Tourism digitalization simulation system and method

Abstract

This invention belongs to the field of tourism exhibition hall crowd control technology, specifically involving a tourism digital simulation system and method. By real-time monitoring of visitor gathering status in various exhibition areas, combined with analysis of the impact of new visitors on crowd gathering and prediction of their distribution ratio in each area, a dynamic simulation model of future crowd gathering trends is constructed using tourism digital simulation technology. Based on the simulation results of this model, the system can provide exhibition area recommendations for new visitors, optimize visitor flow distribution in a timely manner, effectively alleviate local congestion, improve space utilization and visitor comfort, thereby achieving refined, intelligent, and forward-looking crowd management in the exhibition hall, enhancing operational efficiency and visitor experience quality.

Description

Technical Field

[0001] This invention belongs to the field of tourism exhibition hall crowd control technology, specifically involving a tourism digital simulation system and method. Background Technology

[0002] With the continuous development of the tourism industry and the increasing demand for cultural consumption, the number of visitors to exhibition halls is growing daily, leading to increasingly significant crowd gatherings. This high density of people in certain areas not only affects the efficiency of passage within the exhibition hall but also reduces visitor comfort and experience. To address this challenge, the focus of exhibition hall management is gradually shifting towards refined crowd control.

[0003] Existing technologies already include solutions for controlling visitor flow in exhibition halls. For example, Chinese Invention Patent Publication No. CN119940706A proposes a method, device, equipment, and medium for guiding visitor flow in exhibition halls. This solution customizes explanatory videos and their placement strategies (including playback duration and cycle) for each sub-area of ​​the exhibition hall, and dynamically adjusts the video placement strategy based on real-time visitor flow monitoring in each area. When the visitor flow in a certain area is too high, the frequency of video playback in that area is increased or the playback interval is shortened to attract visitors to relatively empty areas, thereby achieving a balanced distribution of visitor flow, reducing reliance on manual guidance, and saving operating costs.

[0004] However, this type of control method is essentially a post-event response control mechanism, that is, control measures are only activated after the flow of people exceeds the set threshold. It lacks the ability to predict the trend of changes in the flow of people in advance. In particular, it fails to effectively predict and guide the exhibition areas that new visitors may choose before they enter the exhibition hall, resulting in a lag in control and difficulty in dealing with sudden surges in visitor flow.

[0005] Furthermore, the aforementioned scheme primarily relies on the number of visitors within a statistical area for monitoring pedestrian flow. This reliance on a single evaluation indicator ignores the micro-level characteristics of crowd aggregation within the exhibition area. Under the same number of visitors, different crowd aggregation patterns significantly impact visitor experience quality, traffic efficiency, environmental comfort, and safety risk levels. Therefore, using only visitor numbers as the basis for control measures can easily lead to misjudgments or over-intervention in crowd flow management strategies, affecting the accuracy and effectiveness of control. Summary of the Invention

[0006] This invention aims to overcome the problems of lagging and crude control in existing exhibition hall crowd management. It proposes a tourism digital simulation system and method, which monitors the crowd gathering status of each exhibition area in real time and introduces tourism digital simulation technology to predict the crowd gathering of each exhibition area after new tourists enter the exhibition hall. Based on this, dynamic guidance is implemented to achieve refined and forward-looking scheduling of exhibition hall crowd management.

[0007] The objective of this invention can be achieved through the following technical solution: The first aspect of this invention provides a digital simulation system for tourism, comprising: an image acquisition module: using image acquisition devices deployed in various exhibition areas of the exhibition hall to acquire real-time images of tourist distribution.

[0008] Crowd aggregation analysis module: Extracts aggregation features from visitor distribution images, including the number of clusters, cluster coverage area, number of visitors within a cluster, and distance between adjacent clusters, and analyzes the crowd aggregation degree in conjunction with the exhibition area layout.

[0009] A new clustering correlation module has been added: By comparing tourist distribution images from adjacent collection times, the module establishes a correspondence between the increase in tourist volume and the increase in population density, and analyzes the tendency of the increase in density corresponding to the increase in unit tourist volume.

[0010] Distribution prediction module: By using path tracking devices deployed at the entrance of the exhibition hall to obtain the preferred exhibition areas of visitors entering the exhibition hall, the distribution ratio of new visitors in each exhibition area is predicted.

[0011] Risk simulation module: It connects with the exhibition hall ticketing system to obtain the number of new visitors in future time periods, and simulates the increase in the population density of each exhibition area after the new visitors enter, based on the allocation ratio and the tendency of the population density increase corresponding to the increase in the number of visitors per unit in each exhibition area.

[0012] Risk identification module: Identify safe exhibition areas by using the simulated incremental values ​​of crowd gathering in each exhibition area.

[0013] Exhibition Area Recommendation Module: Based on the distribution of safe exhibition areas, this module recommends the preferred exhibition areas for new visitors and displays them at the entrance of the exhibition hall.

[0014] The second aspect of the present invention proposes a digital simulation method for tourism, comprising the following steps: S1: Real-time acquisition of tourist distribution images using image acquisition devices deployed in various exhibition areas of the exhibition hall.

[0015] S2: Extract clustering features from the tourist distribution image, including the number of clusters, cluster coverage area, number of tourists within a cluster, and distance between adjacent clusters, and analyze the degree of crowd gathering in combination with the exhibition area layout.

[0016] S3: By comparing tourist distribution images from adjacent collection times, establish the correspondence between tourist increment and population density increment, and conduct correlation analysis on the tendency of population density increment corresponding to unit tourist increment.

[0017] S4: By using path tracking devices deployed at the entrance of the exhibition hall to obtain the preferred exhibition areas of visitors entering the exhibition hall, the distribution ratio of new visitors in each exhibition area can be predicted.

[0018] S5: Connect with the exhibition hall ticketing system to obtain the number of new visitors in future time periods, and simulate the increase in the population density of each exhibition area after the new visitors enter, based on the allocation ratio and the tendency of the population density increase corresponding to the increase in the number of visitors per unit in each exhibition area.

[0019] S6: Identify safe exhibition areas by using the simulated incremental values ​​of crowd density in each exhibition area.

[0020] S7: Recommend the preferred exhibition areas for new visitors based on the distribution of the security exhibition areas and display them at the entrance of the exhibition hall.

[0021] Combining all the above technical solutions, the positive effects of this invention are as follows: 1. By real-time monitoring of visitor gathering status in each exhibition area of ​​the exhibition hall, combined with the analysis of the impact of new visitors on the gathering of people and the prediction of their distribution ratio in each exhibition area, this invention introduces tourism digital simulation technology to dynamically simulate the gathering of people in future periods. Based on this, it provides exhibition area visits recommendations for new visitors, optimizes visitor flow distribution in a timely manner, effectively alleviates local congestion, and thus achieves refined and forward-looking control of visitor flow management in the exhibition hall, which is conducive to enhancing operational management efficiency and visitor experience quality.

[0022] 2. The present invention monitors the gathering status of each exhibition area in the exhibition hall by taking the cluster as the unit, and realizes the detailed presentation of the gathering behavior of tourists in the exhibition area at the micro level. It can reflect the spatial organization characteristics of the crowd more precisely, provide higher precision data support for subsequent crowd flow control, and significantly improve the sensitivity and scientific nature of crowd flow control. Attached Figure Description

[0023] The present invention will be further described with reference to the accompanying drawings, but the embodiments in the drawings do not constitute any limitation on the present invention. For those skilled in the art, other drawings can be obtained based on the following drawings without creative effort.

[0024] Figure 1 This is a schematic diagram of the module connection of a tourism digitalization simulation system provided in Embodiment 1 of the present invention.

[0025] Figure 2 This is an operational implementation diagram of the crowd gathering analysis module in this invention.

[0026] Figure 3 This is a flowchart illustrating the steps of a digital simulation method for tourism provided in Embodiment 2 of the present invention. Detailed Implementation

[0027] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0028] Example 1

[0029] This invention provides a digital simulation system for tourism, comprising: an image acquisition module, a crowd gathering analysis module, a new gathering association module, an allocation prediction module, a risk simulation module, a risk identification module, and an exhibition area recommendation module.

[0030] See Figure 1 As shown, in the above modules, the image acquisition module is connected to the crowd gathering analysis module, the crowd gathering analysis module is connected to the new gathering association module, the new gathering association module and the allocation prediction module are both connected to the risk simulation module, the risk simulation module is connected to the risk identification module, and the risk identification module is connected to the exhibition area recommendation module.

[0031] Specifically, the image acquisition module is used to collect real-time images of visitor distribution using image acquisition devices deployed in various exhibition areas of the exhibition hall.

[0032] In a preferred embodiment, the image acquisition equipment includes, but is not limited to, high-definition cameras and infrared thermal imaging devices, used to acquire images of visitor distribution in each exhibition area at a fixed frequency.

[0033] See Figure 2 As shown, the crowd aggregation analysis module is used to extract aggregation features from the tourist distribution image, including the number of clusters, the cluster coverage area, the number of tourists in the cluster, and the distance between adjacent clusters, and analyzes the crowd aggregation degree in combination with the exhibition area layout.

[0034] It should be noted that the purpose of extracting clustering features from tourist distribution images is to depict the local clustering state of people flow at a micro level, breaking through the traditional coarse-grained analysis method that only relies on the overall number of people in the region.

[0035] The clustering characteristics were chosen based on the number of clusters, the area covered by the clusters, the number of tourists within the clusters, and the distance between adjacent clusters. This is because the number of clusters reflects the dispersion of the population distribution within the region and reveals the spatial complexity of the flow of people.

[0036] Cluster coverage area represents the spatial extent of a specific clustered region.

[0037] The number of tourists within a cluster reflects the flow of people in a local area.

[0038] The combination of cluster coverage area and the number of tourists within the cluster can reflect the population density of a local area.

[0039] The spacing between adjacent clusters characterizes the spatial proximity between different clustering regions.

[0040] The aforementioned clustering characteristics together constitute a multidimensional characterization of the spatial distribution and density level of crowd gathering, providing comprehensive and detailed data for subsequent crowd gathering degree assessment.

[0041] In the manner that the above modules can achieve, the process of extracting clustering features from tourist distribution images is as follows: perform background segmentation on the collected tourist distribution images to separate the foreground region containing tourist activities.

[0042] In the example of the above implementation method, background segmentation can be implemented by background modeling. Background segmentation can effectively remove background interference, focus on the tourist activity area, and improve the accuracy and efficiency of subsequent processing steps.

[0043] Individual tourists are identified within the extracted foreground region, and the location of each tourist in the image is marked with a bounding box.

[0044] The identification and location labeling of individual tourists provided a reliable data foundation for subsequent calculations of distances and clustering between adjacent tourists, which is helpful for more refined analysis of crowd gathering patterns.

[0045] Based on the location of each tourist in the image, the distance between adjacent tourists is obtained, and a clustering algorithm is used to divide tourists who are spatially close into the same cluster, combined with a preset proximity threshold.

[0046] The clustering algorithms mentioned above can effectively and automatically divide tourists into clusters based on their spatial distribution, discover naturally formed clustering patterns, and help understand the spatial structure of crowd gatherings.

[0047] The coverage area of ​​each cluster is obtained by extracting the boundary contour of each cluster, and the number of tourists in each cluster is counted.

[0048] The above method, by extracting the coverage area and number of tourists of each cluster, can quantify the size and density of each cluster.

[0049] The distance between adjacent clusters is obtained based on the geometric center point position of the corresponding boundary contour of the adjacent clusters.

[0050] As an example of the above scheme, the distance between adjacent clusters can be obtained by using the Euclidean distance formula based on the geometric center point of the corresponding boundary contour of adjacent clusters. The geometric center point serves as a representative position of the cluster, which facilitates the quantitative analysis of spatial relationships and helps to understand the relative positional relationships between different clusters.

[0051] In another way that the above module can be implemented, the content of crowd density analysis combined with the exhibition area layout is as follows: the total number of tourists is obtained by summing the number of tourists contained in each cluster in the tourist distribution image, and the basic crowd density is calculated by the ratio of the number of tourists to the physical area of ​​the exhibition area in the exhibition area layout. This can characterize the overall crowd density and is a basic indicator for measuring the congestion state at the macro level.

[0052] The local population density of each independent cluster is obtained by calculating the ratio of the number of tourists contained in the cluster to the area covered by the cluster. This reveals the differences in population density in different areas and reflects the uneven spatial utilization at the micro level.

[0053] It is important to understand that there may be multiple high-density gathering points and relatively open areas within the exhibition area, and relying solely on the overall crowd density cannot accurately reflect local risks.

[0054] Extract the ratio of the maximum and minimum local pedestrian density in all clusters to construct the cluster pedestrian flow difference degree.

[0055] The aforementioned construct of the crowd flow difference quantifies the degree of uneven distribution of crowd density among different areas within the exhibition area, reflecting the coordination and utilization efficiency of spatial resources in terms of crowd carrying capacity. When the local crowd density in a certain area is significantly higher than that in other areas, i.e., the greater the difference between the maximum and minimum local crowd density, the higher the crowd flow difference quantifies, indicating that some areas are experiencing over-concentration and are prone to crowding risks.

[0056] The distances between adjacent clusters are used to construct a cluster spacing matrix. The standard deviation of the distance data in this matrix is ​​calculated by standardizing the distance data in the matrix to construct the spatial dispersion of the clusters.

[0057] It should be noted that the above standardization of matrix distance data is to eliminate dimensions and unify data dimensions, thereby ensuring the accuracy and comparability of subsequent statistical analysis.

[0058] The spatial dispersion of the clusters described above is used to characterize the degree of concentration of the clusters in space. A larger value indicates a more significant difference in the distance between adjacent clusters, meaning that some clusters are too close together while others are too far apart. In particular, excessively small adjacent distances suggest that local high-density areas may be merging, forming larger areas of dense population, thus posing a higher security risk.

[0059] Using basic pedestrian density as a benchmark, and introducing the differences in pedestrian flow and the dispersion of the clustered space as micro-supplementary factors, a fusion model is constructed to obtain the degree of pedestrian flow clustering.

[0060] It should be noted that the baseline pedestrian density only reflects the average relationship between the number of tourists and the spatial area within a region. This is a coarse-grained description at the macro level and is insufficient to depict the non-uniform distribution of people in localized areas and the potential risk of spatial conflict. Therefore, relying solely on this indicator cannot comprehensively and accurately assess the degree of pedestrian gathering in complex scenarios. To address this, the fusion model introduces the two aforementioned micro-level additional factors to supplement and correct the baseline density, enabling a more detailed and scientific quantification of pedestrian gathering.

[0061] Example fusion model is In this model Indicates the degree of crowd gathering. Indicates the basic population density. , These represent the difference in the number of people gathered and the spatial dispersion of the gathering, respectively.

[0062] It should be noted that in the above fusion model This acts as a factor amplifying the total number of people, giving the model output practical physical meaning. The higher the basic population density, the greater the pressure on the exhibition area, and naturally, the higher the risk of overcrowding.

[0063] , Each reflects independently the degree of spatial unevenness and diffusion characteristics of the distribution of people.

[0064] This reflects the synergistic interaction effect between the degree of difference in pedestrian flow and the spatial dispersion. When high degree of difference and high dispersion coexist, it means that pedestrian flow is not only highly concentrated in a local area, but also its distribution shows a multi-point dispersion characteristic, which may lead to the simultaneous occurrence of multiple potential congestion areas, thereby significantly increasing the overall risk level.

[0065] This modeling approach, by quantifying the spatial heterogeneity and diffusion characteristics of pedestrian flow distribution, combining the amplification effect of total population size, and considering the synergistic interaction among multiple factors on the enhanced risk of pedestrian gathering, is more in line with the actual evolutionary laws and risk transmission mechanisms of pedestrian gathering behavior in complex spaces, thus improving the model's adaptability and predictive accuracy in dynamic environments.

[0066] The newly added clustering correlation module establishes a correspondence between the increase in tourist volume and the increase in population density by comparing tourist distribution images at adjacent collection times, and analyzes the tendency of the increase in population density corresponding to the increase in unit tourist volume.

[0067] In one optional implementation, the correspondence between the increase in the number of tourists and the increase in the density of crowds is established by comparing tourist distribution images at adjacent collection times as follows: The total number of tourists at adjacent collection times is compared using tourist distribution images collected in real time in each exhibition area to identify whether there is an increase in the number of tourists. If there is no significant increase in the number of tourists at the current adjacent collection time, the time window is continued to slide backward until the time interval where the increase in the number of tourists is identified is recorded as the increment time interval.

[0068] The aforementioned sliding window mechanism continues searching forward until a meaningful incremental interval is identified when no increase in tourists is detected in the current time window. This mechanism aligns with the discontinuous and sudden nature of changes in passenger flow, effectively preventing the omission of key incremental events.

[0069] For each incremental time interval, the difference in the number of tourists between two consecutive collection times is calculated as the tourist increment for that time interval. Simultaneously, the difference in the population density between the two consecutive collection times within that incremental time interval is calculated to form the population density increment for that time interval.

[0070] It is important to understand that when there is an increase in visitors to the exhibition area, the base population density in the population aggregation fusion model will increase accordingly, which will lead to an overall population aggregation trend. The specific increase is dynamic and depends on the spatial organization of the population flow in the exhibition area after the addition of visitors and its impact on local density and spatial structure, i.e., the aggregation population difference and aggregation space dispersion. Therefore, when there is an increase in visitors, there will inevitably be an increase in population aggregation.

[0071] The incremental tourist volume for each incremental time interval is paired with the corresponding incremental population density to form a correspondence.

[0072] In a further optional implementation, the correlation analysis of the tendency of the clustering increment corresponding to the unit increase in tourists is carried out as follows: for each increment time interval, the ratio between the increment of the population clustering and the increment of tourists is calculated to obtain the population clustering increment caused by the unit increase in tourists within that interval.

[0073] It is important to understand that the increase in the degree of crowd gathering caused by the increase in the number of visitors per incremental time interval represents the marginal contribution of each new visitor to the degree of crowd gathering in the exhibition area under specific time and spatial conditions.

[0074] Cluster analysis was performed on the incremental population density corresponding to the incremental increase of each unit of tourists in each incremental time interval to divide it into multiple cluster groups. The number of incremental time intervals contained in each cluster group was counted, and the dominant cluster group with the highest sample proportion was identified.

[0075] It should be noted that due to significant differences in tourists' behavioral characteristics and activity patterns at different times, the marginal contribution of a single tourist to the degree of crowd gathering in the exhibition area varies across different time periods. Cluster analysis can automatically identify time intervals with similar marginal contribution characteristics and group these time periods with similar response characteristics into the same category. This process helps to reveal the patterned regularity of the contribution of new tourists to the boundary of crowd gathering at different times.

[0076] The tendency of clustering increment per unit tourist increment is obtained by calculating the mean of the clustering increment per unit tourist increment in the dominant cluster group.

[0077] It's important to explain that selecting the cluster with the largest sample size as the dominant pattern reflects the marginal impact of a unit increase in visitor numbers on population density in most cases. This method avoids biases caused by isolated special cases, ensuring more representative and stable analysis results. The relationship between the unit increase in visitor numbers and the increase in population density within the dominant cluster represents the normal behavioral pattern in system operation. Therefore, using the average value within this group as the tendency for population density increase corresponding to a unit increase in visitor numbers has higher statistical reliability and practical application value.

[0078] This invention provides key parameter support for simulating the crowd gathering state after new visitors enter the exhibition hall by quantitatively analyzing the increase in crowd gathering caused by the increase in visitors to each exhibition area.

[0079] The allocation prediction module obtains the preferred exhibition area of ​​visitors entering the exhibition hall through path tracking devices deployed at the entrance of the exhibition hall, and predicts the allocation ratio of new visitors in each exhibition area accordingly.

[0080] In the specific implementation of the above scheme, the preferred exhibition area of ​​visitors entering the exhibition area is obtained by using path tracking equipment deployed at the entrance of the exhibition hall as follows: Infrared sensors deployed at the entrance of the exhibition hall are used to detect visitors. When a visitor is detected to have entered the exhibition hall, the path tracking equipment deployed in the entrance area is linked to track the visitor's location and construct their movement trajectory from the entrance in the time dimension.

[0081] It should be noted that by deploying infrared sensors at the entrance of the exhibition hall, the path tracking mechanism is only activated after a visitor is detected to have actually entered. This effectively avoids continuous tracking of non-target areas, thereby reducing the waste of system resources and the redundant burden of data processing.

[0082] In the example described above, the path tracking device could be a camera, a Wi-Fi probe, an RFID reader, or the like.

[0083] Based on the time series of tourists' stay at each location in the movement trajectory, the duration of their stay at each location is identified. If the duration of a tourist's stay at a certain location exceeds a set value, it indicates that the tourist has a clear intention to visit the exhibition area where that location is located, and the tracking is stopped, which means that the tourist's initial visit after entering the exhibition hall has ended.

[0084] It is important to understand that identifying and analyzing the duration of visitors' stay at various locations after entering the exhibition hall can effectively reflect their visiting behavior and interests. Comparing the actual stay time with a set value, for example, a set value of 2 minutes, helps to distinguish between short visits and stays with a clear intention to visit.

[0085] The complete movement path is reconstructed by using the location information of tourists at multiple consecutive time points, and the exhibition area where the path ends is located is extracted as the tourist's preferred exhibition area.

[0086] It should be noted that the visitor's first choice exhibition area refers to the exhibition area where visitors have a clear intention to act upon entering the exhibition hall. It reflects the content that visitors are most concerned about within a limited time and is a direct manifestation of their interest orientation.

[0087] In the further implementation of the above scheme, the distribution ratio of new visitors in each exhibition area is predicted as follows: the number of visitors who enter the exhibition hall is counted within a set time period, and the preferred exhibition area when a visitor enters each time is classified and summarized to obtain the number of new visitors corresponding to each exhibition area.

[0088] The above-mentioned duration can be dynamically adjusted based on the frequency of visitors entering the exhibition hall. Specifically: when visitors enter the exhibition hall more frequently, such as during peak hours or special events, the duration can be shorter, such as 30 minutes. When visitors enter the exhibition hall less frequently, such as during off-peak hours or less popular times, the duration can be appropriately extended, such as 1 hour.

[0089] The main purpose of setting the duration is to collect a certain amount of visitor sample data in order to classify and summarize the number of new visitors corresponding to each exhibition area, and to calculate the distribution ratio of new visitors in each exhibition area.

[0090] The distribution ratio of new visitors in each exhibition area is calculated by proportionally analyzing the number of new visitors in each exhibition area.

[0091] As an example of the above operation, assume there are three exhibition areas in the exhibition hall: Area A, Area B, and Area C. Within a set time period, such as 1 hour, through path tracking equipment and data analysis, the following statistics are recorded for new visitors entering the exhibition hall and their preferred exhibition areas: Area A: 25 new visitors, Area B: 40 new visitors, Area C: 35 new visitors.

[0092] The distribution ratio of new visitors in each exhibition area was calculated by proportionally analyzing the number of new visitors to each area. The proportion for Area A was... The proportion of area B is The proportion of area C is .

[0093] The risk simulation module is used to connect with the exhibition hall ticketing system to obtain the number of new visitors in future time periods. Based on the allocation ratio and the tendency of the increase in the degree of aggregation corresponding to the increase in the number of visitors per unit in each exhibition area, it simulates the increase in the degree of aggregation of the flow of people in each exhibition area after the new visitors enter.

[0094] In the preferred implementation of the above modules, the process of obtaining the number of new visitors for future periods by connecting with the exhibition hall ticketing system is as follows: The exhibition hall ticketing system has the function of displaying ticket purchase information, including key data such as the ticket purchaser's identity and planned exhibition time period. When a visitor actually enters the exhibition hall and completes the entry verification, the system will record the ticket's redemption status.

[0095] By counting the number of tickets that have not yet been redeemed and combining them with their corresponding planned visiting time periods, we can estimate the number of new visitors expected to enter the exhibition hall in the future.

[0096] In a further preferred implementation of the above module, simulation technology is required in the process of simulating the increase in the crowd density of each exhibition area after the entry of new tourists, based on the allocation ratio and the tendency of the increase in the density of each exhibition area corresponding to the increase in the density of each unit of tourists. For example, a computer simulation model can be used.

[0097] In the example simulation, suppose we have an exhibition hall containing three exhibition areas A, B, and C, and we have already obtained data on the expected 100 additional visitors in the next hour.

[0098] Historical data analysis shows that area A accounts for 25%, area B accounts for 40%, and area C accounts for 35%.

[0099] The 100 new visitors were allocated to each exhibition area according to the above proportions: 25 people in area A, 40 people in area B, and 35 people in area C.

[0100] Assuming that the tendency of the increase in agglomeration degree corresponding to the increase in a unit of tourist increase is +0.1 for area A, +0.15 for area B, and +0.12 for area C, then the increase in agglomeration degree brought by the new tourists is +2.5 for area A, +6 for area B, and +4.2 for area C.

[0101] Computer simulation models were used to simulate the distribution and clustering changes of these 100 new visitors in various exhibition areas after they entered the exhibition hall.

[0102] Generate reports or charts showing the expected changes in the concentration of each exhibition area in the next hour.

[0103] This invention introduces simulation technology to obtain the crowd gathering status after new visitors enter the exhibition hall. It can more accurately predict the actual impact of new visitors entering the exhibition hall on the crowd gathering degree and environmental status of each exhibition area. At the same time, the simulation results can be presented intuitively through visualization methods such as charts and heat maps, making the crowd gathering status after new visitors enter the exhibition hall clearer, more dynamic and easier to understand.

[0104] The risk identification module is used to identify safe exhibition areas by using the simulated incremental values ​​of crowd gathering in each exhibition area. The specific implementation process is as follows: The incremental values ​​of crowd gathering in each exhibition area obtained by the risk simulation module are combined with the actual crowd gathering values ​​obtained by analyzing the tourist distribution image at the current time to obtain the simulated crowd gathering in each exhibition area.

[0105] Air quality is detected using environmental sensing units deployed in each exhibition area at the same frequency as the image acquisition equipment.

[0106] It should be noted that the environmental sensing unit includes a variety of sensing devices, such as CO2 concentration monitoring sensors, which are used to collect air quality data such as CO2 concentration while collecting images of visitor distribution in each exhibition area.

[0107] Correlation analysis was conducted on the real-time data collected from each exhibition area regarding pedestrian density and air quality to construct a mapping relationship between the two.

[0108] It should be added that, since the visitor distribution images and air quality data were collected simultaneously, and information on crowd density can be extracted through image analysis, the two are synchronous in the temporal dimension. As the degree of crowd density increases, the population density within the exhibition area increases, and the impact of human activities such as breathing and movement on the air environment intensifies, leading to an increase in CO2 concentration and manifesting as a downward trend in local air quality.

[0109] This demonstrates a significant dynamic correlation between population density and air quality. To quantify this relationship, a correlation model, such as a statistical regression model, can be established to analyze the mapping relationship between population density and air quality parameters.

[0110] The construction of specific mapping relationships falls within the scope of existing technology and will not be elaborated upon here.

[0111] Based on the preset safe air quality standards, the corresponding critical crowd density is deduced from the above mapping relationship and used as the warning threshold for crowd density in each exhibition area.

[0112] The aforementioned safe air quality standards can usually be found in national or industry-issued indoor air quality specifications. These specifications stipulate the concentration limits of CO2 in enclosed spaces, reflecting the basic environmental quality requirements for ensuring human health and comfort.

[0113] The aforementioned threshold for crowd density, obtained through reverse calculation, represents the maximum reasonable level of crowd density that the exhibition area can accommodate without causing air quality to exceed safety limits.

[0114] The simulated crowd density of each exhibition area is compared with the corresponding crowd density warning threshold, and the exhibition areas that have not reached the warning threshold are marked as safe exhibition areas.

[0115] In this invention, the setting of the warning threshold for crowd gathering is not based on subjective experience or pre-set parameters, but rather on a scientific derivation based on the dynamic correlation between air quality and crowd gathering. By establishing a mapping model between crowd gathering and air quality and combining it with established safe air quality standards, the corresponding critical value for crowd gathering is derived, thereby determining the warning threshold for each exhibition area. The warning threshold determined in this way originates from the intrinsic relationship between actual environmental parameters and crowd behavior, avoiding the uncertainty brought about by subjective settings.

[0116] The exhibition area recommendation module is used to recommend the preferred exhibition area for new visitors based on the distribution of safe exhibition areas and display it at the entrance of the exhibition hall.

[0117] In the above-mentioned optional implementation, the operation of recommending the preferred exhibition area for new visitors based on the distribution of safe exhibition areas is as follows: For each identified safe exhibition area, the difference between its current simulated crowd gathering degree and the warning threshold is calculated to obtain the gathering margin of the exhibition area. This parameter can characterize the crowd gathering degree that the exhibition area can still accept without exceeding the safety boundary.

[0118] Based on the predicted distribution ratio of new visitors in each exhibition area, the tendency of new visitors to choose each safe exhibition area is extracted. This parameter reflects the probability that visitors will naturally choose a safe exhibition area without intervention, and can represent the potential preference intensity of visitors for each exhibition area.

[0119] The recommendation index for each safe exhibition area is calculated by weighting the clustering surplus and the proportion of preferred selections in each safe exhibition area. The exhibition area with the highest recommendation index is selected as the first choice for new visitors.

[0120] It should be noted that the weighting of the clustering surplus and the proportion of preferred choices in the weighted calculation process can be flexibly set according to the focus of the exhibition hall management objectives. If the management strategy focuses more on the safety and balance of visitor flow distribution, a higher weight can be given to the clustering surplus; if more emphasis is placed on visitor experience and visitor willingness, the weight of the proportion of preferred choices can be increased.

[0121] When selecting the preferred exhibition area for new visitors from the identified safe exhibition areas, this invention comprehensively considers two key factors: the clustering surplus of safe exhibition areas and the proportion of preferred selections. This ensures that the recommendation results meet both the requirements of spatial carrying capacity and the behavioral preferences of visitors, thereby achieving an intelligent guidance strategy that emphasizes both safety and service.

[0122] Example 2

[0123] See Figure 3 As shown, the present invention proposes a digital simulation method for tourism, which includes the following steps: S1: Real-time acquisition of tourist distribution images using image acquisition devices deployed in various exhibition areas of the exhibition hall.

[0124] S2: Extract clustering features from the tourist distribution image, including the number of clusters, cluster coverage area, number of tourists within a cluster, and distance between adjacent clusters, and analyze the degree of crowd gathering in combination with the exhibition area layout.

[0125] S3: By comparing tourist distribution images from adjacent collection times, establish the correspondence between tourist increment and population density increment, and conduct correlation analysis on the tendency of population density increment corresponding to unit tourist increment.

[0126] S4: By using path tracking devices deployed at the entrance of the exhibition hall to obtain the preferred exhibition areas of visitors entering the exhibition hall, the distribution ratio of new visitors in each exhibition area can be predicted.

[0127] S5: Connect with the exhibition hall ticketing system to obtain the number of new visitors in future time periods, and simulate the increase in the population density of each exhibition area after the new visitors enter, based on the allocation ratio and the tendency of the population density increase corresponding to the increase in the number of visitors per unit in each exhibition area.

[0128] S6: Identify safe exhibition areas by using the simulated incremental values ​​of crowd density in each exhibition area.

[0129] S7: Recommend the preferred exhibition areas for new visitors based on the distribution of the security exhibition areas and display them at the entrance of the exhibition hall.

[0130] 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, in the form of a computer program product.

[0131] Those skilled in the art will recognize that the modules and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0132] 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.

[0133] 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.

[0134] Finally, 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 digital simulation system for tourism, characterized in that, include: Image acquisition module: Uses image acquisition devices deployed in various exhibition areas of the exhibition hall to collect real-time images of visitor distribution; Crowd aggregation analysis module: Extracts aggregation features from visitor distribution images, including the number of clusters, cluster coverage area, number of visitors within a cluster, and distance between adjacent clusters, and analyzes the crowd aggregation degree in conjunction with the exhibition area layout; A new clustering correlation module has been added: By comparing tourist distribution images from adjacent collection times, the module establishes a correspondence between the increase in tourist volume and the increase in population density, and analyzes the tendency of the increase in population density corresponding to the increase in unit tourist volume. Distribution prediction module: By using path tracking devices deployed at the entrance of the exhibition hall to obtain the preferred exhibition areas of visitors entering the exhibition hall, the distribution ratio of new visitors in each exhibition area is predicted accordingly; Risk simulation module: It connects with the exhibition hall ticketing system to obtain the number of new visitors in future time periods, and simulates the increase in the concentration of people in each exhibition area after the new visitors enter, based on the allocation ratio and the tendency of the concentration increase corresponding to the increase in the number of visitors per unit in each exhibition area. Risk identification module: Identifies safe exhibition areas by using simulated incremental values ​​of crowd gathering in each exhibition area; Exhibition Area Recommendation Module: Based on the distribution of safe exhibition areas, this module recommends the preferred exhibition areas for new visitors and displays them at the entrance of the exhibition hall. The analysis of crowd density is as follows: The total number of tourists is obtained by summing the number of tourists in each cluster in the tourist distribution image, and the basic pedestrian density is calculated by the ratio of the number of tourists to the physical area of ​​the exhibition area in the exhibition layout. For each independent cluster, the local population density of the cluster is obtained by calculating the ratio of the number of tourists contained therein to the area covered by the cluster. Extract the ratio of the maximum and minimum local pedestrian density in all clusters to construct the clustered pedestrian flow difference degree; The distances between adjacent clusters are used to form a cluster spacing matrix. The spatial dispersion of the clusters is formed by standardizing the distance data in this matrix and calculating the standard deviation. Using basic pedestrian density as a benchmark, and introducing the difference in clustered pedestrian flow and the dispersion of clustered spatial as micro-supplementary factors, a fusion model is constructed to obtain the pedestrian flow clustering degree. The correlation between the increase in tourist volume and the increase in population density will be established as follows: By comparing the total number of visitors at adjacent collection times using real-time images of visitor distribution in each exhibition area, it can be determined whether there is an increase in the number of visitors. If there is no increase in the number of visitors at the current adjacent collection time, the time window is continued to slide forward until the time interval with an increase in visitors is identified and recorded as the incremental time interval. For each incremental time interval, the difference in the number of tourists between two consecutive collection times is calculated as the tourist increment for that time interval. Simultaneously, the difference in the population density between the two consecutive collection times within that incremental time interval is calculated to form the population density increment for that time interval. The incremental tourist volume for each incremental time interval is paired with the corresponding incremental population density to form a corresponding relationship; The correlation analysis shows that the increase in clustering degree corresponding to the increase in the number of tourists per unit is as follows: For each incremental time interval, the ratio between the increase in population density and the increase in tourists is calculated to obtain the increase in population density caused by a unit increase in tourists within that interval. Cluster analysis was performed on the increase in population density caused by the increase in number of tourists per unit time interval to divide the population into multiple cluster groups. The number of incremental time intervals contained in each cluster group was counted, and the dominant cluster group with the highest sample proportion was identified. The tendency of clustering increment per unit tourist increment is obtained by calculating the mean of the clustering increment per unit tourist increment in the dominant cluster group.

2. The tourism digital simulation system as described in claim 1, characterized in that: The process for extracting clustering features from tourist distribution images is as follows: Background segmentation was performed on the collected tourist distribution images to separate the foreground region containing tourist activities; Individual tourists are identified within the extracted foreground area, and the location of each tourist in the image is marked with a bounding box. Based on the location of each tourist in the image, the distance between adjacent tourists is obtained, and a clustering algorithm is used to divide tourists who are spatially close into the same cluster, combined with a preset proximity threshold. The coverage area of ​​each cluster is obtained by extracting the boundary contour of each cluster, and the number of tourists in each cluster is counted. The distance between adjacent clusters is obtained based on the geometric center point position of the corresponding boundary contour of the adjacent clusters.

3. The tourism digital simulation system as described in claim 1, characterized in that: The method of obtaining visitors' preferred exhibition areas by deploying path tracking devices at the entrance of the exhibition hall is implemented as follows: Infrared sensors deployed at the entrance of the exhibition hall are used to detect visitors. When a visitor is detected entering the exhibition hall, the path tracking equipment deployed in the entrance area is linked to track the visitor's location and construct their movement trajectory from the entrance in the time dimension. Based on the time series of tourists' stay at each location in the movement trajectory, the duration of their stay at each location is identified. If the duration of a tourist's stay at a certain location exceeds a set value, the tracking is stopped. The complete movement path is reconstructed by using the location information of tourists at multiple consecutive time points, and the exhibition area where the path ends is located is extracted as the tourist's preferred exhibition area.

4. The tourism digital simulation system as described in claim 3, characterized in that: The predicted distribution ratio of new visitors in each exhibition area is achieved as follows: Within a set time period, the number of visitors who enter the exhibition hall is counted, and the preferred exhibition area when a visitor enters each time is categorized and summarized to obtain the number of new visitors corresponding to each exhibition area. The distribution ratio of new visitors in each exhibition area is calculated by proportionally analyzing the number of new visitors in each exhibition area.

5. The tourism digital simulation system as described in claim 1, characterized in that: The risk identification module is implemented as follows: The incremental value of crowd gathering degree for each exhibition area obtained from the risk simulation module is combined with the actual crowd gathering degree value obtained from the current time through the analysis of the tourist distribution image to obtain the simulated crowd gathering degree for each exhibition area. Air quality is detected using environmental sensing units deployed in each exhibition area at the same frequency as the image acquisition equipment. Correlation analysis was conducted on the real-time data collected from each exhibition area regarding pedestrian density and air quality to construct a mapping relationship between the two. Based on the preset safe air quality standards, the corresponding critical crowd density is deduced from the above mapping relationship and used as the crowd density warning threshold for each exhibition area. The simulated crowd density of each exhibition area is compared with the corresponding crowd density warning threshold, and the exhibition areas that have not reached the warning threshold are marked as safe exhibition areas.

6. The tourism digitalization simulation system as described in claim 5, characterized in that: The recommendation of preferred exhibition areas for new visitors based on the distribution of security exhibition areas is implemented as follows: For each identified safe zone, the difference between its current simulated crowd density and the warning threshold is calculated to obtain the crowd density of that zone. Based on the predicted distribution ratio of new visitors in each exhibition area, the proportion of new visitors' preferred choices for each safe exhibition area is extracted. The recommendation index for each safe exhibition area is calculated by weighting the clustering surplus and the proportion of preferred selections in each safe exhibition area. The exhibition area with the highest recommendation index is selected as the first choice for new visitors.

7. A tourism digital simulation method, executed by the tourism digital simulation system as described in any one of claims 1-6, characterized in that: Includes the following steps: S1: Real-time acquisition of visitor distribution images using image acquisition devices deployed in various exhibition areas of the exhibition hall; S2: Extract clustering features from the visitor distribution image, including the number of clusters, cluster coverage area, number of visitors within a cluster, and distance between adjacent clusters, and analyze the degree of crowd gathering in combination with the exhibition area layout; S3: By comparing tourist distribution images from adjacent collection times, establish the correspondence between tourist increment and population density increment, and conduct correlation analysis on the tendency of population density increment corresponding to unit tourist increment. S4: By using path tracking devices deployed at the entrance of the exhibition hall, the preferred exhibition areas of visitors entering the exhibition hall can be obtained, and the distribution ratio of new visitors in each exhibition area can be predicted accordingly; S5: Connect with the exhibition hall ticketing system to obtain the number of new visitors in future time periods, and simulate the increase in the population density of each exhibition area after the new visitors enter, based on the allocation ratio and the tendency of the population density increase corresponding to the increase in the number of visitors per unit in each exhibition area. S6: Identify safe exhibition areas using simulated incremental values ​​of crowd density in each exhibition area; S7: Recommend the preferred exhibition areas for new visitors based on the distribution of the security exhibition areas and display them at the entrance of the exhibition hall.

Images