Commercial complex crowd management system based on real-time LoT sensor

Abstract

The invention provides a commercial complex crowd management system based on a real-time LoT sensor, and relates to the technical field of intelligent management. The management main system comprises a data acquisition module, a data processing module, a dynamic environment optimization module, a people flow guidance and excitation module, a resource scheduling module, a safety monitoring and response module, an external cooperation module, a space value optimization module, a user feedback and experience module and a control flow management module; the real-time LoT sensor is deployed to comprehensively monitor the people flow density, the environmental parameters and the equipment state in the commercial complex, the problems of crowded areas and uneven resource allocation in the peak period can be found in time, and user experience decline and potential safety hazards caused by delayed response are effectively avoided. The system achieves minute-level density monitoring in peak hours, and the real-time performance and response efficiency of crowd management are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of intelligent management technology, specifically to a crowd management system for commercial complexes based on real-time IoT sensors. Background Technology

[0002] With the acceleration of urbanization and the rapid development of commercial complexes, the efficiency and safety of pedestrian flow management in large commercial complexes, as core locations with high pedestrian traffic, are receiving increasing attention. Crowd congestion during peak hours not only affects users' shopping and leisure experiences but can also lead to safety hazards, such as chaos caused by overcrowding or uneven resource allocation. Therefore, effectively monitoring and managing pedestrian flow distribution, improving space resource utilization, and enhancing user satisfaction have become crucial issues in the operation and management of commercial complexes.

[0003] Currently, crowd management in commercial complexes mainly relies on the following technological means:

[0004] Manual management: Security personnel patrol and guide people on-site, combined with simple surveillance cameras to observe the distribution of people and assist in adjusting resource allocation.

[0005] Video surveillance technology: Utilizing high-definition cameras and basic video analytics algorithms, it can count crowd density and identify potentially crowded areas for manual intervention.

[0006] Mobile app guidance: Push navigation information or coupons for low-traffic areas to users through an application on their smartphones to encourage the diversion of traffic.

[0007] While these technologies have improved crowd management in commercial complexes to some extent, many problems still exist:

[0008] First, manual management relies on the experience and immediate response of security personnel, which is time-consuming and has limited coverage. It cannot achieve real-time monitoring of the distribution of people, and it is especially difficult to deal with sudden congestion during peak hours.

[0009] Secondly, video surveillance technology is limited by environmental factors such as light and obstruction, resulting in low analysis accuracy. Moreover, it is mostly passive observation and lacks proactive linkage with environmental adjustment or resource scheduling, making it difficult to achieve comprehensive optimization.

[0010] Secondly, mobile application guidance relies on active user participation, resulting in a low participation rate. Furthermore, existing systems typically involve one-way information push and lack a real-time feedback mechanism, making it difficult to dynamically adjust strategies based on actual changes in pedestrian traffic.

[0011] Finally, existing technologies mostly rely on a single data source (such as video images or user location) and lack integrated analysis of multi-dimensional data (environmental parameters, crowd density, equipment status). The real-time nature and intelligence of monitoring methods are insufficient, making it difficult to provide accurate and timely response solutions during peak crowds or emergencies.

[0012] Therefore, a crowd management system for commercial complexes based on real-time IoT sensors is needed to solve the above problems. Summary of the Invention

[0013] Technical problems to be solved

[0014] To address the shortcomings of existing technologies, this invention provides a commercial complex crowd management system based on real-time IoT sensors, which solves the problems mentioned in the background.

[0015] Technical solution

[0016] To achieve the above objectives, the present invention provides the following technical solution: a commercial complex crowd management system based on real-time IoT sensors, comprising a main management system, which includes a data acquisition module, a data processing module, a dynamic environment optimization module, a crowd guidance and incentive module, a resource scheduling module, a security monitoring and response module, an external collaboration module, a space value optimization module, a user feedback and experience module, and a control flow management module. The data acquisition module is used to collect environmental parameters, crowd distribution data, and facility operation status data within the commercial complex in real time, and transmit them to the data processing module via a low-power wide-area network. The data processing module is used to process and analyze the collected data, generate dynamic control commands, and distribute them to various functional modules through the control flow management module. The dynamic environment optimization module and the crowd guidance and incentive module... The system comprises a resource scheduling module, a security monitoring and response module, an external collaboration module, and a space value optimization module. These modules execute environmental adjustments, pedestrian flow guidance, resource scheduling, security response, external collaboration, and space optimization operations based on dynamic control commands, and provide real-time feedback to users through the user feedback and experience module. The control flow management module coordinates command flow, data transmission priority management, and feedback loop optimization among the modules to ensure the real-time performance and stability of the system. Specifically, the data acquisition module dynamically adjusts the data acquisition frequency based on peak and off-peak pedestrian traffic in the commercial complex; the data processing module generates dynamic control commands and distributes them through the control flow management module; after each functional module executes its operation, feedback data is collected through the user feedback and experience module, and this feedback data is transmitted to the data acquisition module through the control flow management module, forming a closed-loop management system.

[0017] Preferably, the data acquisition module includes an environmental monitoring unit, a pedestrian flow tracking unit, and an equipment status monitoring unit, which respectively collect environmental parameters, pedestrian flow distribution data, and facility operation status data within the commercial complex. The environmental monitoring unit collects baseline data 24 times daily during the initial operation phase for planning pedestrian flow management schemes. During operation, it collects data every 15 minutes during peak hours (10:00-14:00 and 17:00-21:00 daily) and every 30 minutes during off-peak hours (0:00-10:00 and 14:00-17:00 daily). After operation ends, it collects evaluation data weekly. The pedestrian flow tracking unit collects data every [time period missing] during peak hours... The system collects pedestrian density and movement speed data every 5 minutes, and every 10 minutes during off-peak hours; the equipment status monitoring unit collects facility operation status data every 30 minutes; the data processing module includes an embedded computing unit and an edge computing unit for real-time processing and analysis of the data transmitted by the data acquisition module. The embedded computing unit is responsible for data denoising, formatting, and classification, while the edge computing unit analyzes pedestrian distribution trends, environmental comfort index, and facility utilization efficiency based on preset pedestrian density thresholds, environmental parameter thresholds, and facility utilization rate thresholds, generating dynamic control commands; the dynamic environment optimization module includes an air conditioning controller and a lighting regulator. The system includes: odor diffusion devices and digital signage for adjusting temperature, light color temperature, odor concentration, and information display within the commercial complex according to the dynamic control commands; a pedestrian guidance and incentive module configured to guide users to low-traffic areas and provide incentive feedback via user interaction terminals and digital signage according to the dynamic control commands; a resource scheduling module including a facility control unit for dynamically adjusting the operating status and number of open elevators, parking spaces, and restrooms according to the dynamic control commands; a security monitoring and response module including a security dispatch unit for monitoring abnormal behavior and generating security response commands according to the dynamic control commands; and an external collaboration module via R... The ESTfulAPI interface communicates with urban transportation systems and shared mobility platforms to optimize external pedestrian flow based on the dynamic control commands. The spatial value optimization module generates space leasing and activity planning suggestions based on the dynamic control commands to optimize the space utilization of commercial complexes. The user feedback and experience module is configured to collect user satisfaction feedback on the environment, guidance, facilities, and safety through user interaction terminals and transmit the feedback data to the data acquisition module. The control flow management module includes a command distribution unit, a data transmission monitoring unit, and a feedback loop optimization unit, used to coordinate command flow, data transmission priority management, and feedback loop optimization.The data acquisition module transmits the acquired data in encrypted JSON format to the data processing module via a low-power wide-area network. The data processing module generates dynamic control commands and distributes them to each functional module using a priority queue through the control flow management module. After each functional module executes its operation, it provides real-time feedback to the user through the user feedback and experience module. This feedback data is transmitted back to the data acquisition module through the control flow management module, which monitors the real-time performance and stability of the data and command flows.

[0018] Preferably, the environmental monitoring unit of the data acquisition module includes a temperature and humidity sensor, a light sensor, and an odor sensor, which collect data on temperature, humidity, light intensity, and air odor concentration, respectively; the people tracking unit includes an infrared ranging sensor and a pressure sensor, which collect data on people density, movement speed, and dwell time, respectively; the equipment status monitoring unit includes an RFID tag and a Bluetooth Low Energy beacon, which collect operational status data of elevators, parking spaces, and restrooms; the data acquisition module collects environmental and people flow data every 15 minutes during peak hours (10:00-14:00 and 17:00-21:00 daily), and every 30 minutes during off-peak hours (0:00-10:00 and 14:00-17:00 daily), and collects equipment status data every 30 minutes; the collected data is transmitted to the data processing module in encrypted JSON format via a low-power wide area network, and the data packets are anonymized, retaining only location, density, and status data.

[0019] Preferably, the embedded computing unit of the data processing module performs noise reduction, formatting, and classification on the collected data. The edge computing unit analyzes the distribution trend of people flow, environmental comfort index, and facility utilization efficiency based on preset thresholds for pedestrian density (10 people per square meter), environmental parameters (temperature 22-26 degrees Celsius, humidity 40-60%), and facility utilization (elevator utilization 80%), and generates dynamic control commands. The dynamic control commands are transmitted to each functional module via a 5G network through the control flow management module. The control flow management module allocates transmission bandwidth according to command type (safety commands have the highest priority, followed by environmental commands, and then incentive commands have the lowest priority). The transmission delay of safety commands is less than 50 milliseconds.

[0020] Preferably, the air conditioning controller, lighting regulator, and odor diffusion device of the dynamic environment optimization module adjust the temperature of the area to 22-26 degrees Celsius, the light color temperature to 3000-5000K, and the odor concentration to 0.1-0.5 mg / m³ according to dynamic control commands; the digital signage displays the real-time environmental status ("current area temperature 24 degrees Celsius") and guidance information; the operation results of the dynamic environment optimization module are fed back to the user interaction terminal in the form of push notifications through the user feedback and experience module, and the feedback data is transmitted to the data acquisition module in JSON format through the control flow management module, and the control flow management module ensures that the feedback data transmission delay is less than 100 milliseconds.

[0021] Preferably, the pedestrian flow guidance and incentive module pushes path guidance and incentive information for low-pedestrian areas to users through a user interaction terminal and digital signage, based on the dynamic control instructions. The incentive information includes points rewards (10 points for every 10 minutes spent in a low-pedestrian area, 100 points can be redeemed for a 5 yuan coupon) and limited-time discounts (a 10% discount within 5 minutes of entering a low-pedestrian area, valid for 30 minutes). The pedestrian flow guidance and incentive module generates feedback data based on the user's selection behavior through the user interaction terminal (clicking on a path or accepting a discount) and transmits it to the data acquisition module through the control flow management module. The control flow management module adjusts the incentive push frequency based on the user's response time (less than 30 seconds is high priority), pushing 1-3 times per hour.

[0022] Preferably, the facility control unit of the resource scheduling module adjusts the elevator operating frequency (twice per minute during peak hours and once per minute during off-peak hours), the number of parking spaces open (90% open during peak hours and 50% open during off-peak hours), and the restroom cleaning cycle (once per hour during peak hours and once every two hours during off-peak hours) according to the dynamic control instructions; the resource scheduling module pushes the location information of the nearest available facility (distance less than 200 meters) through the user interaction terminal; the operation results are collected through the user feedback and experience module to obtain user satisfaction feedback (rating 1-5 points), and the satisfaction feedback is transmitted to the data acquisition module through the control flow management module. The control flow management module ensures that the feedback data transmission delay is less than 100 milliseconds. The security dispatch unit of the security monitoring and response module detects abnormal behavior through cameras and vibration sensors. Abnormal behavior includes a gathering density of more than 15 people per square meter or a vibration frequency of more than 5 Hz. The security dispatch unit generates patrol route optimization instructions (prioritizing coverage of areas with a gathering density of more than 10 people per square meter) and evacuation guidance information based on dynamic control instructions, and pushes them through digital signage and user interaction terminals. The operation results are collected through the user feedback and experience module to collect user safety feedback (rating 1-5 points). The feedback data is transmitted to the data acquisition module through the control flow management module.

[0023] Preferably, the external collaboration module communicates with the urban transportation system and the shared mobility platform via a RESTful API interface in JSON format. Combining pedestrian density data from the data acquisition module and external parking sensor data (collected every 10 minutes), it generates comprehensive traffic guidance instructions. These instructions include recommendations for the nearest parking space (less than 100 meters away) and public transportation arrival times (within the next 10 minutes). The external collaboration module pushes guidance information through the user interaction terminal and collects user feedback on transportation choices (choosing shared bicycles or public transportation). This feedback is transmitted to the data acquisition module via the control flow management module, which ensures that the transmission delay of the traffic guidance instructions is less than 100 milliseconds. The value optimization module generates a regional pedestrian value assessment report based on the pedestrian density and dwell time analysis of the data processing module. The regional pedestrian value assessment report includes the consumption conversion rate (spending per 100 people) and activity participation rate (number of participants per hour) for each area. The space value optimization module generates dynamic leasing suggestions based on the regional pedestrian value assessment report. The dynamic leasing suggestions include short-term pop-up booth locations (areas with pedestrian density of less than 5 people per square meter) and long-term shop rent adjustment plans (adjusted by 10-20% based on the consumption conversion rate), which are pushed through the management terminal. Finally, the operation results are collected by the user feedback and experience module to gather merchant satisfaction feedback (rating from 1 to 5 points), and transmitted to the data acquisition module through the control flow management module.

[0024] Preferably, the user feedback and experience module collects user satisfaction feedback on the environment, guidance, facilities, and safety through a user interaction terminal. The feedback data includes ratings (1-5 points), text comments, and behavioral selection data (clicking paths or accepting incentives). The user feedback and experience module transmits the feedback data to the data acquisition module in JSON format via the control flow management module. The control flow management module adjusts the transmission priority based on the amount of feedback data (more than 100 data points per hour is high priority, less than 50 is low priority). High-priority feedback data transmission latency is less than 50 milliseconds, and low-priority latency is less than 200 milliseconds. The data acquisition module updates its acquisition strategy based on the feedback data. The control flow management module includes an instruction distribution unit, The system includes a data transmission monitoring unit and a feedback loop optimization unit. The instruction distribution unit distributes dynamic control instructions to each functional module via a 5G network according to their priority (safety instructions have the highest priority, followed by environmental instructions, and then incentive instructions have the lowest priority), with a safety instruction transmission latency of less than 50 milliseconds. The data transmission monitoring unit monitors data transmission latency (target less than 100 milliseconds) and packet loss rate (target less than 1%) in real time. The feedback loop optimization unit adjusts the instruction execution frequency (3-5 times per hour during peak hours and 1-2 times per hour during off-peak hours) and data acquisition cycle (every 5-15 minutes during peak hours and every 10-30 minutes during off-peak hours) of each functional module based on user feedback and feedback data from the experience module, ensuring the stability of the closed-loop control flow.

[0025] Preferably, the main management system further includes a lost and found tracking module. This module detects the location of items within the commercial complex using Bluetooth Low Energy (BLE) beacons and RFID tags. The BLE beacons are deployed in public areas (rest areas, dining areas, and passageways) and cover 80% of the area. The RFID tags are bound to items (wallets, keys) by users via user interaction terminals, and reusable tags are provided by the commercial complex. The lost and found tracking module generates lost item location information (positioning accuracy 5 meters) based on dynamic control commands and pushes retrieval paths through the user interaction terminal. Operation results are collected through a user feedback and experience module (rating from 1 to 5 points) to user feedback on the retrieval experience, and transmitted to the data acquisition module through a control flow management module.

[0026] Beneficial effects

[0027] This invention provides a crowd management system for commercial complexes based on real-time IoT sensors. It offers the following advantages:

[0028] 1. This invention utilizes real-time IoT sensors to comprehensively monitor pedestrian density, environmental parameters, and equipment status within commercial complexes. This enables timely detection of congested areas and uneven resource allocation during peak hours, effectively preventing user experience degradation and safety hazards caused by delayed responses. The system achieves minute-level density monitoring during peak hours, significantly improving the real-time nature and response efficiency of crowd management. Unlike traditional manual management that relies on experience and delayed observation, this invention achieves precise perception of pedestrian dynamics through the wide coverage and high-frequency acquisition of the sensor network.

[0029] 2. This invention employs a multi-module collaborative working mechanism, including a data processing module for analyzing multi-dimensional data and a dynamic environment optimization module for adjusting the system. This generates intelligent control commands, automatically guiding users to low-traffic areas and optimizing resource scheduling. For example, the system guides 30% of users to low-density areas through a pedestrian guidance and incentive module, reducing the density of the dining area from 12 people / square meter to 8 people / square meter. Simultaneously, the resource scheduling module adjusts the elevator frequency to twice per minute, significantly alleviating peak-hour congestion. Compared to existing video surveillance technologies, which are susceptible to environmental influences and have low accuracy, this invention integrates IoT sensor data to achieve more reliable dynamic adjustments and resource optimization, improving management efficiency.

[0030] 3. This invention coordinates the instruction flow and data transmission between modules through a control flow management module, forming a closed-loop optimization by combining user feedback and experience modules. It dynamically adjusts the collection frequency and guidance strategy based on user behavior and satisfaction. For example, when the feedback volume exceeds 100 messages / hour during peak periods, the collection frequency is shortened from 5 minutes to 3 minutes, ensuring the system adapts quickly to changes. Compared to the limitations of mobile applications' single push notifications lacking feedback, this invention optimizes crowd distribution and environmental comfort through a real-time feedback mechanism, providing more flexible responsiveness.

[0031] 4. This invention also utilizes a lost and found tracking module with low-power Bluetooth beacons and RFID tags to locate items, enhancing user experience and the completeness of services within the complex. Unlike existing technologies that rely on a single data source, this invention integrates multi-dimensional data and, through in-depth analysis by a data processing module, achieves accurate risk identification and resource management, significantly improving the operational efficiency and user satisfaction of commercial complexes. Attached Figure Description

[0032] Figure 1 This is a flowchart of the management system of the present invention;

[0033] Figure 2 This is a system framework diagram of the present invention;

[0034] Figure 3 This is a system simulation diagram of the present invention. Detailed Implementation

[0035] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention. Specific Implementation Example 1:

[0037] like Figures 1 to 3 As shown, the crowd management system for commercial complexes based on real-time IoT sensors is an intelligent solution designed for commercial complexes. Through a main management system, it coordinates multiple functional modules, including data acquisition, data processing, dynamic environment optimization, pedestrian guidance and incentives, resource scheduling, security monitoring and response, external collaboration, space value optimization, user feedback and experience, control flow management, and lost and found tracking, to achieve optimized pedestrian flow, environmental regulation, resource scheduling, security response, external collaboration, and maximized space utilization. The system transmits data and commands via LoRa and 5G networks, collects multi-dimensional data in real time, generates dynamic control commands, coordinates the actions of each module, and forms a closed-loop optimization through user feedback. The "App" in the user interaction terminal is a mobile application installed on the user's smartphone, allowing users to receive real-time notifications (guided routes, parking recommendations, discount information), submit feedback (satisfaction ratings or reviews), and interact with system functions (binding lost items or redeeming points). It supports multiple languages ​​and accessibility features, is simple and easy to use, and ensures easy operation for different users. The system operates in a closed loop through data acquisition, analysis, instruction generation, action execution, and feedback optimization. The following details the role of each module, the purpose of data acquisition, the content of dynamic control instructions, the basis for judgment, the actions to be executed, and the interactions between modules.

[0038] The system operation begins with data acquisition. The data acquisition module uses IoT sensors to perceive environmental parameters, pedestrian flow distribution, and facility status within the commercial complex in real time. The data is transmitted to the data processing module via a low-power wide-area network in encrypted JSON data packets (anonymized, retaining only location, density, and status data to comply with privacy regulations). The data processing module analyzes the data and generates dynamic control commands based on preset thresholds. These commands are then distributed to various functional modules via a 5G network through the control flow management module. Each functional module performs actions such as environmental adjustment, pedestrian guidance, and resource scheduling. The results are fed back to the user through a user interaction terminal (App) or digital signage. The user feedback and experience module collects user ratings, reviews, and behavioral selection data, transmitting this data back to the data acquisition module through the control flow management module to optimize the acquisition strategy and command generation. The control flow management module coordinates command distribution, data transmission priority, and feedback loops to ensure system real-time performance and stability.

[0039] The data acquisition module collects data through an environmental monitoring unit (temperature and humidity sensors, light sensors, and odor sensors), a people tracking unit (infrared ranging sensors and pressure sensors), and an equipment status monitoring unit (RFID tags and Bluetooth Low Energy beacons). The environmental monitoring unit collects temperature (degrees Celsius), humidity (percentage), light intensity (lux), and odor concentration (mg / m³) to adjust air conditioning, lighting, and odor diffusion devices to improve comfort, such as maintaining a temperature of 22-26°C, humidity of 40-60%, and odor concentration of 0.1-0.5 mg / m³. During the initial operation phase, baseline data is collected 24 times per day (once per hour). During peak operating hours (10:00-14:00 and 17:00-21:00, density >5 people / m²), data is collected every 15 minutes. During off-peak hours (0:00-10:00 and 14:00-17:00), data is collected every 30 minutes. After the end of operation, evaluation data is collected weekly. The people tracking unit collects data on people density (people / square meter), movement speed (meters / second), and dwell time (minutes) to identify crowded areas (density > 10 people / square meter triggers guidance) and analyze user behavior (dwell time > 10 minutes prompts incentives). Data is collected every 5 minutes during peak hours and every 10 minutes during off-peak hours. The equipment status monitoring unit collects data on elevator operation frequency, parking space occupancy rate, and restroom usage status every 30 minutes to optimize resource allocation, such as opening more parking spaces when parking space occupancy rate > 80%. The data acquisition module transmits data to the data processing module via a LoRa network, receives feedback data from the user feedback and experience module (via the control flow management module), and adjusts the collection frequency accordingly, for example, shortening the collection cycle to 10 minutes when users report a poor environment.

[0040] The data processing module processes data through embedded computing units and edge computing units. The embedded computing unit performs data denoising (removing outliers, such as sudden temperature changes to 30°C), formatting (using a unified JSON format), and classification (by environment, pedestrian flow, and equipment status). The edge computing unit analyzes data based on preset thresholds (pedestrian density 10 people / square meter, temperature 22-26°C, humidity 40-60%, elevator utilization 80%) and generates dynamic control commands. For example, if the density in the dining area is 12 people / square meter and the temperature is 28°C, it generates commands such as "lower the temperature to 24°C," "guide users to the leisure area (density < 5 people / square meter), push a 10% discount," and "increase elevator frequency to twice per minute." Commands are distributed via the control flow management module using a 5G network, with safety commands having the highest priority (latency < 50 milliseconds). The data processing module receives data from the data acquisition module, generates commands, and distributes them to various functional modules through the control flow management module. It also receives feedback data to optimize thresholds (adjusting the density threshold to 8 people / square meter).

[0041] The dynamic environment optimization module receives instructions from the control flow management module ("Temperature in the dining area reduced to 24°C, odor concentration set to 0.3 mg / m³"), adjusts the temperature to 22-26°C via the air conditioning controller, adjusts the color temperature to 3000-5000K via the lighting regulator, controls the odor diffusion device to 0.1-0.5 mg / m³, and displays "Current temperature 24°C" or guidance information on digital signs. The judgment criterion is that environmental parameters exceed the threshold (temperature > 26°C), and the actions performed include adjusting the environment and display status. The operation results are fed back to the user via an app notification through the user feedback and experience module. The feedback data ("Comfort rating 4 points") is transmitted to the data acquisition module through the control flow management module to optimize the environmental data acquisition strategy.

[0042] The pedestrian guidance and incentive module receives instructions ("Guide users to the leisure area, push a 10% discount") and pushes the path ("Walk 5 minutes to the leisure area") and incentive information (10 points for staying for 10 minutes, 100 points can be redeemed for a 5 yuan coupon; 10% discount within 5 minutes of entering, valid for 30 minutes). The criteria for judgment are density > 10 people / square meter or stay time > 10 minutes. Actions include pushing guidance and incentives. Users click on the path or accept the discount through the app, generating behavioral selection data. Feedback data is transmitted to the data acquisition module through the control flow management module. The control flow management module adjusts the push frequency (1-3 times per hour) based on response time (<30 seconds is high priority).

[0043] The resource scheduling module receives instructions ("Open 90% of parking spaces, increase elevator frequency to twice per minute") and adjusts the elevator frequency (twice per minute during peak hours, once per minute during off-peak hours) and the number of parking spaces open (90% during peak hours, 50% during off-peak hours) and restroom cleaning cycle (once per hour during peak hours, once every 2 hours during off-peak hours) through the facility control unit. The judgment is based on equipment utilization (parking space occupancy > 80%), and the actions performed include scheduling facilities and pushing available parking space information (distance < 200 meters). Operation results are collected through the user feedback and experience module to gather satisfaction feedback (rating from 1 to 5 points), and transmitted to the data acquisition module through the control flow management module to optimize the scheduling strategy.

[0044] The security monitoring and response module receives instructions ("Dining area density > 15 people / square meter, generate evacuation routes"), detects abnormal behavior (density > 15 people / square meter, vibration frequency > 5 Hz) through cameras and vibration sensors, generates patrol route optimization instructions (prioritizing coverage areas with a density > 10 people / square meter) or evacuation guidance information, and pushes it to digital signage and the App. The judgment is based on the abnormal behavior threshold, and the actions taken include pushing evacuation routes and notifying security personnel. User safety feedback (rating 1-5 points) is collected through the user feedback and experience module, transmitted to the data acquisition module via the control flow management module, and used to optimize security strategies.

[0045] The external collaboration module communicates with the city's transportation system and ride-sharing platform via a RESTful API in JSON format. Combining pedestrian density and external parking lot sensor data (collected every 10 minutes), it generates instructions ("Recommended parking space within 100 meters, bus arrival time within the next 10 minutes"), which are then pushed to the app. The criteria for determination are parking lot occupancy > 80% or pedestrian density > 10 people / square meter, and actions include pushing traffic guidance information. User traffic selection feedback (e.g., choosing public transportation) is transmitted to the data acquisition module through the control flow management module, optimizing the external collaboration strategy with a transmission latency of <100 milliseconds.

[0046] The space value optimization module receives the instruction ("Recommend the leisure area as a pop-up booth, adjust the rent by 15%), generates an area foot traffic value assessment report based on pedestrian density and dwell time (consumption conversion rate: spending per 100 people; activity participation rate: number of participants per hour), generates rental suggestions (select areas with a density of <5 people / square meter for pop-up booths, adjust the rent by 10-20% based on the conversion rate), and pushes it to the management terminal. The judgment criterion is a consumption conversion rate lower than the average, and the action includes pushing rental suggestions. Merchant satisfaction feedback (rating 1-5 points) is collected through the user feedback and experience module and transmitted to the data acquisition module via the control flow management module.

[0047] The User Feedback and Experience module collects user feedback on the environment, guidance, facilities, and safety via the App (ratings from 1-5 stars, text comments, and behavioral choices such as click paths). This feedback is transmitted in JSON format to the Data Acquisition module via the Control Flow Management module. The priority is determined by the volume of feedback data (>100 data points / hour for high priority, latency <50 milliseconds; <50 data points for low priority, latency <200 milliseconds). Actions taken include transmitting feedback and optimizing the data acquisition strategy. The module collects operation results from various functional modules, and the feedback data affects the data acquisition module's collection frequency.

[0048] The control flow management module coordinates command flow, data transmission, and feedback loops. It includes a command distribution unit (prioritized by security > environment > stimulus, distributed via 5G, with security command latency <50 milliseconds), a data transmission monitoring unit (monitoring latency <100 milliseconds, packet loss rate <1%), and a feedback loop optimization unit (adjusting command frequency based on feedback: 3-5 times / hour during peak periods, 1-2 times / hour during off-peak periods; data collection cycle 5-15 minutes during peak periods, 10-30 minutes during off-peak periods). The decision-making criteria are command priority and feedback data volume, and the actions performed include command distribution, transmission monitoring, and loop optimization. This module connects all modules to ensure stable data and command flow.

[0049] The lost and found tracking module locates lost items via Bluetooth Low Energy beacons (covering 80% of public areas with a positioning accuracy of 5 meters) and RFID tags (users bind their tags via the app or the complex provides reusable tags). Upon receiving a command ("Locate lost item in the dining area"), it pushes the retrieval path to the app. The determination is based on lost item signal detection, and actions include pushing location information. User feedback on the retrieval experience (rating from 1 to 5 stars) is collected through the user feedback and experience module and transmitted to the data acquisition module via the control flow management module.

[0050] Overall Operation Flow: During system initialization, the data acquisition module collects baseline data 24 times daily to establish a baseline. During operation, IoT sensors dynamically collect data based on peak / off-peak periods (environment / pedestrian flow every 5-30 minutes, device status every 30 minutes), transmitting the data to the data processing module via LoRa. The data processing module analyzes the data and generates instructions based on thresholds (including "lower temperature" and "guide pedestrian flow"), which are then distributed through the control flow management module. Each functional module executes actions (including adjusting the environment and pushing discounts), with results fed back via the App or digital signage. The user feedback and experience module collects feedback and transmits it to the data acquisition module via the control flow management module to optimize acquisition and instruction strategies. The control flow management module monitors latency (<100 milliseconds) and packet loss rate (<1%) to ensure closed-loop stability. A weekly evaluation is conducted after operation ends to optimize long-term strategies. Specific Implementation Example 2:

[0052] like Figures 1 to 3As shown, the key algorithm mentioned in Example 1 will be analyzed in detail below, including its core mathematical formulas and explanations:

[0053] Data acquisition module:

[0054] Dynamic sampling frequency optimization algorithm:

[0055] Human flow density - sampling frequency mapping formula:

[0056] formula:

[0057] Parameter description:

[0058] Real-time sampling frequency (times / minute); Real-time pedestrian density (people / square meter); Density threshold (10 people / square meter); Peak sampling frequency (1 / 5 times / minute); Low peak sampling frequency (1 / 10 times / minute).

[0059] Problems to be solved:

[0060] Data redundancy versus real-time performance conflict: The sampling frequency is dynamically adjusted based on pedestrian density to avoid network congestion caused by high-frequency sampling during off-peak hours, while ensuring real-time data during peak hours (e.g., collecting pedestrian flow data every 5 minutes during peak hours).

[0061] Practical application: The people tracking unit collects data via infrared sensors. ,like ,trigger (Every 5 minutes), otherwise switch to (Once every 10 minutes) to balance data volume and system load.

[0062] Data processing module:

[0063] Environmental comfort index calculation:

[0064] Multi-parameter weighted comfort model:

[0065] formula:

[0066] Parameter description:

[0067] Comfort index (the lower the value, the more comfortable);

[0068] Real-time temperature (°C), humidity (%), and light intensity (lux);

[0069] Optimal environmental parameters;

[0070] Temperature tolerance range;

[0071] : Parameter weights.

[0072] Problems to be solved:

[0073] Multi-dimensional environmental assessment: Parameters such as temperature, humidity, and light intensity are quantified into a unified index for the dynamic environmental optimization module's control decisions (air conditioning, lighting adjustment).

[0074] Practical application: If the calculation yields This triggers the dynamic environment optimization module to adjust the temperature to 22-26℃ and the light color temperature to 3000-5000K, making... Within the regression threshold, improve the user experience.

[0075] Crowd guidance and incentive module:

[0076] Incentive strategy optimization:

[0077] Objective function for pedestrian flow balance:

[0078] formula:

[0079] Parameter description: Regional population flow balance ( (for complete equilibrium); : No. Population density in the area; Average crowd density throughout the venue; Total number of regions.

[0080] This solved the problem of uneven foot traffic distribution: by using incentive strategies (points, discounts) to guide users to areas with low foot traffic, maximizing [their reach / experience]. .

[0081] Practical application: When a certain area At that time, the system generates an incentive plan (e.g., 10 points for 10 minutes) and pushes it to the user's interactive terminal, aiming to make the user... Increase it to above 0.8 to alleviate congestion.

[0082] Resource scheduling module:

[0083] Elevator dispatch response time model:

[0084] formula:

[0085]

[0086] Parameter description: Average response time (seconds); : Vertical distance (meters) to the i-th floor; Elevator speed (m / s); Elevator operating frequency (times / minute); Waiting time base (seconds)

[0087] Problem solved: Elevator congestion during peak hours: Dynamic adjustment based on passenger flow density (peak hours (times / minute) to ensure Second.

[0088] Practical application: When the data processing module detects that the elevator occupancy rate is >80%, it triggers... Increase from 1 beat / minute to 2 beats / minute, shortening the time. This will improve traffic efficiency.

[0089] Security monitoring module:

[0090] Abnormal behavior detection:

[0091] Formula for determining abnormal cluster density:

[0092] formula:

[0093] Parameter description: : Anomaly flag (1 indicates an anomaly); Population density change rate (people / square meter / minute)

[0094] Problems to be solved:

[0095] Early warning of sudden gathering risks: Real-time monitoring of high-density and rapidly growing crowd gatherings, triggering security response (patrol route optimization).

[0096] Practical application: If a certain area people per square meter and increasing every minute people per square meter The security dispatch unit generates evacuation guidance instructions, which are then pushed out via digital signage. Specific Implementation Example 3:

[0098] like Figures 1 to 3 As shown, the following is a detailed description of the hardware composition and hardware specifications of each module in Embodiment 1:

[0099] The data acquisition module consists of an environmental monitoring unit, a people tracking unit, and an equipment status monitoring unit, used to collect real-time environmental parameters, people distribution data, and facility operation status data within the commercial complex. The environmental monitoring unit includes a temperature and humidity sensor (DHT22, measuring temperature range -40 to 80°C, accuracy ±0.5°C; humidity range 0-100%, accuracy ±2%), a light sensor (BH1750, measuring range 0-65535 lux, accuracy ±20%), and an odor sensor (MQ-135, detecting air odor concentration 0-10 mg / m³, sensitivity ±5%). These sensors are deployed in key areas of the commercial complex (dining areas, leisure areas, passageways), with one set (approximately 3-5 sensors) installed per 100 square meters. They are connected to a LoRa module (SX1278, 868MHz band, transmission distance 1-2 km, power consumption <20mA) via a low-power microcontroller (Arduino Nano, 32-bit, 16MHz). Temperature and humidity sensors monitor environmental comfort (temperature 22-26°C, humidity 40-60%), light sensors adjust lighting brightness, and odor sensors control fragrance diffusion. Data is used to generate environmental optimization commands. Data collection frequency is 24 times per day (once per hour) during the initial operation phase, every 15 minutes during peak hours (10:00-14:00 and 17:00-21:00, density >5 people / square meter), every 30 minutes during off-peak hours (0:00-10:00 and 14:00-17:00), and once per week after operation ends. The people tracking unit includes an infrared ranging sensor (VL53L0X, measuring distance 0.05-2 meters, accuracy ±3%) and a pressure sensor (FSR-402, pressure range 0.1-10 kg, sensitivity ±2%), deployed on the ground and at the entrance area (one infrared sensor per 50 square meters, one pressure sensor per 10 meters in the passageway), connected to a LoRa module via a microcontroller. Infrared sensors measure pedestrian density (people / square meter) and movement speed (meters / second), while pressure sensors record dwell time (minutes). This data is used to identify crowded areas (density > 10 people / square meter) and generate guidance instructions. Data is collected every 5 minutes during peak hours and every 10 minutes during off-peak hours. The equipment status monitoring unit includes RFID tags (MIFARE Classic 1K, 13.56MHz, reading distance 0-5 cm) and Bluetooth low-power beacons (iBeacon, BLE 5.0, transmission distance 50 meters, power consumption <10mA). RFID tags are attached to elevators, parking spaces, and restroom equipment (one per elevator, one per 10 parking spaces, and one per 5 restrooms). Bluetooth beacons are deployed around the facility (one per 100 square meters). These devices monitor elevator operating frequency, parking space occupancy, and restroom usage status. The data is used for resource scheduling and is collected every 30 minutes.The data acquisition module transmits data in JSON format to the data processing module via the LoRa module. Anonymization ensures privacy, retaining only location, density, and status data.

[0100] The data processing module's hardware comprises embedded computing units and edge computing units, used to process and analyze data to generate dynamic control commands. The embedded computing unit uses a single-board computer (Raspberry Pi 4, 4-core 1.5GHz, 4GB RAM), equipped with a storage module (32GB microSD card) and a Wi-Fi module (2.4 / 5GHz, 802.11ac), deployed in the server room of the commercial complex (one unit per building). It is responsible for data denoising (removing outliers, such as temperature sudden changes to 30°C), formatting (standardizing JSON format), and classification (by environment, pedestrian flow, and equipment status), with a processing capacity supporting 1000 data packets per second. The edge computing unit uses an edge computing device (NVIDIA Jetson Nano, 4-core 1.43GHz, 4GB RAM, GPU acceleration), also deployed in the server room, running preset algorithms to analyze data and generating commands based on thresholds (pedestrian density 10 people / square meter, temperature 22-26°C, humidity 40-60%, elevator utilization 80%). For example, if the density of the dining area is 12 people / square meter and the temperature is 28°C, the system generates commands such as "lower the temperature to 24°C," "guide people to the lounge area and offer a 10% discount," and "increase the elevator frequency to twice per minute." These commands are distributed via the control flow management module through a 5G module (Quectel RM500Q, 2.5Gbps speed, latency <10 milliseconds). The data processing module receives LoRa data from the data acquisition module, generates commands, interacts with the control flow management module, and receives user feedback to optimize thresholds.

[0101] The hardware of the dynamic environment optimization module includes an air conditioning controller (Modbus compatible, supporting temperature adjustment to 22-26°C with an accuracy of ±0.5°C), a lighting controller (DALI compatible, adjusting color temperature to 3000-5000K and brightness to 0-100%), an odor diffusion device (ultrasonic atomizer, concentration control 0.1-0.5 mg / m³, 500 ml capacity), and digital signage (55-inch LED screen, 1920x1080 resolution, supporting Wi-Fi connectivity). These devices are deployed in various areas (one set of air conditioning and lighting controllers per 1000 square meters, one odor diffusion device per 500 square meters in the dining area, and one digital signage per 50 meters at entrances and passageways). The module receives instructions from the control flow management module ("Dining area temperature reduced to 24°C, odor concentration 0.3 mg / m³"), and executes adjustments based on a temperature > 26°C or humidity > 60%. The digital signage displays "Current temperature 24°C" or guidance information. The operation results are fed back to the user feedback and experience module via the Wi-Fi module to optimize the environment strategy.

[0102] The hardware for the pedestrian guidance and incentive module includes a user interaction terminal (a smartphone app supporting iOS / Android and running on 4G / 5G networks) and digital signage (the same as the aforementioned digital signage). The module receives instructions ("Guide to the leisure area, push 10% discount"), and determines the direction based on a density > 10 people / square meter or a dwell time > 10 minutes. It then pushes a path ("Walk 5 minutes to the leisure area") and incentives via the app (10 points for 10 minutes, 100 points can be redeemed for a 5 yuan coupon; 10% discount within 5 minutes, valid for 30 minutes). Users click on the path or accept the discount through the app, and the behavioral data is transmitted via 5G to the user feedback and experience module to optimize the push frequency (1-3 times per hour).

[0103] The hardware for the resource scheduling module includes a facility control unit (a Siemens S7-1200 PLC controller, supporting Modbus TCP, controlling elevators, parking spaces, and restroom facilities). Deployed in the facility management center (one unit per building), it receives instructions ("open 90% of parking spaces") and adjusts elevator frequency (twice per minute during peak hours, once per minute during off-peak hours), parking space availability (90% during peak hours, 50% during off-peak hours), and restroom cleaning frequency (once per hour during peak hours, once every two hours during off-peak hours) based on parking space occupancy >80% or elevator usage >80%. Available parking space information (distance <200 meters) is pushed via the app, and satisfaction feedback (rating 1-5 points) is transmitted to the user feedback and experience module.

[0104] The security monitoring and response module's hardware includes high-definition cameras (1080p, 120° field of view, with night vision, deployed at one per 500 square meters), vibration sensors (detection frequency 0-10 Hz, accuracy ±5%, deployed at one per 50-meter corridor), and a security dispatch terminal (industrial tablet, 10-inch, supporting 5G). The module receives instructions ("Density > 15 people / square meter, generate evacuation routes"), determines evacuation routes based on abnormal behavior (density > 15 people / square meter, vibration > 5 Hz), and pushes the routes to digital signage and the App. User safety feedback (rating 1-5 points) is transmitted to the user feedback and experience module.

[0105] The external collaboration module's hardware includes an API server (Dell PowerEdge R240, 4 cores 3.1GHz, 16GB RAM, supports RESTful API, JSON format, deployed in a data center) that connects to the city's transportation system and ride-sharing platform. It receives instructions ("Recommended parking space <100 meters"), and based on external parking lot sensors (collecting data every 10 minutes) or a density >10 people / square meter, pushes traffic guidance to the app. User feedback is transmitted via 5G to the user feedback and experience module.

[0106] The hardware for the space value optimization module includes a management terminal (15-inch touchscreen, 1920x1080 resolution, Wi-Fi supported, deployed in the management office). Reports (conversion rate, activity participation rate) are generated based on foot traffic density and dwell time. If the conversion rate is below average, rental suggestions are generated (pop-up booths should be located in areas with a density of <5 people / square meter, with a rent adjustment of 10-20%), and pushed to the management terminal. Merchant feedback (ratings of 1-5 stars) is transmitted to the user feedback and experience module.

[0107] The hardware for the user feedback and experience module includes a user interaction terminal (App) and a feedback server (same as the API server). It collects ratings (1-5 points), comments, and behavioral choices (such as click paths), and transmits them via 5G to the data acquisition module based on feedback volume (>100 feedbacks / hour, high priority, latency <50 milliseconds) to optimize the collection strategy.

[0108] The control flow management module's hardware includes a control server (same as the API server), a 5G module (Quectel RM500Q), and a network switch (supporting 10Gbps, deployed in the data center). The command distribution unit distributes commands according to priority (security > environment > incentives). The data transmission monitoring unit ensures latency <100 milliseconds and packet loss rate <1%. The feedback loop optimization unit adjusts the command frequency (3-5 times / hour during peak periods, 1-2 times / hour during off-peak periods) and the collection cycle (5-15 minutes during peak periods, 10-30 minutes during off-peak periods) based on feedback. The module connects to all modules, ensuring the smooth flow of data and commands.

[0109] The lost and found tracking module's hardware includes Bluetooth Low Energy beacons (covering 80% of public areas, with an accuracy of 5 meters, one beacon per 100 square meters) and RFID tags (user-bound or provided by the complex, with a reading distance of 0-5 centimeters). Upon receiving a command (such as "locate lost item in the dining area"), the system pushes the tracking path to the App based on signal detection. Recovery feedback (rating 1-5 points) is transmitted to the user feedback and experience module.

[0110] Overall hardware interaction: The IoT sensor transmits data to the data processing module via LoRa. The data processing module generates instructions and distributes them to the functional modules via the control flow management module. The functional modules provide feedback through an App or digital signage. User feedback is transmitted to the data acquisition module via 5G. The control flow management module coordinates the closed-loop operation to meet real-time and stability requirements. Specific Implementation Example 4:

[0112] like Figures 1 to 3 As shown, the following are specific use cases:

[0113] Daily operation scenario examples:

[0114] Case 1: Crowd Management During Weekend Shopping Peak

[0115] At 11:00 AM on a Saturday in a commercial complex (during peak hours of 10:00 AM to 2:00 PM), the crowd tracking unit of the data acquisition module collected crowd density data every 5 minutes using infrared ranging sensors and pressure sensors. It was found that the crowd density in the women's clothing section on the second floor reached 12 people / square meter, exceeding the threshold of 10 people / square meter. After analysis by the edge computing unit of the data processing module, dynamic control commands were generated and distributed to the crowd guidance and incentive module via a priority queue through the control flow management module.

[0116] The module immediately pushes low-traffic area guidance to users entering the second floor via user interaction terminals and digital signage, such as "The sports brand area on the third floor has less traffic; you can enjoy a 10-point reward for 10 minutes there." Simultaneously, the dynamic environment optimization module adjusts the air conditioning temperature in the women's clothing area to 24 degrees Celsius and the lighting color temperature to 4000K, improving environmental comfort. The resource scheduling module adjusts the elevator operation frequency on the second floor from once per minute during off-peak hours to twice per minute during peak hours, alleviating elevator congestion.

[0117] The user feedback and experience module collects user click path guidance behavior data and satisfaction scores, which are then fed back to the data collection module to form a closed-loop management system. Ultimately, the pedestrian density in the second-floor women's clothing area dropped to 8 people per square meter within 30 minutes, the pedestrian flow balance E increased from 0.6 to 0.85, and the user satisfaction score rose from 3.2 to 4.1.

[0118] Case 2: Restaurant resource allocation during weekday lunch break:

[0119] At 13:00 on Monday (peak hours 10:00-14:00), the data acquisition module detected a pedestrian density of 11 people per square meter in the fourth-floor dining area, with elevator utilization reaching 85%, exceeding the 80% threshold. The data processing module generated instructions, and the facility control unit of the resource scheduling module adjusted the elevator operating frequency to twice per minute and opened 90% of the parking spaces (previously 50% during off-peak hours). Simultaneously, the restroom cleaning cycle was shortened from once every 2 hours during off-peak hours to once per hour.

[0120] The dynamic environment optimization module activates the odor diffusion device, releasing food aromas in the dining area at a concentration controlled at 0.3 mg / m³ to attract users. The pedestrian flow guidance and incentive module pushes limited-time discount information from neighboring restaurants to users in queues: "Enjoy a 10% discount within 5 minutes of entering the Hunan cuisine restaurant, valid for 30 minutes." The external collaboration module communicates with the city's transportation system via a RESTful API interface, combining pedestrian density data to recommend the nearest parking space within 100 meters to drivers and display public transportation arrival times.

[0121] After adjustments, the flow of people in the dining area became more balanced, the elevator waiting time was reduced from an average of 45 seconds to 28 seconds, the restroom satisfaction rating increased from 3.5 to 4.3, and 72% of users selected recommended parking spaces in their transportation feedback.

[0122] Special time period scenario examples:

[0123] Case 3: Security Monitoring of Holiday Promotional Activities

[0124] During the National Day holiday, at 3:00 PM on a certain day (off-peak hours 2:00 PM - 5:00 PM), due to a large-scale promotional event held in the shopping mall, the pedestrian density in the first-floor atrium suddenly surged to 16 people / square meter, exceeding the anomaly threshold of 15 people / square meter. Furthermore, the pedestrian density change rate Δρ / Δt was 0.8 people / square meter / minute, greater than the threshold of 0.5. The security monitoring and response module's security dispatch unit detected the anomaly, generated a security command (highest priority), and transmitted it via the control flow management module using a 5G network with a latency of less than 50 milliseconds.

[0125] Digital signage and user interaction terminals immediately push evacuation guidance information, and security personnel prioritize proceeding to the atrium area according to patrol route optimization instructions. The dynamic environment optimization module adjusts the brightness of lights near the atrium and activates emergency lighting mode. The pedestrian flow guidance and incentive module stops regular incentive pushes and fully cooperates with safe evacuation guidance. The control flow management module monitors the data flow to ensure that safety instructions are transmitted without delay.

[0126] Within 10 minutes, the pedestrian density in the atrium dropped to 12 people per square meter, and the anomaly was resolved. User safety feedback scores rose from 2.8 at the beginning of the event to 3.9. The system recorded the anomaly, providing data support for future event planning.

[0127] Case 4: Space Value Assessment After Operation Ends

[0128] Every Sunday after the mall closes, the environmental monitoring unit of the data acquisition module collects assessment data weekly, while the equipment status monitoring unit collects facility operation status data every 30 minutes. The spatial value optimization module generates a regional pedestrian value assessment report based on the weekly pedestrian density and dwell time analysis provided by the data processing module.

[0129] The report shows that the average foot traffic density in the northwest corner of the fourth floor this week was 4 people / square meter (less than 5 people / square meter), with a conversion rate (R_c) of 600 yuan / 100 people, lower than the overall average. In contrast, the southeast corner of the second floor had a foot traffic density of 8 people / square meter and a conversion rate of 1000 yuan / 100 people. Based on this, the space value optimization module generated dynamic leasing suggestions: designate the northwest corner of the fourth floor as a short-term pop-up stall with a 20% rent reduction; and increase the rent for long-term shops in the southeast corner of the second floor by 15%.

[0130] After receiving the suggestions, the management terminal implemented the adjustments. One month later, the occupancy rate of the pop-up stalls on the fourth floor increased from 30% to 75%, the turnover of the shops on the second floor increased by 12%, and the merchant satisfaction score rose from 3.6 to 4.2.

[0131] Emergency Situation Case Studies:

[0132] Case 5: Equipment Failure Interlock Response:

[0133] At 9:30 AM one day (off-peak period 0:00-10:00), the equipment status monitoring unit of the data acquisition module detected a malfunction and abnormal operation of the elevator on the east side of the third floor via RFID tags and Bluetooth Low Energy beacons. The data processing module generated an instruction, and the resource scheduling module immediately shut down the elevator, opened the adjacent elevator, and temporarily increased the elevator's operating frequency from once per minute during off-peak hours to 1.5 times per minute.

[0134] The safety monitoring and response module monitors pedestrian flow at elevator entrances via cameras. If the density exceeds 10 people per square meter, it promptly generates a security response command. The dynamic environment optimization module adds digital signs near the elevator malfunction area displaying guidance information such as "Elevator under maintenance, adjacent elevators are available." The user feedback and experience module collects user satisfaction feedback on elevator malfunction handling. This feedback data is transmitted to the data acquisition module via the control flow management module for optimizing equipment maintenance strategies.

[0135] During this troubleshooting process, there was no abnormal crowding in the elevator malfunction area, and the user satisfaction score remained at 3.8. The equipment maintenance efficiency was improved due to real-time system monitoring.

[0136] Case 6: Lost and Found Service

[0137] At 4:00 PM one day, a user lost their wallet in the rest area on the third floor of the mall. The user activated the lost and found tracking function through the RFID tag attached to the user's interactive terminal. The lost and found tracking module detected the wallet signal via a Bluetooth Low Energy beacon (covering 80% of the public area), with a positioning accuracy of 5 meters, and determined that the wallet was located near a trash can in the third-floor rest area.

[0138] The system generates the location information of the lost item and pushes the retrieval path through the user's interactive terminal. After finding the wallet according to the instructions, the user rated the retrieval experience in the user feedback and experience module, receiving a score of 4.5. This feedback data is transmitted to the data acquisition module through the control flow management module to optimize the beacon deployment location and improve the accuracy of lost item tracking. In this service, the user took 8 minutes from reporting the loss to finding the wallet, resulting in improved satisfaction with the mall's service.

[0139] External collaboration scenario examples:

[0140] Case 7: Optimization of External Pedestrian Traffic During Heavy Rain:

[0141] At 18:00 one day (peak hours 17:00-21:00), a sudden downpour occurred. The external coordination module obtained congestion information of surrounding roads from the city's traffic system via a RESTful API interface. At the same time, the data acquisition module monitored a surge in pedestrian traffic in the parking lot outside the shopping mall. The module combined pedestrian density data with data collected every 10 minutes by external parking lot sensors to generate comprehensive traffic guidance instructions.

[0142] The system pushes a message to drivers via user interaction terminals: "90% of parking spaces remain in the mall's underground parking lot; we recommend entering from the east gate." It also displays public transportation arrival times (3 buses are scheduled within the next 10 minutes). Simultaneously, it communicates with ride-sharing platforms, suggesting cyclists take public transportation or enter the mall to avoid the rain.

[0143] The dynamic environment optimization module adjusted the lighting brightness at the mall entrance and activated anti-slip digital signage. The pedestrian flow guidance and incentive module pushed incentive messages to users entering the mall to seek shelter from the rain, offering a discount on umbrella rentals for purchases over 50 yuan at the first-floor coffee shop. During this rainstorm response, traffic congestion outside the mall was alleviated, the utilization rate of the underground parking lot increased from 60% to 85%, and 43% of users entering the mall to seek shelter from the rain effectively boosted mall revenue.

[0144] The above cases cover a variety of common and special scenarios, demonstrating the system's comprehensive management capabilities. Specific Implementation Example 5:

[0146] like Figures 1 to 3 As shown, the following are the specific experimental data:

[0147] Module Scene Key Indicators Experimental data Effect description Data acquisition module Weekend peak (11:00) Data collection frequency (people flow) Every five minutes The density of the dining area is 12 people per square meter, and optimization is triggered in real time. Data processing module Weekend peak (11:00) Instruction generation time (milliseconds) 80 Generate "cooling" and "guidance" commands to quickly address congestion. Dynamic Environment Optimization Module Weekend peak (11:00) Temperature adjustment time (minutes) 10 (from 28°C to 24°C) The comfort rating for the dining area rose from 3 to 4 points. Crowd guidance and incentive module Weekend peak (11:00) Guided acceptance rate 30% The density of women's clothing area decreased from 12 to 8 people per square meter. Resource scheduling module weekday lunch break (13:00) Parking space availability 15% (90% of parking spaces available) Parking space occupancy rate decreased from 85% to 70%, with a rating of 4.3. Security monitoring and response module Holiday promotions (15:00) Anomaly detection accuracy 98% The density of people in the atrium decreased from 16 to 12 per square meter, resulting in a score of 3.9. External collaboration module Heavy rain (18:00) Parking space recommendation acceptance rate 20% Parking lot utilization increased from 60% to 85%, alleviating congestion. Spatial Value Optimization Module Operations closed (every Sunday). pop-up booth occupancy rate 75% (up from 30%) The conversion rate on the fourth floor increased from 600 to 800 yuan per 100 people, with a rating of 4.2. User Feedback and Experience Module Weekend peak (11:00) Feedback data volume (pieces / hour) 120 The rating for the dining area rose from 3 to 4 points, triggering frequent data collection. Control flow management module Weekend peak (11:00) Command transmission delay (milliseconds) 50 (Safety Instruction) Security commands are prioritized for distribution, ensuring system stability. Lost item tracking module Lost and Found (16:00) Retrieval time (minutes) 8 The wallet is located at table A12 and has a rating of 4.5.

[0148] Data source explanation:

[0149] Experimental scenario:

[0150] The data comes from a simulated operation of a large commercial complex (100,000 square meters, including a food court, shopping area, and parking lot), based on four representative cases in the implementation examples:

[0151] Weekend peak (Saturday 11:00): Optimization of pedestrian flow in the dining and consumption areas.

[0152] Weekday lunch break (Monday 13:00): Resource allocation in the catering area.

[0153] Holiday promotion (National Day 15:00): Central courtyard security monitoring.

[0154] Lost Item Tracking (16:00): Wallet recovered.

[0155] Simulation method:

[0156] Hardware simulation: Based on the performance of temperature and humidity sensor (accuracy ±0.5°C), infrared ranging sensor (accuracy ±3%), low power wide area network (packet loss rate <1%), and 5G module (latency <10 milliseconds), data acquisition and transmission are simulated. The sensor generates JSON data packets every 5-30 minutes.

[0157] Software simulation: The edge computing unit (4 cores, 4GB RAM) runs the instruction generation algorithm (generation time 80 milliseconds, accuracy 95%), the path planning algorithm simulates guidance (acceptance rate 30%), and the anomaly detection algorithm simulates security monitoring (accuracy 98%).

[0158] User behavior: Poisson distribution was used to simulate pedestrian density (5-16 people / square meter), and normal distribution was used to simulate user feedback rating (3-4.5 points, standard deviation 0.5), generating guidance acceptance rate and satisfaction data.

[0159] Assumptions:

[0160] The complex has an average daily foot traffic of 100,000 people, with peak hours (10:00-14:00, 17:00-21:00) accounting for 60% of the traffic, and a density of 5-16 people per square meter.

[0161] Sensor coverage is 90%, mobile application usage is 70%, and feedback participation is 50%.

[0162] The parking lot has a capacity of 1,000 parking spaces and 10 elevators. The probability of abnormal events (such as a density of >15 people / square meter) is 5%.

[0163] Data validation:

[0164] Data references are commercial complex operation logs (2024, typical large shopping mall) and IoT system test reports (low-power network, 5G performance).

[0165] User feedback is based on a questionnaire survey of 1,000 people (rated 3-5 points, collected in 2024).

[0166] Leasing performance is referenced from commercial real estate data (conversion rate increased by 20% in 2024).

[0167] The experiment verified the effectiveness of the hardware and algorithms through laboratory simulation (December 2024, Smart City Lab) and field testing (December 2024, Large Shopping Mall).

[0168] Appendix Figure 3 The diagram shown is a simulation of the system, in which... Figure 3 middle:

[0169] X-axis: Time (minutes), ranging from 0 to 30 minutes, with a step size of 5 minutes, reflecting a simulation duration of 30 minutes.

[0170] Y-axis: People density (people / square meter), ranging from 8 to 12 people / square meter, showing density changes.

[0171] The blue solid line represents the trajectory of pedestrian density over time. The initial density is 12 people / square meter, which drops rapidly from 0 minutes, approaching 10 people / square meter after about 10 minutes, and then decreases at a slower rate, stabilizing at around 8 people / square meter after about 20-25 minutes.

[0172] The red dashed line represents the density threshold (10 people / square meter), which serves as the baseline for triggering the guidance command. When the density exceeds this threshold, the system will activate the guidance mechanism.

[0173] The simulation diagram visually demonstrates the core functions of the crowd management system: by monitoring the crowd density in real time (12 people / square meter), guidance is triggered when the threshold (10 people / square meter) is exceeded. After 30% of users accept the guidance, the density drops to 8 people / square meter and stabilizes within 25 minutes, verifying the efficiency and practicality of the system.

[0174] The key performance comparisons between this invention and traditional commercial complex management solutions are as follows:

[0175] index Traditional solution Invention Solution Increase Response time >5 minutes <1 minute 80%+ Crowd density monitoring accuracy ±2 people / square meter ±0.5 people / square meter 75%+ Resource scheduling efficiency Mainly manual intervention Automated dynamic scheduling 60%+ Security Incident Response Average 10 minutes Real-time triggering (<50 milliseconds) 99%+

[0176] Taking the scenario of crowd control in the catering area as an example, traditional video surveillance solutions require manual adjustment of air conditioning and directional signs after crowding is detected, which takes an average of 6 minutes. This invention, through sensor networks and edge computing, can complete the entire process from data acquisition to instruction execution in just 45 seconds. It can also simultaneously mobilize 6 major modules such as environmental adjustment and resource scheduling to work together, reducing the average waiting time per person in the catering area from 22 minutes to 8 minutes.

[0177] Data source explanation:

[0178] Response Time: A three-month comparative monitoring study was conducted on five traditional commercial complexes in a first-tier city and five similar commercial complexes using the solution of this invention. Simulated events such as sudden surges in customer traffic and equipment malfunctions were recorded, showing the time from the occurrence of the event to the system's initial response. Data for the traditional solution came from manual recording and review of monitoring videos; data for the solution of this invention was automatically generated from the system's built-in event logs and timestamps, and the average value from multiple tests was taken.

[0179] Crowd density monitoring accuracy: Referring to the research methods of Shengjing Interactive on passenger flow statistics systems, this invention utilizes high-precision cameras and the sensor network of this invention to simultaneously collect crowd flow data in different areas of the commercial complex (such as entrances, corridors, and shops). Traditional solutions use conventional cameras combined with simple counting algorithms, while this invention's solution is based on multi-source data fusion and deep learning algorithms. Data is collected at different times over 10 consecutive days, and the monitoring accuracy is determined by comparing the error between the actual number of people and the number counted by the system. The data is then analyzed and processed using professional statistical software.

[0180] Resource scheduling efficiency: This assessment evaluates the scheduling of resources such as lighting, air conditioning, and elevators in the commercial complex. Traditional solutions rely on the operator's daily work records to track the time and frequency of manual resource scheduling tasks. This invention analyzes the execution time and task completion rate of automated scheduling through the system's resource scheduling logs. Data collection covers peak and off-peak hours of the commercial complex for a period of one month to ensure data comprehensiveness.

[0181] Security Incident Response: In collaboration with fire and security departments, simulate security incidents such as fires and thefts within commercial complexes. Traditional solutions rely on manual alarms and emergency procedures, using surveillance video and on-site recordings to obtain response times. This invention utilizes a system-wide event perception and automatic alarm mechanism, combined with time recording from an emergency command system, achieving millisecond-level accuracy. Twenty simulation tests were conducted in different areas and scenarios to calculate the average response time.

[0182] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising a reference structure" does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes the element.

[0183] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A commercial complex crowd management system based on real-time IoT sensors, comprising a main management system, characterized in that: The main management system includes a data acquisition module, a data processing module, a dynamic environment optimization module, a pedestrian flow guidance and incentive module, a resource scheduling module, a safety monitoring and response module, an external collaboration module, a space value optimization module, a user feedback and experience module, and a control flow management module. The data acquisition module collects environmental parameters, pedestrian flow distribution data, and facility operation status data within the commercial complex in real time and transmits them to the data processing module via a low-power wide-area network. The data processing module processes and analyzes the collected data, generates dynamic control commands, and distributes them to each functional module through the control flow management module. The dynamic environment optimization module, pedestrian flow guidance and incentive module, resource scheduling module, safety monitoring and response module, external collaboration module, and space value optimization module execute environmental adjustment, pedestrian flow guidance, resource scheduling, safety response, external collaboration, and space optimization operations according to the dynamic control commands, and provide real-time feedback to users through the user feedback and experience module. The control flow management module coordinates the instruction flow, data transmission priority management, and feedback loop optimization among various modules to ensure the real-time performance and stability of the system. Specifically, the data acquisition module dynamically adjusts the data acquisition frequency based on peak and off-peak hours of the commercial complex; the data processing module generates dynamic control instructions and distributes them through the control flow management module; after each functional module executes its operation, feedback data is collected through the user feedback and experience module, and this feedback data is transmitted to the data acquisition module through the control flow management module, forming a closed-loop management system.

2. The commercial complex crowd management system based on real-time IoT sensors according to claim 1, characterized in that: The data acquisition module includes an environmental monitoring unit, a pedestrian flow tracking unit, and an equipment status monitoring unit, which respectively collect environmental parameters, pedestrian flow distribution data, and facility operation status data within the commercial complex. The data processing module includes an embedded computing unit and an edge computing unit for real-time processing and analysis of the data transmitted by the data acquisition module. The embedded computing unit is responsible for data denoising, formatting, and classification, while the edge computing unit, based on preset pedestrian density thresholds, environmental parameter thresholds, and facility utilization rate thresholds, analyzes pedestrian flow distribution trends, environmental comfort index, and facility utilization efficiency, generating dynamic control commands. The dynamic environmental optimization module includes an air conditioning controller and a lighting regulator. The system includes: an odor diffusion device and digital signage for adjusting temperature, light color temperature, odor concentration, and information display within the commercial complex according to the dynamic control commands; a pedestrian guidance and incentive module configured to guide users to low-traffic areas and provide incentive feedback via user interaction terminals and digital signage according to the dynamic control commands; a resource scheduling module, including a facility control unit, for dynamically adjusting the operating status and number of open elevators, parking spaces, and restrooms according to the dynamic control commands; a security monitoring and response module, including a security dispatch unit, for monitoring abnormal behavior and generating security response commands according to the dynamic control commands; an external collaboration module communicating with the urban transportation system and shared mobility platform via a RESTful API interface for optimizing external pedestrian flow based on the dynamic control commands; and a space value optimization module for generating space leasing and activity planning suggestions based on the dynamic control commands to optimize the space utilization of the commercial complex. The user feedback and experience module is configured to collect user satisfaction feedback on the environment, guidance, facilities, and safety through a user interaction terminal, and transmit the feedback data to the data acquisition module; the control flow management module includes an instruction distribution unit, a data transmission monitoring unit, and a feedback loop optimization unit, used to coordinate instruction flow, data transmission priority management, and feedback loop optimization.

3. The commercial complex crowd management system based on real-time IoT sensors according to claim 2, characterized in that: The environmental monitoring unit of the data acquisition module includes a temperature and humidity sensor, a light sensor, and an odor sensor, which collect data on temperature, humidity, light intensity, and air odor concentration, respectively; the people tracking unit includes an infrared ranging sensor and a pressure sensor, which collect data on people density, movement speed, and dwell time, respectively. The device status monitoring unit includes RFID tags and Bluetooth Low Energy beacons to collect operational status data of elevators, parking spaces, and restrooms. The collected data is transmitted to the data processing module in JSON format via a low-power wide area network. The data packets are anonymized, retaining only location, density, and status data.

4. The commercial complex crowd management system based on real-time IoT sensors according to claim 2, characterized in that: The embedded computing unit of the data processing module performs noise reduction, formatting, and classification on the collected data. The edge computing unit analyzes the distribution trend of pedestrian flow, environmental comfort index, and facility utilization efficiency based on preset thresholds for pedestrian density, environmental parameters, and facility utilization, and generates dynamic control commands. The dynamic control commands are transmitted to each functional module via a 5G network through the control flow management module, which allocates transmission bandwidth according to the command type.

5. The commercial complex crowd management system based on real-time IoT sensors according to claim 2, characterized in that: The air conditioning controller, lighting regulator, and odor diffusion device of the dynamic environment optimization module adjust the temperature, light color temperature, and odor concentration of the area according to dynamic control commands; the digital signage displays the real-time environmental status and guidance information; the operation results of the dynamic environment optimization module are fed back to the user interaction terminal in the form of push notifications through the user feedback and experience module, and the feedback data is transmitted to the data acquisition module in JSON format through the control flow management module.

6. The commercial complex crowd management system based on real-time IoT sensors according to claim 1, characterized in that: The pedestrian flow guidance and incentive module pushes path guidance and incentive information for low-pedestrian areas to users through a user interaction terminal and digital signage according to the dynamic control instructions. The incentive information includes points rewards and limited-time discounts. The pedestrian flow guidance and incentive module generates feedback data based on the user's selection behavior through the user interaction terminal and transmits it to the data acquisition module through the control flow management module. The control flow management module adjusts the incentive push frequency according to the user response time, pushing 1-3 times per hour.

7. The commercial complex crowd management system based on real-time IoT sensors according to claim 2, characterized in that: The facility control unit of the resource scheduling module adjusts the elevator operating frequency and restroom cleaning cycle according to dynamic control commands; the resource scheduling module pushes the location information of the nearest available facility through the user interaction terminal; the operation results are collected through the user feedback and experience module to collect user satisfaction feedback, which is transmitted to the data acquisition module through the control flow management module; the security scheduling unit of the safety monitoring and response module detects abnormal behavior through cameras and vibration sensors, and generates patrol route optimization commands and evacuation guidance information according to dynamic control commands, which are pushed through digital signage and the user interaction terminal; the operation results are collected through the user feedback and experience module to collect user safety feedback, which is transmitted to the data acquisition module through the control flow management module.

8. The commercial complex crowd management system based on real-time IoT sensors according to claim 2, characterized in that: The external collaboration module communicates with the urban transportation system and shared mobility platform via a RESTful API interface in JSON format. Combining pedestrian density data from the data acquisition module and external parking sensor data, it generates comprehensive traffic guidance instructions, including recommendations for the nearest parking spaces and public transportation arrival times. The external collaboration module pushes guidance information through user interaction terminals and collects user traffic choice feedback, which is transmitted to the data acquisition module via the control flow management module. The spatial value optimization module generates a regional pedestrian value assessment report based on pedestrian density and dwell time analysis from the data processing module. This report includes consumption conversion rates and activity participation rates for each area. The spatial value optimization module generates dynamic leasing suggestions based on the regional pedestrian value assessment report, including short-term pop-up stall locations and long-term shop rent adjustment plans, which are pushed through the management terminal. Finally, the operation results are collected from merchant satisfaction feedback through the user feedback and experience module and transmitted to the data acquisition module via the control flow management module.

9. The commercial complex crowd management system based on real-time IoT sensors according to claim 2, characterized in that: The user feedback and experience module collects user satisfaction feedback on the environment, guidance, facilities, and safety through a user interaction terminal. This feedback data includes ratings, text comments, and behavioral selection data. The user feedback and experience module transmits this feedback data to the data acquisition module in JSON format via the control flow management module. The control flow management module adjusts the transmission priority based on the amount of feedback data. The data acquisition module updates its acquisition strategy based on the feedback data. The control flow management module includes an instruction distribution unit, a data transmission monitoring unit, and a feedback loop optimization unit. The instruction distribution unit distributes dynamic control instructions to each functional module via a 5G network according to their priority. The data transmission monitoring unit monitors data transmission latency and packet loss rate in real time. The feedback loop optimization unit adjusts the instruction execution frequency and data acquisition cycle of each functional module based on the feedback data from the user feedback and experience module to ensure the stability of the closed-loop control flow.

10. The commercial complex crowd management system based on real-time IoT sensors according to claim 1, characterized in that: The main management system further includes a lost and found tracking module. This module detects the location of items within the commercial complex using Bluetooth Low Energy (BLE) beacons and RFID tags. The BLE beacons are deployed in public areas, covering 80% of the area. The RFID tags are bound to items by users through user interaction terminals, and reusable tags are provided by the commercial complex. The lost and found tracking module generates lost item location information based on dynamic control commands and pushes retrieval paths through user interaction terminals. The operation results are collected through a user feedback and experience module to gather user feedback on the retrieval experience, and then transmitted to a data acquisition module through a control flow management module.

Images