A museum exhibition dynamic visitor calibration and visitor scheduling system and method

Abstract

The present invention provides a dynamic visitor calibration and visitor scheduling system and method for museum exhibitions, which includes a visitor calibration device and a central server. The visitor calibration device is installed on a monitoring pole in the exhibition hall and consists of a sensor module, a main control unit and a communication module. The sensor module monitors the carbon dioxide concentration and captures visitor image data. The main control unit uses a dynamic target detection algorithm to analyze the image data and obtain real-time visitor information. The communication module transmits the data to the central server. The central server is equipped with a visitor scheduling model, including a data input module, a multi-objective optimization algorithm module, a scheduling strategy generation module and a scheduling execution module. The model determines the optimal visitor scheduling plan based on real-time data, and converts it into a specific strategy to communicate to the visitors. Through real-time monitoring and intelligent analysis, this system achieves precise control and efficient management of museum visitor flow, improving the exhibition hall's operating efficiency, visitor experience and safety.

Description

Technical Field

[0001] The present invention relates to the technical field of museum management, and in particular to a system and method for dynamic visitor calibration and visitor scheduling for museum exhibitions. Background Art

[0002] In museums and heritage sites, dynamic calibration refers to the real-time collection and analysis of data such as visitor location, movement speed, and density in order to effectively manage visitor flow and avoid congestion. Key technologies include: real-time positioning system, which uses wireless sensor networks, Radio Frequency Identification (RFID) technology, or positioning technology based on Bluetooth Low Energy (BLE) to accurately locate visitor locations. Movement speed prediction, which calculates the real-time movement speed of visitors by analyzing the time and distance of their movement, thereby evaluating their movement status and activity level. Density estimation, based on real-time positioning data, uses spatial statistical methods or machine learning algorithms to estimate the density of visitors in different areas, helping to predict and manage congestion.

[0003] Existing technologies employ dynamic calibration solutions, including image processing, RFID, and Wi-Fi and Bluetooth positioning. Image processing, including deep learning-based image recognition, can extract visitor movement information from video streams. These technologies have already been used in some large-scale events and public venues, but they require further optimization in environments such as museums to address issues such as changing lighting and occlusion. RFID technology allows visitors to accurately track their location and movement by attaching RFID tags to their bodies. While highly accurate, this technology is costly and requires visitors to cooperate with the device. Wi-Fi and Bluetooth positioning can more accurately locate a visitor's location and movement trajectory by analyzing the Wi-Fi and Bluetooth signals from their phones. This method has already been used in some large shopping malls and airports, but in museum settings, signal interference and accuracy issues still need to be addressed.

[0004] The second existing technology adopts a visitor diversion scheme, which includes rule-based methods and optimization-based methods. The rule-based method presets some rules, such as the maximum carrying capacity of each exhibition area. When an exhibition area approaches the maximum carrying capacity, new visitors are restricted from entering. This method is simple and easy to implement, but it has poor flexibility and cannot respond to changes in real time. The optimization-based method uses optimization techniques such as linear programming and integer programming, combined with real-time data, to dynamically adjust the flow direction and speed of visitors. This method can better balance the number of visitors in each exhibition area, but the computational complexity is high and requires strong computing power.

[0005] In the process of implementing the present invention, the inventors found that the shortcomings of the prior art are:

[0006] The accuracy of image processing technology is affected by environmental factors such as lighting changes and occlusion, resulting in reduced accuracy and reliability. Furthermore, real-time processing of large amounts of video data requires high computing power, resulting in high computational complexity and increased equipment and operating costs. The disadvantage of RFID technology is its high cost. Each visitor needs to be equipped with an RFID tag and a large number of read-write devices need to be deployed, resulting in high initial investment and subsequent maintenance costs. Furthermore, visitors are less receptive to wearing RFID devices, which impacts their experience. The accuracy of Wi-Fi and Bluetooth positioning technologies is easily affected by signal interference and multipath effects, making it difficult to guarantee accuracy, especially in complex indoor environments. Furthermore, this technology requires collecting data from visitors' mobile devices, which raises privacy concerns and reduces visitor acceptance.

[0007] Rule-based approaches lack flexibility. Due to their rigid pre-set rules, they cannot effectively respond to real-time changes in visitor flow. Furthermore, overly strict rules can lead to uneven resource utilization, such as leaving some exhibition areas vacant while others are overcrowded, reducing overall scheduling efficiency. Optimization-based approaches often have high computational complexity and require significant computing power to process large-scale, real-time data. This results in slow response times and makes it difficult to respond to sudden changes in visitor flow. Summary of the Invention

[0008] In view of this, an embodiment of the present invention provides a system and method for dynamic visitor calibration and visitor scheduling of museum exhibitions to improve the accuracy and real-time performance of dynamic calibration of museum exhibitions, reduce system costs, and enhance system stability and adaptability, thereby improving museum exhibition management and visitor experience.

[0009] To achieve the above objectives, in a first aspect, a museum exhibition dynamic visitor calibration and visitor scheduling system is provided, which includes:

[0010] The visitor calibration device is installed on the monitoring pole in the museum's exhibition hall. The visitor calibration device includes:

[0011] The sensor module includes: a carbon dioxide concentration monitoring module for monitoring real-time carbon dioxide concentration data in the exhibition hall; an image sensor for capturing real-time visitor image data in the exhibition hall;

[0012] a main control unit, configured to receive the real-time carbon dioxide concentration data and the real-time visitor image data, and analyze the real-time visitor image data based on a dynamic target detection algorithm to obtain real-time visitor information, wherein the real-time visitor information includes any one of visitor quantity information, visitor location information, visitor flow information, visitor distribution information, visitor stay time information in the exhibition hall, and visitor queue time information;

[0013] a communication module, electrically connected to the main control unit, for transmitting the real-time visitor information and the real-time carbon dioxide concentration data to a central server;

[0014] The central server is configured with a visitor scheduling model, wherein the visitor scheduling model includes:

[0015] A data input module, configured to receive the real-time visitor information and the real-time carbon dioxide concentration data;

[0016] a multi-objective optimization algorithm module, configured to determine an optimal tourist scheduling plan based on the real-time tourist information and the real-time carbon dioxide concentration data based on a multi-objective optimization algorithm;

[0017] A scheduling strategy generation module, used to convert the optimal tourist scheduling plan into a specific scheduling strategy;

[0018] The scheduling execution module is used to convey the scheduling strategy to tourists.

[0019] In a second aspect, a method for the museum exhibition dynamic visitor calibration and visitor scheduling system based on the first aspect is provided, comprising the following steps:

[0020] The visitor calibration device monitors the real-time carbon dioxide concentration data in the exhibition hall and captures real-time visitor image data in the exhibition hall; analyzes the real-time visitor image data based on a dynamic target detection algorithm to obtain real-time visitor information, wherein the real-time visitor information includes any one of visitor quantity information, visitor location information, visitor flow information, visitor distribution information, visitor stay time in the exhibition hall, and visitor queue time; and transmits the real-time visitor information and the real-time carbon dioxide concentration data to a central server;

[0021] The central server receives the real-time visitor information and the real-time carbon dioxide concentration data through a visitor scheduling model; determines an optimal visitor scheduling plan based on the real-time visitor information and the real-time carbon dioxide concentration data based on a multi-objective optimization algorithm; converts the optimal visitor scheduling plan into a specific scheduling strategy; and communicates the scheduling strategy to the visitors.

[0022] According to a third aspect, an electronic device is provided, comprising:

[0023] one or more processors;

[0024] a storage device for storing one or more programs,

[0025] When the one or more programs are executed by the one or more processors, the one or more processors implement the method as described in the second aspect.

[0026] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored, and when the program is executed by a processor, the method as described in the second aspect is implemented.

[0027] The above technical solution has the following beneficial technical effects:

[0028] The museum exhibition dynamic visitor calibration and visitor scheduling system of the present invention collects carbon dioxide concentration data and visitor image data in real time through a visitor calibration device installed in the exhibition hall, and uses a dynamic target detection algorithm to analyze and obtain comprehensive real-time visitor information. This information is processed by the visitor scheduling model of the central server, and the optimal visitor scheduling plan is generated using a multi-objective optimization algorithm, and is converted into a specific scheduling strategy. The implementation of this system can effectively balance the distribution of visitors in the exhibition hall, reduce congestion, optimize visitor routes, and improve the carrying capacity and utilization rate of the exhibition hall. At the same time, by monitoring the concentration of carbon dioxide, the system can adjust the exhibition hall environment in a timely manner to ensure the health and safety of visitors. This intelligent management method can not only enhance the visitor's visiting experience, but also help museum managers operate the exhibition hall more efficiently and achieve the optimal allocation of resources. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are provided for a better understanding of the present invention and are not intended to limit the present invention.

[0030] Figure 1 This is a functional block diagram of a dynamic visitor calibration and visitor scheduling system for museum exhibitions according to an embodiment of the present invention;

[0031] Figure 2 is a functional block diagram of a multi-objective optimization algorithm module according to an embodiment of the present invention;

[0032] Figure 3 is a functional block diagram of a scheduling strategy generation module according to an embodiment of the present invention;

[0033] Figure 4 is a functional block diagram of a scheduling execution module according to an embodiment of the present invention;

[0034] Figure 5 This is a functional block diagram of another museum exhibition dynamic visitor calibration and visitor scheduling system according to an embodiment of the present invention;

[0035] Figure 6 This is a flow chart of a method for a dynamic visitor calibration and visitor scheduling system based on a museum exhibition according to an embodiment of the present invention;

[0036] Figure 7 is a specific flow chart of step S160 in an embodiment of the present invention;

[0037] Figure 8Schematic diagram of the structure of a computer system according to an embodiment of the present invention. DETAILED DESCRIPTION

[0038] The following description of exemplary embodiments of the present invention is made in conjunction with the accompanying drawings, in which various details of the embodiments of the present invention are included to facilitate understanding. These details should be considered as merely exemplary. Therefore, it should be appreciated by those skilled in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope and spirit of the present invention. Similarly, for the sake of clarity and conciseness, descriptions of well-known functions and structures are omitted in the following description.

[0039] The embodiments of the present invention target the phenomenon of "museum fever" by calibrating the density and activity of tourists in semi-enclosed sites or museum spaces. On the premise of ensuring the safety of cultural relics and personnel, the embodiments of the present invention achieve the scheduling of cultural and museum resources and tourists in the tour space, tap the potential of non-popular exhibits, exhibition areas or idle spaces, improve the rational utilization rate of cultural and tourism resources and space, alleviate the pressure of sightseeing in related popular areas, and reduce the impact of carbon dioxide emissions caused by excessive concentration of tourists on the cultural relics themselves.

[0040] Example 1

[0041] like Figure 1 As shown, this embodiment provides a museum exhibition dynamic visitor calibration and visitor scheduling system, including: a visitor calibration device, installed on a monitoring pole in the exhibition hall of the museum, the visitor calibration device includes: a sensor module, which includes a carbon dioxide concentration monitoring module for monitoring real-time carbon dioxide concentration data in the exhibition hall; an image sensor for capturing real-time visitor image data in the exhibition hall; a main control unit for receiving the real-time carbon dioxide concentration data and the real-time visitor image data, and analyzing the real-time visitor image data based on a dynamic target detection algorithm to obtain real-time visitor information, the real-time visitor information including visitor quantity information, visitor location information, visitor flow information, visitor distribution information, and the time visitors stay in the exhibition hall. any multiple of the time information and the tourist queuing time information; a communication module, electrically connected to the main control unit, for transmitting the real-time tourist information and the real-time carbon dioxide concentration data to a central server; the central server is configured with a tourist scheduling model, and the tourist scheduling model includes: a data input module, for receiving the real-time tourist information and the real-time carbon dioxide concentration data; a multi-objective optimization algorithm module, for determining the optimal tourist scheduling plan according to the real-time tourist information and the real-time carbon dioxide concentration data based on a multi-objective optimization algorithm; a scheduling strategy generation module, for converting the optimal tourist scheduling plan into a specific scheduling strategy; a scheduling execution module, for conveying the scheduling strategy to tourists.

[0042] In a specific embodiment, the visitor calibration device adopts a modular design for easy installation and maintenance. The sensor module is integrated into an IP67 waterproof aluminum alloy housing and contains an NDIR (non-dispersive infrared) carbon dioxide concentration monitoring module with an accuracy of ±30ppm and a 1080p high-resolution camera as an image sensor with a field of view of up to 120°. The main control unit can use a quad-core processor based on the ARM Cortex-A72 architecture, with a main frequency of 2.0GHz, running a customized Linux operating system, equipped with 4GB of RAM and 64GB of eMMC storage, providing sufficient computing power to execute the YOLOv8-based dynamic target detection algorithm. The communication module uses a wireless communication module that supports 5G SA / NSA, with an uplink rate of up to 1Gbps, ensuring real-time data transmission. The central server is deployed on Alibaba Cloud ECS (Elastic Compute Service) and adopts a distributed architecture orchestrated by Kubernetes containers to improve system scalability and reliability. The visitor dispatch model was implemented in Python 3.9, using the PyTorch 1.9 deep learning framework to build and train a multi-objective optimization algorithm based on NSGA-II or NSGA-III. The dispatch strategy was implemented through multiple channels, including the exhibition hall's 4K resolution OLED electronic display, a cross-platform mobile app developed with Flutter, and an intelligent voice broadcast system with voice recognition, ensuring that information is conveyed to visitors in a timely and effective manner.

[0043] In this embodiment, the multi-objective optimization algorithm module utilizes an advanced multi-objective optimization algorithm, comprehensively considering real-time visitor information (e.g., visitor numbers, locations, flows, distribution, dwell time, and queue times) as well as real-time CO2 concentration data to determine the optimal visitor scheduling plan. This algorithm simultaneously considers multiple objectives, such as maximizing visitor experience, minimizing crowding, and optimizing air quality. For example, when visitor density in a particular exhibition area is too high and CO2 concentrations are elevated, the algorithm generates a visitor scheduling plan that recommends directing some visitors to other, less crowded exhibition areas. The scheduling strategy generation module then translates this high-level scheduling plan into specific, executable scheduling strategies or instructions. These scheduling strategies can include adjusting the maximum capacity of specific exhibition areas, changing the opening hours of certain exhibits, and assigning different tour routes to different visitor groups. For example, in the above scenario, a specific strategy might be: "For the next 30 minutes, limit the visitor capacity of exhibition area A to 50 people, and recommend a tour route to exhibition area B to newly arrived visitors." This approach ensures both comprehensive and optimized decision-making and feasible and specific execution, thereby enabling intelligent and dynamic management of museum visitor flow.

[0044] In some alternative embodiments, the sensor module can be supplemented with an infrared thermal imaging camera to more accurately detect visitor locations and flows in low-light environments. The main control unit can use the NVIDIA Jetson Xavier NX module with an integrated GPU acceleration unit to further improve the performance of the target detection algorithm. The communication module can be supplemented with a Wi-Fi 6 module to provide a backup communication method in areas with poor 5G signal coverage. The central server can adopt a hybrid cloud architecture, with key data and core algorithms running on a private cloud and non-sensitive data processing performed on a public cloud to balance security and cost. The visitor scheduling model can introduce reinforcement learning algorithms, such as PPO (Proximal Policy Optimization), to adapt to dynamically changing environments and continuously optimize scheduling strategies. Scheduling strategy execution can add AR (Augmented Reality) guide functions to provide real-time personalized navigation and exhibit information through visitors' smart glasses or smart watches.

[0045] In some alternative embodiments, air quality sensors and / or sound sensors can be used to monitor the environmental conditions in the exhibition hall. Air quality sensors can detect PM2.5 (fine particulate matter) concentrations and other air quality indicators, such as PM10 (inhalable particulate matter), VOCs (volatile organic compounds), formaldehyde, ozone (O3), carbon monoxide (CO), nitrogen dioxide (NO2) and sulfur dioxide (SO2). These indicators can comprehensively reflect the air quality conditions in the exhibition hall and help to promptly detect and deal with potential air pollution problems. At the same time, sound sensors can be used to monitor the noise level in the exhibition hall, and indirectly reflect the density and activities of people in the exhibition hall through changes in decibel values. The use of these two sensors alone or in combination can provide more comprehensive environmental monitoring data.

[0046] The system's technical benefits include high real-time and accuracy. Using high-precision sensors and advanced image processing algorithms, it accurately captures visitor distribution and environmental data within the exhibition hall in real time, providing a reliable basis for subsequent scheduling decisions. Secondly, the system is intelligent and adaptive. A scheduling model based on a multi-objective optimization algorithm comprehensively considers multiple factors, automatically generates an optimal scheduling plan, and dynamically adjusts based on real-time conditions. Furthermore, the system provides personalized and efficient services, offering personalized visitor recommendations and route planning tailored to the characteristics and needs of individual visitors, enhancing the visitor experience while also optimizing overall visitor efficiency. Regarding safety and comfort, the system effectively ensures air quality and visitor comfort within the exhibition hall, mitigating safety risks, through real-time monitoring and adjustment of carbon dioxide concentrations and crowd density. The system's modular design and standardized interfaces ensure scalability and compatibility, adapting to the needs of museums of varying sizes and types.

[0047] Example 2

[0048] In some embodiments, the dynamic object detection algorithm includes a dynamic object detection algorithm based on the YOLOv8 architecture; the multi-objective optimization algorithm includes the NSGA-II multi-objective genetic optimization algorithm; the optimization objectives of the multi-objective optimization algorithm module include maximizing visitor satisfaction, minimizing visitor congestion, and minimizing carbon dioxide concentration; and the constraints of the multi-objective optimization algorithm module include the maximum capacity of the exhibition hall and the visitor flow speed limit. In this embodiment, the dynamic object detection algorithm utilizes the latest YOLOv8 architecture, which improves detection speed and accuracy compared to previous versions. For example, on computer vision datasets, the YOLOv8-1 model can achieve 52.9% mAP (mean average precision) while maintaining high real-time performance, processing 1080p video streams at over 60 frames per second. The multi-objective optimization algorithm utilizes NSGA-II (Non-dominated Sorting Genetic Algorithm II), a highly efficient multi-objective optimization algorithm that can quickly converge to a Pareto optimal solution while maintaining population diversity. The optimization objectives encompass three key areas: visitor experience, exhibition hall management, and environmental control. The objectives are to enhance the visitor experience by maximizing visitor satisfaction, minimize crowding to ensure safety and comfort, and minimize carbon dioxide concentration to maintain good air quality. Constraints consider the physical limitations and safety requirements of the exhibition hall, ensuring that the optimization results are feasible in practical applications. This multi-objective optimization approach can find a balance between multiple conflicting objectives, providing comprehensive decision-making support for museum managers.

[0049] like Figure 2As shown, in some embodiments, the multi-objective optimization algorithm module specifically includes: an exhibition area optimization target definition submodule, which is used to define the exhibition area optimization target, which includes the following multiple indicators: average walking path length, calculated by the following formula: Among them, m is the total number of visitors in the exhibition hall, L i is the walking path length of the i-th tourist; the average stay time is calculated by the following formula: Among them, T i is the stay time of the i-th tourist; the average queuing time is calculated by the following formula: Where Wi is the queuing time of the i-th tourist; the chaos index is calculated by the following formula: When the average walking speed of tourists is greater than 2m / s, the chaos index is 1; when the average walking speed of tourists is less than or equal to 2m / s, the chaos index is 0. i is the walking speed of the i-th visitor; the passenger flow density of the exhibition area is calculated by the following formula: ρ = m / S, where S is the exhibition area and ρ is the passenger flow density of the exhibition area; the passenger flow crowding index is calculated by the following formula: crowding = ∑(ρ*t i ) / ∑(t i ), where t i represents the hourly time weight coefficient, which is positively correlated with the number of tourists; tourist satisfaction is calculated using the following formula:

[0050]

[0051] Among them, d1, d2, d3, and d4 are preset weights, d1 and d2 are positive weight values, and d3 and d4 are negative weight values.

[0052] In this embodiment, the exhibition area optimization target definition submodule quantifies the key indicators that affect the visitor experience and exhibition hall operations through a series of mathematical formulas. These indicators include average walking path length, average dwell time, average queuing time, chaos index, exhibition area passenger flow density, passenger flow congestion index and visitor satisfaction. Each indicator has its own specific calculation formula, taking into account different factors and weights. For example, the chaos index is judged based on the average walking speed of tourists, the passenger flow congestion index takes into account the time weight coefficient, and the visitor satisfaction integrates multiple factors and introduces positive and negative weights. This multi-dimensional optimization target definition enables the system to comprehensively evaluate and optimize the operation of the exhibition hall.

[0053] like Figure 2As shown, in some embodiments, the multi-objective optimization algorithm module specifically includes: a constraint definition submodule, which is used to define the constraints that the optimization process must meet, and the constraints include: all tourists in the queue outside the exhibition hall will eventually enter the venue; the average walking speed of tourists in the exhibition hall shall not exceed 2 meters per second; the maximum carrying capacity of each exhibition area shall not exceed the safe capacity of the exhibition area; the tourist density per unit area of ​​the exhibition area shall not exceed the design limit of the exhibition area; the chaos index of the exhibition area shall not exceed the preset threshold; the carbon dioxide concentration in the exhibition hall shall not exceed the preset concentration upper limit; an optimization algorithm processing submodule, which is used to use a non-dominated sorting genetic algorithm II (NSGA-II) combined with a gray wolf genetic algorithm to perform multi-objective optimization, with tourist satisfaction, passenger flow congestion and carbon dioxide concentration as optimization objectives, and through initialization, optimization, non-dominated sorting and crowding distance calculation steps, determine the priority of the exhibition area and generate a set of recommended exhibition areas, and finally determine the optimal visitor scheduling plan based on the Pareto optimal solution set, the comprehensive ranking of the exhibition areas, the most recommended destination exhibition area and the specific index values ​​of each exhibition area; it specifically includes: executing the solution set initialization step, which The method includes initializing N initial solutions, where N is the number of exhibition halls; for each initial solution, obtaining the satisfaction, passenger congestion, and carbon dioxide concentration value of the corresponding exhibition hall; optimizing the N initial solutions using a gray wolf genetic algorithm to improve satisfaction and reduce passenger congestion and carbon dioxide concentration, thereby obtaining N optimized new solutions; performing a non-dominated sorting step, including merging the N initial solutions and the N optimized new solutions to form a set of 2N solutions; performing non-dominated sorting on the 2N solutions to obtain a Pareto optimal solution set; performing a crowding distance calculation step, including calculating the crowding distance of each solution in the Pareto optimal solution set; determining the most recommended destination exhibition area based on the crowding distance; generating a comprehensive ranking of the exhibition areas based on the non-dominated level and crowding distance of each solution in the Pareto optimal solution set, wherein the non-dominated level is determined by comparing the pros and cons of each solution with respect to the three objectives of satisfaction, passenger congestion, and carbon dioxide concentration, with a lower non-dominated level indicating a higher priority of the exhibition area; and determining an optimal visitor scheduling plan based on the most recommended destination exhibition area, the comprehensive ranking of the exhibition areas, and the satisfaction, passenger congestion, and carbon dioxide concentration values ​​of each exhibition area.

[0054] Specifically, the optimization algorithm processing submodule uses the gray wolf genetic algorithm to optimize the initial solution to improve satisfaction, reduce passenger congestion and carbon dioxide concentration, and obtain N optimized new solutions. In specific implementation, the algorithm simulates the social hierarchy and hunting behavior of wolves, regards the optimal solution as prey, and guides the ω wolf (other solutions) to update their positions through the α wolf (optimal solution), β wolf (second-optimal solution) and δ wolf (third-optimal solution). At the same time, the crossover and mutation operations of the genetic algorithm are combined to enhance population diversity and search capabilities. In each iteration, the algorithm evaluates the performance of each solution on the three objectives and updates the wolf pack position according to a predefined fitness function, ultimately obtaining a set of optimized new solutions that have improved on all three objectives.

[0055] Specifically, the crowding distance calculation is used to evaluate the distribution of each solution in the Pareto optimal solution set. The calculation process is as follows: First, for each objective function (satisfaction, passenger congestion, carbon dioxide concentration), the solutions are sorted according to the value of the objective function. Then, for the sorted solutions, the normalized difference between the two adjacent solutions on the objective function is calculated. For boundary solutions (that is, solutions that achieve the maximum or minimum value on a certain objective function), an infinite crowding distance is assigned to ensure that they are retained. Finally, the differences on all objective functions are added to obtain the crowding distance of each solution. This distance reflects the density of the solution in the target space. The larger the distance, the sparser the solutions around the solution, which is conducive to maintaining the diversity of the population.

[0056] Specifically, the process of determining the most recommended destination exhibition area based on the crowding distance is as follows: in the Pareto optimal solution set, select the solution with the largest crowding distance. The first exhibition area in the exhibition area sequence corresponding to this solution is the most recommended destination exhibition area. The solution with the largest crowding distance is selected to ensure the diversity of recommendations and avoid all visitors being directed to the same exhibition area, thereby reducing possible overcrowding in certain exhibition areas. This method not only takes into account the excellence of the exhibition area (because it is in the Pareto optimal solution set), but also its uniqueness (because it has the largest crowding distance). In addition, the system can set up a dynamic update mechanism, which can recalculate and update the recommendation when the real-time status of the most recommended exhibition area changes significantly (for example, it suddenly becomes crowded).

[0057] Specifically, generating a comprehensive ranking of exhibition areas is a multi-step process that takes into account both non-dominated rank and crowding distance. First, solutions are sorted according to their non-dominated rank, with lower rank rankings resulting in higher rankings. This ensures that solutions that perform well across multiple objectives receive higher rankings. Solutions with the same non-dominated rank are then sorted according to crowding distance, with larger distances resulting in higher rankings, which helps maintain solution diversity. Then, based on this sorting, a comprehensive ranking value is assigned to each solution. Next, the position and frequency of each exhibition area's appearance across different solutions are counted, and a weighted average ranking of each exhibition area is calculated based on the comprehensive ranking of the solutions. Finally, the exhibition areas are finally sorted based on this weighted average ranking to obtain a comprehensive ranking of the exhibition areas. This approach considers both the comprehensive performance of an exhibition area across multiple objectives and its importance among the different excellent solutions.

[0058] Specifically, determining the optimal visitor scheduling plan is a dynamic and personalized process that comprehensively considers multiple factors. First, the most recommended destination exhibition area is used as the starting point. This exhibition area performs best in terms of satisfaction, crowding, and air quality. Then, based on the comprehensive ranking of the exhibition areas, the approximate order of visitor visits is determined, providing an overall optimal tour route. Simultaneously, the system monitors the satisfaction, crowding, and carbon dioxide concentration values ​​of each exhibition area in real time and dynamically adjusts the visit order accordingly. For example, if the crowding or carbon dioxide concentration of a particular exhibition area exceeds a preset threshold, the system temporarily removes it from the recommended sequence to prevent a degradation of the visitor experience. Furthermore, the system provides a personalized next recommended exhibition area based on the visitor's actual location, interests, and the conditions of surrounding exhibition areas. In this way, the scheduling plan can flexibly respond to real-time conditions while ensuring overall optimization, providing each visitor with the best possible experience.

[0059] In one example, the optimization algorithm processing submodule is implemented as follows: First, a ranking scheme for the five exhibition areas (A, B, C, D, E) is initialized, such as [A, B, C, D, E] and [B, A, E, C, D]. These initial solutions are then optimized using a gray wolf genetic algorithm to improve visitor satisfaction, reduce visitor crowding, and reduce carbon dioxide concentrations. This algorithm simulates the hunting behavior of a wolf pack, using wolves α, β, and δ to guide the other wolves in updating their positions. The algorithm also incorporates the genetic algorithm's crossover and mutation operations. After optimization, a new ranking scheme, such as [C, A, E, B, D], is obtained. Next, the initial and optimized solutions are combined and a non-dominated sort is performed to obtain a Pareto-optimal set of solutions. The crowding distance is calculated for these solutions, reflecting their distribution in the target space. Based on the crowding distance, the solution with the largest distance is selected, and its first exhibition area is designated as the most recommended destination area. A comprehensive ranking of the exhibition areas is then generated based on the non-dominated level and crowding distance. Finally, the optimal visitor scheduling scheme is determined. Starting with the most recommended exhibition area, the visit order is determined based on the comprehensive ranking. The system monitors the conditions of each exhibition area in real time, dynamically adjusts the order of visits, and provides personalized recommendations based on individual visitor needs. For example, the final recommendation is: first visit Exhibition Area C, then Exhibition Area A, Exhibition Area E, Exhibition Area B, and Exhibition Area D. However, if Exhibition Area A suddenly becomes crowded, the system recommends visiting Exhibition Area E first and then returning to Exhibition Area A after the situation improves, ensuring every visitor has the best experience.

[0060] like Figure 2 As shown, in this embodiment, the constraint definition submodule sets a series of specific constraints to ensure the feasibility and safety of the optimization results in actual operation. These constraints cover multiple aspects such as visitor flow, exhibition area capacity, and safety indicators. The optimization algorithm processing submodule adopts an innovative algorithm combination, namely the non-dominated sorting genetic algorithm II (NSGA-II) combined with the gray wolf genetic algorithm. This module goes through a series of steps, including initializing the solution set, gray wolf genetic algorithm optimization, non-dominated sorting, crowding distance calculation, etc., to finally determine the optimal visitor scheduling plan. This method makes full use of the advantages of NSGA-II in multi-objective optimization and the ability of the gray wolf algorithm in global search. It can quickly find high-quality solutions in complex multi-objective spaces and provide scientific and reasonable scheduling suggestions for museum managers.

[0061] The technical effects of the above embodiments mainly include the following aspects: First, the dynamic target detection algorithm based on YOLOv8 greatly improves the system's recognition accuracy and speed of visitor behavior and location, providing a reliable data basis for real-time scheduling. Secondly, the multi-objective optimization method of NSGA-II combined with the gray wolf genetic algorithm can quickly find high-quality solutions that balance multiple objectives in a complex decision space, thereby improving the overall effect of the scheduling scheme. Thirdly, through refined indicator definitions and constraint setting, the system can comprehensively consider various factors that affect the operation of the exhibition hall and the visitor experience, making the optimization results closer to actual needs. For example, the calculation formula for visitor satisfaction comprehensively considers multiple factors such as walking path length, stay time, queuing time and chaos, and adjusts the importance of each factor through different weights. Finally, this intelligent scheduling system can not only improve visitor satisfaction, but also effectively control the congestion and air quality in the exhibition hall.

[0062] Example 3

[0063] like Figure 3As shown, in some embodiments, the scheduling strategy generation module specifically includes: a first scheduling strategy generation submodule, which is used to guide the movement path of tourists in the exhibition hall based on real-time visitor flow information and visitor stay time information in the exhibition hall; a second scheduling strategy generation submodule, which is used to dynamically adjust the maximum number of tourists that can be accommodated at the same time in each exhibition area according to current visitor distribution information; a third scheduling strategy generation submodule, which is used to adjust the number of open rest areas and the open and closed states of evacuation passages according to visitor quantity information, visitor distribution information and visitor flow information. The specific scheduling strategies include: visitor tour route planning, which is used to guide the movement path of tourists in the exhibition hall based on real-time visitor flow information and visitor stay time information in the exhibition hall; access restriction setting for each exhibition area in the exhibition hall, which is used to dynamically adjust the maximum number of tourists that can be accommodated at the same time in each exhibition area according to current visitor distribution information; and public area management, which is used to adjust the number of open rest areas and the open and closed states of evacuation passages according to visitor quantity information, visitor distribution information and visitor flow information. In this embodiment, the scheduling strategy encompasses three key aspects: First, visitor route planning leverages real-time data to dynamically optimize visitor routes. For example, when a particular exhibition area is crowded, the system can direct newly arrived visitors to visit other, relatively unoccupied areas first, thereby balancing overall visitor flow. Second, exhibition area access restrictions adjust the capacity of each exhibition area based on real-time conditions. For example, during particularly popular temporary exhibitions, the system may reduce the maximum simultaneous occupancy of that area to ensure visitor quality and safety. Finally, public area management effectively responds to fluctuating visitor flows at different times by flexibly adjusting the status of rest areas and evacuation routes. For example, during peak visitor flow periods, the system increases the number of open rest areas while maintaining more evacuation routes open to improve overall evacuation capacity. This comprehensive scheduling strategy not only improves the operational efficiency of the exhibition hall, but also enhances the visitor experience while ensuring its safe operation.

[0064] like Figure 4As shown, in some embodiments, the scheduling execution module specifically includes: a first control submodule, used to control multiple display screens to display visual guidance information for all tourists in real time, and the multiple display screens are installed at different locations in the exhibition hall as devices independent of the central server and the tourist calibration device; a second control submodule, used to control the broadcasting system to play audio scheduling information for all tourists, and the broadcasting system is installed in the exhibition hall as a device independent of the central server and the tourist calibration device; a third control submodule, used to control the server application running on the central server to send personalized guidance information to the client application of the tourist's mobile phone through the wireless network; wherein, the guidance information for all tourists, the scheduling information for all tourists and the personalized guidance information are all generated by the scheduling execution module according to the scheduling strategy, and the personalized guidance information is determined accordingly according to the specific situation of each tourist.

[0065] In this embodiment, the scheduling execution module implements comprehensive information transmission and scheduling execution through three submodules. The first control submodule manages the exhibition hall's display screens, located in key locations such as entrances and intersections of major exhibition areas, and displays real-time visual guidance information. For example, it can display the real-time congestion level of each exhibition area and recommended tour routes. The second control submodule manages the broadcast system, which plays audio scheduling information, such as safety reminders and temporary exhibition opening hours. The third control submodule provides personalized guidance services to each visitor through a mobile application, such as recommending the next most suitable visitor location based on their interests and exhibits already visited. These three submodules work together to ensure comprehensive and targeted information transmission. For example, if a particular exhibition area is about to reach capacity, the system can simultaneously display a warning message on the display screen, play a reminder through the broadcast system, and send personalized suggestions to visitors' mobile phones on their way to that exhibition area, guiding them to visit other exhibition areas first. This multi-level, multi-channel information transmission and scheduling execution mechanism improves the system's efficiency and flexibility, enabling it to better cope with various complex exhibition hall operation scenarios.

[0066] By comprehensively considering visitor flow, exhibition area capacity, and public area management, the system optimizes the utilization of exhibition hall resources. For example, dynamically adjusting exhibition area access restrictions can effectively prevent overcrowding in certain popular exhibition areas while guiding visitors to other relatively unoccupied areas, thereby balancing overall visitor flow. Secondly, a multi-level scheduling and execution mechanism (display screens, broadcast systems, and personal mobile phone applications) ensures comprehensive and timely information transmission. This not only improves the visitor experience but also enhances the exhibition hall's emergency response capabilities. For example, in the event of an emergency evacuation, the system can simultaneously disseminate information through multiple channels, improving evacuation efficiency. Thirdly, the provision of personalized guidance information ensures that each visitor has a tailored visitor experience. This not only increases visitor satisfaction but also helps disperse visitor flow and avoid localized congestion. Finally, this intelligent scheduling system improves the exhibition hall's operational efficiency.

[0067] Example 4

[0068] like Figure 5 As shown, in some embodiments, the visitor scheduling model also includes a feedback and adjustment module for real-time monitoring of scheduling effectiveness, including visitor distribution information, CO2 concentration changes, and emergency information, and dynamically adjusting scheduling strategies based on these information. Emergency information is obtained through at least one of the following: emergency reports uploaded by visitors via a mobile application; or abnormal behavior associated with emergency information detected through image analysis. In this embodiment, the feedback and adjustment module continuously monitors and optimizes scheduling effectiveness. This module analyzes visitor distribution information in real time, such as whether certain exhibition areas are congested; monitors CO2 concentration changes to ensure air quality within the exhibition hall; and promptly responds to emergencies. For example, if CO2 concentration in a particular exhibition area suddenly rises, the system will reduce the maximum capacity of that area and redirect some visitors to other areas. The system employs a dual safeguard mechanism for emergency monitoring: first, visitors can directly report emergencies, such as safety hazards, via the mobile application; and second, the system uses advanced image analysis technology to automatically detect abnormal behavior, such as sudden gatherings or rapid movement of visitors. This comprehensive monitoring and rapid response mechanism improves the safety and operational efficiency of the exhibition hall, and can take timely measures before problems escalate, ensuring the safety and good experience of visitors.

[0069] In some embodiments, the visitor calibration device further includes: a power supply module electrically connected to the main control unit, the sensor module and the communication module, for providing power to the visitor calibration device; the carbon dioxide concentration monitoring module, the image sensor and the wireless communication receiving module are all electrically connected to the main control unit; the sensor module further includes a wireless communication receiving module for receiving wireless signal data sent by a visitor's mobile device; the main control unit is further used to: process the wireless signal data to obtain visitor location information; fuse the visitor location information with the real-time visitor image data to obtain enhanced real-time visitor information; wherein the enhanced real-time Visitor information also includes visitor interest data; wherein, based on the continuous visitor location information of a single visitor, the movement trajectory data of a single visitor is generated through time series analysis; the movement trajectory data of multiple visitors are aggregated and analyzed to obtain visitor flow information representing the overall visitor movement trend; wherein, the visitor interest data is obtained through a comprehensive method, including: obtaining a multi-dimensional data source, which includes visitor stay time, visit frequency, movement trajectory pattern, interactive behavior, social media activities, questionnaire feedback, consumption behavior, and reservation data; based on the multi-dimensional data source, combined with a deep learning algorithm, a comprehensive visitor interest model is generated to output visitor interest data for different exhibition areas.

[0070] To obtain accurate visitor interest data, the system combines multi-dimensional data sources with advanced deep learning algorithms. Specifically, the system first collects various types of data: dwell time, which refers to the length of time visitors spend in each exhibition area, such as a 45-minute stay in the dinosaur exhibit; visit frequency, which refers to the number of times visitors repeatedly visit an exhibition area, such as multiple returns to the aquarium; movement patterns, which record visitors' routes and stops within the park, such as visiting the Giant Panda Pavilion and then the Butterfly Garden; interactive behavior, which includes the number and methods of interaction with exhibits, such as frequent use of interactive devices in the Science and Technology Museum; social media activity, which analyzes visitors' posts, likes, and comments about the exhibition areas on various platforms; questionnaire responses, which directly collect visitors' evaluations and suggestions for the exhibition areas; consumption behavior, which records visitors' shopping and dining activities within the park, such as purchasing souvenirs in the rainforest area; and reservation data, which analyzes visitors' pre-selected exhibition areas or activities. The system then applies deep learning algorithms, such as multi-layer neural networks or recurrent neural networks, to process and analyze this complex, multi-dimensional data. Deep learning models can automatically learn the underlying features and patterns in the data. For example, they find that exhibition areas with long stays, multiple interactions, and frequent social sharing tend to have higher interest levels. The model can also identify associations between different data sources. For example, positive questionnaire feedback but short stays indicate that the exhibition area's content is attractive but the scale is small. In this way, the system generates a comprehensive visitor interest model that takes into account the complex relationships and mutual influences between various factors. Ultimately, the model outputs each visitor's interest data in different exhibition areas. These data are continuous values ​​(for example, between 0 and 1) that accurately reflect the visitor's interest in each exhibition area. For example, the model shows that a visitor's interest in the oceanarium is 0.9, while his interest in the insectarium is 0.3. Through this comprehensive and precise approach, the system can capture subtle differences in visitors' interests and preferences, thereby improving the visitor experience.

[0071] In this embodiment, the visitor tracking device is a highly integrated intelligent system, integrating multiple functional modules. The power module ensures continuous operation of the device, while the wireless communication receiving module receives signals from visitors' mobile devices to achieve precise location tracking. The main control unit, serving as the data processing center, not only processes wireless signal data to obtain location information but also fuses this information with image data to generate enhanced real-time visitor information. This data fusion technology improves the accuracy and reliability of the system. For example, when the Wi-Fi signal is unstable, the system can rely on image data to supplement positioning information. Furthermore, the system generates individual movement trajectories through time series analysis and uses aggregate analysis to derive overall visitor flow trends. The method for acquiring visitor interest data integrates multi-dimensional data sources, including behavioral data (dwell time, visit frequency), social data, and questionnaire responses, and combines it with deep learning algorithms to generate a comprehensive interest model. This comprehensive data collection and analysis approach enables the system to accurately grasp visitor preferences, thereby providing more personalized services. For example, if the system detects that a visitor is particularly interested in modern art exhibits, it will prioritize relevant exhibition areas when recommending itineraries. This deep personalization not only improves visitor satisfaction, but also helps optimize the allocation of exhibition hall resources, such as adjusting exhibit layouts according to visitor interests or developing new themed exhibitions.

[0072] The advantages of this technical solution lie in the following: the introduction of a feedback and adjustment module enables the system to adapt itself, dynamically adjusting scheduling strategies based on real-time conditions. This not only increases the system's flexibility but also strengthens the exhibition hall's ability to respond to emergencies. For example, if an abnormally high CO2 concentration is detected in a particular area, the system can immediately adjust the maximum occupancy of that area and redirect visitors to other areas, thereby ensuring the safety of the exhibition hall environment. Secondly, the multifunctional integrated design of the visitor tracking device improves the comprehensiveness and accuracy of data collection. By integrating Wi-Fi signal positioning and image analysis, the system can more accurately track visitor location and behavior, maintaining high accuracy even in complex indoor environments. Thirdly, a visitor interest model based on multi-dimensional data sources and deep learning algorithms enables the system to deeply understand the preferences of individual visitors. This not only provides a highly personalized visiting experience but also helps exhibition hall managers better understand visitor needs, thereby optimizing exhibition design and resource allocation. For example, if the system identifies a particular type of exhibit that most visitors are particularly interested in, the exhibition hall can add related exhibitions or expand the display area for that type of exhibit.

[0073] Example 5

[0074] like Figure 6 As shown, this embodiment provides a method based on the museum exhibition dynamic visitor calibration and visitor scheduling system, which includes the following steps:

[0075] S110: Visitor calibration device monitors real-time carbon dioxide concentration data in the exhibition hall;

[0076] S120: The visitor calibration device captures real-time visitor image data in the exhibition hall;

[0077] S130: The visitor calibration device analyzes the real-time visitor image data based on a dynamic target detection algorithm to obtain real-time visitor information, wherein the real-time visitor information includes any one of visitor quantity information, visitor location information, visitor flow information, visitor distribution information, visitor stay time in the exhibition hall, and visitor queue time;

[0078] S140: The visitor calibration device transmits the real-time visitor information and the real-time carbon dioxide concentration data to a central server;

[0079] S150: The central server receives the real-time visitor information and the real-time carbon dioxide concentration data through a visitor scheduling model;

[0080] S160: The central server determines an optimal tourist scheduling plan based on the real-time tourist information and the real-time carbon dioxide concentration data based on a multi-objective optimization algorithm;

[0081] S170: The central server converts the optimal tourist scheduling plan into a specific scheduling strategy;

[0082] S180: The central server communicates the scheduling strategy to the visitors.

[0083] Specifically, the visitor calibration device is a small piece of hardware containing an algorithm and navigation system. It is installed directly on the existing three-dimensional monitoring poles in the venue space. It also needs to integrate the functional zones of the entire site / museum space to calibrate the guided tour routes, rest routes, emergency evacuation routes, and their visitor capacity. The visitor calibration device is a small hardware device consisting of the following main components: a main control unit responsible for data processing and overall system operation; a sensor module, including a carbon dioxide concentration monitoring module and a camera module, for real-time monitoring of visitor numbers, movement speed, dwell time, queue time, and other information, as well as the carbon dioxide concentration within the venue; a communication module for exchanging data with a central server; a power supply module for providing power for device operation; and a mounting bracket for securing the calibration device to the existing three-dimensional monitoring poles in the venue space. The visitor calibration device uses the sensor module to detect the carbon dioxide concentration within the venue, while the camera module captures visitor activity within the venue. This data is transmitted to the central server via the communication module. The main control unit processes this data using dynamic object detection based on the YOLOv8 architecture to obtain quantitative information such as the number of visitors, movement speed, dwell time, and queue time.

[0084] The sensor module collects real-time information about visitor location and movement, as well as the real-time carbon dioxide concentration within the venue. The main control unit analyzes and processes this data, calibrating visitor and carbon dioxide distribution. The communication module then transmits this data to a central server. The central server analyzes the results and uses the navigation system to guide visitors along pre-set routes.

[0085] The optimization scheduling model is a system that integrates the NSGA-II genetic optimization algorithm and real-time scheduling strategy. It is used to rationally distribute visitor flows within spaces such as museums or heritage sites to improve visitor experience, protect cultural relics and optimize space utilization.

[0086] The optimization scheduling model mainly includes the following parts:

[0087] The data input module is used to receive real-time data from the visitor calibration device, including the number of visitors, the time they stay in the venue, the length of their movement trajectory, the queuing time and the carbon dioxide concentration.

[0088] The multi-objective optimization algorithm module is used to initialize the initial variables involved in the evaluation (carbon dioxide concentration, exhibition area visitor density, and visitor satisfaction) based on the received data and calculate the optimal visitor scheduling plan. This multi-objective optimization algorithm module uses the advanced NSGA-II genetic optimization algorithm to handle complex multi-objective optimization problems.

[0089] The scheduling strategy generation module is used to convert the solution calculated by the optimization algorithm into a specific scheduling strategy.

[0090] The scheduling execution module is used to convey the scheduling strategy to tourists and guide them to move along the preset route through display screens, broadcasts, mobile applications, etc.

[0091] The feedback and adjustment module is used to monitor the scheduling effect in real time and dynamically adjust the scheduling strategy based on feedback information to ensure the effectiveness and flexibility of scheduling.

[0092] This multi-objective optimization algorithm module uses the NSGA-II multi-objective genetic optimization algorithm to simultaneously optimize multiple objectives, including maximizing visitor satisfaction, minimizing crowding, and minimizing carbon dioxide concentration. Maximizing visitor satisfaction prioritizes venues that attract the most visitors and provide the highest satisfaction, taking into account visitor duration, route length, average dwell time, and average waiting time. Minimizing crowding reduces crowding by integrating visitor density across various time periods throughout the day. Minimizing carbon dioxide concentration reduces damage to cultural relics within the exhibition halls through real-time monitoring of carbon dioxide concentrations.

[0093] like Figure 7 The specific steps are as follows:

[0094] S161: Construct the objective function and define the exhibition area optimization goal.

[0095] Maximizing visitor satisfaction takes into account visitor duration, distance traveled, waiting times, and the presence of disturbances, recommending venues with the highest visitor satisfaction. Minimizing exhibition area crowding controls visitor density in each exhibition area to prevent overcrowding. Minimizing carbon dioxide emissions controls carbon dioxide concentrations to reduce environmental impacts on cultural relics.

[0096] Chaos Index or Riot:

[0097] Average walking distance:

[0098] Average length of stay:

[0099] Average waiting time:

[0100] Customer Satisfaction:

[0101]

[0102] Among them, L i is the trajectory length, T i is the residence time, W i is the queuing time, m is the number of visitors in the exhibition hall, S is the exhibition area, d1, d2, d3, d4 are preset weights, d1 and d2 are positive weights, and d3 and d4 are negative weights;

[0103] Visitor flow density in the exhibition area: ρ = m / S;

[0104] Passenger flow congestion index: crowding=∑(ρ*t i ) / ∑(t i );

[0105] Among them, t i is the daily time weight coefficient (time interval is 1h), which is positively correlated with the number of tourists, and the CO2 concentration ρ co2 .

[0106] S162: Define the constraints that the optimization process must meet.

[0107] The model's assumptions and constraints are as follows: Visitors queuing outside the exhibition hall will definitely enter the venue; visitors in the exhibition hall walk slowly and orderly, with a walking speed of <2m / s; the longer the visitors stay and the longer they visit, the more interested they are in the exhibition hall, and waiting time will reduce the exhibition hall's appeal to tourists; the maximum carrying capacity of each exhibition area must not exceed the safe capacity of the exhibition area; the flow speed of visitors must be limited to prevent riots and other safety incidents.

[0108] S163: A non-dominated sorting genetic algorithm II combined with a grey wolf genetic algorithm is used for multi-objective optimization to determine the optimal tourist scheduling solution.

[0109] The NSGA-II genetic optimization algorithm is used to evaluate the priority of exhibition areas and obtain the recommended exhibition areas (sets) with the highest comprehensive scores, thereby giving suggestions for visitor scheduling.

[0110] Initialize N initial solutions (N is the number of exhibition halls) and obtain the satisfaction and congestion of these N exhibition halls.

[0111] The three initial parameters are optimized using the grey wolf genetic algorithm to obtain N optimized new solutions.

[0112] Perform non-dominated sorting on the obtained 2N solutions to obtain the Pareto solution set, which is the recommended exhibition hall list.

[0113] The crowding distance of each solution in the Pareto solution set is calculated to further obtain the most recommended destination exhibition area and the comprehensive ranking of the exhibition areas.

[0114] The scheduling strategy generation module is used to convert the plan calculated by the optimization algorithm into a specific scheduling strategy, including: guiding visitors' movement route planning; setting dynamic access restrictions to the exhibition area; and adjusting the opening of rest areas and evacuation passages.

[0115] The scheduling execution module is used to communicate scheduling strategies to tourists through the following means: display screens, which are set up at key locations to display tourist guidance information in real time; the broadcasting system, which releases scheduling information through the in-building broadcasting system; and the mobile phone application, which pushes personalized guidance information to tourists through the mobile phone application in the building via Wi-Fi or Bluetooth services.

[0116] The feedback and adjustment module monitors scheduling effectiveness in real time and collects feedback on emergencies and abnormal events. This module automatically triggers an alarm when a disturbance occurs (i.e., when the Chaos Index reaches 1). Based on this feedback, the three parameters for each exhibition hall are modified in real time, dynamically adjusting the scheduling strategy to ensure both effectiveness and flexibility.

[0117] The workflow is described as follows:

[0118] The sensor module collects data and transmits it to the central server. The central server's data input module receives real-time data, including visitor location, density, and movement information. The multi-objective optimization algorithm module calculates the optimal scheduling solution based on this real-time data. The scheduling strategy generation module translates the optimization results into a specific scheduling strategy. The scheduling execution module communicates the scheduling strategy to visitors via display screens, broadcasts, and mobile apps. The feedback and adjustment module dynamically adjusts the scheduling strategy based on actual conditions and feedback, ensuring a balanced distribution of exhibition areas and visitor satisfaction.

[0119] In this embodiment, the visitor calibration system incorporates deep learning and embeds real-time object detection based on the YOLOv8 architecture. This system detects visitor information captured in real time, thereby calculating visitor density, dwell time, and trajectory length. In this embodiment, the visitor calibration device, combined with a carbon dioxide detection device and a camera, enables real-time data calibration, data exchange with a remote server, and the delivery of recommended scheduling information to visitors. In this embodiment, the visitor scheduling model utilizes the NSGA-II algorithm, which comprehensively evaluates three factors through non-dominated sorting to obtain the optimal Pareto solution set, which serves as the optimized solution set, i.e., the recommended exhibition hall list. This optimal solution set can then be further sorted by congestion level to obtain the best recommended exhibition areas.

[0120] The beneficial technical effects of the above technical solution of the embodiment of the present invention are as follows:

[0121] Embodiments of the present invention are beneficial for improving the accuracy and real-time performance of dynamic calibration. By integrating multi-source data fusion technology with sensor, video analysis, and mobile device data, the shortcomings of a single data source are effectively reduced, improving calibration accuracy. Furthermore, by employing efficient data processing algorithms and edge computing technology, the algorithm is optimized to reduce computational complexity, thereby improving data processing efficiency and enabling more accurate and real-time dynamic calibration.

[0122] The embodiments of the present invention help reduce costs and enhance the visitor experience. By reducing reliance on high-cost RFID tags and devices and instead adopting low-cost, high-precision positioning technologies such as Wi-Fi, Bluetooth, and sensor fusion, the overall system cost is effectively reduced. Furthermore, the embodiments of the present invention utilize anonymization and privacy protection technologies to protect visitor privacy while increasing system acceptance and improving the visitor experience.

[0123] Embodiments of the present invention facilitate improving the flexibility and efficiency of visitor scheduling models. By constructing a dynamic multi-objective optimization model, it comprehensively considers multiple objectives, including visitor satisfaction, exhibition area utilization, and cultural relic protection, enabling more flexible scheduling. Furthermore, based on real-time data and feedback, scheduling strategies are dynamically adjusted, improving the system's responsiveness and scheduling efficiency to adapt to the ever-changing exhibition environment and visitor needs.

[0124] The embodiments of the present invention improve system stability and adaptability. By improving intelligent algorithms, the convergence speed and solution quality are increased, and sensitivity to initial conditions is reduced, thereby enhancing system robustness. Furthermore, the embodiments of the present invention incorporate adaptive control technology, enabling the system to autonomously adjust its scheduling strategy based on real-time environmental changes, further enhancing system stability and adaptability to cope with various complex exhibition hall situations.

[0125] In this embodiment of the present invention, the YOLOv8 computer vision model, trained on extensive datasets, is fast, accurate, and easy to use for object detection (in this case, people), improving image recognition accuracy. The model is mature and easy to use, with data training and prediction performed on cloud servers, effectively reducing costs. The model samples camera video, eliminating the need for visitor interaction and impacting the visitor experience.

[0126] In the tourist scheduling model, the embodiment of the present invention uses a gray wolf genetic algorithm to optimize the initial solution set, which has better convergence and can provide more accurate tourist scheduling suggestions. The optimization based on the genetic algorithm reduces the computational complexity.

[0127] In terms of the calibration device, the embodiment of the present invention integrates multiple modules, has high integration and good systematization, and can autonomously adjust the scheduling strategy according to real-time environmental changes, thereby enhancing the stability and adaptability of the system.

[0128] The visitor scheduling model of the embodiment of the present invention optimizes the distribution and activities of tourists in space based on dynamically calibrated data to achieve the goal of improving resource utilization and visitor experience. Multi-objective optimization algorithms, such as genetic algorithms, particle swarm algorithms, or multi-objective evolutionary algorithms, are used to balance and optimize multiple objectives (such as minimizing congestion, maximizing the utilization of resources such as non-popular exhibits / exhibition areas / idle spaces, and maximizing visitor satisfaction); a real-time decision support system, which combines real-time data and predictive analysis to automatically adjust tourist guided routes, recommend non-popular areas, reduce tourist concentration and overcrowding, and upload tourist congestion phenomena to the management center server in real time. The management center makes relief decisions and notifies the audience through broadcasting; artificial intelligence and machine learning, which analyze big data to learn tourists' preferences and behavior patterns, provide personalized guided tours and recommendation services, and adjust the utilization of spatial resources at the same time.

[0129] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated into one processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0130] An embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon, wherein the program implements any one of the above methods when executed by a processor.

[0131] If the integrated module / unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the process in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program, when executed by the processor, can implement the steps of the above-mentioned various method embodiments. Wherein, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium, etc. Of course, there are other ways of readable storage media, such as quantum memory, graphene memory, etc. It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practices in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practices, computer-readable media do not include electrical carrier signals and telecommunication signals.

[0132] The present invention further provides an electronic device. The electronic device according to an embodiment of the present invention includes: one or more processors; and a storage device for storing one or more programs, wherein when the one or more programs are executed by the one or more processors, the one or more processors implement the method of the present invention.

[0133] Reference below Figure 8 , which shows a schematic structural diagram of a computer system 800 of an electronic device suitable for implementing an embodiment of the present invention. Figure 8 The electronic device shown is only an example and should not limit the functions and scope of use of the embodiments of the present invention.

[0134] like Figure 8 As shown, the computer system 800 includes a central processing unit (CPU) 801, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 802 or a program loaded from a storage unit 808 into a random access memory (RAM) 803. Various programs and data required for the operation of the computer system 800 are also stored in the RAM 803. The CPU 801, the ROM 802, and the RAM 803 are connected to each other via a bus 804. An input / output (I / O) interface 805 is also connected to the bus 804.

[0135] The following components are connected to the I / O interface 805: an input section 806 including a keyboard, a mouse, and the like; an output section 807 including devices such as a cathode ray tube (CRT), a liquid crystal display (LCD), and a speaker; a storage section 808 including a hard disk; and a communication section 809 including a network interface card such as a LAN card or a modem. The communication section 809 performs communication processing via a network such as the Internet. A drive 810 is also connected to the I / O interface 805 as needed. A removable medium 811, such as a magnetic disk, an optical disk, a magneto-optical disk, or a semiconductor memory, is installed in the drive 810 as needed, so that computer programs read therefrom can be installed in the storage section 808 as needed.

[0136] In particular, according to embodiments disclosed herein, the processes described in the main step diagrams above can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a computer-readable medium, the computer program containing program code for executing the methods shown in the main step diagrams. In the above embodiments, the computer program can be downloaded and installed from a network via the communication section 809 and / or installed from removable media 811. When the computer program is executed by the central processing unit 801, the above-described functions defined in the system of the present invention are performed.

[0137] It should be noted that the computer-readable medium described in the present invention may be a computer-readable signal medium or a computer-readable storage medium, or any combination thereof. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or component, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to, an electrical connection having one or more conductors, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, device, or component. In the present invention, a computer-readable signal medium may include a data signal propagated in baseband or as part of a carrier wave, carrying computer-readable program code. This propagated data signal may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. A computer-readable signal medium may also be any computer-readable medium other than a computer-readable storage medium that can transmit, propagate, or transport a program for use by or in conjunction with an instruction execution system, apparatus, or device. Program code embodied on a computer-readable medium may be transmitted using any suitable medium, including but not limited to wireless, wireline, optical cable, RF, or any suitable combination thereof.

[0138] The flowcharts and block diagrams in the accompanying drawings illustrate the possible implementation architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. In this regard, each box in the flowchart or block diagram can represent a module, program segment, or a part of code, and the above-mentioned module, program segment, or a part of code contains one or more executable instructions for implementing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in an order different from that marked in the accompanying drawings. For example, two boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram or flowchart, and the combination of boxes in the block diagram or flowchart, can be implemented with a dedicated hardware-based system that performs the specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0139] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A museum exhibition dynamic visitor calibration and visitor scheduling system, characterized in that: include: The visitor calibration device is installed on the monitoring pole in the museum's exhibition hall. The visitor calibration device includes: The sensor module includes: a carbon dioxide concentration monitoring module for monitoring real-time carbon dioxide concentration data in the exhibition hall; an image sensor for capturing real-time visitor image data in the exhibition hall; a main control unit, configured to receive the real-time carbon dioxide concentration data and the real-time visitor image data, and analyze the real-time visitor image data based on a dynamic target detection algorithm to obtain real-time visitor information, wherein the real-time visitor information includes any one of visitor quantity information, visitor location information, visitor flow information, visitor distribution information, visitor stay time information in the exhibition hall, and visitor queue time information; a communication module, electrically connected to the main control unit, for transmitting the real-time visitor information and the real-time carbon dioxide concentration data to a central server; The central server is configured with a visitor scheduling model, wherein the visitor scheduling model includes: A data input module, configured to receive the real-time visitor information and the real-time carbon dioxide concentration data; a multi-objective optimization algorithm module, configured to determine an optimal tourist scheduling plan based on the real-time tourist information and the real-time carbon dioxide concentration data based on a multi-objective optimization algorithm; A scheduling strategy generation module, used to convert the optimal tourist scheduling plan into a specific scheduling strategy; A scheduling execution module, used to convey the scheduling strategy to tourists; The dynamic target detection algorithm includes: a dynamic target detection algorithm based on the YOLOv8 architecture; the multi-objective optimization algorithm includes: a non-dominated sorting genetic algorithm II; The optimization objectives of the multi-objective optimization algorithm module include: maximizing tourist satisfaction, minimizing passenger flow congestion, and minimizing carbon dioxide concentration; The constraints of the multi-objective optimization algorithm module include: the maximum carrying capacity of the exhibition hall and the speed limit of visitor flow.

2. The system according to claim 1, wherein: The multi-objective optimization algorithm module specifically includes: The exhibition area optimization target definition submodule is used to define the exhibition area optimization target, which includes the following indicators: The average walking path length is calculated using the following formula: Among them, m is the total number of visitors in the exhibition hall, L i is the walking path length of the i-th tourist; The average residence time is calculated using the following formula: Among them, T i is the stay time of the i-th tourist; The average waiting time is calculated using the following formula: Among them, W i is the queuing time of the i-th tourist; The chaos index is calculated using the following formula: When the average walking speed of tourists is greater than 2m / s, the chaos index is 1; when the average walking speed of tourists is less than or equal to 2m / s, the chaos index is 0. i is the walking speed of the i-th tourist; The passenger flow density of the exhibition area is calculated by the following formula: ρ = m / S, where S is the exhibition area and ρ is the passenger flow density of the exhibition area; The passenger flow congestion index is calculated by the following formula: crowding = ∑(ρ*t i ) / ∑(t i ), where t i represents the hourly time weight coefficient, which is positively correlated with the number of tourists; Tourist satisfaction is calculated using the following formula: Among them, d1, d2, d3, and d4 are preset weights, d1 and d2 are positive weight values, and d3 and d4 are negative weight values; The constraint definition submodule is used to define the constraints that must be met during the optimization process. The constraints include: all visitors in the queue outside the exhibition hall will eventually enter the venue; the average walking speed of visitors in the exhibition hall shall not exceed 2 meters per second; the maximum carrying capacity of each exhibition area shall not exceed the safe capacity of the exhibition area; the visitor density per unit area of ​​the exhibition area shall not exceed the design limit of the exhibition area; the chaos index of the exhibition area shall not exceed the preset threshold; the carbon dioxide concentration in the exhibition hall shall not exceed the preset concentration limit; The optimization algorithm processing submodule is used to perform multi-objective optimization using the non-dominated sorting genetic algorithm II combined with the gray wolf genetic algorithm to determine the optimal visitor scheduling plan; it specifically includes: executing the solution set initialization step, which includes initializing N initial solutions, where N is the number of pavilions; for each initial solution, obtaining the satisfaction, passenger flow congestion and carbon dioxide concentration values ​​of the corresponding pavilion; using the gray wolf genetic algorithm to optimize the N initial solutions to improve satisfaction, reduce passenger flow congestion and carbon dioxide concentration, and obtain N optimized new solutions; executing the non-dominated sorting step, including merging the N initial solutions and the N optimized new solutions to form a set of 2N solutions; performing the 2N solutions Perform non-dominated sorting to obtain a Pareto optimal solution set; perform a crowding distance calculation step, which includes calculating the crowding distance of each solution in the Pareto optimal solution set; determine the most recommended destination exhibition area based on the crowding distance; generate a comprehensive ranking of the exhibition areas according to the non-dominated level and crowding distance of each solution in the Pareto optimal solution set, wherein the non-dominated level is determined by comparing the pros and cons of each solution in terms of satisfaction, passenger flow congestion, and carbon dioxide concentration, and the lower the non-dominated level, the higher the priority of the exhibition area; determine the optimal visitor scheduling plan according to the most recommended destination exhibition area, the comprehensive ranking of the exhibition areas, and the satisfaction, passenger flow congestion, and carbon dioxide concentration values ​​of each exhibition area.

3. The system according to claim 1, wherein: The scheduling strategy generation module specifically includes: The first scheduling strategy generation submodule is used to guide the movement paths of tourists in the exhibition hall based on the real-time tourist flow information and the tourists' stay time in the exhibition hall; The second scheduling strategy generation submodule is used to dynamically adjust the maximum number of visitors that can be accommodated at the same time in each exhibition area according to the current visitor distribution information; The third scheduling strategy generation submodule is used to adjust the number of open rest areas and the opening and closing states of evacuation passages according to the information on the number of tourists, the distribution of tourists and the flow of tourists.

4. The system according to claim 3, characterized in that The scheduling execution module specifically includes: A first control submodule is configured to control a plurality of display screens to display visual guidance information for all visitors in real time, wherein the plurality of display screens are installed at different locations in the exhibition hall as devices independent of the central server and the visitor calibration device; A second control submodule controls a broadcasting system to play audio scheduling information for all visitors, wherein the broadcasting system is installed in the exhibition hall as a device independent of the central server and the visitor calibration device; a third control submodule, configured to control the server application running on the central server to send personalized guidance information to the client application on the tourist's mobile phone via a wireless network; The visual guidance information for all tourists, the audio scheduling information for all tourists and the personalized guidance information are all generated by the scheduling execution module according to the scheduling strategy, and the personalized guidance information is determined accordingly according to the specific situation of each tourist.

5. The system according to claim 1, wherein: The tourist scheduling model also includes a feedback and adjustment module for real-time monitoring of scheduling effects, which include tourist distribution information, changes in carbon dioxide concentration, and emergency information, and dynamically adjusting scheduling strategies based on the tourist distribution information, changes in carbon dioxide concentration, and emergency information; wherein the emergency information is obtained through at least one of the following methods: emergency reports uploaded by tourists through mobile applications; abnormal behaviors associated with emergency information detected based on image analysis.

6. The system according to claim 1, wherein: The visitor calibration device further includes: a power module electrically connected to the main control unit, the sensor module and the communication module, for providing power to the visitor calibration device; the sensor module further includes a wireless communication receiving module for receiving wireless signal data sent by a visitor's mobile device; the carbon dioxide concentration monitoring module, the image sensor and the wireless communication receiving module are all electrically connected to the main control unit; The main control unit is further configured to: process the wireless signal data to obtain visitor location information; fuse the visitor location information with the real-time visitor image data to obtain enhanced real-time visitor information; wherein the enhanced real-time visitor information also includes visitor interest data; Among them, based on the continuous tourist location information of a single tourist, the movement trajectory data of a single tourist is generated through time series analysis; the movement trajectory data of multiple tourists are aggregated and analyzed to obtain the tourist flow information representing the overall tourist movement trend; Among them, the tourist interest data is obtained through a combination of methods, including: obtaining multi-dimensional data sources, which include tourist stay time, visit frequency, movement trajectory patterns, interactive behavior, social media activities, questionnaire feedback, consumption behavior, and reservation data; based on the multi-dimensional data sources, combined with deep learning algorithms, a comprehensive tourist interest model is generated to output tourist interest data for different exhibition areas.

7. A method based on the museum exhibition dynamic visitor calibration and visitor scheduling system according to any one of claims 1 to 6, characterized in that: The following steps are involved: The visitor calibration device monitors the real-time carbon dioxide concentration data in the exhibition hall and captures real-time visitor image data in the exhibition hall; analyzes the real-time visitor image data based on a dynamic target detection algorithm to obtain real-time visitor information, wherein the real-time visitor information includes any one of visitor quantity information, visitor location information, visitor flow information, visitor distribution information, visitor stay time in the exhibition hall, and visitor queue time; and transmits the real-time visitor information and the real-time carbon dioxide concentration data to a central server; The central server receives the real-time visitor information and the real-time carbon dioxide concentration data through a visitor scheduling model; determines an optimal visitor scheduling plan based on the real-time visitor information and the real-time carbon dioxide concentration data based on a multi-objective optimization algorithm; converts the optimal visitor scheduling plan into a specific scheduling strategy; and communicates the scheduling strategy to the visitors.

8. An electronic device, characterized in that: include: one or more processors; a storage device for storing one or more programs, When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to claim 7.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to claim 7 is implemented.

Images