Digital twinning method and system based on text travel industry
The digital twin model is constructed through sensor networks and three-dimensional modeling technology, combined with machine learning and time series analysis, and the problems of insufficient data collection and inaccurate prediction in the cultural and tourism industry are solved, intelligent management and decision-making support of facilities are realized, and operational efficiency and tourist experience are improved.
Patent Information
- Application Number
- CN202510371882.0
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-03-27
- Publication Date
- 2025-07-22
AI Technical Summary
In the cultural and tourism industry, physical facilities management lacks systematic data collection methods, and data real-time and accuracy are insufficient. Traditional prediction methods are backward, resulting in frequent facility failures, affected tourist experience and increased operating costs.
The sensor network is used to collect physical data from cultural and tourism facilities, combine three-dimensional modeling technology to build a three-dimensional geometric model, collect dynamic data in real time, and optimize the digital twin model using machine learning and time series analysis algorithms to generate future operating status reports, providing a basis for decision-making.
It has realized all-round data-driven management of cultural and tourism facilities, improved scientific and forward-looking decision-making, ensured the safe and stable operation of the facilities, and improved the tourist experience and operation efficiency.
Smart Images
Figure CN120354483A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of cultural and tourism digital twins, and specifically relates to a digital twin method and system based on the cultural and tourism industry. Background Technique
[0002] The cultural and tourism industry is an industry formed by utilizing the development of cultural tourism resources to meet people's cultural tourism needs. It attracts people with regional cultural differences, takes cultural conflicts and exchanges as the process, and takes cultural integration as the ultimate goal. It has national characteristics, artistry, mystery, diversity and interactivity. With the rapid development of the cultural and tourism industry, people have put forward higher requirements for the quality of cultural and tourism experiences and management efficiency.
[0003] Under the traditional operation system of the cultural and tourism industry, the management of physical cultural and tourism facilities faces many difficulties. First of all, there are serious shortcomings in data acquisition and integration. On the one hand, for the physical data of cultural and tourism facilities, such as building structure parameters, facility layout information, and equipment operation parameters, there are no systematic and comprehensive collection methods, making it difficult to accurately evaluate the overall condition of the facilities. For example, for cultural and tourism facilities of ancient architecture type, their building structures have gone through years of changes, and potential structural safety hazards are difficult to detect due to the lack of continuous and accurate data monitoring. On the other hand, in terms of dynamic data collection, such as tourist flow data, facility usage frequency data, and environmental monitoring data, traditional methods often rely on manual statistics or simple counting devices, greatly reducing the timeliness and accuracy of the data. Taking tourist flow statistics as an example, traditional manual counting cannot grasp the distribution and movement trends of tourists in each area in real time, making it difficult to provide timely and effective support for operation decisions.
[0004] Backward prediction means is another major problem. Traditional predictions are mostly based on limited experience and simple statistical analysis, and cannot fully explore the potential laws in a large amount of historical data. When predicting the future operation status of cultural and tourism facilities, the prediction accuracy of key elements such as equipment failures, peak tourist flow periods, and facility maintenance needs is low, making it difficult for decision-makers to plan countermeasures in advance, resulting in frequent facility failures, affected tourist experiences, and increased operation costs. Summary of the Invention
[0005] To solve the above technical problems, a digital twin method and system based on the cultural and tourism industry are provided, and the present technical solution solves the above problems.
[0006] To achieve the above objectives, the technical solution adopted by the present invention is as follows:
[0007] A digital twin method and system based on the cultural and tourism industry, including the following steps:
[0008] S1. Collect various physical data of cultural and tourism facilities, including but not limited to building structure parameters, facility layout information, and equipment operation parameters, and use 3D modeling technology to construct a 3D geometric model of the cultural and tourism facilities;
[0009] S2. Establish an attribute database for the cultural and tourism facilities, associate the collected physical data with the 3D geometric model, and form a preliminary digital twin model.
[0010] S3. Set up a data collection interface to collect real-time dynamic data during the operation of cultural and tourism facilities, including tourist flow data, facility usage frequency data, and environmental monitoring data;
[0011] S4. Input the real-time collected dynamic data into the preliminary digital twin model, and use machine learning algorithms to train and optimize the preliminary digital twin model so that the digital twin model can accurately reflect the real-time operation status of cultural and tourism facilities;
[0012] S5. Based on the optimized digital twin model, use time series analysis algorithms to predict the future operation status of cultural and tourism facilities;
[0013] S6. Generate a future operation status report according to the prediction results, provide a decision-making basis for decision-makers, so as to make adjustments and decisions in advance and avoid potential problems and risks.
[0014] Preferably, in step S1, when collecting the physical data of cultural and tourism facilities, a sensor network is used for data collection. The sensor network includes temperature sensors, pressure sensors, and displacement sensors, which are respectively used to collect the environmental temperature, facility structure pressure, and facility component displacement data of cultural and tourism facilities.
[0015] Preferably, in step S3, when collecting tourist flow data in real time, video image recognition technology is used. By installing cameras at the entrances, exits, and key areas of cultural and tourism facilities, the video images are analyzed to identify the number of tourists and the tourist behavior trajectories.
[0016] Preferably, in step S3, when collecting environmental monitoring data in real time, air quality sensors and water quality sensors are used, which are respectively used to collect air quality data and water quality data around cultural and tourism facilities.
[0017] Preferably, in step S6, the future operation status report includes information on equipment failure prediction, peak tourist flow period prediction, and facility maintenance requirement prediction of cultural and tourism facilities within a future period of time.
[0018] Preferably, in step S4, the machine learning algorithm uses the gradient descent algorithm, and its objective function is:
[0019]
[0020] where m is the number of training samples, and h θ (x (i) is the predicted value, y (i) is the true value, and θ is the model parameter.
[0021] Preferably, in the step S5, the time series analysis algorithm is an ARIMA(p, d, q) model, and its prediction formula is:
[0022] Φ(B) d X t = Θ(B)∈ t
[0023] where Φ(B) is the autoregressive operator, Θ(B) is the moving average operator, p is the autoregressive order, d is the differencing order, q is the moving average order, X t is the time series data, and ∈ t is the white noise sequence.
[0024] A digital twin system based on the culture and tourism industry, comprising:
[0025] A data acquisition module: used to collect various physical data of cultural and tourism facilities and dynamic data during the operation process. The physical data includes building structure parameters, facility layout information, and equipment operation parameters. The dynamic data includes tourist flow data, facility usage frequency data, and environmental monitoring data;
[0026] A digital twin model construction module: used to construct a three-dimensional geometric model of cultural and tourism facilities using three-dimensional modeling technology based on the collected physical data, establish an attribute database, and associate the physical data with the three-dimensional geometric model to form a preliminary digital twin model;
[0027] A model optimization module: used to input the real-time collected dynamic data into the preliminary digital twin model, and use machine learning algorithms to train and optimize the preliminary digital twin model so that the digital twin model can accurately reflect the real-time operation status of cultural and tourism facilities;
[0028] A prediction module: used to predict the future operation status of cultural and tourism facilities based on the optimized digital twin model using time series analysis algorithms, and generate a future operation status report according to the prediction results;
[0029] A decision support module: used to receive the future operation status report, provide a decision-making basis for decision-makers, so as to make adjustments and decisions in advance to avoid potential problems and risks.
[0030] Preferably, the data acquisition module includes an abnormal data recognition algorithm, which can automatically identify abnormal values in physical data collected by temperature sensors, pressure sensors, etc., and dynamic data such as tourist flow data and facility usage frequency data based on preset physical data and dynamic data ranges, and eliminate them. In case of data loss, the linear interpolation method is used to estimate and fill in the missing data based on data at adjacent time nodes or spatial positions.
[0031] Preferably, the model optimization module includes an adaptive adjustment unit, which real-time monitors the performance indicators of the digital twin model and automatically adjusts the hyperparameters of the machine learning algorithm when the model performance shows a downward trend.
[0032] Compared with the prior art, the beneficial effects of the present invention are as follows: By constructing an accurate digital twin model, integrating physical and dynamic data, and realizing all-round data-driven for physical cultural and tourism facilities. The model deeply mines historical data, uses scientific algorithms to accurately predict equipment failure probabilities, peak tourist flow periods, and facility maintenance requirement time points, etc., providing detailed basis for decision-making, improving the scientificity and forward-looking of decision-making, avoiding risks, and ensuring the efficient operation of facilities. Using a sensor network to collect physical data, combining 3D modeling to construct a 3D geometric model and associating with an attribute database to form a preliminary model, and then inputting real-time dynamic data for training and optimization to accurately reflect the real-time operation status of the facilities, helping managers to respond quickly, ensuring the safety and stability of the facilities and extending their service life. Using video image recognition technology to collect tourist flow and behavior trajectories, helping cultural and tourism venues to scientifically plan tourist routes and reasonably divert, improving the smoothness and comfort of tourists' tours. With the help of air quality and water quality sensors to collect environmental data in real time, operators can adjust operation strategies in a timely manner to create a high-quality and safe environment. The adaptive adjustment unit in the model optimization module real-time monitors the model performance, and once the performance drops, it automatically adjusts the hyperparameters of the machine learning algorithm to maintain the accuracy and reliability of the model, providing technical guarantee for the long-term stable operation of the facilities. BRIEF DESCRIPTION OF THE DRAWINGS
[0033] Figure 1 is the flow chart of the present invention;
[0034] Figure 2 is the system block diagram of the present invention. DETAILED DESCRIPTION OF THE INVENTION
[0035] 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 described below are only examples, and those skilled in the art can think of other obvious variations.
[0036] Refer to Figure 1 As shown, a digital twin method and system based on the cultural and tourism industry includes the following steps:
[0037] S1. Collect various physical data of cultural and tourism facilities, including but not limited to building structure parameters, facility layout information, and equipment operation parameters, and use 3D modeling technology to construct a 3D geometric model of the cultural and tourism facilities;
[0038] S2. Establish an attribute database for the cultural and tourism facilities, associate the collected physical data with the 3D geometric model, and form a preliminary digital twin model.
[0039] S3. Set up a data collection interface to collect dynamic data during the operation of cultural and tourism facilities in real time, including tourist flow data, facility usage frequency data, and environmental monitoring data;
[0040] S4. Input the dynamically collected data in real time into the preliminary digital twin model, and use machine learning algorithms to train and optimize the preliminary digital twin model so that the digital twin model can accurately reflect the real-time operation status of the cultural and tourism facilities;
[0041] S5. Based on the optimized digital twin model, use time series analysis algorithms to predict the future operation status of cultural and tourism facilities;
[0042] S6. Generate a future operation status report according to the prediction results, provide a decision-making basis for decision-makers, so as to make adjustments and decisions in advance, and avoid potential problems and risks.
[0043] Specifically, in step S1, when collecting the physical data of cultural and tourism facilities, a sensor network is used for data collection. The sensor network includes temperature sensors, pressure sensors, and displacement sensors, which are respectively used to collect the environmental temperature, facility structure pressure, and facility component displacement data of cultural and tourism facilities. Subsequently, in step S2, the physical data is associated with the 3D geometric model to establish an attribute database and form a preliminary digital twin model, endowing the model with actual data connotations. Then, in step S3, dynamic data is collected in real time to inject real-time change information into the model; in step S4, the dynamic data is input into the preliminary model, and machine learning algorithms are used to optimize the model so that it can accurately reflect the real-time operation status. The optimized model uses time series analysis algorithms to predict the future operation status in step S5, and the prediction results generate a future operation status report in step S6, providing a basis for decision-makers, so as to adjust decisions in advance, realizing a complete process of the cultural and tourism facilities from basic construction, real-time monitoring to future prediction and decision support, and achieving intelligent and precise management of the cultural and tourism facilities.
[0044] In step S1, when collecting the physical data of cultural and tourism facilities, a sensor network is used for data collection. The sensor network includes temperature sensors, pressure sensors, and displacement sensors, which are respectively used to collect the environmental temperature, facility structure pressure, and facility component displacement data of cultural and tourism facilities.
[0045] Specifically, the temperature sensor utilizes components such as thermistors, whose resistance values change with temperature, and indirectly obtains environmental temperature data by measuring the change in resistance values; the pressure sensor is based on the piezoresistive effect, and when subjected to pressure, the internal resistance changes, and the structural pressure data of the facility is obtained by detecting the resistance change; the displacement sensor is based on principles such as electromagnetic induction, for example, by detecting the change in electromagnetic induction between coils to measure the displacement data of facility components. This sensor network can comprehensively and accurately collect the key physical data of cultural and tourism facilities, providing rich and reliable data support for the subsequent construction of accurate three-dimensional geometric models and digital twin models. For example, in facility maintenance, technicians can accurately judge whether there are potential problems in the facility structure based on these accurate physical data, and carry out maintenance in advance to ensure the safe and stable operation of the facility.
[0046] In step S3, when collecting real-time tourist flow data, video image recognition technology is adopted. By installing cameras at the entrances, exits and key areas of cultural and tourism facilities, the video images are analyzed to identify the number of tourists and the tourist behavior trajectories.
[0047] Specifically, this technology provides real-time and accurate tourist flow and behavior information for the operation and management of cultural and tourism facilities. Managers can reasonably plan the scenic tour routes based on this information, and adjust the operation strategies in a timely manner during peak tourist hours, such as increasing guiding personnel and opening alternative channels, to enhance the tourist experience and avoid safety hazards and reduced experience caused by tourist congestion.
[0048] In step S3, when collecting real-time environmental monitoring data, air quality sensors and water quality sensors are adopted, which are respectively used to collect air quality data and water quality data around cultural and tourism facilities.
[0049] Specifically, the air quality sensor detects the concentration of pollutants in the air using different principles. For example, the electrochemical sensor generates an electric current through a chemical reaction, and the magnitude of the current is related to the pollutant concentration, thereby measuring the pollutant concentration; the optical sensor uses the characteristics of light absorption and scattering, and determines the pollutant concentration by detecting the change in the optical signal. The water quality sensor measures parameters such as conductivity and acidity in the water body by the electrode method, and measures indicators such as dissolved oxygen and turbidity in the water body by the optical method. The real-time collected environmental monitoring data helps cultural and tourism facilities respond to the impact of environmental changes on facilities and tourists in a timely manner. For example, when the air quality sensor detects that the concentration of harmful gases exceeds the standard, the ventilation equipment can be started in a timely manner to ensure the health of tourists; according to the water quality sensor data, the water body can be purified in a timely manner to maintain the ecological environment of the scenic area and improve the overall quality of the scenic area.
[0050] In step S6, the future operation status report includes information on equipment failure prediction, peak tourist flow time prediction, and facility maintenance requirement prediction of cultural and tourism facilities within a future period of time.
[0051] Specifically, it provides clear and comprehensive decision-making basis for decision-makers, enabling them to plan and arrange resources in advance. For example, according to equipment failure prediction, reserve maintenance spare parts and arrange maintenance personnel in advance to reduce the impact of equipment failures on operations; based on the prediction of peak tourist flow periods, rationally allocate resources such as transportation and catering services to improve tourist satisfaction.
[0052] In step S4, the machine learning algorithm adopts the gradient descent algorithm, and its objective function is:
[0053]
[0054] where m is the number of training samples, h θ (x (i) is the predicted value, y (i) is the true value, and θ is the model parameter.
[0055] Specifically, it improves the accuracy of the digital twin model in reflecting the real-time operating status of cultural and tourism facilities, enabling the model to better fit the actual data and providing a more reliable basis for subsequent prediction and decision-making. For example, in the monitoring of the operating status of facilities and equipment, it can more accurately predict equipment failures and give early warnings to ensure the stable operation of the facilities.
[0056] In the said step S5, the time series analysis algorithm is the ARIMA(p, d, q) model, and its prediction formula is:
[0057] Φ(B) d X t =Θ(B)∈ t
[0058] where Φ(B) is the autoregressive operator, Θ(B) is the moving average operator, p is the autoregressive order, d is the differencing order, q is the moving average order, X t is the time series data, and ∈ t is the white noise sequence.
[0059] Specifically, the autoregressive operator Φ(B) constructs the autoregressive relationship of the time series by considering the influence of the data at the past p time points on the current data; the moving average operator Θ(B) takes into account the influence of the past q prediction errors on the current data; the differencing order d is used to process non-stationary time series and transform them into stationary time series so that the model can effectively analyze and predict. By performing the above processing on the time series data X t and combining with the white noise sequence ∈ t, to achieve the prediction of the future operating status of cultural and tourism facilities. This model can make full use of the laws of historical data to accurately predict the future operating status of cultural and tourism facilities, providing strong support for early decision-making. For example, accurately predicting peak tourist flow periods to help managers allocate resources in advance and avoid tourist congestion; predicting facility maintenance needs, reasonably arranging maintenance plans, reducing maintenance costs, and ensuring the long-term stable operation of facilities.
[0060] A digital twin system based on the cultural and tourism industry, comprising:
[0061] Data acquisition module: used to collect various physical data of cultural and tourism facilities and dynamic data during the operation process. The physical data includes building structure parameters, facility layout information, and equipment operation parameters. The dynamic data includes tourist flow data, facility usage frequency data, and environmental monitoring data;
[0062] Digital twin model construction module: used to construct a three-dimensional geometric model of cultural and tourism facilities using three-dimensional modeling technology based on the collected physical data, and establish an attribute database, associating the physical data with the three-dimensional geometric model to form a preliminary digital twin model;
[0063] Model optimization module: used to input the real-time collected dynamic data into the preliminary digital twin model, and use machine learning algorithms to train and optimize the preliminary digital twin model so that the digital twin model can accurately reflect the real-time operating status of cultural and tourism facilities;
[0064] Prediction module: used to predict the future operating status of cultural and tourism facilities based on the optimized digital twin model using time series analysis algorithms, and generate a future operating status report according to the prediction results;
[0065] Decision support module: used to receive the future operating status report and provide a decision-making basis for decision-makers so as to make adjustments and decisions in advance and avoid potential problems and risks.
[0066] Specifically, the data acquisition module collects the physical and dynamic data of cultural and tourism facilities through various sensors and data acquisition interfaces according to certain data acquisition rules. The digital twin model construction module uses 3D modeling technology to construct a 3D geometric model based on the physical data provided by the data acquisition module, and establishes an attribute database to associate the physical data with the 3D geometric model to form a preliminary digital twin model. The model optimization module obtains real-time dynamic data from the data acquisition module and uses machine learning algorithms (gradient descent algorithms) to train and optimize the preliminary digital twin model. Based on the digital twin model optimized by the model optimization module, the prediction module uses the ARIMA (p, d, q) time series analysis algorithm to predict the future operating status of cultural and tourism facilities and generate a future operating status report. The decision support module receives the report generated by the prediction module, provides decision-makers with a basis for decision-making, and interacts with the external cultural and tourism resource scheduling system when necessary. The modules of the system work together to achieve full-process automation and intelligent management from data acquisition, model construction and optimization, prediction to decision support. The data collection module ensures the acquisition of comprehensive and accurate data; the digital twin model construction module provides the digital foundation of the facilities; the model optimization module improves the accuracy and adaptability of the model; the prediction module provides forward-looking information for decision-making; the decision support module realizes scientific decision-making and rational allocation of resources, and overall improves the efficiency and service quality of operation and management of the cultural and tourism industry.
[0067] The data acquisition module includes an abnormal data identification algorithm, which can automatically identify and eliminate abnormal values in physical data collected by temperature sensors, pressure sensors, etc. and dynamic data such as tourist flow data and facility usage frequency data based on preset physical data and dynamic data ranges. In the case of missing data, linear interpolation method is used to estimate and fill in the missing data based on data from adjacent time nodes or spatial positions.
[0068] Specifically, in the case of missing data, the linear interpolation method is used. According to the data of adjacent time nodes or spatial positions, the linear interpolation formula x1, x2, ..., x n , if x i Missing, and x is known i-1 and x i+1 ,but Estimation and filling of missing data ensures the quality of data input into subsequent modules and provides a reliable data foundation for the construction, training and prediction of digital twin models. High-quality data can improve the accuracy and reliability of the model and reduce decision-making errors caused by incorrect or missing data.
[0069] The model optimization module includes an adaptive adjustment unit, which monitors the performance metrics of the digital twin model in real time and automatically adjusts the hyperparameters of the machine learning algorithm when the model performance shows a downward trend.
[0070] Specifically, when the model convergence speed is too slow, appropriately increase the learning rate of the gradient descent algorithm; reasonably adjust hyperparameters such as the number of iterations according to the actual situation of model training to optimize the model performance. Enable the digital twin model to continuously and accurately reflect the real-time operation status of cultural and tourism facilities, and improve the adaptability and stability of the model. In the case of continuous changes in the operation of cultural and tourism facilities (such as facility renovation, change in tourist flow pattern), the adaptive adjustment unit can optimize the model in a timely manner, enabling the system to always operate efficiently and providing reliable support for prediction and decision-making.
[0071] 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.
Claims
1. A digital twin method based on the cultural and tourism industry, characterized in that, It includes the following steps: S1. Collect various physical data of cultural and tourism facilities, including but not limited to building structure parameters, facility layout information, and equipment operation parameters, and use 3D modeling technology to construct a 3D geometric model of the cultural and tourism facilities; S2. Establish an attribute database for the cultural and tourism facilities, associate the collected physical data with the 3D geometric model, and form a preliminary digital twin model. S3. Set up a data collection interface to collect dynamic data during the operation of cultural and tourism facilities in real time, including tourist flow data, facility usage frequency data, and environmental monitoring data; S4. Input the dynamically collected data in real time into the preliminary digital twin model, and use machine learning algorithms to train and optimize the preliminary digital twin model so that the digital twin model can accurately reflect the real-time operation status of cultural and tourism facilities; S5. Based on the optimized digital twin model, use time series analysis algorithms to predict the future operation status of cultural and tourism facilities; S6. Generate a future operation status report according to the prediction results, provide a decision-making basis for decision-makers, so as to make adjustments and decisions in advance and avoid potential problems and risks.
2. The digital twin method based on the cultural and tourism industry according to claim 1, wherein In step S1, when collecting the physical data of cultural and tourism facilities, a sensor network is used for data collection. The sensor network includes temperature sensors, pressure sensors, and displacement sensors, which are respectively used to collect the environmental temperature, facility structure pressure, and facility component displacement data of cultural and tourism facilities.
3. A digital twin method based on the cultural and tourism industry according to claim 1, characterized in that, In step S3, when collecting tourist flow data in real time, video image recognition technology is used. By installing cameras at the entrances, exits, and key areas of cultural and tourism facilities, the video images are analyzed to identify the number of tourists and the tourist behavior trajectories.
4. A digital twin method based on the cultural and tourism industry according to claim 1, wherein In step S3, when collecting environmental monitoring data in real time, air quality sensors and water quality sensors are used, which are respectively used to collect air quality data and water quality data around cultural and tourism facilities.
5. A digital twin method based on the cultural and tourism industry according to claim 1, characterized in that, In step S6, the future operation status report includes information on equipment failure prediction, peak tourist flow period prediction, and facility maintenance requirement prediction of cultural and tourism facilities within a certain period in the future.
6. According to the digital twin method based on the cultural and tourism industry described in claim 1, characterized in that in step S4, the machine learning algorithm uses the gradient descent algorithm, and its objective function is: where m is the number of training samples, h θ (x (i) is the predicted value, y (i) is the true value, and θ is the model parameter.
7. A digital twin method based on the cultural and tourism industry according to claim 1, characterized in that, in step S5, the time series analysis algorithm is the ARIMA(p, d, q) model, and its prediction formula is: Φ(B) d X t = Θ(B) ∈ t where Φ(B) is the autoregressive operator, Θ(B) is the moving average operator, p is the autoregressive order, d is the differencing order, q is the moving average order, and X t is the time series data, and ∈ t is the white noise sequence.
8. A digital twin system based on the cultural and tourism industry, according to any one of claims 1-7, a digital twin method based on the cultural and tourism industry, characterized in that, It includes: Data collection module: used to collect various physical data of cultural and tourism facilities and dynamic data during operation. The physical data includes building structure parameters, facility layout information, and equipment operation parameters, and the dynamic data includes tourist flow data, facility usage frequency data, and environmental monitoring data; Digital twin model construction module: used to construct a 3D geometric model of cultural and tourism facilities according to the collected physical data, use 3D modeling technology, and establish an attribute database to associate the physical data with the 3D geometric model to form a preliminary digital twin model; Model optimization module: used to input the real-time collected dynamic data into the preliminary digital twin model, and use the machine learning algorithm to train and optimize the preliminary digital twin model so that the digital twin model can accurately reflect the real-time operating status of cultural and tourism facilities; Prediction module: used to predict the future operation status of cultural and tourism facilities based on the optimized digital twin model and use the time series analysis algorithm, and generate a future operation status report based on the prediction results; Decision support module: used to receive future operation status reports and provide decision makers with a basis for making decisions so that they can make adjustments and decisions in advance to avoid potential problems and risks.
9. A digital twin system based on the cultural and tourism industry according to claim 1, characterized in that, The data acquisition module includes an abnormal data identification algorithm, which can automatically identify and eliminate abnormal values in physical data collected by temperature sensors, pressure sensors, etc. and dynamic data such as tourist flow data and facility usage frequency data based on preset physical data and dynamic data ranges. In the case of missing data, linear interpolation method is used to estimate and fill in the missing data based on data from adjacent time nodes or spatial positions.
10. A digital twin system based on the cultural and tourism industry according to claim 1, characterized in that, The model optimization module includes an adaptive adjustment unit, which monitors the performance indicators of the digital twin model in real time and automatically adjusts the hyperparameters of the machine learning algorithm when the model performance shows a downward trend.