Scenic Area Intelligent Control System and Method Based on Internet of Things and Big Data Analysis

Abstract

The present invention discloses a scenic area intelligent control system and method based on the Internet of Things and big data analysis, specifically relating to the technical field of scenic area intelligent control; through big data analysis algorithms, the real-time performance of data transmission between devices in the scenic area is predicted and modeled, and the data transmission rate between devices is adjusted according to the prediction results. At the same time, combined with the energy management system, the working states of devices are dynamically scheduled to optimize the energy efficiency of devices, the tourist flow data is re-collected, and machine learning algorithms are used to analyze the flow fluctuations to achieve precise personnel evacuation and optimized decision-making for resource scheduling, effectively solving the problems of insufficient network bandwidth, data transmission delay and packet loss in the scenic area, improving the real-time performance and accuracy of data transmission, especially in remote areas, ensuring that the intelligent control system of the scenic area can reflect the dynamic situation in real time, and improving the management efficiency and tourist experience.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management and control of scenic spots, and specifically relates to an intelligent management and control system and method for scenic spots based on the Internet of Things and big data analysis. Background Art

[0002] With the rapid development of Internet technology, the Internet of Things (IoT) and big data analysis have gradually become important supporting technologies in various industries. As the core part of the tourism industry, scenic spot management faces challenges such as large tourist flows, decentralized management, and diverse service demands. Traditional scenic spot management methods often rely on manual experience and have a low degree of informatization, resulting in unreasonable resource allocation, low management efficiency, and even affecting the tourist experience. Based on IoT technology, scenic spots can achieve real-time monitoring of various facilities and tourist behaviors, collect big data through sensors, intelligent devices, etc., and use big data analysis technology to deeply mine these data to provide accurate prediction and decision-making support.

[0003] The existing technologies have the following deficiencies:

[0004] In the process of realizing the intelligent management and control of scenic spots based on the Internet of Things and big data analysis, after a large number of IoT devices are deployed in the scenic spot environment, how to ensure data integrity while solving problems such as insufficient network bandwidth, data transmission delay and packet loss between devices, so that big data analysis can reflect the dynamic situation of the scenic spot in real time, has become a key difficulty in realizing intelligent management and control. Especially in some remote areas of scenic spots, poor network signals and device battery life problems further reduce the real-time nature of data transmission. Summary of the Invention

[0005] The purpose of the present invention is to provide an intelligent management and control system and method for scenic spots based on the Internet of Things and big data analysis to solve the deficiencies in the background art.

[0006] To achieve the above purpose, the present invention provides the following technical solutions: An intelligent management and control method for scenic spots based on the Internet of Things and big data analysis, including the following steps:

[0007] S1: Arrange a variety of IoT sensors and intelligent devices in the scenic spot. The sensors and intelligent devices include network environment monitoring devices, tourist behavior monitoring devices, security monitoring devices, and resource management devices, which are used to collect multi-source data in the scenic spot in real time;

[0008] S2: Transmit the multi-source data collected by various sensors to the central data processing platform through a wireless communication network. The multi-source data includes tourist flow data, network environment data, and facility status data;

[0009] S3: Analyze the collected network environment data and facility status data in real time, and predict and model the real-time performance of data transmission among intelligent devices in the scenic area through big data analysis algorithms;

[0010] S4: Based on the prediction results, adjust the data transmission rate among intelligent devices in the scenic area in real time, including reducing the power consumption communication protocol of intelligent devices in the scenic area, and dynamically scheduling the working status of tourist behavior monitoring devices and security monitoring devices in the scenic area in combination with the energy management system;

[0011] S5: Re-collect tourist flow data through the adjusted tourist behavior monitoring devices and security monitoring devices, analyze the fluctuations of tourist flow through machine learning algorithms, and make optimized decisions on personnel guidance and resource scheduling according to the analysis results.

[0012] Preferably, in S3, generate a bandwidth utilization drift value after real-time monitoring and analysis of the bandwidth utilization rate. The method for obtaining the bandwidth utilization drift value is as follows:

[0013] Bandwidth utilization rate refers to the ratio between the currently actually used bandwidth of the network and the total available bandwidth: ; In the formula, represents the bandwidth used in the network at time point t, represents the total network bandwidth;

[0014] In each time interval, collect the bandwidth usage of the network in real time , and calculate the bandwidth utilization rate at the current moment ;

[0015] Set a time window Δt, calculate the change in bandwidth utilization rate within this time window, and calculate the difference between the bandwidth utilization rate at each time point and the previous time point: ; represents the change value of the bandwidth utilization rate at time point t, represents the bandwidth utilization rate at the previous time point;

[0016] The bandwidth utilization drift value EQS is an index measuring the change rate of bandwidth utilization rate, and its calculation formula is: ; In the formula, Δt is the time interval for calculating the bandwidth change, and n is the length of the statistical window.

[0017] Preferably, analyze the load condition of facilities with abnormal usage status to generate a facility load anomaly value. The method for obtaining the facility load anomaly value is as follows:

[0018] Set the real-time load value represents the actual usage load of the facility at time h, and the rated load value Indicates the rated usage load of the facility under normal operation, and the load utilization rate Indicates the ratio of the real-time load value of the facility to the rated load value, and is used to measure the current load status: ; By comparing the real-time load value with the historical load trend, calculate the deviation degree of the load. Based on the historical operation data of the facility, calculate the load mean and standard deviation within a period window: ; In the formula, is the historical mean of the facility load, is the historical standard deviation of the facility load, and m is the number of historical data samples; Calculate the real-time load deviation value through the deviation between the real-time load value and the historical mean : ; Set a threshold value λ. When the load deviation value exceeds the standard deviation of the threshold multiple, it is considered that the load status of the facility is abnormal: If , it is determined that the facility load is abnormal; Calculate the facility load anomaly value WAS, and the specific formula is: .

[0019] Preferably, normalize the bandwidth utilization rate drift value and the facility load anomaly value, and calculate the real-time coefficient of data transmission between intelligent devices in the scenic area through the normalized bandwidth utilization rate drift value and the facility load anomaly value.

[0020] Preferably, compare the obtained real-time coefficient of data transmission between intelligent devices in the scenic area with the real-time reference threshold set according to historical data. If the real-time coefficient of data transmission between intelligent devices in the scenic area is greater than or equal to the set real-time reference threshold, it indicates that the real-time performance of data transmission between intelligent devices in the scenic area is high, and no warning signal is generated at this time; If the real-time coefficient of data transmission between intelligent devices in the scenic area is less than the set real-time reference threshold, it indicates that the real-time performance of data transmission between intelligent devices in the scenic area is low, and a warning signal is generated at this time, and it is necessary to adjust the data transmission rate between intelligent devices in the scenic area.

[0021] Preferably, in S4, the data transmission rate is an important indicator of data transmission between intelligent devices, and needs to be adjusted according to real-time requirements. The dynamic adjustment formula of the data transmission rate is: ; Wherein: is the dynamic data transmission rate at time t, is the basic transmission rate, the maximum supported transmission rate of the device, is the facility load anomaly value, is the maximum value of the facility load anomaly value, is the bandwidth utilization rate drift value, is the maximum value of the bandwidth usage drift value, and α and β are dynamic adjustment coefficients, which are set according to the priority and working requirements of the device;

[0022] The communication protocol selection formula is: ; where: The communication protocol power consumption of the device at time t, is the power consumption adjustment coefficient; Dynamically schedule the working state of the device, and the specific adjustment formula is: ; In the formula, is the working state of the device at time t, and are scheduling coefficients;

[0023] Devices with high load and low real-time requirements: Reduce the data transmission rate, enable a low-power communication protocol, and place the device in a low-power standby or off state; Devices with low load and high real-time requirements: Increase the data transmission rate, use a high-power protocol, ensure that the device is always on, and ensure real-time data transmission.

[0024] Preferably, in S5, the traffic data is modeled and predicted through cluster analysis to identify the tourist traffic fluctuation law and predict the future traffic fluctuation trend, including:

[0025] Before performing cluster analysis, it is necessary to preprocess the collected tourist traffic data;

[0026] Select the number of clusters, randomly select K initial centers, and according to the distance metric, assign each tourist traffic data point to the nearest cluster center; Calculate the average value of each cluster and update the cluster center; Keep repeating until the cluster center no longer changes. After clustering is completed, the scenic area analyzes different tourist traffic fluctuation patterns according to the traffic pattern characteristics of each cluster.

[0027] Preferably, the tourist traffic fluctuation patterns include: peak mode, trough mode, stable mode and abnormal mode.

[0028] The present invention also provides a scenic area intelligent control system based on the Internet of Things and big data analysis, including a data acquisition module, a data transmission module, a modeling module, an adjustment module and a machine learning analysis module;

[0029] Data acquisition module: Arrange a variety of Internet of Things sensors and intelligent devices in the scenic area. The sensors and intelligent devices include network environment monitoring devices, tourist behavior monitoring devices, security monitoring devices and resource management devices, which are used to collect multi-source data in the scenic area in real time;

[0030] Data transmission module: Transmit the multi-source data collected by various sensors to the central data processing platform through a wireless communication network. The multi-source data includes tourist traffic data, network environment data and facility status data;

[0031] Modeling module: Real-time analyze the collected network environment data and facility status data, and predict and model the real-time performance of data transmission between intelligent devices in the scenic area through big data analysis algorithms;

[0032] Adjustment module: Based on the prediction results, adjust the data transmission rate between intelligent devices in the scenic area in real time, including reducing the power consumption communication protocol of intelligent devices in the scenic area, and dynamically scheduling the working status of tourist behavior monitoring devices and security monitoring devices in the scenic area in combination with the energy management system;

[0033] Machine learning analysis module: Re-collect tourist flow data through the adjusted tourist behavior monitoring devices and security monitoring devices, analyze the tourist flow fluctuation situation through machine learning algorithms, and optimize decisions on personnel guidance and resource scheduling according to the analysis results.

[0034] In the above technical solution, the technical effects and advantages provided by the present invention are as follows:

[0035] 1. Through the real-time collection and analysis of multi-source data, the present invention can timely predict the real-time performance of data transmission between intelligent devices in the scenic area, and adjust the data transmission rate based on the prediction results, optimize the communication protocol and working status of the devices, so as to ensure the efficiency and real-time performance of data transmission. Especially in remote areas of the scenic area, the performance and reliability of the intelligent control system are significantly improved. Through in-depth analysis and clustering modeling of tourist flow data, the present invention can also identify different flow fluctuation patterns, implement precise personnel guidance and resource scheduling, and improve the intelligent level of scenic area management and tourist experience.

[0036] 2. By introducing a dynamic adjustment mechanism, based on the real-time monitoring and analysis of the bandwidth usage drift value and facility load anomaly value, the present invention provides a more flexible adjustment ability for data transmission between intelligent devices in the scenic area, and significantly improves the cooperation efficiency between devices. At the same time, the intelligent scheduling system can perform dynamic optimization according to the real-time load and flow fluctuation requirements of the facilities, avoiding excessive resource consumption and ensuring the stable operation of high-real-time-demand devices, and ensuring the efficient and stable operation of the scenic area. Generally speaking, the present invention solves the problems of data transmission delay and uneven device load in traditional scenic area management, has strong innovation and application value, and is especially suitable for the intelligent control system of large-scale and complex scenic areas. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments recorded in the present invention. For those of ordinary skill in the art, other drawings can also be obtained according to these drawings.

[0038] Figure 1 This is the flowchart of the method of the present invention.

[0039] Figure 2 This is the system module diagram of the present invention. Specific embodiments

[0040] To make the objectives, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Apparently, the described embodiments are some but not all of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the scope of protection of the present invention.

[0041] Example 1. Please refer to Figure 1 As shown, the method for intelligent management and control of scenic spots based on the Internet of Things and big data analysis in this embodiment includes the following steps:

[0042] S1: Arrange a variety of Internet of Things sensors and intelligent devices in the scenic spot. The sensors and intelligent devices include network environment monitoring devices, tourist behavior monitoring devices, security monitoring devices and resource management devices, which are used to collect multi-source data in the scenic spot in real time;

[0043] S2: Transmit the multi-source data collected by various sensors to the central data processing platform through a wireless communication network. The multi-source data includes tourist flow data, network environment data and facility status data;

[0044] S3: Perform real-time analysis on the collected network environment data and facility status data, and predict and model the real-time performance of data transmission between intelligent devices in the scenic spot through big data analysis algorithms;

[0045] S4: Based on the prediction results, adjust the data transmission rate between intelligent devices in the scenic spot in real time, including reducing the power consumption communication protocol of the intelligent devices in the scenic spot, and dynamically scheduling the working status of the tourist behavior monitoring devices and security monitoring devices in the scenic spot in combination with the energy management system;

[0046] S5: Re-collect tourist flow data through the adjusted tourist behavior monitoring devices and security monitoring devices, analyze the tourist flow fluctuation situation through machine learning algorithms, and make optimized decisions on personnel guidance and resource scheduling according to the analysis results.

[0047] In S1, the network environment monitoring devices are mainly used to monitor the network conditions within the scenic area to ensure the smooth communication of Internet of Things devices. These devices include: Wireless network quality monitoring devices: used to monitor parameters such as the coverage, bandwidth, latency, and signal strength of wireless communication networks such as Wi-Fi, LoRa, and NB-IoT within the scenic area. These data are crucial for ensuring the stable connection and data transmission of Internet of Things devices. Network bandwidth usage monitors: real-time monitor the bandwidth usage of the network, identify bottlenecks in data transmission, and ensure that measures are taken to adjust the bandwidth or optimize the transmission method during high network loads. Through these devices, the management system can promptly detect areas with unstable network signals or insufficient bandwidth, adjust the network configuration, and ensure the real-time and stability of data transmission.

[0048] The visitor behavior monitoring devices comprehensively monitor visitors' behaviors within the scenic area through the combination of sensors and intelligent technologies. These devices include: Visitor flow monitoring devices: such as infrared sensors, video surveillance, Wi-Fi signal probes, etc., used to detect the flow of visitors within the scenic area in real time, helping management personnel grasp the visitor density and distribution in the scenic area. This is important for visitor guidance, queuing management, and scenic area security. Visitor trajectory tracking devices: through technologies such as mobile phone apps, Bluetooth beacons, and Wi-Fi positioning, real-time track the movement trajectories of visitors within the scenic area. This can not only help management personnel optimize the visitor experience but also promptly detect abnormal situations such as visitors staying in one place or getting lost. Visitor behavior analysis devices: combine technologies such as intelligent cameras, facial recognition, and behavior recognition algorithms to analyze visitors' behavior patterns, such as stay time, interest point preferences, and social behaviors, to provide more precise personalized services and marketing strategies. The visitor behavior monitoring devices can provide accurate data on visitors' activities for scenic area managers, supporting subsequent resource scheduling, service optimization, and emergency response.

[0049] The security monitoring devices are mainly used to ensure the safety of visitors and the order of the scenic area, including: Video surveillance devices: deploy high-definition cameras in key areas of the scenic area for round-the-clock video surveillance to identify suspicious behaviors and abnormal events in real time. For example, through video surveillance, it is possible to detect visitor gatherings, violent incidents, sudden fires, etc. Intelligent access control systems: control the entrances and exits of the scenic area to ensure that only visitors with valid tickets or authorizations can enter and prevent illegal entry. Environmental sensors: such as smoke, temperature, humidity, gas sensors, etc., real-time monitor the environmental safety conditions within the scenic area and give early warnings of possible fire or harmful gas leakage incidents. The security monitoring devices not only ensure the safety of visitors but also assist scenic area management personnel in quickly responding to emergencies and reducing potential safety hazards.

[0050] The resource management device is used to monitor the status of various infrastructure and public resources in the scenic area in real time, ensuring the efficient utilization and management of resources. These devices include: Facility status monitoring devices: Monitor various facilities in the scenic area, including toilets, parking lots, street lights, elevators, trash cans, etc. Through sensors, monitor the usage and fault status of these facilities and promptly feedback to the management system to ensure that the facilities are maintained in a timely manner and reasonably allocated. For example, when the toilet equipment overflows, the system will automatically notify the management staff for cleaning and repair.

[0051] Energy management devices: Used to monitor the energy consumption of electricity, water, gas, etc. in the scenic area to ensure the efficient utilization of energy resources. Through the real-time monitoring of energy consumption, scenic area managers can conduct energy scheduling and energy-saving optimization according to demand. Garbage management devices: Monitor the capacity of trash cans through sensors to ensure timely garbage cleaning, keep the scenic area clean, and avoid the negative impact of garbage accumulation on the tourist experience. The resource management device can effectively optimize the allocation of various resources in the scenic area, reduce operating costs, and improve the service quality of the scenic area.

[0052] In S2, the tourist flow data is one of the most basic and important data in scenic area management. By using sensors and intelligent devices to monitor the movement of tourists in real time, the scenic area management platform can effectively understand the distribution and density of tourists. This type of data is mainly collected through the following methods:

[0053] Infrared sensors and video surveillance: Infrared sensors or intelligent cameras in the scenic area can monitor the number and distribution of tourists in real time. Infrared sensors can calculate the number of tourists passing through a specific area, and the video surveillance system can assist in determining the tourist flow trend by analyzing the number and behavior of tourists in the video stream.

[0054] Wi-Fi and Bluetooth beacons: By deploying Wi-Fi hotspots or Bluetooth beacons in the scenic area, the system can track the movement trajectories of tourists in real time. The movement paths and staying positions of tourists can be captured through their mobile phone signals, thereby generating a detailed distribution map of tourist flow.

[0055] Inlet and outlet flow monitoring: Sensors are installed at the entrances and exits of the scenic area to count the number of tourists entering and leaving in real time. This helps to conduct tourist diversion and management during peak hours and avoid overcrowding of the crowd.

[0056] Network environment data is used to monitor the wireless communication network status in the scenic area to ensure the stable connection and data transmission of all Internet of Things devices. The main purpose of collecting this type of data is to ensure the reliability and real-time nature of wireless communication and avoid affecting the data transmission quality due to network instability. The main network environment data includes:

[0057] Network signal strength and coverage: By deploying network quality monitoring devices within the scenic area, monitor the signal strength, coverage, and stability of networks such as Wi-Fi, LoRa, and NB-IoT in various areas of the scenic area. This helps to identify areas with signal blind spots or network bottlenecks, and adjust network facilities in a timely manner to optimize the network layout.

[0058] Bandwidth usage and network load: Monitor the bandwidth usage of the wireless network within the scenic area and analyze network load and transmission speed. By monitoring the bandwidth usage rate in real time, network congestion can be detected in a timely manner to avoid data transmission delays or packet loss problems.

[0059] Network latency and packet loss rate: The transmission latency and packet loss rate of data packets are crucial for the real-time management of the scenic area. By monitoring network latency and packet loss rate, the system can take appropriate measures, such as dynamically adjusting the data transmission rate or selecting the optimal route, to ensure the timeliness and accuracy of data.

[0060] Facility status data is used to monitor the operating status of various infrastructure facilities within the scenic area, ensure the normal operation of the facilities, detect problems in a timely manner, and perform repairs. This type of data is mainly collected through various sensors, specifically including:

[0061] Facility operation status sensors: Monitor the usage status of facilities within the scenic area (such as elevators, vending machines, public toilets, lights, air conditioners, etc.) through sensors. For example, the load sensor of the elevator monitors the number of passengers in the elevator, the inventory sensor of the vending machine checks the remaining quantity of goods, and the liquid level sensor of the toilet determines whether cleaning or replenishment of items is required.

[0062] Facility fault and health monitoring: By monitoring the status of facilities in real time, the device can detect faults or abnormal operating conditions of the device. For example, when the sensor monitors the water pipe pressure, the device can automatically give an early warning when the pressure is too high or too low to avoid failures.

[0063] Energy consumption monitoring: By installing energy consumption monitoring devices, collect the consumption of resources such as electricity, gas, and water of various facilities within the scenic area in real time. This helps scenic area managers to understand the energy efficiency performance of various facilities in a timely manner, conduct energy optimization management, and reduce operating costs.

[0064] These data are transmitted to the central data processing platform through a wireless communication network (such as Wi-Fi, LoRa, NB-IoT, etc.). The data transmission process needs to ensure the efficiency and accuracy of the data, and usually adopts the following methods:

[0065] Wireless Transmission: The wireless network coverage deployed within the scenic area ensures that various sensor data can be uploaded to the cloud platform in real time for processing and analysis. Data Encryption and Protection: To ensure data security, encryption technologies such as the SSL / TLS protocol are usually adopted during the transmission process to ensure the confidentiality and integrity of data during transmission. Real-time Data Synchronization: Efficient transmission protocols (such as MQTT, CoAP, etc.) are used to ensure real-time data synchronization and avoid data delay or loss due to network problems.

[0066] In S3, monitor the bandwidth usage of the wireless network within the scenic area, analyze the network load and transmission speed, and generate a bandwidth usage drift value through real-time monitoring and analysis of the bandwidth usage rate. Among them, the method for obtaining the bandwidth usage drift value is as follows:

[0067] Bandwidth Usage Rate refers to the ratio between the currently actually used bandwidth of the network and the total available bandwidth, usually expressed as a percentage: ; In the formula, represents the bandwidth used in the network at time point t. represents the total network bandwidth (usually a fixed value, with the unit of Mbps or Gbps).

[0068] The bandwidth usage drift value reflects the changing trend of the bandwidth usage situation. By calculating the change of the bandwidth usage rate over time, the fluctuation degree of the network load can be judged. The specific steps are as follows:

[0069] At each time interval (such as every minute or every second), collect the bandwidth usage situation of the network in real time , and calculate the bandwidth usage rate at the current moment .

[0070] Set a time window Δt (such as 5 minutes or 1 hour), and calculate the change of the bandwidth usage rate within this time window. For example, calculate the difference between the bandwidth usage rate at each time point and the previous time point: ; represents the change value of the bandwidth usage rate at time point t, represents the bandwidth usage rate at the previous time point (t - Δt).

[0071] The bandwidth usage drift value EQS is an index to measure the change rate of the bandwidth usage rate, and its calculation formula is: ; In the formula, Δt is the time interval for calculating the bandwidth change, and n is the length of the statistical window, which can be the average value of multiple time points (such as the sum of differences of the past 5 time points).

[0072] The calculation result of the bandwidth usage drift value EQS can be used in multiple optimization scenarios:

[0073] Network load analysis: When the drift value is large, it indicates that the network load has changed drastically, and it may be necessary to optimize bandwidth allocation or perform traffic regulation.

[0074] Network congestion warning: If the drift value continues to increase, it may mean that the network is about to become congested, and it can be addressed through traffic control or intelligent scheduling.

[0075] Traffic optimization and adjustment: By monitoring the change of the drift value in real time, dynamically adjust the transmission rate of the data stream to avoid the overload area from affecting other network devices.

[0076] Monitor the usage status of facilities in the scenic area (such as elevators, vending machines, public toilets, lights, air conditioners, etc.) through sensors, and analyze the load conditions of facilities with abnormal usage status to generate facility load anomaly values. The method for obtaining the facility load anomaly value is as follows:

[0077] Facility load usually represents the current usage degree or working intensity of the facility, and the degree of deviation from the rated capacity or standard load value of the facility reflects the abnormal state of the facility. The definition of load indicators includes:

[0078] Real-time load value Represents the actual usage load of the facility at time h (such as the current load of the elevator, the transaction volume of the vending machine, the toilet usage rate, the light power, etc.).

[0079] Rated load value Represents the rated usage load of the facility under normal operation, usually provided by the equipment manufacturer or determined through historical data.

[0080] Load utilization rate Represents the ratio of the real-time load value of the facility to the rated load value, and is used to measure the current load status: ;

[0081] When detecting whether the facility load is abnormal, the degree of load deviation can be calculated by comparing the real-time load value with the historical load trend. Based on the historical operation data of the facility, calculate the load mean and standard deviation within a time window to establish the normal range of the load: ; In the formula, is the historical mean of the facility load, is the historical standard deviation of the facility load, and m is the number of historical data samples; calculate the real-time load deviation value through the deviation between the real-time load value and the historical mean : ; Set a threshold value λ (usually 2 or 3, adjusted according to requirements). When the load deviation value exceeds the standard deviation of the threshold multiple, it is considered that the load status of the facility is abnormal: If , then it is determined that the facility load is abnormal.

[0082] To quantify the degree of abnormality, the facility load anomaly value WAS is calculated, and the specific formula is: ; A high facility load anomaly value WAS indicates that the facility load anomaly is relatively serious and requires priority investigation and maintenance.

[0083] Normalize the bandwidth utilization rate drift value and the facility load anomaly value, and calculate the real-time coefficient of data transmission between intelligent devices in the scenic area through the normalized bandwidth utilization rate drift value and the facility load anomaly value.

[0084] For example, the present invention can use the following formula to calculate the real-time coefficient of data transmission between intelligent devices in the scenic area, and the calculation expression is: ; In the formula, is the real-time coefficient of data transmission between intelligent devices in the scenic area, is the bandwidth utilization rate drift value, is the facility load anomaly value, is the proportionality coefficient of the bandwidth utilization rate drift value and the facility load anomaly value, and are all greater than 0.

[0085] Compare the obtained real-time coefficient of data transmission between intelligent devices in the scenic area with the real-time reference threshold set according to historical data. If the real-time coefficient of data transmission between intelligent devices in the scenic area is greater than or equal to the set real-time reference threshold, it indicates that the real-time performance of data transmission between intelligent devices in the scenic area is high, and no warning signal is generated at this time; if the real-time coefficient of data transmission between intelligent devices in the scenic area is less than the set real-time reference threshold, it indicates that the real-time performance of data transmission between intelligent devices in the scenic area is low, and a warning signal is generated at this time, and it is necessary to adjust the data transmission rate between intelligent devices in the scenic area.

[0086] In S4, the data transmission rate is an important indicator of data transmission between intelligent devices. An excessively high transmission rate will consume too much bandwidth and power, so it needs to be adjusted according to real-time requirements. The dynamic adjustment formula for the data transmission rate is: ; Wherein: is the dynamic data transmission rate at time t, is the basic transmission rate, the maximum supported transmission rate of the device, is the facility load anomaly value, is the maximum value of the facility load anomaly value for standardization, is the bandwidth utilization rate drift value, is the maximum value of the bandwidth usage drift value, which is used for standardization. α and β are dynamic adjustment coefficients, which are set according to the priority and working requirements of the device. For example, the tourist behavior monitoring device may have a higher priority than the security monitoring device, and the values of α and β can be adjusted according to the importance of different devices.

[0087] On the premise of ensuring the normal operation of the device, reducing the device power consumption is crucial for the long-term operation of intelligent devices in the scenic area. To achieve this goal, low-power communication protocols (such as LoRa, Zigbee, etc.) can be used to reduce the data transmission power consumption between devices.

[0088] Dynamically select an appropriate communication protocol according to the real-time load of the device and the network bandwidth usage. For example, adopt the following strategies:

[0089] Low traffic and low bandwidth requirements: For devices with a small amount of data to be transmitted and low real-time requirements (such as some security devices or non-critical sensors), use low-power protocols (such as Zigbee, LoRa) to reduce energy consumption.

[0090] High traffic and high real-time requirements: For devices that require a large amount of data transmission or have high real-time requirements (such as tourist behavior monitoring devices, key security devices), use high-speed but more power-consuming protocols (such as Wi-Fi, 4G / 5G) to ensure the timely transmission of data.

[0091] The communication protocol selection formula is: ; where: is the communication protocol power consumption of the device at time t, is the power consumption adjustment coefficient, which is set according to the real-time requirements and importance of the device. Usually, when it is larger, it tends to select a high-power protocol, and vice versa, it selects a low-power protocol.

[0092] Combined with the energy management system (EMS) in the scenic area, dynamically schedule the working states of tourist behavior monitoring devices and security monitoring devices to achieve the optimal allocation of energy and the balance of device loads.

[0093] The working state of the device (such as on / off, standby, etc.) is closely related to factors such as its task priority, real-time requirements, power consumption, etc. Dynamically schedule the working state of the device, and the specific adjustment formula is: ; In the formula, is the working state of the device at time t (0 means shutdown, 1 means on, and values between 0 and 1 mean standby or low-power state). and is the scheduling coefficient, representing the device priority. For high-priority devices (such as tourist behavior monitoring devices, security monitoring devices, etc.), the coefficient is larger, and the devices remain in the on state for a longer time; low-priority devices (such as auxiliary facility devices) can enter the low-power standby state.

[0094] Devices with high load and low real-time requirements: Reduce the data transmission rate, enable low-power communication protocols, and place the devices in the low-power standby or off state.

[0095] Devices with low load and high real-time requirements: Increase the data transmission rate, use high-power protocols, ensure that the devices are always on, and guarantee real-time data transmission.

[0096] According to the calculated dynamic adjustment results, the energy management system will schedule the working states and data transmission strategies of each device in real time in the background, ensuring that while maintaining the real-time performance of data transmission for intelligent devices in the scenic area, the energy consumption is reduced. The scheduling strategies include: Switching security monitoring devices and tourist behavior monitoring devices to the low-power mode during low-traffic periods. Prioritize ensuring the stable operation of devices for emergency tasks (such as monitoring devices, public safety devices). Other non-critical devices enter the standby or off state to reduce unnecessary energy consumption.

[0097] In this application, by dynamically adjusting the data transmission rate between intelligent devices, combining low-power communication protocols with the dynamic scheduling of the energy management system, the scenic area can reduce energy consumption and improve the real-time response ability of the system while ensuring the efficient operation of the devices. By calculating the facility load, bandwidth utilization rate, and device priority in real time, the intelligent scheduling system can maintain the best resource allocation and energy management in the changing scenic area environment.

[0098] In S5, after adjusting the working states of tourist behavior monitoring devices and security monitoring devices, the intelligent system of the scenic area restarts collecting tourist flow data. The collected tourist flow data includes but is not limited to: Real-time location and density of tourists: Through sensors installed at various key locations in the scenic area (such as cameras, infrared sensors, Wi-Fi tracking devices, etc.), collect the real-time location, path, and density information of tourists. Flow change trend: Analyze the flow rules of tourists in different time periods (such as peak hours, off-peak hours, etc.), and the change in tourist density in specific areas. Tourist retention situation: Monitor the stay time of tourists in specific scenic spots or areas to identify potential congestion areas.

[0099] Model and predict the flow data through cluster analysis to identify the rules of tourist flow fluctuations and predict future flow fluctuation trends, including:

[0100] Before performing cluster analysis, it is necessary to preprocess the collected tourist flow data to ensure its suitability for machine learning models. Common preprocessing steps include:

[0101] Data cleaning: Remove invalid data and outliers, and fill in missing values.

[0102] Standardization / Normalization: Convert the data into a standardized form to avoid some features having too much influence on the clustering process. Common standardization methods include Z-score standardization, min-max normalization, etc.

[0103] Feature extraction: Extract meaningful features from the tourist flow data, such as the amplitude of flow fluctuations, tourist stay time, tourist flow speed, etc.

[0104] Taking K-means clustering as an example, after standardizing the tourist flow data and extracting the corresponding features (such as: hourly tourist flow, tourist density, amplitude of flow fluctuations, etc.). Then, the clustering algorithm can be applied to group the tourist flow data.

[0105] K-means clustering process:

[0106] Select the number of clusters (K): Select the number of clusters through algorithms or experience. Methods such as the silhouette coefficient and the elbow method can be used to determine the optimal K value.

[0107] Initialize the cluster centers: Randomly select K initial centers (centroids).

[0108] Assign data points: According to the distance metric (such as Euclidean distance), assign each tourist flow data point to the nearest cluster center.

[0109] Update the cluster centers: Calculate the average value of each cluster and update the cluster centers.

[0110] Repeat continuously until the cluster centers no longer change or reach the preset number of iterations.

[0111] After clustering, the scenic area can analyze different tourist flow fluctuation patterns according to the flow pattern characteristics of each cluster. For example:

[0112] Peak mode (Cluster 1): Represents the peak period of tourist flow, usually occurring on holidays or specific time periods (such as 3 pm to 5 pm).

[0113] Trough mode (Cluster 2): Represents the period with relatively low tourist flow, usually occurring in the morning or at night.

[0114] Stable mode (Cluster 3): The tourist flow fluctuates less and is in the normal fluctuation range.

[0115] Abnormal Pattern (Cluster 4): There is a sudden change in the tourist flow, such as fluctuations in flow due to special events or weather changes.

[0116] Based on the results of cluster analysis, the scenic area can predict the future fluctuation trend of tourist flow through the following steps: Each flow pattern after clustering can be regarded as a specific "flow pattern". Using time series analysis or regression models, model the time evolution trend of each pattern. For example, use time series models such as ARIMA (Autoregressive Integrated Moving Average Model) or LSTM (Long Short-Term Memory Network) to analyze the historical changes in tourist flow patterns and predict future flow fluctuations. For example, when using the ARIMA model, the flow data in each cluster can be modeled: ; where: y(s) represents the tourist flow at time s, p and q are the coefficients of the model, and ϵ(s) is the error term, representing the random fluctuations of the model.

[0117] Based on historical data and prediction models, it is possible to predict the tourist flow in the next few time periods. For example, predict the tourist flow trend in the next hour, day, or during a specific event.

[0118] Through cluster analysis and flow prediction, the scenic area can make the following optimization decisions:

[0119] Personnel Scheduling and Flow Guidance: According to the prediction of different flow patterns, dynamically adjust the arrangement of security, service personnel, and tourist guidance facilities. For example, if a peak period is predicted, adjust the tourist flow direction in advance, and add guiding signs and service windows.

[0120] Facility Resource Optimization: According to the changes in tourist flow, intelligently schedule the facility resources in the scenic area, such as the activation and deactivation of equipment such as elevators, air conditioners, and toilets, to avoid high-load operation.

[0121] Traffic and Security Warning: When it is predicted that the tourist flow in a certain area or time period will exceed the safety capacity, activate the traffic scheduling and security warning system to avoid congestion or accidents.

[0122] To ensure the effectiveness and accuracy of the decision-making, the system needs to continuously update and feedback real-time data. Whenever new tourist flow data is collected, the cluster analysis and flow prediction models will recalculate, correct the tourist flow fluctuation trend, and adjust the optimization strategy. This real-time feedback mechanism will help the scenic area respond to the dynamically changing flow demands and maintain efficient personnel guidance and resource allocation.

[0123] In this embodiment, a variety of Internet of Things sensors and intelligent devices are first deployed in the scenic area, including network environment monitoring, tourist behavior monitoring, security monitoring, and resource management devices, which are used to collect multi-source data in real time. Through the wireless communication network, data such as tourist flow, network environment, and facility status collected are transmitted to the central data processing platform, and big data analysis algorithms are used to predict and model the real-time nature of data transmission. Based on the prediction results, the data transmission rate between intelligent devices is adjusted in real time, including reducing the device power consumption communication protocol, and dynamically scheduling the working status of tourist behavior monitoring devices and security monitoring devices in combination with the energy management system. The adjusted devices re-collect tourist flow data, apply machine learning algorithms to analyze the tourist flow fluctuations, and optimize the decisions on personnel guidance and resource scheduling according to the analysis results to achieve efficient scenic area management and services.

[0124] Embodiment 2, please refer to Figure 2 As shown, the scenic area intelligent control system based on the Internet of Things and big data analysis described in this embodiment includes a data collection module, a data transmission module, a modeling module, an adjustment module, and a machine learning analysis module;

[0125] Data collection module: A variety of Internet of Things sensors and intelligent devices are deployed in the scenic area. The sensors and intelligent devices include network environment monitoring devices, tourist behavior monitoring devices, security monitoring devices, and resource management devices, which are used to collect multi-source data in the scenic area in real time;

[0126] Data transmission module: Through the wireless communication network, the multi-source data collected by various sensors are transmitted to the central data processing platform. The multi-source data includes tourist flow data, network environment data, and facility status data;

[0127] Modeling module: Conduct real-time analysis on the collected network environment data and facility status data, and predict and model the real-time nature of data transmission between intelligent devices in the scenic area through big data analysis algorithms;

[0128] Adjustment module: Based on the prediction results, adjust the data transmission rate between intelligent devices in the scenic area in real time, including reducing the power consumption communication protocol of the intelligent devices in the scenic area, and dynamically scheduling the working status of tourist behavior monitoring devices and security monitoring devices in the scenic area in combination with the energy management system;

[0129] Machine learning analysis module: Re-collect tourist flow data through the adjusted tourist behavior monitoring devices and security monitoring devices, analyze the tourist flow fluctuations through machine learning algorithms, and optimize the decisions on personnel guidance and resource scheduling according to the analysis results.

[0130] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by collecting a large amount of data and performing software simulation to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0131] It should be understood that the term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships can exist. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. Among them, A and B can be singular or plural. In addition, the character " / " in this article generally represents an "or" relationship between the front and back associated objects, but it may also represent an "and / or" relationship. The specific meaning can be understood by referring to the context before and after.

[0132] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed in this article can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of this application.

[0133] As described above, the above is only the specific implementation manner of this application, but the protection scope of this application is not limited thereto. Any person skilled in the art within the technical scope disclosed in this application can easily think of changes or substitutions, and all should be covered within the protection scope of this application.

Claims

1. A smart scenic area management and control method based on the Internet of Things and big data analysis, characterized by: The following steps are involved: S1: deploy a variety of IoT sensors and smart devices in the scenic area, including network environment monitoring equipment, tourist behavior monitoring equipment, security monitoring equipment and resource management equipment, for real-time collection of multi-source data in the scenic area; S2: Transmitting multi-source data collected by various sensors to a central data processing platform via a wireless communication network, wherein the multi-source data includes tourist flow data, network environment data, and facility status data; S3: Analyze the collected network environment data and facility status data in real time, and use big data analysis algorithms to predict and model the real-time performance of data transmission between smart devices in the scenic area. Specifically: The bandwidth usage rate drift value is generated by real-time monitoring and analysis of the bandwidth usage rate. The bandwidth usage rate drift value is obtained as follows: It refers to the ratio between the bandwidth actually used by the network and the total available bandwidth: ; In the formula, represents the bandwidth used in the network at time point t, Indicates the total network bandwidth; at each time interval, collects the network bandwidth usage in real time , and calculate the bandwidth usage at the current moment ; Set a time window Δt, calculate the change in bandwidth usage within the time window, and calculate the difference between the bandwidth usage at each time point and the previous time point: ; Indicates the change in bandwidth usage at time point t, Indicates the bandwidth usage at the last point in time; the bandwidth usage drift value EQS is an indicator to measure the bandwidth usage change rate, and its calculation formula is: ; In the formula, Δt is the time interval for calculating bandwidth changes, and n is the length of the statistical window; S4: Based on the prediction results, the data transmission rate between smart devices in the scenic area is adjusted in real time, including the communication protocol for reducing power consumption of smart devices in the scenic area, and the dynamic scheduling of the working status of tourist behavior monitoring equipment and security monitoring equipment in the scenic area in combination with the energy management system; S5: Re-collect tourist flow data through the adjusted tourist behavior monitoring equipment and security monitoring equipment, analyze tourist flow fluctuations through machine learning algorithms, and make optimal decisions on personnel guidance and resource scheduling based on the analysis results.

2. The method for intelligent management and control of scenic spots based on the Internet of Things and big data analysis according to claim 1 is characterized in that: After analyzing the load conditions of the facilities with abnormal usage status, the abnormal load value of the facility is generated. The method for obtaining the abnormal load value of the facility is as follows: Set real-time load value Indicates the actual load of the facility at time h, the rated load value Indicates the rated load of the facility under normal operation, load utilization rate Indicates the ratio of the facility's real-time load value to the rated load value, used to measure the current load status: ; By comparing the real-time load value with the historical load trend, the degree of load deviation is calculated. Based on the historical operation data of the facility, the load mean and standard deviation within a time window are calculated: ; In the formula, is the historical average of the facility load, is the historical standard deviation of the facility load, and m is the number of historical data samples; the real-time load deviation value is calculated by the deviation between the real-time load value and the historical mean. : ; A threshold λ is set. When the load deviation value exceeds the standard deviation of the threshold multiple, the load state of the facility is considered abnormal: , then the facility load is determined to be abnormal; the facility load abnormality value WAS is calculated, and the specific formula is: .

3. The method for intelligent management and control of scenic spots based on the Internet of Things and big data analysis according to claim 2 is characterized in that: The bandwidth utilization drift value and the facility load anomaly value are normalized, and the real-time coefficient of data transmission between smart devices in the scenic area is calculated based on the normalized bandwidth utilization drift value and the facility load anomaly value.

4. The method for intelligent management and control of scenic spots based on the Internet of Things and big data analysis according to claim 3 is characterized in that: The obtained real-time coefficient of data transmission between smart devices in the scenic area is compared with the real-time reference threshold set according to historical data. If the real-time coefficient of data transmission between smart devices in the scenic area is greater than or equal to the set real-time reference threshold, it means that the real-time of data transmission between smart devices in the scenic area is high, and no warning signal is generated at this time; if the real-time coefficient of data transmission between smart devices in the scenic area is less than the set real-time reference threshold, it means that the real-time of data transmission between smart devices in the scenic area is low, and a warning signal is generated at this time, and the data transmission rate between smart devices in the scenic area needs to be adjusted.

5. The method for intelligent management and control of scenic spots based on the Internet of Things and big data analysis according to claim 1 is characterized in that: In S4, the data transfer rate It is an important indicator of data transmission between smart devices and needs to be adjusted according to real-time requirements. The dynamic adjustment formula of data transmission rate is: ;in: is the dynamic data transmission rate at time t, is the basic transmission rate, the maximum supported transmission rate of the device, is the facility load anomaly, is the maximum value of the abnormal value of the facility load, is the bandwidth usage drift value, is the maximum value of the bandwidth usage drift value, α and β are dynamic adjustment coefficients, which are set according to the priority and working requirements of the device; The communication protocol selection formula is: ;in: The communication protocol power consumption of the device at time t is: is the power consumption adjustment coefficient; the working state of the dynamic scheduling equipment, the specific adjustment formula is: ; In the formula, is the working status of the equipment at time t, and is the scheduling coefficient; Devices with high load and low real-time requirements: reduce the data transmission rate, enable low-power communication protocols, and put the device into low-power standby or shutdown state; Devices with low load and high real-time requirements: increase the data transmission rate, use high-power protocols, ensure that the device is always on and guarantee real-time data transmission.

6. The method for intelligent management and control of scenic spots based on the Internet of Things and big data analysis according to claim 5 is characterized by: In S5, cluster analysis is used to model and predict traffic data to identify the fluctuation patterns of tourist traffic and predict future traffic fluctuation trends, including: Before cluster analysis, the collected tourist flow data needs to be preprocessed; Select the number of clusters, randomly select K initial centers, and assign each tourist flow data point to the nearest cluster center based on the distance metric; calculate the average value of each cluster and update the cluster center; repeat until the cluster center no longer changes. After clustering is completed, the scenic spot analyzes different tourist flow fluctuation patterns based on the flow pattern characteristics of each cluster.

7. The method for intelligent management and control of scenic spots based on the Internet of Things and big data analysis according to claim 6 is characterized by: Tourist flow fluctuation modes include: peak mode, trough mode, stable mode and abnormal mode.

8. A scenic spot intelligent management and control system based on the Internet of Things and big data analysis, used to implement the scenic spot intelligent management and control method based on the Internet of Things and big data analysis as described in any one of claims 1 to 7, characterized in that: It includes data acquisition module, data transmission module, modeling module, adjustment module and machine learning analysis module; Data collection module: a variety of IoT sensors and smart devices are deployed in the scenic area, including network environment monitoring equipment, tourist behavior monitoring equipment, security monitoring equipment and resource management equipment, which are used to collect multi-source data in the scenic area in real time; Data transmission module: transmits multi-source data collected by various sensors to the central data processing platform through a wireless communication network, wherein the multi-source data includes tourist flow data, network environment data and facility status data; Modeling module: conducts real-time analysis on the collected network environment data and facility status data, and predicts and models the real-time performance of data transmission between smart devices in the scenic area through big data analysis algorithms; Adjustment module: Based on the prediction results, the data transmission rate between smart devices in the scenic area is adjusted in real time, including the communication protocol for reducing power consumption of smart devices in the scenic area, and the dynamic scheduling of the working status of tourist behavior monitoring equipment and security monitoring equipment in the scenic area in combination with the energy management system; Machine learning analysis module: re-collect tourist flow data through adjusted tourist behavior monitoring equipment and security monitoring equipment, analyze tourist flow fluctuations through machine learning algorithms, and make optimized decisions on personnel guidance and resource scheduling based on the analysis results.

Images