of intangible cultural heritage and the spatial audio and behavioral trajectory data of viewers through data comparison and analysis according to the present invention; Figure 3 is a flowchart of dynamically adjusting the process of dynamic demonstration of intangible cultural heritage according to the quantitative evaluation result of the consistency of intangible cultural heritage imitation behavior according to the present invention; Figure 4 is a flowchart of comprehensively evaluating the acceptance level of viewers' imitation behavior of intangible cultural heritage according to the dynamic demonstration result of intangible cultural heritage according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0015] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0016] Referring to Figure 1 as shown, a method for digitizing intangible cultural heritage includes: Based on the standard data of intangible cultural heritage projects, extract the spatial audio and behavioral trajectory features in intangible cultural heritage, and establish a standard library of intangible cultural heritage features; Based on the standard library of intangible cultural heritage features, use Autodesk Maya 3D modeling software to construct a dynamic 3D display model of intangible cultural heritage that integrates multi-modal data; Use a spatial audio acquisition device and a multi-view camera array to collect simultaneous data, and realize the dynamic capture of the spatial audio information and behavioral trajectory of viewers; Based on the standard library of intangible cultural heritage features and the spatial audio and behavioral trajectory data of viewers, through data comparison and analysis, realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors; According to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors, dynamically adjust the process of the dynamic demonstration of intangible cultural heritage; According to the results of the dynamic demonstration of intangible cultural heritage, comprehensively evaluate the acceptance level of viewers' imitation behaviors of intangible cultural heritage.

[0017] It can be explained that due to the use of static displays and single-touch interactions in traditional technologies, users can only receive information unidirectionally and it is difficult to form cultural resonance and in-depth understanding through active participation. Therefore, this solution creates a multi-modal human-computer interaction to achieve a multi-sensory fusion dynamic imitation experience by quantitatively evaluating the consistency of intangible cultural heritage imitation behaviors, dynamically adjusting the process of the dynamic demonstration of intangible cultural heritage, and comprehensively evaluating the acceptance level of viewers' imitation behaviors of intangible cultural heritage. Through the real-time interaction between the standard library of intangible cultural heritage features and the spatial audio and behavioral trajectory data of viewers, dynamically and comprehensively evaluate the acceptance level of viewers' imitation behaviors of intangible cultural heritage, so as to break through the limitations of the interactivity of traditional static displays.

[0018] The specific steps of extracting the spatial audio and behavioral trajectory features in intangible cultural heritage and establishing a standard library of intangible cultural heritage features based on the standard data of intangible cultural heritage projects are as follows: According to the categories of intangible cultural heritage projects, use professional audio and behavioral trajectory acquisition devices to obtain the standard data of intangible cultural heritage projects; According to the standard data of intangible cultural heritage projects, extract the spatial audio and behavioral trajectory features in intangible cultural heritage; Among them, the spatial audio features include: time-domain features, frequency-domain features, and MFCC features, and the behavioral trajectory features include: the starting point, ending point, amplitude, speed of the action, as well as the coordinates, direction, and curvature of the trajectory; Normalize the spatial audio and behavioral trajectory feature data in intangible cultural heritage to eliminate the influence of data dimensions; Based on the filtering algorithm, filter and denoise the spatial audio and behavioral trajectory feature data in the intangible cultural heritage; Establish a feature standard library for intangible cultural heritage to store the category of intangible cultural heritage projects, text introductions, spatial audio features, and behavioral trajectory feature data.

[0019] It can be explained that to ensure the accuracy of the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors, it is necessary to accurately extract the spatial audio and behavioral trajectory features and feature data in the intangible cultural heritage. Through the comparison and analysis of the intangible cultural heritage feature standard data and the spatial audio and behavioral trajectory feature data of the viewers, the consistency of intangible cultural heritage imitation behaviors can be effectively quantified and evaluated. Therefore, this solution extracts the spatial audio and behavioral trajectory features in the intangible cultural heritage according to the standard data of intangible cultural heritage projects. Among them, the spatial audio is extracted by splitting the spatial audio data into time-domain features and frequency-domain features through wavelet transform or Fourier transform, and the MFCC features reflecting the auditory perception characteristics of the human ear are extracted through the Mel Frequency Cepstral Coefficient (MFCC) algorithm to comprehensively cover the time-frequency structure and perception characteristics of the audio. At the same time, for the behavioral trajectory features, three-dimensional spatial coordinate data is collected through a multi-view camera array, and spatio-temporal dynamic features such as trajectory speed, acceleration, and joint angles are extracted by combining key point detection and kinematic modeling, and finally a joint feature representation of spatial audio and behavioral trajectory is formed, providing a standardized data basis for subsequent dynamic modeling and quantitative evaluation of intangible cultural heritage.

[0020] Based on the intangible cultural heritage feature standard library, constructing a dynamic three-dimensional display model of intangible cultural heritage that integrates multi-modal data through Autodesk Maya three-dimensional modeling software specifically includes: According to the category of intangible cultural heritage projects, based on Autodesk Maya three-dimensional modeling software, build the scenes of the intangible cultural heritage project categories respectively; According to the intangible cultural heritage feature standard library, convert the format of the spatial audio and behavioral trajectory feature data in the intangible cultural heritage into a format recognizable by Autodesk Maya; According to the intangible cultural heritage feature standard library, based on Autodesk Maya three-dimensional modeling software, construct a dynamic three-dimensional display model of intangible cultural heritage that integrates multi-modal data.

[0021] It can be explained that Autodesk Maya is an industrial-grade 3D computer graphics software developed by Autodesk. It is widely used in fields such as film and television animation, game development, virtual reality (VR), architectural visualization, and industrial design. One of its core functions is 3D modeling, that is, creating, editing, and optimizing the geometric shapes and structures of 3D objects or scenes through software tools. Through polygon modeling, NURBS modeling, and sculpting tools, it can completely retain the geometric forms, texture details, and spatial structures of traditional handicrafts, architectural components, performance props, etc., forming digital assets that can be permanently stored. And through the Maya animation production system, keyframe animations and motion capture data of traditional dance movements, martial arts moves, handicraft production processes, etc. can be constructed. By importing data such as intangible cultural heritage project categories, text introductions, spatial audio features, and behavioral trajectory features, functions such as digital recording of technical actions can be realized.

[0022] The simultaneous data acquisition using the spatial audio acquisition device and the multi-view camera array to achieve dynamic capture of the spatial audio information and behavioral trajectories of viewers specifically includes: Using the spatial audio acquisition device and the multi-view camera array to construct a multi-sensory fusion intangible cultural heritage imitation environment; Applying the simultaneous data acquisition technology to synchronously capture the spatial audio signals and behavioral movement trajectory data of viewers during intangible cultural heritage imitation under a unified time reference; Under the same time reference, for the dynamic 3D display model of intangible cultural heritage that integrates multi-modal data, synchronously collect the spatial audio and behavioral movement trajectory data in the model; Respectively use the spatial audio signals and behavioral movement trajectory data during imitation as the test data set, and the spatial audio and behavioral movement trajectory data in the model as the target data set.

[0023] It can be explained that in the digital protection and interactive experience of intangible cultural heritage, realizing the real-time interaction between dynamic 3D display data and the spatial audio and behavioral trajectory data of viewers is a key technical link. To achieve this goal, it is necessary to construct a multi-modal synchronous acquisition system during the data acquisition stage to ensure that the dynamic 3D data of intangible cultural heritage and the interactive data of viewers (spatial audio, behavioral trajectory) are strictly aligned on the same time benchmark, so as to ensure the spatio-temporal consistency, accuracy, and reliability of the data. At the same time, it provides data support for dynamically adjusting the process of the dynamic demonstration of intangible cultural heritage in the future. Therefore, this solution uses a spatial audio acquisition device and a multi-view camera array to construct a multi-sensory fusion intangible cultural heritage imitation environment, and applies the simultaneous time-series data acquisition technology to synchronously capture the spatial audio signals and behavioral movement trajectory data of viewers during the imitation of intangible cultural heritage under the unified time benchmark, and at the same time benchmark, for the dynamic 3D display model of intangible cultural heritage that integrates multi-modal data, synchronously acquire the spatial audio and behavioral movement trajectory data in the model, so as to complete the acquisition of simultaneous time-series data.

[0024] Refer to Figure 2 As shown, the specific quantification evaluation of the consistency of intangible cultural heritage imitation behaviors based on the intangible cultural heritage feature standard library and the spatial audio and behavioral trajectory data of viewers through data comparison and analysis includes: Each sample in the test data set and the historical samples before and after the simultaneous time-series points in the target data set constitute an input pair, and by adjusting the sliding window, the length of the target data window is controlled; Adopt a FIFO queue to dynamically adjust the length of the target data window to maintain the time continuity of the data in the window and always retain the most recent standard time-series data; According to the length of the target data window, based on the DTW algorithm, calculate the DTW distance between the current observation value and each standard value in the window; Take the DTW distance values between each current observation value and each standard value in the window as input quantities, and the quantification evaluation value of the consistency of intangible cultural heritage imitation behaviors as the output quantity; According to the attention mechanism, dynamically weight the contributions of the DTW distance values of the spatial audio and behavioral trajectory features in each intangible cultural heritage; Based on the LSTM neural network algorithm, establish a quantification evaluation model for the consistency of intangible cultural heritage imitation behaviors to dynamically evaluate the consistency of intangible cultural heritage imitation behaviors.

[0025] It can be explained that when the viewer imitates the intangible cultural heritage, due to the errors in the hardware and actions, the spatial audio and behavioral trajectory data deviate, resulting in the inconsistency between the standard library of intangible cultural heritage features with strict same time sequence and the viewer's spatial audio and behavioral trajectory data. This leads to inaccurate results in the consistency evaluation of the imitation behavior of intangible cultural heritage, thus affecting the subsequent data support. Therefore, in this solution, each sample of the test data set and historical samples before and after the same time sequence point in the target data set form an input pair. By associating several data in the target data set before and after the same time sequence in the test data set, the fault tolerance of the model to the delay or advance phenomenon of the viewer's imitation behavior is improved, and the accuracy and reliability of the consistency quantitative evaluation model of the imitation behavior of intangible cultural heritage for the imitation behavior of intangible cultural heritage are improved. Among them, The expression of the LSTM neural network algorithm is as follows: The forgetting gate adopts: The input gate adopts: The candidate memory adopts: The memory update adopts: The output gate adopts: The hidden state adopts: In the formula, , , , , , , , are weight matrices, , , , are bias vectors, is the Sigmoid function, is the DTW distance value weighted by the attention mechanism, is the hyperbolic tangent function, ; Through the Softmax activation function of the fully connected layer, the hidden state data is mapped to the output label space to obtain the probability distribution of the output label, that is, the consistency evaluation value of the imitation behavior of intangible cultural heritage; The expression of the consistency evaluation value of the imitation behavior of intangible cultural heritage is: ; In the formula, The th consistency evaluation value of the imitation behavior of intangible cultural heritage, is the weight matrix, is the bias vector.

[0026] Reference Figure 3 As shown, the process of dynamically adjusting the dynamic demonstration of intangible cultural heritage according to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors specifically includes: According to the quantitative evaluation model of the consistency of intangible cultural heritage imitation behaviors, obtain the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors and the DTW distances between the current observation value and each standard value within the window; According to the requirements for the consistency of intangible cultural heritage imitation behaviors, set the boundary threshold of the DTW distances between the current observation value and each standard value within the window; Obtain the number of continuous occurrences of the DTW distances between the current observation value and each standard value within the window lengths within the boundary threshold range for each time series; Dynamically adjust the process of the dynamic demonstration of intangible cultural heritage according to the number of continuous occurrences of the DTW distances for each standard value within the window lengths; Establish a dynamic demonstration speed adjustment model for intangible cultural heritage according to the matching positions of the DTW distances for each standard value within the window lengths, and dynamically adjust the dynamic demonstration speed of intangible cultural heritage; The process of dynamically adjusting the dynamic demonstration of intangible cultural heritage specifically includes: The DTW distances for each standard value within the window lengths are divided into the first frames, the current frame, and the subsequent frames; If the continuity of each window length is within the first frames, it indicates that the intangible cultural heritage imitation behavior has a time series delay, and the speed of the dynamic demonstration of intangible cultural heritage needs to be reduced; If the continuity of each window length is at the current frame, it indicates that the intangible cultural heritage imitation behavior has a time series consistency, and the dynamic demonstration of intangible cultural heritage is carried out normally; If the continuity of each window length is within the subsequent frames, it indicates that the intangible cultural heritage imitation behavior has a time series lead, and the speed of the dynamic demonstration of intangible cultural heritage needs to be increased; The expression of the dynamic demonstration speed adjustment model for intangible cultural heritage: ; In the formula, is the dynamic demonstration speed adjustment value for intangible cultural heritage, , are the coefficients of the linear term and the quadratic term respectively, which can be obtained by the least squares method, is the average value of the DTW distance values of the window standard values, is the DTW distance value of the th window standard value, The number of windows of the DTW distance value for the standard value, where, takes a value of 1 or , is the symbol selection function.

[0027] It can be explained that through the number of continuous window lengths of the DTW distance of each standard value, the dynamic demonstration of intangible cultural heritage can be effectively adjusted according to the spatial audio and behavioral trajectory characteristic data generated by the viewer. By dividing the window lengths of the DTW distance of the standard value into the first frames, the current frame, and the subsequent frames, the dynamic demonstration speed of the intangible cultural heritage is dynamically adjusted according to the range where the window length continuity is located. Therefore, in this solution, by establishing a dynamic demonstration speed adjustment model for intangible cultural heritage, the dynamic demonstration speed of intangible cultural heritage is dynamically adjusted. Among them, through the dynamic demonstration speed adjustment model of intangible cultural heritage, the dynamic demonstration speed adjustment value of intangible cultural heritage is obtained. By dynamically adjusting the comparison result of the dynamic demonstration process of intangible cultural heritage, the symbol of the symbol selection function is set, where, ; Among them, the "consistency requirement" refers to the degree of compliance that the imitation behavior of intangible cultural heritage and the standard behavior need to achieve in terms of timing and feature matching. On the one hand, the timing consistency requirement means that the imitation behavior and the standard behavior are synchronized in time. On the other hand, the feature matching consistency requirement means the consistency of the similarity between the imitation behavior features and the standard behavior features. Through the timing consistency and feature matching consistency, the state of the imitation behavior is comprehensively judged, so as to dynamically adjust the process of the dynamic demonstration of intangible cultural heritage. Among them, the imitation behavior states include: delay, consistency, and advance.

[0028] Referring to Figure 4 as shown, the comprehensive evaluation of the acceptance level of the viewer for the imitation behavior of intangible cultural heritage based on the dynamic demonstration result of intangible cultural heritage specifically includes: Obtain the consistency evaluation result of the imitation behavior of intangible cultural heritage and the dynamic demonstration speed adjustment result under the same time sequence, and establish a list of imitation behaviors under different time sequences; According to the list of imitation behaviors under different time sequences, based on the weighted formula, establish an evaluation model for the acceptance level of the viewer for the imitation behavior of intangible cultural heritage; Through the evaluation model of the acceptance level of the viewer for the imitation behavior of intangible cultural heritage, comprehensively evaluate the acceptance level of the viewer for the imitation behavior of intangible cultural heritage; The expression of the evaluation model for the acceptance level of the viewer for the imitation behavior of intangible cultural heritage is: ; In the formula, is the evaluation value of the acceptance level of the intangible cultural heritage imitation behavior by the viewer, , , are the weights of the evaluation result of the consistency of the intangible cultural heritage imitation behavior, the adjustment value of the dynamic demonstration speed of the intangible cultural heritage, and the adjustment frequency of the dynamic demonstration speed of the intangible cultural heritage respectively, is the -th evaluation value of the consistency of the intangible cultural heritage imitation behavior, is the -th weight of the adjustment of the dynamic demonstration speed of the intangible cultural heritage, is the -th adjustment value of the dynamic demonstration speed of the intangible cultural heritage, is the average adjustment frequency of the dynamic demonstration speed of the intangible cultural heritage, is the number of evaluation results of the consistency of the intangible cultural heritage imitation behavior, is the number of adjustments of the dynamic demonstration speed of the intangible cultural heritage.

[0029] It can be explained that the comprehensive evaluation of the acceptance level of the intangible cultural heritage imitation behavior by the viewer is correlated with the evaluation result of the consistency of the intangible cultural heritage imitation behavior, the adjustment value of the dynamic demonstration speed of the intangible cultural heritage, and the adjustment frequency of the dynamic demonstration speed of the intangible cultural heritage. In this solution, an evaluation model for the acceptance level of the intangible cultural heritage imitation behavior by the viewer is constructed through a weighted formula to comprehensively evaluate the acceptance level of the intangible cultural heritage imitation behavior by the viewer. Among them, is the -th weight of the adjustment of the dynamic demonstration speed of the intangible cultural heritage, , the above formula dynamically sets the weight of the adjustment of the dynamic demonstration speed of the intangible cultural heritage according to the adjustment value of the dynamic demonstration speed of the intangible cultural heritage. Among them, , , are fixed constants, so as to ensure the weights of the dynamic adjustment of the dynamic demonstration speed of different intangible cultural heritages, thereby improving the evaluation accuracy and reliability of the evaluation model for the acceptance level of the intangible cultural heritage imitation behavior by the viewer.

[0030] Furthermore, based on the same inventive concept as the above intangible cultural heritage digitization method, this solution proposes an intangible cultural heritage digitization system, including: A standard library module, which is used to extract the spatial audio and behavior trajectory features in the intangible cultural heritage based on the standard data of the intangible cultural heritage project and establish an intangible cultural heritage feature standard library; A three-dimensional display module, which is used to construct a dynamic three-dimensional display model of intangible cultural heritage integrating multi-modal data based on the intangible cultural heritage feature standard library through Autodesk Maya three-dimensional modeling software; A dynamic capture environment module, which is used to use a spatial audio acquisition device and a multi-view camera array to collect simultaneous sequence data, and realize the dynamic capture of the spatial audio information and behavior trajectory of the viewer; A comprehensive evaluation module, which is used to realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors based on the intangible cultural heritage feature standard library and the viewer's spatial audio and behavior trajectory data through data comparison and analysis; according to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors, dynamically adjust the process of the dynamic demonstration of intangible cultural heritage; according to the results of the dynamic demonstration of intangible cultural heritage, comprehensively evaluate the acceptance level of the viewer's imitation behaviors of intangible cultural heritage.

[0031] The comprehensive evaluation module includes: A consistency evaluation unit, which is used to realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors based on the intangible cultural heritage feature standard library and the viewer's spatial audio and behavior trajectory data through data comparison and analysis; A dynamic demonstration unit, which is used to dynamically adjust the process of the dynamic demonstration of intangible cultural heritage according to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors; An acceptance evaluation unit, which is used to comprehensively evaluate the acceptance level of the viewer's imitation behaviors of intangible cultural heritage according to the results of the dynamic demonstration of intangible cultural heritage.

[0032] In summary, the advantages of the present invention are as follows: A digital model of intangible cultural heritage is constructed by using three-dimensional dynamic modeling and real-time interaction technology, and a multi-sensory fusion dynamic imitation experience is realized through human-computer interaction, breaking through the interactive limitations of traditional static displays.

[0033] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art of this industry should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection claimed by the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for digitizing intangible cultural heritage, characterized in that, Including: Based on the standard data of intangible cultural heritage projects, extract the spatial audio and behavior trajectory features in intangible cultural heritage, and establish a standard library of intangible cultural heritage features; Based on the standard library of intangible cultural heritage features, use Autodesk Maya 3D modeling software to construct a dynamic 3D display model of intangible cultural heritage that integrates multi-modal data; Use a spatial audio acquisition device and a multi-view camera array to collect simultaneous data, and realize the dynamic capture of the spatial audio information and behavior trajectory of viewers; Based on the standard library of intangible cultural heritage features and the spatial audio and behavior trajectory data of viewers, through data comparison and analysis, realize the quantitative evaluation of the consistency of intangible cultural heritage imitation behaviors; According to the quantitative evaluation results of the consistency of intangible cultural heritage imitation behaviors, dynamically adjust the process of the dynamic demonstration of intangible cultural heritage; According to the results of the dynamic demonstration of intangible cultural heritage, comprehensively evaluate the acceptance level of viewers for intangible cultural heritage imitation behaviors.

2. The digitalization method of intangible cultural heritage according to claim 1, characterized in that, The specific steps of extracting the spatial audio and behavior trajectory features in intangible cultural heritage and establishing a standard library of intangible cultural heritage features based on the standard data of intangible cultural heritage projects include: According to the categories of intangible cultural heritage projects, use professional audio and behavior trajectory acquisition devices to obtain the standard data of intangible cultural heritage projects; According to the standard data of intangible cultural heritage projects, extract the spatial audio and behavior trajectory features in intangible cultural heritage; Among them, the spatial audio features include: time domain features, frequency domain features and MFCC features, and the behavior trajectory features include: the starting point, ending point, amplitude, speed of the action, as well as the coordinates, direction and curvature of the trajectory; Normalize the spatial audio and behavior trajectory feature data in intangible cultural heritage to eliminate the influence of data dimensions; Based on the filtering algorithm, filter and denoise the spatial audio and behavior trajectory feature data in intangible cultural heritage; Establish a standard library of intangible cultural heritage features to store the categories of intangible cultural heritage projects, text introductions, spatial audio features and behavior trajectory feature data.

3. The digitalization method of intangible cultural heritage according to claim 2, characterized in that The specific steps of constructing a dynamic 3D display model of intangible cultural heritage that integrates multi-modal data based on the standard library of intangible cultural heritage features through Autodesk Maya 3D modeling software include: According to the categories of intangible cultural heritage projects, based on Autodesk Maya 3D modeling software, build the scenes of different categories of intangible cultural heritage projects respectively; According to the standard library of intangible cultural heritage features, convert the format of the spatial audio and behavior trajectory feature data in intangible cultural heritage into a format recognizable by Autodesk Maya; According to the standard library of intangible cultural heritage features, based on Autodesk Maya 3D modeling software, construct a dynamic 3D display model of intangible cultural heritage that integrates multi-modal data.

4. The digitalization method of intangible cultural heritage according to claim 3, characterized in that, The specific steps of using a spatial audio acquisition device and a multi-view camera array to collect simultaneous data and realizing the dynamic capture of the spatial audio information and behavior trajectory of viewers include: Construct a multi-sensory fusion intangible cultural heritage imitation environment using a spatial audio acquisition device and a multi-view camera array; Apply the simultaneous time-series data acquisition technology to synchronously capture the spatial audio signal and the behavioral movement trajectory data of the viewer during the intangible cultural heritage imitation under a unified time reference; Under the same time reference, for the dynamic three-dimensional display model of the intangible cultural heritage that fuses multi-modal data, synchronously collect the spatial audio and behavioral movement trajectory data in the model; Use the spatial audio signal and the behavioral movement trajectory data during imitation as the test data set, and the spatial audio and behavioral movement trajectory data in the model as the target data set respectively.

5. A method for digitizing intangible cultural heritage according to claim 4, characterized in that The specific implementation of the quantitative evaluation of the consistency of the intangible cultural heritage imitation behavior based on the intangible cultural heritage feature standard library and the viewer's spatial audio and behavioral trajectory data through data comparison and analysis includes: For each sample in the test dataset, an input pair is formed by combining it with the historical samples before and after the same-time sequence points in the target dataset. By adjusting the sliding window, the length of the target data window is controlled. Adopt a FIFO queue to dynamically adjust the length of the target data window, maintain the time continuity of the data within the window, and always retain the most recent standard timing data; Based on the DTW algorithm, calculate the DTW distance between the current observation value and each standard value within the window according to the target data window length; Use the DTW distance values between each current observation value and each standard value within the window as the input quantity, and the quantitative evaluation value of the consistency of the intangible cultural heritage imitation behavior as the output quantity; According to the attention mechanism, dynamically weight the contributions of the DTW distance values of the spatial audio and behavioral trajectory features in each intangible cultural heritage; Based on the LSTM neural network algorithm, establish a quantitative evaluation model for the consistency of the intangible cultural heritage imitation behavior to dynamically evaluate the consistency of the intangible cultural heritage imitation behavior.

6. The digitalization method of intangible cultural heritage according to claim 5, wherein, The specific implementation of dynamically adjusting the process of the intangible cultural heritage dynamic demonstration according to the quantitative evaluation result of the consistency of the intangible cultural heritage imitation behavior includes: According to the quantitative evaluation model of the consistency of the intangible cultural heritage imitation behavior, obtain the quantitative evaluation result of the consistency of the intangible cultural heritage imitation behavior and the DTW distance between the current observation value and each standard value within the window; Set the boundary threshold of the DTW distance between the current observation value and each standard value within the window according to the requirements of the consistency of the intangible cultural heritage imitation behavior; Obtain within the boundary threshold range The number of continuous occurrences of the DTW distances between each current observation value of the time series within the boundary threshold range and each standard value within the window for each window length Dynamically adjust the process of the intangible cultural heritage dynamic demonstration according to the number of continuous windows of the DTW distance of each standard value; Establish a dynamic demonstration speed adjustment model for the intangible cultural heritage based on the matching position of the DTW distance of each standard value for each window length, and dynamically adjust the dynamic demonstration speed of the intangible cultural heritage; The specific implementation of dynamically adjusting the process of the intangible cultural heritage dynamic demonstration includes: The DTW distances of the standard values are divided into the first frame, the current frame, and the subsequent frame; If the continuity of each window length is within the previous frame, it indicates that the imitation behavior of intangible cultural heritage has a time sequence delay, and it is necessary to reduce the speed of the dynamic demonstration of intangible cultural heritage; If the continuity of each window length is on the current frame, it means that the intangible cultural heritage imitation behavior has temporal consistency, and the dynamic demonstration of the intangible cultural heritage proceeds normally; If the continuity of each window length is later within the frame, it means that the imitation behavior of intangible cultural heritage has time series lead, and the speed of dynamic demonstration of intangible cultural heritage needs to be increased; The expression of the dynamic demonstration speed adjustment model of the intangible cultural heritage: ; In the formula, is the adjustment value of the dynamic demonstration speed of the intangible cultural heritage, , are the coefficients of the linear term and the quadratic term respectively, which can be obtained by the least squares method, is the average value of the DTW distance values of the window standard values, is the th DTW distance value of the window standard value, is the number of windows of the DTW distance value of the standard value, where takes the value of 1 or , is the symbol selection function.

7. A method for digitizing intangible cultural heritage according to claim 6, characterized in that The specific implementation of comprehensively evaluating the acceptance level of the viewer for the intangible cultural heritage imitation behavior according to the dynamic demonstration result of the intangible cultural heritage includes: Obtain the evaluation result of the consistency of the intangible cultural heritage imitation behavior and the dynamic demonstration speed adjustment result of the intangible cultural heritage under the same time series, and establish a list of imitation behaviors under different time series; Based on the list of imitation behaviors under different time series and the weighted formula, establish an evaluation model for the acceptance level of the viewer for the intangible cultural heritage imitation behavior. Through an evaluation model of the acceptance level of the imitative behavior of intangible cultural heritage by viewers, comprehensively evaluate the acceptance level of the imitative behavior of intangible cultural heritage by viewers; The expression of the evaluation model of the acceptance level of the imitative behavior of intangible cultural heritage by viewers is: ; Wherein, is the evaluation value of the viewer's acceptance level of the intangible cultural heritage imitation behavior, , , are respectively the weights of the consistency evaluation result of the intangible cultural heritage imitation behavior, the adjustment value of the intangible cultural heritage dynamic demonstration speed, and the adjustment frequency of the intangible cultural heritage dynamic demonstration speed, is the -th consistency evaluation value of the intangible cultural heritage imitation behavior, is the weight of the -th adjustment of the intangible cultural heritage dynamic demonstration speed, is the -th adjustment value of the intangible cultural heritage dynamic demonstration speed, is the average adjustment frequency of the intangible cultural heritage dynamic demonstration speed, is the number of consistency evaluation results of the intangible cultural heritage imitation behavior, is the number of adjustments of the intangible cultural heritage dynamic demonstration speed.

8. A digital system for intangible cultural heritage, characterized in that, Used to implement the intangible cultural heritage digitization method described in any one of claims 1-7, including: A standard library module, which is used to extract the spatial audio and behavior trajectory features in intangible cultural heritage based on the standard data of intangible cultural heritage projects, and establish a standard library of intangible cultural heritage features; A 3D display module, which is used to construct a dynamic 3D display model of intangible cultural heritage integrating multi-modal data through Autodesk Maya 3D modeling software based on the standard library of intangible cultural heritage features; A dynamic capture environment module, which is used to use a spatial audio acquisition device and a multi-view camera array to collect simultaneous sequence data to realize the dynamic capture of the spatial audio information and behavior trajectory of viewers; A comprehensive evaluation module, which is used to realize the quantitative evaluation of the consistency of the imitative behavior of intangible cultural heritage through data comparison and analysis based on the standard library of intangible cultural heritage features and the spatial audio and behavior trajectory data of viewers; according to the quantitative evaluation result of the consistency of the imitative behavior of intangible cultural heritage, dynamically adjust the process of the dynamic demonstration of intangible cultural heritage; according to the dynamic demonstration result of intangible cultural heritage, comprehensively evaluate the acceptance level of the imitative behavior of intangible cultural heritage by viewers.

9. The digital system for intangible cultural heritage according to claim 8, characterized in that, The comprehensive evaluation module includes: A consistency evaluation unit, which is used to realize the quantitative evaluation of the consistency of the imitative behavior of intangible cultural heritage through data comparison and analysis based on the standard library of intangible cultural heritage features and the spatial audio and behavior trajectory data of viewers; A dynamic demonstration unit, which is used to dynamically adjust the process of the dynamic demonstration of intangible cultural heritage according to the quantitative evaluation result of the consistency of the imitative behavior of intangible cultural heritage; An acceptance evaluation unit, which is used to comprehensively evaluate the acceptance level of the imitative behavior of intangible cultural heritage by viewers according to the dynamic demonstration result of intangible cultural heritage.

Citation Information

Patent Citations

  • Digitalization method for intangible cultural heritage

    CN104036091A

  • Information display method and device and related equipment

    CN118609598A

  • Method and Apparatus for Providing Audio Motion Feedback in a Simulated Three-Dimensional Environment

    US20090285407A1