A Smart Park Digital Twin System and Method Based on Artificial Intelligence

Abstract

This invention discloses a smart park digital twin system and method based on artificial intelligence, specifically relating to the field of digital twin simulation optimization technology. It addresses the problems of simulation distortion and low reliability of emergency drills caused by insufficient modeling of the dynamic correlation of entity behavior in existing technologies. The system constructs a hierarchical analysis network of propagation paths by real-time collection of entity attribute data and dynamic interaction behavior data. Based on path length and behavior type, it classifies group and individual behavior data, identifies key disturbance nodes, and quantifies their propagation path correlation strength. Through dynamic changes in differences and correlation strength, it generates simulation model adjustment strategies, corrects the propagation direction and density weight parameters of key nodes, and generates high-precision simulation results. Based on the feedback mechanism of behavior deviations of non-key nodes, it updates behavior weights in reverse through correlation strength, forming a closed-loop optimization system that links the virtual and real worlds, thereby improving the reliability of digital twin simulations in complex scenarios.

Description

Technical Field

[0001] This invention relates to the field of digital twin simulation optimization technology, and more specifically, to a smart park digital twin system and method based on artificial intelligence. Background Technology

[0002] In the dynamic management of smart parks, digital twin technology is often used to simulate the behavioral patterns of complex systems such as pedestrian and vehicle traffic in order to rehearse emergency strategies. Digital twin technology usually relies on historical data and rule models to simplify and abstract the interactive behavior of entities (such as pedestrians and vehicles) in large-scale scenarios, thereby generating predictive simulation results. However, the behavior of entities in real scenarios is highly dynamic and interconnected. For example, individual decisions are affected by multiple factors such as group behavior and environmental feedback, forming a complex nonlinear interactive network.

[0003] Currently, during simulation, due to the dynamic interaction between entities, local behavioral disturbances may trigger global anomalies through unpredictable chain effects. For example, path selection deviations in a certain area may be amplified step by step due to group effects, resulting in unexpected clustering or path congestion in the simulation results. This makes it impossible for the prediction model to accurately depict the evolution of the real scene, thereby reducing the reliability of the simulation strategy. Summary of the Invention

[0004] In order to overcome the above-mentioned defects of the prior art, embodiments of the present invention provide a smart park digital twin system and method based on artificial intelligence to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution:

[0006] A digital twin method for smart parks based on artificial intelligence includes the following steps:

[0007] S1. Obtain real-time status data of entities within the smart park. Real-time status data includes entity attribute data and dynamic interaction data.

[0008] S2. Based on the propagation path length and behavior type of dynamic interactive data, dynamic interactive data is divided into group behavior data and individual behavior data.

[0009] S3. Identify key disturbance nodes that meet preset disturbance conditions based on the propagation path hierarchy and density dynamic changes of group behavior data;

[0010] S4. Based on the dynamic changes in the entity attribute data and historical behavior data of key disturbance nodes, and combined with the propagation path hierarchy of key disturbance nodes and other nodes, assess the correlation strength and generate dynamic adjustment strategies.

[0011] S5. Adjust the propagation direction and density weight of key disturbance nodes in the dynamic simulation model based on the propagation path hierarchy and correlation strength to generate simulation results;

[0012] S6. When the deviation between the behavioral data of non-critical disturbance nodes and the simulation results exceeds the preset range, the behavioral weights of non-critical disturbance nodes are updated in reverse based on the correlation strength of the propagation path level.

[0013] In a preferred embodiment, entity attribute data includes location and real-time movement speed, and dynamic interaction data includes avoidance behavior, following behavior, and group density distribution between entity objects.

[0014] In a preferred embodiment, based on the propagation path length and behavior type of the dynamic interaction data, the dynamic interaction data is divided into group behavior data and individual behavior data, including:

[0015] Iterate through the propagation path length of dynamic interactive data and select dynamic interactive data whose propagation path length exceeds a preset path length threshold.

[0016] Associate dynamic interactive data whose propagation path length exceeds a preset path length threshold with behavior type;

[0017] Detect dynamic interaction data of follow-up behaviors in the detection behavior type;

[0018] The dynamic interaction data corresponding to the detected following behavior is classified as group behavior data, and the remaining dynamic interaction data is classified as individual behavior data.

[0019] In a preferred embodiment, based on the propagation path hierarchy and density dynamic change conditions of the group behavior data, key disturbance nodes that meet preset disturbance conditions are identified, including:

[0020] Determine the propagation path hierarchy of group behavior data, and divide the propagation path hierarchy according to the number of nodes covered by the influence scope of group behavior data;

[0021] The rate of change of density in group behavior data is detected, and the rate of change of density is calculated by the increase or decrease of the group density distribution value per unit time.

[0022] Compare the propagation path level with the preset propagation path level range, and compare the density change rate with the preset density change rate range;

[0023] When the propagation path level is within the preset propagation path level range and the density change rate exceeds the preset density change rate range, the corresponding node is determined to be a critical disturbance node.

[0024] In a preferred embodiment, based on the dynamic differences between the entity attribute data and historical behavior data of key disturbance nodes, and by assessing the association strength between key disturbance nodes and other nodes through the propagation path hierarchy, a dynamic adjustment strategy is generated, including:

[0025] Based on the position offset and velocity change rate in the entity attribute data of the key disturbance nodes, the dynamic change difference between the current time and the historical data of the same period is calculated. The position offset is the difference in Euclidean distance between the real-time position coordinates and the historical position coordinates, and the velocity change rate is the ratio of the real-time velocity to the historical velocity.

[0026] Determine the propagation path level coverage ratio between the critical disturbance node and other nodes. The propagation path level coverage ratio is the quotient of the number of propagation path levels of the critical disturbance node and the number of propagation path levels of other nodes.

[0027] A dynamic adjustment strategy is generated based on the product of the dynamic change difference and the coverage ratio of the propagation path hierarchy. The dynamic adjustment strategy includes the propagation direction offset angle and the density weight allocation ratio.

[0028] When the dynamic changes exceed the change threshold of historical data for the same period, the priority of adjusting the propagation direction offset angle is based on the coverage ratio of the propagation path hierarchy.

[0029] In a preferred embodiment, the propagation direction and density weight of key perturbation nodes in the dynamic simulation model are adjusted based on the propagation path hierarchy and correlation strength to generate simulation results, including:

[0030] Based on the offset angle of the propagation direction, the movement direction of the key disturbance nodes in the dynamic simulation model is adjusted. The movement direction is calculated based on the vector synthesis of the offset angle and the current propagation direction.

[0031] Based on the density weight allocation ratio, the density weight of key perturbation nodes in the dynamic simulation model is adjusted, and the density weight is updated by multiplying the current density value by the allocation ratio.

[0032] The adjusted movement direction and density weights are input into the dynamic simulation model, and simulation calculations are performed to generate simulation results.

[0033] Once the density weight of the critical disturbance node is updated, the density weight of the adjacent nodes is updated synchronously, and the distribution is proportional to the propagation path hierarchy association strength between the adjacent nodes and the critical disturbance node.

[0034] In a preferred embodiment, when the deviation between the behavioral data of non-critical perturbation nodes and the simulation results exceeds a preset range, the behavioral weights of the non-critical perturbation nodes are updated in reverse based on the association strength at the propagation path level, including:

[0035] The dynamic deviation rate between the behavioral data of non-critical disturbance nodes and the simulation results is detected. The dynamic deviation rate is the ratio of the absolute value of the difference between the real-time behavioral data and the simulated behavioral data to the historical average deviation.

[0036] Obtain the set of association strengths of the propagation path hierarchy between non-critical disturbance nodes and all critical disturbance nodes. Each element in the association strength set is the coverage ratio of the propagation path hierarchy between a single critical disturbance node and its corresponding non-critical disturbance node.

[0037] Calculate the behavioral weight correction ratio of non-critical disturbance nodes based on the maximum value in the correlation strength set and the preset adjustment coefficient;

[0038] When the dynamic deviation rate exceeds the preset deviation threshold, the behavior weight of non-critical disturbance nodes is adjusted in reverse based on the behavior weight correction ratio, and the dynamic adjustment strategy priority of the corresponding critical disturbance nodes in the association strength set is updated synchronously.

[0039] If the adjusted behavior weights still cause the dynamic deviation rate to exceed the preset deviation threshold, then the behavior weight correction ratio will be recalculated based on the second largest value in the association strength set for a second correction.

[0040] On the other hand, the present invention provides a smart park digital twin system based on artificial intelligence, comprising:

[0041] Data acquisition module: Acquires real-time status data of entities within the smart park, including entity attribute data and dynamic interaction data;

[0042] Classification processing module: Based on the propagation path length and behavior type of dynamic interactive data, the dynamic interactive data is divided into group behavior data and individual behavior data;

[0043] Node identification module: Based on the propagation path hierarchy and density dynamic changes of group behavior data, identify key disturbance nodes that meet preset disturbance conditions;

[0044] Strategy generation module: Based on the dynamic changes in the entity attribute data and historical behavior data of key disturbance nodes, and combined with the evaluation of the correlation strength between key disturbance nodes and other nodes through the propagation path hierarchy, a dynamic adjustment strategy is generated.

[0045] Simulation construction module: Based on the propagation path hierarchy and correlation strength, adjust the propagation direction and density weight of key disturbance nodes in the dynamic simulation model to generate simulation results;

[0046] Feedback correction module: When the deviation between the behavior data of non-critical disturbance nodes and the simulation results exceeds the preset range, the behavior weights of non-critical disturbance nodes are updated in reverse based on the correlation strength of the propagation path level.

[0047] Compared with the prior art, the present invention has the following beneficial effects:

[0048] 1. By collecting entity attribute data and dynamic interaction data in real time, a hierarchical analysis mechanism for the propagation path of dynamic interactive behavior is established, which can more accurately reflect the correlation and evolution of group behavior and individual behavior. Based on the dual classification criteria of propagation path length and behavior type, the impact of group effects and individual decisions on the system is effectively distinguished, providing a reliable basis for the identification of local disturbance sources. Through the collaborative analysis of the dynamic changes of key disturbance nodes and the correlation strength of the propagation path hierarchy, targeted dynamic adjustment strategies are generated, enabling the simulation model parameters to adapt to the nonlinear change characteristics of entity behavior in real time, and improving the reliability of evolution law prediction in complex scenarios.

[0049] 2. By analyzing the dynamic deviation between the behavior data of non-critical nodes and the simulation results, the behavior weights are updated in reverse and the policy priorities of associated nodes are corrected simultaneously, so as to achieve bidirectional dynamic adaptation between the simulation model and the entity behavior. This mechanism enables the system to autonomously suppress the abnormal propagation caused by local disturbances. Through the weight allocation optimization driven by the correlation strength, it ensures that the simulation results are close to the evolution trajectory of the real scene, thereby enhancing the effectiveness of the emergency drill strategy and the robustness of the system. Attached Figure Description

[0050] Figure 1 This is a flowchart of a smart park digital twin method based on artificial intelligence according to the present invention;

[0051] Figure 2 This is a schematic diagram of the structure of a smart park digital twin system based on artificial intelligence according to the present invention. Detailed Implementation

[0052] The following will provide a clear and complete description of the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0053] Example 1: Figure 1 This invention presents a digital twin method for smart parks based on artificial intelligence, which includes the following steps:

[0054] S1. Obtain real-time status data of entities within the smart park. Real-time status data includes entity attribute data and dynamic interaction data.

[0055] S2. Based on the propagation path length and behavior type of dynamic interactive data, dynamic interactive data is divided into group behavior data and individual behavior data.

[0056] S3. Identify key disturbance nodes that meet preset disturbance conditions based on the propagation path hierarchy and density dynamic changes of group behavior data;

[0057] S4. Based on the dynamic changes in the entity attribute data and historical behavior data of key disturbance nodes, and combined with the propagation path hierarchy of key disturbance nodes and other nodes, assess the correlation strength and generate dynamic adjustment strategies.

[0058] S5. Adjust the propagation direction and density weight of key disturbance nodes in the dynamic simulation model based on the propagation path hierarchy and correlation strength to generate simulation results;

[0059] S6. When the deviation between the behavioral data of non-critical disturbance nodes and the simulation results exceeds the preset range, the behavioral weights of non-critical disturbance nodes are updated in reverse based on the correlation strength of the propagation path level.

[0060] S1. Obtain real-time status data of entities within the smart park. Real-time status data includes entity attribute data and dynamic interaction data, including:

[0061] Entity attribute data includes location and real-time movement speed, while dynamic interaction data includes avoidance behavior, following behavior, and group density distribution between entity objects.

[0062] The location in the entity attribute data is obtained through a GPS or Bluetooth beacon positioning device deployed in the smart park. The real-time movement speed is calculated by integrating the acceleration data collected by inertial sensors set on the entity. The avoidance behavior in the dynamic interaction data is determined by cameras set in the smart park capturing the movement trajectory of the entity and identifying trajectory change points. The following behavior is determined by infrared sensors or cameras detecting changes in the relative distance between entities and determining the synchronization of movement directions. The group density distribution is calculated in real time by Wi-Fi probes in the smart park counting the number of active devices in the area and combining it with camera image analysis.

[0063] The position and real-time movement speed in the entity attribute data are used to analyze the differences in dynamic changes of entity objects in subsequent steps. The avoidance and following behaviors in the dynamic interaction data are used to distinguish between group behavior data and individual behavior data in subsequent steps. The group density distribution is used to determine the conditions for dynamic density changes in subsequent steps.

[0064] The acquisition frequency of real-time status data is dynamically adjusted according to the motion status of physical objects within the smart park. When physical objects are stationary or moving at a constant speed, a low-frequency acquisition mode is used, while when physical objects are accelerating or turning, a high-frequency acquisition mode is switched. During the avoidance behavior recognition process of dynamic interactive data, when the camera captures the motion trajectory of a physical object and the angle deviation or speed drop exceeds a threshold within a preset time, it is determined that an avoidance behavior has occurred. During the following behavior recognition process of dynamic interactive data, when the relative distance between two physical objects is continuously less than a preset safety distance and the angle between their motion directions is less than a preset angle, it is determined that a following behavior has occurred. During the real-time calculation of the group density distribution, the number of active devices counted by the Wi-Fi probe and the number of physical objects identified by the camera are weighted and fused. When the difference between the two exceeds a preset error range, the density distribution is corrected by prioritizing the camera recognition result.

[0065] The weighted fusion method for the number of active devices counted by Wi-Fi probes and the number of entities identified by cameras is as follows: based on the consistency of the results recorded by the two devices in historical statistics, different credibility weights are pre-assigned to Wi-Fi probes and cameras; since cameras have shown higher recognition accuracy in past data, their weight value is slightly higher than that of Wi-Fi probes, and the sum of the weights of the two is constant at the complete credibility; when the difference in the number of active devices counted in real time between the two devices is within a reasonable fluctuation range, the system adopts a weighted fusion method to combine the data of the two, with camera data accounting for a larger proportion; the threshold of this fluctuation range is determined by analyzing the typical fluctuation amplitude of the difference between the two in historical data, for example, it can be set to the normal deviation level; if the difference in real-time data exceeds this reasonable range, it is judged as an abnormal situation. At this time, the system will fully adopt the recognition result of the camera as the final density value and suspend the fusion calculation of Wi-Fi probe data to prioritize the accuracy of the data; this dynamic adjustment mechanism not only ensures the complementarity of data in daily situations, but also automatically selects a more reliable data source when there are significant discrepancies between devices.

[0066] S2. Based on the propagation path length and behavior type of dynamic interaction data, dynamic interaction data is divided into group behavior data and individual behavior data, including:

[0067] The propagation path length of dynamic interactive data is obtained through positioning devices deployed in the smart park. The positioning devices include a global positioning system receiver or a Bluetooth beacon. The propagation path length is calculated based on the movement trajectory of the entity. The movement trajectory is generated by continuously recording the location data of the entity. The recording interval of the location data is dynamically adjusted according to the movement state of the entity. When the entity is stationary or in uniform motion, a low-frequency recording mode is used, and when the entity is accelerating or turning, it switches to a high-frequency recording mode.

[0068] The preset path length threshold is set according to the physical space size of different functional areas in the smart park. For example, the first path length threshold is set in the main road area of ​​the park, and the second path length threshold is set in the passage between buildings. The first path length threshold is greater than the second path length threshold. The specific value of the preset path length threshold is determined by the average propagation distance of group behavior in the statistical historical data.

[0069] The behavior types of dynamic interactive data are collected by cameras or infrared sensors deployed in the smart park. The rules for determining the behavior types include: when the movement trajectory of an entity object deviates from the direction by more than a preset angle or changes in speed by more than a preset proportion within a preset time, it is determined to be an avoidance behavior; when the relative distance between two entity objects is continuously less than a preset safe distance and the angle between their movement directions is less than a preset angle, it is determined to be a following behavior.

[0070] The association between dynamic interactive data and behavior type is achieved through data tags. Data tags include timestamps, location coordinates, and behavior type codes. The data tags are stored in a structured database entry format, with each piece of dynamic interactive data corresponding to an independent data tag.

[0071] The detection of dynamic interactive data of following behavior is achieved by traversing the behavior type codes in the data labels. The behavior type codes are preset character or number combinations. For example, the code corresponding to the following behavior is "F" and the code corresponding to the avoidance behavior is "A". During the detection process, the data labels with the behavior type code "F" are selected and their corresponding dynamic interactive data are marked as group behavior data.

[0072] The distinction between group behavior data and individual behavior data is accomplished by a data classifier, which is a rule-based conditional judgment program. The judgment logic of the data classifier includes: if the dynamic interaction data simultaneously meets the conditions that the propagation path length exceeds the preset path length threshold and the behavior type code is "F", it is classified as group behavior data; if the dynamic interaction data meets the conditions that the propagation path length does not exceed the preset path length threshold or the behavior type code is "A", it is classified as individual behavior data.

[0073] The rule priority of the data classifier is set to prioritize propagation path length determination over behavior type determination. When the propagation path length of dynamic interactive data exceeds the preset path length threshold but the behavior type is coded as "A", it is prioritized to be determined as group behavior data based on the propagation path length.

[0074] The group behavior data and individual behavior data are stored in separate database partitions. The group behavior database partition is used for the identification of key disturbance nodes in subsequent steps, while the individual behavior database partition is used for the feedback correction of non-key disturbance nodes in subsequent steps.

[0075] The update cycle of the preset path length threshold is set according to the frequency of change in the density of people in the smart park. When the number of entities in the same area exceeds the preset density threshold, the preset path length threshold is recalculated. The recalculation process is based on the statistical distribution of the propagation path length of group behavior in the current real-time data.

[0076] The preset safe distance during the follow behavior detection process is set according to ergonomic standards, with a range of 0.5 meters to 1.5 meters. The specific value is determined by statistically analyzing the average follow distance of entities in historical data. During the dynamic interaction data segmentation process, if the same entity exhibits both follow and avoidance behaviors within a continuous time window, the final classification is determined based on the behavior type with the higher duration within the time window. The duration percentage is calculated by dividing the sum of the time segments of different behavior types by the total duration.

[0077] The judgment logic of the data classifier is implemented through a programmable logic controller (PLC). The PLC's parameter configuration interface allows administrators to adjust the preset path length threshold and behavior type judgment rules according to the actual scenario. After the parameters are adjusted, the data classifier automatically reloads the configuration and performs data partitioning.

[0078] The segmented group behavior data and individual behavior data are displayed using a data visualization tool. The data visualization tool marks the group behavior data with the first color and the individual behavior data with the second color. The data of different colors are overlaid and displayed on the digital twin map of the smart park.

[0079] The results of dynamic interactive data partitioning are recorded in log files. The log files include the partitioning time, the number of data entries, and a summary of the classification criteria. The storage path of the log files is associated with the database partition path, and the access permissions of the log files are set according to the administrator role hierarchy.

[0080] S3. Based on the propagation path hierarchy and density dynamic changes of group behavior data, identify key disturbance nodes that meet preset disturbance conditions, including:

[0081] The propagation path hierarchy is determined by counting the number of nodes affected by the group behavior data. Nodes are physical areas or devices with independent identification within the smart park. Physical areas include entrances and exits, passage intersections, or gathering areas. Devices include cameras or sensors. The number of nodes covered by the affected area is calculated by accumulating the number of nodes traversed by the propagation path of the group behavior data.

[0082] The propagation path of group behavior data is generated by superimposing the movement trajectories of entity objects. The movement trajectory is the position sequence of entity objects within a preset time period. The sampling interval of the position sequence is dynamically adjusted according to the movement speed of the entity objects. The faster the entity objects move, the shorter the sampling interval.

[0083] The rate of density change is calculated by recording the population density distribution values ​​within adjacent time windows and calculating the difference. The length of the time window is set according to the fluctuation frequency of pedestrian flow in the smart park. A shorter time window is used when pedestrian flow fluctuations are frequent, and a longer time window is used when pedestrian flow fluctuations are gentle.

[0084] The preset propagation path level range is set according to the statistical distribution of group behavior propagation paths in historical data. For example, when the group behavior propagation path levels in historical data are concentrated in the first to third levels, the preset propagation path level range is set to the first to third levels. The first level corresponds to affecting 1 to 3 nodes, the second level corresponds to affecting 4 to 6 nodes, and the third level corresponds to affecting 7 to 9 nodes.

[0085] The preset density change rate range is determined by analyzing the mutation threshold of population density in historical data. For example, when the density increase exceeds 10% or the decrease exceeds 15% per unit time, it is determined that the density change rate exceeds the preset range.

[0086] The comparison between the propagation path level and the preset propagation path level range is achieved by traversing the propagation path level of the current group behavior data and checking whether it is between the preset minimum level and the maximum level. For example, when the propagation path level is the second level and the preset range is from the first level to the third level, it is determined to meet the conditions.

[0087] The comparison between the density change rate and the preset density change rate range is achieved by calculating the absolute value of the current density change rate and comparing it with the preset threshold. For example, when the density change rate reaches 12% per minute, it exceeds the preset threshold of 10% per minute and is determined to be outside the preset range.

[0088] The logic for determining critical disturbance nodes is that a node is marked as a critical disturbance node if and only if the propagation path level is within a preset level range and the density change rate exceeds a preset speed range. For example, if the propagation path level of a certain area is the second level and the density change rate increases by 12% per minute, then the area is determined to be a critical disturbance node.

[0089] The preset propagation path hierarchy range is updated by periodically analyzing the distribution of the propagation path hierarchy in the latest group behavior data. The update cycle is set according to the type of activity in the smart park, for example, once a day during large-scale events and once a week during regular operations.

[0090] The preset density change rate range is dynamically adjusted by monitoring the variance of density changes in real-time data. When the variance continuously exceeds the historical variance mean, the preset density change rate range is automatically expanded, for example, from increasing by 10% per minute to increasing by 12% per minute. The marking information of key disturbance nodes includes node identifier, propagation path level, density change rate, and judgment timestamp. The marking information is stored in a separate key node database partition.

[0091] During the calculation of the propagation path hierarchy, if a node is affected by multiple group behavior data at the same time, the propagation path hierarchy is calculated by weighting the number of group behavior data that affect the node. For example, when a node is affected by three group behavior data, the propagation path hierarchy is the average of the hierarchy of the three group behavior data.

[0092] In the process of calculating the rate of density change, if the population density distribution value within a certain time window is missing due to abnormal data collection, it is supplemented by linear interpolation of the density distribution values ​​of the previous time window and the next time window. The weight of the linear interpolation is allocated according to the ratio of the missing window to the time distance before and after it.

[0093] The relationship between the preset propagation path level range and the preset density change rate range is achieved by establishing a two-dimensional decision matrix. The rows of the two-dimensional decision matrix correspond to the propagation path level, the columns correspond to the density change rate, and the matrix elements are the decision results (key nodes or non-key nodes). The parameters of the two-dimensional decision matrix are trained based on the frequency of occurrence of key nodes in historical data.

[0094] The results of identifying key disturbance nodes are marked with highlighted blocks on the digital twin map using visualization tools. The color of the blocks is displayed in a graded manner according to the combination of the propagation path level and the speed of density change. For example, red corresponds to nodes with high level and fast speed, and orange corresponds to nodes with medium level and medium speed.

[0095] The judgment log of key disturbance nodes includes the judgment time, node identifier, propagation path level, density change rate and judgment basis. The log file is indexed by timestamp and associated with the simulation result database, and supports retrieval by time range or node identifier.

[0096] During the determination of critical disturbance nodes, if a node is determined to be a critical node in multiple consecutive time windows, an early warning mechanism is triggered. The warning level increases according to the number of consecutive time windows. For example, a level one warning is triggered when a node is determined to be a critical node in three consecutive time windows, and a level two warning is triggered when a node is determined to be a critical node in five consecutive time windows.

[0097] The initial values ​​of the preset propagation path level range and the preset density change rate range are configured through the administrator interface, which provides a slider or numerical input box for users to adjust.

[0098] The determination results of key disturbance nodes are transmitted to the emergency management system of the smart park through the application programming interface. The emergency management system automatically generates evacuation routes or resource dispatch instructions based on the location and severity of the key nodes.

[0099] S4. Based on the dynamic differences between the entity attribute data and historical behavior data of key disturbance nodes, and combined with the propagation path hierarchy between key disturbance nodes and other nodes, assess the correlation strength and generate dynamic adjustment strategies, including:

[0100] The position offset in the entity attribute data of key disturbance nodes is calculated by the Euclidean distance difference between real-time position coordinates and historical position coordinates. The formula for calculating the Euclidean distance difference is as follows: ;in, This represents the difference in Euclidean distance. and This indicates the real-time location coordinates of the key disturbance nodes at the current moment. and This indicates the location coordinates of the same node in the historical data. The historical data is the average location data within the same time period over a preset number of consecutive days. For example, the average location coordinates at the same time over the past 7 days can be selected as historical data.

[0101] The rate of change of velocity is calculated by the ratio of real-time velocity to historical velocity. Real-time velocity is the instantaneous velocity value collected by the inertial sensor at the current moment, while historical velocity is the average velocity value of the same node in the historical data of the same period.

[0102] The statistical period for historical velocity is consistent with the statistical period for historical location coordinates. The propagation path level coverage ratio is calculated by dividing the number of propagation path levels of the key disturbance node by the number of propagation path levels of other nodes. The number of propagation path levels is determined based on the propagation path levels identified in step S3. For example, if the number of propagation path levels of the key disturbance node is 5 and the number of propagation path levels of other nodes is 3, then the coverage ratio is 5 / 3.

[0103] The dynamic adjustment strategy is generated by multiplying the dynamic variation difference by the coverage ratio of the propagation path hierarchy. The product calculation formula is as follows: ;in, This represents the coverage ratio of the propagation path hierarchy. For strategy weight coefficients, The velocity is the rate of change.

[0104] The strategy weighting coefficient is used to calculate the propagation direction offset angle and the density weight allocation ratio. The propagation direction offset angle is calculated by multiplying the strategy weighting coefficient by a preset reference angle. The preset reference angle is set according to the physical structure of the path layout in the smart park. For example, the reference angle is set to 30 degrees in a straight channel and 45 degrees in a curved channel.

[0105] The density weight allocation ratio is calculated by the ratio of the strategy weight coefficient to the preset benchmark density. The preset benchmark density is set according to the average population density distribution value of the same area in historical data. For example, when the strategy weight coefficient is 1.8 and the benchmark density is 50 people / square meter, the density weight allocation ratio is 1.8 / 50=0.036.

[0106] When the dynamic change difference exceeds the change threshold of the historical data for the same period, the change threshold of the historical data for the same period is determined by statistically analyzing the 90th percentile of the dynamic change difference within a preset period. For example, when the 90th percentile of the dynamic change difference over the past 30 days is 1.5, the change threshold is set to 1.5.

[0107] The priority adjustment rule is as follows: when the dynamic change difference exceeds the change threshold, the calculation weight of the propagation direction offset angle is increased to the preset priority coefficient. The preset priority coefficient is configured through the administrator interface. For example, if the priority coefficient is set to 2, the propagation direction offset angle will be adjusted to twice the original calculated value.

[0108] During the generation of the dynamic adjustment strategy, if the coverage ratio of the propagation path hierarchy of the key disturbance node is less than 1, the density weight allocation ratio will be limited to no more than a preset upper limit. The preset upper limit is set according to the maximum value of the density weight in the historical data. For example, when the historical maximum density weight is 0.05, the upper limit is set to 0.05.

[0109] The calculation results of the policy weight coefficients are recorded in a log file. The log file includes the calculation time, key disturbance node identifiers, policy weight coefficients, and priority adjustment flags. The log file is indexed by timestamps and associated with the simulation results database.

[0110] The propagation direction offset angle and density weight allocation ratio are displayed on the digital twin map using visualization tools as vector arrows and color block transparency. The length of the vector arrow represents the size of the offset angle, and the color block transparency represents the density weight.

[0111] The effective period of the dynamic adjustment strategy is dynamically set according to the density change rate of the key disturbance nodes. The faster the density change rate, the shorter the effective period. For example, when the density change rate exceeds 10% per minute, the effective period is shortened to 10 seconds.

[0112] The preset reference angle and preset reference density are updated through periodic analysis of the latest data. The update cycle is synchronized with the update cycle of the preset disturbance conditions in step S3, for example, once a week. The parameter configuration interface of the dynamic adjustment strategy allows the administrator to manually adjust the preset reference angle, preset reference density, and priority coefficient. After the parameters are adjusted, the strategy is automatically recalculated and the simulation model is updated.

[0113] S5. Adjust the propagation direction and density weight of key disturbance nodes in the dynamic simulation model based on the propagation path hierarchy and correlation strength, and generate simulation results, including:

[0114] In the dynamic simulation model, the movement direction adjustment of key disturbance nodes is achieved by vector synthesis of the propagation direction offset angle and the current propagation direction. The current propagation direction is the real-time movement direction of the entity object in the dynamic simulation model, and the propagation direction offset angle is the parameter in the dynamic adjustment strategy generated in step S4. The vector synthesis calculation process is to superimpose the unit vector corresponding to the current propagation direction with the rotation vector corresponding to the offset angle, and the direction of the superimposed vector is used as the adjusted movement direction.

[0115] The density weight is adjusted by multiplying the current density value by the density weight allocation ratio generated in step S4. The current density value is the real-time population density distribution value of the area where the key disturbance node is located in the dynamic simulation model. The density weight allocation ratio is calculated in step S4 by multiplying the dynamic change difference and the coverage ratio of the propagation path level. For example, when the current density value is 50 people / square meter and the allocation ratio is 0.036, the updated density weight is 50 × 0.036 = 1.8.

[0116] After the adjusted movement direction and density weights are input into the dynamic simulation model, the dynamic simulation model recalculates the motion trajectory and density distribution of the entity object based on the updated parameters, and generates simulation results. The output format of the simulation results is a data sequence containing timestamps, position coordinates and density values.

[0117] The density weight of adjacent nodes is updated synchronously by proportionally allocating the association strength. The association strength is the coverage ratio of the propagation path level calculated in step S4. The synchronization update ratio is the product of the association strength and the preset ratio range. The preset ratio range is set according to the density fluctuation threshold of adjacent nodes in historical data. For example, when the association strength is 1.5 and the preset ratio range is 0.1, the synchronization update ratio is 1.5 × 0.1 = 0.15, and the density weight of adjacent nodes is updated to the current density value × 0.15.

[0118] During the vector synthesis process of the propagation direction offset angle and the current propagation direction, if the offset angle exceeds the preset angle upper limit, the offset angle will be limited. The preset angle upper limit is set according to the maximum allowable turning angle of the path in the smart park. For example, the upper limit is set to 90 degrees at a right-angle turn, and the part exceeding it is calculated as 90 degrees.

[0119] In the application of density weight allocation ratio, if the updated density weight exceeds the maximum load threshold of the dynamic simulation model, the weight correction mechanism is triggered. The maximum load threshold is set according to the design parameters of the dynamic simulation model. For example, if the maximum load threshold is 2.0, it will be forcibly corrected to 2.0 when it is exceeded.

[0120] The scope of synchronous updates for adjacent nodes is determined based on the number of propagation path levels of the critical disturbance node. The higher the number of propagation path levels, the more adjacent nodes are updated synchronously. For example, when the number of propagation path levels is 3, the 3 nodes directly adjacent to the critical disturbance node are updated synchronously.

[0121] The timing at which the adjusted movement direction takes effect in the dynamic simulation model is set according to the simulation time step, which is synchronized with the real-time data acquisition frequency. For example, if real-time data is acquired once per second, the simulation time step is set to 1 second. The update results of the density weights are recorded in a log file, which includes the update time, node identifier, original density value, updated density value, and synchronization update ratio. The log file storage path is associated with the simulation result database.

[0122] The priority of synchronous updates between adjacent nodes is sorted according to the strength of the association. Adjacent nodes with higher association strength are updated first. For example, a node with an association strength of 2.0 will update before a node with an association strength of 1.0.

[0123] During the recalculation of the dynamic simulation model, if the deviation between the simulation result and the real-time data exceeds the preset fault tolerance threshold, the model parameter rollback mechanism is triggered. The preset fault tolerance threshold is set according to the statistical distribution of historical simulation errors. For example, when the deviation exceeds the 95th percentile of historical errors, the parameters are rolled back to the previous time step.

[0124] In the process of vector synthesis calculation of the propagation direction offset angle, if the current propagation direction is a zero vector, the direction corresponding to the offset angle is directly used as the adjusted movement direction.

[0125] The preset range of density weight allocation ratio can be configured through the administrator interface. The administrator interface provides input boxes for the minimum and maximum values ​​of the ratio range. The input values ​​are limited to decimals between 0 and 1. For example, the ratio range can be set to 0.01 to 0.05.

[0126] The effective conditions for the synchronization update ratio are dynamically adjusted based on the density change rate of adjacent nodes. The faster the density change rate, the lower the effective ratio. For example, when the density change rate exceeds 15% per minute, the effective ratio is reduced to 50% of the original ratio.

[0127] The output simulation results of the dynamic simulation model are displayed through a visualization interface. The visualization interface displays the adjusted movement direction as an arrow icon superimposed on the digital twin map. The length and direction of the arrow correspond to the adjusted movement direction parameters. The density weight is presented as a color gradient heat map, with the color depth corresponding to the density weight.

[0128] It is worth noting that the dynamic simulation model is a digital twin model, which is a simulation program based on real-time state data and dynamic adjustment strategies. It receives the propagation direction offset angle and density weight allocation ratio generated in step S4 as input parameters. By updating the movement direction vector and density weight value of key disturbance nodes, it simulates the motion trajectory of the entity and the change of the group density distribution, and outputs a simulation result data sequence containing timestamps, location coordinates and density values.

[0129] S6. When the deviation between the behavioral data of non-critical disturbance nodes and the simulation results exceeds a preset range, the behavioral weights of non-critical disturbance nodes are updated in reverse based on the association strength at the propagation path level, including:

[0130] The dynamic deviation rate is calculated by dividing the absolute value of the difference between real-time behavior data and simulated behavior data by the historical average deviation. The historical average deviation is the average absolute value of the deviation at the same node within the same time period over a consecutive preset number of days. For example, the average deviation value from 9 am to 10 am over the past 30 days is used as the historical benchmark.

[0131] The set of association strengths of propagation path levels is obtained by traversing all key disturbance nodes and calculating the propagation path level coverage ratio between each key disturbance node and non-key disturbance nodes. The propagation path level coverage ratio is the quotient of the number of levels of a single key disturbance node generated in step S4 divided by the number of levels of non-key disturbance nodes. For example, when the key disturbance node level is 5 and the non-key disturbance node level is 2, the coverage ratio is 5 / 2 = 2.5.

[0132] The calculation of the behavior weight correction ratio is achieved by multiplying the maximum value in the set of association strengths by a preset adjustment coefficient. The preset adjustment coefficient is set according to the effectiveness statistics of the correction ratio in historical data. For example, when the correction ratio in historical data is 0.8, the deviation suppression effect is the best, so the preset adjustment coefficient is set to 0.8.

[0133] The preset deviation threshold for dynamic deviation rate is determined by analyzing the 90th percentile of dynamic deviation rate in historical data. For example, when the 90th percentile of historical dynamic deviation rate is 1.2, the preset deviation threshold is set to 1.2.

[0134] The formula for adjusting the weights of the reverse behavior is: ;in, For the adjusted behavior weights, As the weight of the current action, Adjust the weight ratio for the behavior.

[0135] The priority of the dynamic adjustment strategy for synchronously updating key disturbance nodes is achieved by reducing the priority coefficient of the corresponding key disturbance node. The reduction of the priority coefficient is 50% of the correction ratio. For example, when the correction ratio is 0.8, the priority coefficient is reduced by 0.4.

[0136] If the adjusted behavioral weights still cause the dynamic deviation rate to exceed the preset deviation threshold, the correction ratio is recalculated based on the second largest value in the association strength set. The formula for the second correction is: ;in, This is a secondary correction ratio; This is the initial correction ratio; This is the secondary correction attenuation coefficient, for example, set to 0.5.

[0137] The secondary correction attenuation coefficient is set based on the success rate of secondary correction in historical data. For example, when the historical success rate of secondary correction is 60%, the secondary correction attenuation coefficient is set to 0.6.

[0138] Elements in the association strength set are sorted from largest to smallest. If the same coverage ratio appears during the sorting process, they are sorted according to the density change rate of the key perturbation nodes, with nodes having higher density change rates having higher priority. The secondary correction results of the behavior weights are recorded in a log file, which includes the correction time, node identifier, initial correction ratio, secondary correction ratio, and final behavior weight. The log file storage path is associated with the simulation result database of step S5.

[0139] The reverse-adjusted behavioral weights are displayed as numerical labels overlaid on the digital twin map using visualization tools. The color of the numerical labels changes gradually according to the magnitude of the correction ratio; for example, they are displayed in red when the correction ratio is greater than 0.5 and in green when it is less than 0.3.

[0140] The synchronous update results of the priority of key disturbance nodes are transmitted to the dynamic adjustment strategy in step S4, triggering the reloading and activation of the strategy parameters. During the calculation of the dynamic deviation rate, if the historical average deviation is zero, a preset minimum deviation value is used instead. The preset minimum deviation value is set according to the minimum resolution of the dynamic simulation model, for example, the minimum deviation value is set to 0.1.

[0141] During the application of the behavior weight correction ratio, if the correction ratio exceeds the preset upper limit, the correction ratio will be limited. The preset upper limit is set based on the maximum effective value of the correction ratio in historical data, for example, the upper limit is set to 0.9. The update cycle of the association strength set is synchronized with the data collection cycle of non-critical disturbance nodes. For example, data is collected every 5 seconds, and the association strength set is updated every 5 seconds.

[0142] The triggering conditions for secondary correction also include checking whether the second largest value in the association strength set is greater than a preset association strength threshold. The preset association strength threshold is set based on the statistical distribution of effective association strengths in historical data. For example, secondary correction is allowed when the second largest value is greater than 1.0. The timing of the reverse-adjusted behavioral weights taking effect in the dynamic simulation model is synchronized with the simulation time step. For example, if the simulation time step is 1 second, the behavioral weights are updated every 1 second.

[0143] Example 2: Figure 2 A schematic diagram of the structure of an AI-based smart park digital twin system is provided. The AI-based smart park digital twin system includes:

[0144] Data acquisition module: Acquires real-time status data of entities within the smart park, including entity attribute data and dynamic interaction data;

[0145] Classification processing module: Based on the propagation path length and behavior type of dynamic interactive data, the dynamic interactive data is divided into group behavior data and individual behavior data;

[0146] Node identification module: Based on the propagation path hierarchy and density dynamic changes of group behavior data, identify key disturbance nodes that meet preset disturbance conditions;

[0147] Strategy generation module: Based on the dynamic changes in the entity attribute data and historical behavior data of key disturbance nodes, and combined with the evaluation of the correlation strength between key disturbance nodes and other nodes through the propagation path hierarchy, a dynamic adjustment strategy is generated.

[0148] Simulation construction module: Based on the propagation path hierarchy and correlation strength, adjust the propagation direction and density weight of key disturbance nodes in the dynamic simulation model to generate simulation results;

[0149] Feedback correction module: When the deviation between the behavior data of non-critical disturbance nodes and the simulation results exceeds the preset range, the behavior weights of non-critical disturbance nodes are updated in reverse based on the correlation strength of the propagation path level.

[0150] The above formulas are all dimensionless calculations. The formulas are derived from software simulations using a large amount of collected data, and are the closest to the real situation. The preset parameters and thresholds in the formulas are set by those skilled in the art according to the actual situation.

[0151] It should be noted that this invention can be deployed on the device itself to realize embedded applications, or it can run on a PC or other terminal with a user interface, thereby meeting various hardware environments and usage requirements.

[0152] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented using software, the above embodiments can be implemented, in whole or in part, as a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more sets of available media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium can be a solid-state drive.

[0153] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and modules described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0154] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple modules or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or modules may be electrical, mechanical, or other forms.

[0155] The modules described as separate components may or may not be physically separate. The components shown as modules may or may not be physical modules; they may be located in one place or distributed across multiple network modules. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0156] In addition, the functional modules in the various embodiments of this application can be integrated into one processing module, or each module can exist physically separately, or two or more modules can be integrated into one module.

[0157] If the aforementioned functions are implemented as software functional modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0158] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

[0159] In conclusion, the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. A method for creating a digital twin of a smart park based on artificial intelligence, characterized in that, Includes the following steps: S1. Obtain real-time status data of entities within the smart park. Real-time status data includes entity attribute data and dynamic interaction data. S2. Based on the propagation path length and behavior type of dynamic interactive data, dynamic interactive data is divided into group behavior data and individual behavior data. S3. Identify key disturbance nodes that meet preset disturbance conditions based on the propagation path hierarchy and density dynamic changes of group behavior data; S4. Based on the dynamic changes in the entity attribute data and historical behavior data of key disturbance nodes, and combined with the propagation path hierarchy of key disturbance nodes and other nodes, assess the correlation strength and generate dynamic adjustment strategies. S5. Adjust the propagation direction and density weight of key disturbance nodes in the dynamic simulation model based on the propagation path hierarchy and correlation strength to generate simulation results; S6. When the deviation between the behavioral data of non-critical disturbance nodes and the simulation results exceeds the preset range, the behavioral weights of non-critical disturbance nodes are updated in reverse based on the correlation strength of the propagation path level.

2. The method for creating a smart park digital twin based on artificial intelligence according to claim 1, characterized in that, Entity attribute data includes location and real-time movement speed, while dynamic interaction data includes avoidance behavior, following behavior, and group density distribution between entity objects.

3. The method for creating a smart park digital twin based on artificial intelligence according to claim 2, characterized in that, Based on the propagation path length and behavior type of dynamic interactive data, dynamic interactive data is divided into group behavior data and individual behavior data, including: Iterate through the propagation path length of dynamic interactive data and select dynamic interactive data whose propagation path length exceeds a preset path length threshold. Associate dynamic interactive data whose propagation path length exceeds a preset path length threshold with behavior type; Detect dynamic interaction data of follow-up behaviors in the detection behavior type; The dynamic interaction data corresponding to the detected following behavior is classified as group behavior data, and the remaining dynamic interaction data is classified as individual behavior data.

4. The method for creating a smart park digital twin based on artificial intelligence according to claim 3, characterized in that, Based on the propagation path hierarchy and density dynamic changes of group behavior data, key disturbance nodes that meet preset disturbance conditions are identified, including: Determine the propagation path hierarchy of group behavior data, and divide the propagation path hierarchy according to the number of nodes covered by the influence scope of group behavior data; The rate of change of density in group behavior data is detected, and the rate of change of density is calculated by the increase or decrease of the group density distribution value per unit time. Compare the propagation path level with the preset propagation path level range, and compare the density change rate with the preset density change rate range; When the propagation path level is within the preset propagation path level range and the density change rate exceeds the preset density change rate range, the corresponding node is determined to be a critical disturbance node.

5. The method for creating a smart park digital twin based on artificial intelligence according to claim 4, characterized in that, Based on the dynamic differences between the entity attribute data and historical behavior data of key disturbance nodes, and by assessing the correlation strength between key disturbance nodes and other nodes through the propagation path hierarchy, a dynamic adjustment strategy is generated, including: Based on the position offset and velocity change rate in the entity attribute data of the key disturbance nodes, the dynamic change difference between the current time and the historical data of the same period is calculated. The position offset is the difference in Euclidean distance between the real-time position coordinates and the historical position coordinates, and the velocity change rate is the ratio of the real-time velocity to the historical velocity. Determine the propagation path level coverage ratio between the critical disturbance node and other nodes. The propagation path level coverage ratio is the quotient of the number of propagation path levels of the critical disturbance node and the number of propagation path levels of other nodes. A dynamic adjustment strategy is generated based on the product of the dynamic change difference and the coverage ratio of the propagation path hierarchy. The dynamic adjustment strategy includes the propagation direction offset angle and the density weight allocation ratio. When the dynamic changes exceed the change threshold of historical data for the same period, the priority of adjusting the propagation direction offset angle is based on the coverage ratio of the propagation path hierarchy.

6. The method for creating a smart park digital twin based on artificial intelligence according to claim 5, characterized in that, Based on the propagation path hierarchy and correlation strength, the propagation direction and density weight of key perturbation nodes in the dynamic simulation model are adjusted to generate simulation results, including: Based on the offset angle of the propagation direction, the movement direction of the key disturbance nodes in the dynamic simulation model is adjusted. The movement direction is calculated based on the vector synthesis of the offset angle and the current propagation direction. Based on the density weight allocation ratio, the density weight of key perturbation nodes in the dynamic simulation model is adjusted, and the density weight is updated by multiplying the current density value by the allocation ratio. The adjusted movement direction and density weights are input into the dynamic simulation model, and simulation calculations are performed to generate simulation results. Once the density weight of the critical disturbance node is updated, the density weight of the adjacent nodes is updated synchronously, and the distribution is proportional to the propagation path hierarchy association strength between the adjacent nodes and the critical disturbance node.

7. The method for creating a smart park digital twin based on artificial intelligence according to claim 6, characterized in that, When the deviation between the behavioral data of non-critical perturbation nodes and the simulation results exceeds a preset range, the behavioral weights of non-critical perturbation nodes are updated in reverse based on the association strength at the propagation path level, including: The dynamic deviation rate between the behavioral data of non-critical disturbance nodes and the simulation results is detected. The dynamic deviation rate is the ratio of the absolute value of the difference between the real-time behavioral data and the simulated behavioral data to the historical average deviation. Obtain the set of association strengths of the propagation path hierarchy between non-critical disturbance nodes and all critical disturbance nodes. Each element in the association strength set is the coverage ratio of the propagation path hierarchy between a single critical disturbance node and its corresponding non-critical disturbance node. Calculate the behavioral weight correction ratio of non-critical disturbance nodes based on the maximum value in the correlation strength set and the preset adjustment coefficient; When the dynamic deviation rate exceeds the preset deviation threshold, the behavior weight of non-critical disturbance nodes is adjusted in reverse based on the behavior weight correction ratio, and the dynamic adjustment strategy priority of the corresponding critical disturbance nodes in the association strength set is updated synchronously. If the adjusted behavior weights still cause the dynamic deviation rate to exceed the preset deviation threshold, then the behavior weight correction ratio will be recalculated based on the second largest value in the association strength set for a second correction.

8. A smart park digital twin system based on artificial intelligence, used to implement the smart park digital twin method based on artificial intelligence as described in any one of claims 1-7, characterized in that, include: Data acquisition module: Acquires real-time status data of entities within the smart park, including entity attribute data and dynamic interaction data; Classification processing module: Based on the propagation path length and behavior type of dynamic interactive data, the dynamic interactive data is divided into group behavior data and individual behavior data; Node identification module: Based on the propagation path hierarchy and density dynamic changes of group behavior data, identify key disturbance nodes that meet preset disturbance conditions; Strategy generation module: Based on the dynamic changes in entity attribute data and historical behavior data of key disturbance nodes, and combined with the evaluation of the correlation strength between key disturbance nodes and other nodes through the propagation path hierarchy, a dynamic adjustment strategy is generated. Simulation construction module: Based on the propagation path hierarchy and correlation strength, adjust the propagation direction and density weight of key disturbance nodes in the dynamic simulation model to generate simulation results; Feedback correction module: When the deviation between the behavior data of non-critical disturbance nodes and the simulation results exceeds the preset range, the behavior weights of non-critical disturbance nodes are updated in reverse based on the correlation strength of the propagation path level.

Images