An Internet of Things integrated management method and system for an intelligent walking path

Abstract

The present invention discloses an intelligent trail Internet of Things integrated management method and system, specifically relating to the technical field of integrated management. Specifically, it includes real-time collection of the pedestrian flow information of the intelligent trail, analyzing the current capacity of the intelligent trail to accommodate users according to the data processing capabilities of the monitoring devices, measuring the user experience in the intelligent trail based on the pedestrian flow information of the intelligent trail and the capacity of the intelligent trail to accommodate users, analyzing the integrity and consistency of the data of adjacent monitoring nodes in the intelligent trail according to the data of adjacent monitoring nodes in the intelligent trail, and analyzing the connection strength between each monitoring node in the intelligent trail by drawing a node association relationship diagram of the intelligent trail, comprehensively evaluating the adjacent monitoring nodes of the intelligent trail to determine the degree of potential hazards existing in the adjacent monitoring nodes. The present invention helps to improve the user experience and, based on real-time pedestrian flow analysis, helps to identify and prevent data loss or misjudgment problems caused by overloading of the monitoring devices.

Description

Technical Field

[0001] The present invention relates to the technical field of integrated management, and more specifically, to an intelligent trail Internet of Things integrated management method and system. Background Art

[0002] By integrating a variety of advanced monitoring devices and technologies, intelligent trails can collect and analyze the movement data and environmental data of users on the trail in real time, so as to achieve intelligent management and optimization of the trail. The core of the intelligent trail lies in the deployment of monitoring devices to collect data such as the flow information of users on the trail, movement trajectories, and environmental parameters in real time. However, the data processing ability of the monitoring devices in the intelligent trail will affect the system's real-time recognition and analysis of multiple people running. With the increase of users, it increases the difficulty of processing data on the intelligent runway, and the intelligent trail cannot guarantee the complete recognition of all users. There may be stranded users in the intelligent trail, resulting in a large number of errors in the intelligent trail system, thus affecting the user experience in the intelligent trail.

[0003] To solve the above defects, a technical solution is provided now. Summary of the Invention

[0004] In order to overcome the above defects of the prior art, embodiments of the present invention provide an intelligent trail Internet of Things integrated management method and system to solve the problems raised in the above background art.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] An intelligent trail Internet of Things integrated management method specifically includes the following steps:

[0007] S1: Through the monitoring devices of the intelligent trail, collect the flow information of the intelligent trail in real time, and analyze the ability of the current intelligent trail to accommodate users according to the data processing ability of the monitoring devices;

[0008] S2: Measure the experience of users in the intelligent trail according to the flow information of the intelligent trail and the ability of the intelligent trail to accommodate users, and generate a warning signal or a safety signal;

[0009] S3: Analyze the integrity and consistency of the data of adjacent monitoring nodes in the intelligent trail according to the data of adjacent monitoring nodes in the intelligent trail within the monitoring time interval, and analyze the connection strength between each monitoring node in the intelligent trail by drawing a node association relationship diagram of the intelligent trail;

[0010] S4: Comprehensively evaluate the adjacent monitoring nodes of the intelligent trail within the monitoring time interval, determine the degree of potential hazards existing in the adjacent monitoring nodes within the monitoring time interval, and classify the operating state of the intelligent trail according to the number of warning signals generated by the intelligent trail within the monitoring time interval.

[0011] In a preferred embodiment, collecting the flow of people information of the smart trail includes:

[0012] The crowd flow information is expressed by the crowd flow coefficient;

[0013] The logic for obtaining the crowd congestion coefficient is as follows: according to the identification device of each monitoring node, the number of users identified by each node is obtained in real time, a threshold value for the number of users identified by the monitoring node is set, and a threshold value for the number of users identified by the overall processing of the smart trail is set;

[0014] The load level of each node is determined by the ratio of the number of users identified by each monitoring node to the threshold number of users identified by the monitoring node. The overall system load level is determined by the number of users identified by each monitoring node, and the crowding coefficient is calculated by the formula.

[0015] In a preferred embodiment, analyzing the current smart trail's ability to accommodate users includes:

[0016] The ability of the smart trail to accommodate users is expressed by the retention risk coefficient;

[0017] The logic for obtaining the retention risk coefficient is as follows: a unique ID is established for each user using the smart trail through face recognition technology, and the number of people in the smart trail is obtained by subtracting the number of people leaving the smart trail from the number of people entering the smart trail through face recognition, thereby obtaining the number of people in the smart trail;

[0018] Set a retention time threshold to determine the time point from when the user enters the smart trail through face recognition. If the user is not recognized by any monitoring node within the retention time threshold, it is considered that the user may be stranded in the smart trail, and the number of users who may be stranded in the smart trail is obtained;

[0019] Set a departure time threshold. If the user is not recognized by any monitoring node within the departure time threshold, it is considered that the user may have left the smart trail midway. The number of users who may have left the smart trail midway is obtained, and the retention risk coefficient is calculated through the formula.

[0020] In a preferred embodiment, measuring the user experience in the smart trail includes:

[0021] Comprehensively analyze crowd flow coefficient and detention risk coefficient, establish data analysis model, and generate early warning assessment coefficient;

[0022] Set the warning assessment coefficient threshold, compare the real-time warning assessment coefficient of the smart trail with the warning assessment coefficient threshold, if the warning assessment coefficient is greater than the warning assessment coefficient threshold, generate a warning signal, if the warning assessment coefficient is less than the warning assessment coefficient threshold, no warning signal is generated.

[0023] In a preferred embodiment, analyzing the integrity and consistency of data of adjacent monitoring nodes includes:

[0024] The integrity of the data is represented by a data coverage coefficient, and the acquisition logic of the data coverage coefficient is as follows: According to the number of identified users between adjacent monitoring nodes and the frequency of user movement, determine the data generated by the expected users of the system within the monitoring time interval, obtain the number of user data collected by the monitoring devices in the actual adjacent monitoring nodes within the monitoring time interval, and compare the number of user data collected by the monitoring devices in the actual adjacent monitoring nodes with the data generated by the expected users of the system to obtain the data coverage coefficient;

[0025] The consistency of the data is represented by a speed logic coefficient, and the acquisition logic of the speed logic coefficient is as follows: Record the time points when the monitoring devices identify users within the monitoring time interval, and obtain the distance between adjacent monitoring nodes. According to the time points of the users at the adjacent monitoring nodes, determine the time taken by the users from the previous monitoring node to the next monitoring node, and compare the distance between adjacent monitoring nodes with the time taken by the users from the previous monitoring node to the next monitoring node to obtain the average speed of the users at the adjacent monitoring nodes;

[0026] Set an average speed threshold, obtain the average speed of all users within the adjacent monitoring nodes during the monitoring time interval, compare the average speed of all users within the adjacent monitoring nodes with the average speed threshold, obtain the average speed of the users whose average speed is greater than the average speed threshold, and calculate the speed logic coefficient through a formula.

[0027] In a preferred embodiment, analyzing the connection strength between each monitoring node in the intelligent walking path includes;

[0028] By collecting the location information, timestamps, and movement data of users from the monitoring nodes, construct a node association relationship graph, where the monitoring nodes in the intelligent walking path are the nodes of the node association relationship graph, and the movement paths of users between adjacent monitoring nodes are the edges of the node association relationship graph;

[0029] The connection strength between the monitoring nodes is represented by a connection strength coefficient, and the acquisition logic of the connection strength coefficient is as follows: Obtain the user flow and movement frequency of adjacent nodes in the intelligent walking path during the monitoring time interval, and obtain the user flow of adjacent nodes by calculating the average value of the number of users identified by adjacent monitoring nodes;

[0030] Determine the movement frequency of users through the number of times of repeated identification of users by adjacent monitoring nodes during the monitoring time interval. According to the user flow and movement frequency during the monitoring time interval, calculate the connection strength between two monitoring nodes, and determine the connection strength coefficient through a weighted summation calculation method.

[0031] In a preferred embodiment, determining the degree of potential hazards existing in adjacent monitoring nodes within a monitoring time interval includes:

[0032] Establish a data analysis model with the data coverage coefficient, speed logic coefficient, and connection strength coefficient to generate a node evaluation coefficient.

[0033] In a preferred embodiment, classifying the operating state of the smart footpath includes:

[0034] Set a threshold for the node evaluation coefficient, compare the node evaluation coefficient with the node evaluation coefficient threshold, set a threshold for the number of warning signals, obtain the number of warning signals within the monitoring time interval, and compare the number of warning signals within the monitoring time interval with the warning signal number threshold to generate the following situations:

[0035] If the node evaluation coefficient of adjacent monitoring nodes in the smart footpath is greater than the node evaluation coefficient threshold, and the number of warning signals of the smart footpath is greater than the warning signal number threshold, then generate a first abnormal signal;

[0036] If the node evaluation coefficient of adjacent monitoring nodes in the smart footpath is greater than the node evaluation coefficient threshold, and the number of warning signals of the smart footpath is less than the warning signal number threshold, then generate a quality inspection signal;

[0037] If there is no node evaluation coefficient of adjacent monitoring nodes in the smart footpath greater than the node evaluation coefficient threshold, and the number of warning signals of the smart footpath is greater than the warning signal number threshold, then generate a second abnormal signal;

[0038] If there is no node evaluation coefficient of adjacent monitoring nodes in the smart footpath greater than the node evaluation coefficient threshold, and the number of warning signals of the smart footpath is less than the warning signal number threshold, then no other signals are generated.

[0039] In a preferred embodiment, an intelligent footpath Internet of Things integrated management system includes a data acquisition module, a warning evaluation module, an operation evaluation module, and a classification module, and the modules are signal-connected to each other;

[0040] The data acquisition module is used to collect the motion data and pedestrian flow information of users in real time through the monitoring devices of each monitoring node in the smart footpath, and transmit the collected data to the warning evaluation module and the operation evaluation module through a wireless network;

[0041] The warning evaluation module is used to calculate the real-time accommodation capacity of the smart footpath according to the processing capacity of the monitoring device and the current pedestrian flow information, and generate a real-time warning evaluation coefficient of the smart footpath;

[0042] An operation evaluation module, which is used to analyze the data integrity and consistency of adjacent monitoring nodes according to the data within the monitoring time interval, draw a node association relationship diagram, and generate a node evaluation coefficient of adjacent monitoring nodes within the monitoring time interval;

[0043] A classification module, which is used to classify the operation status of the intelligent footpath according to the hidden danger evaluation and early warning signal statistics results, and generate a management report.

[0044] The technical effects and advantages of the present invention:

[0045] 1. By analyzing the flow of people at different monitoring nodes in the intelligent footpath in real time and combining the computing power of the monitoring equipment of the intelligent footpath, the present invention evaluates the real-time user accommodation ability of the intelligent footpath, which helps to take timely measures to avoid congestion on the footpath, ensure the comfort and safety of users, and help identify and prevent data loss or misjudgment problems caused by overload of monitoring equipment based on real-time flow analysis of people;

[0046] 2. By comprehensively analyzing the data collected by specific adjacent monitoring nodes of the intelligent footpath and the relationship between adjacent monitoring nodes, the present invention determines the size of hidden dangers existing in adjacent monitoring nodes, and classifies the operation status of the intelligent footpath according to the number of early warning signals generated by the intelligent footpath within the monitoring time interval, which helps to improve the efficiency of safety management and resource allocation, significantly improves the user experience, and provides strong support for the scientific decision-making and long-term management of the intelligent footpath. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] For the convenience of those skilled in the art to understand, the present invention will be further described below with reference to the accompanying drawings;

[0048] Figure 1 It is a schematic flow chart of an intelligent footpath Internet of Things integrated management method of the present invention;

[0049] Figure 2 It is a schematic structural diagram of an intelligent footpath Internet of Things integrated management system of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0050] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0051] Embodiment 1

[0052] The present invention provides as Figure 1Flow schematic diagram of an intelligent trail Internet of Things integrated management method shown in the figure, specifically including the following steps:

[0053] S1: Through the monitoring devices of the intelligent trail, collect the flow information of the intelligent trail in real time, and analyze the capacity of the current intelligent trail to accommodate users according to the data processing capabilities of the monitoring devices;

[0054] S2: According to the flow information of the intelligent trail and the capacity of the intelligent trail to accommodate users, measure the experience of users in the intelligent trail, and generate warning signals or safety signals;

[0055] S3: According to the data of adjacent monitoring nodes in the intelligent trail within the monitoring time interval, analyze the integrity and consistency of the data of adjacent monitoring nodes, and by drawing a node association relationship diagram of the intelligent trail, analyze the connection strength between each monitoring node in the intelligent trail;

[0056] S4: Comprehensively evaluate the adjacent monitoring nodes of the intelligent trail within the monitoring time interval, determine the degree of potential hazards existing in the adjacent monitoring nodes within the monitoring time interval, and classify the operating status of the intelligent trail according to the number of warning signals generated by the intelligent trail within the monitoring time interval.

[0057] Generate abnormal signals or normal signals according to the accuracy of the data provided by the intelligent trail in multiple time periods, and evaluate the potential hazards existing in the intelligent trail according to the relationship between the number of warning signals and the number of abnormal signals in multiple time periods.

[0058] According to the monitoring devices of the intelligent trail, comprehensively monitor and record the motion data of runners, including the identification of each user in the intelligent trail, obtain the motion data of each user at different monitoring nodes, and be able to analyze the motion data of each user at different monitoring nodes to obtain the motion data of the user in the intelligent trail.

[0059] Among them, the monitoring devices of the intelligent trail include identification devices. The identification devices are installed at the entrance where users enter the intelligent trail and the exit where users leave the intelligent trail. Through face recognition, determine the time when users enter or leave the intelligent trail;

[0060] The identification devices are installed at different monitoring nodes. Through multi-target tracking algorithms and data processing technologies, achieve precise identification and monitoring of each user, obtain comprehensive motion data, and provide real-time feedback and analysis to improve the running experience and training effect of users.

[0061] The motion data includes the instantaneous speed of the user at the monitoring node and the average speed between different monitoring nodes.

[0062] The monitoring device of the intelligent walking path has the function of storing and managing user data, including memorizing user information and deleting expired or long-unused user data, which can improve the operation efficiency of the system and ensure data security and privacy.

[0063] Local storage, edge computing devices or local servers, which are used for temporarily storing and processing real-time data, specifically including users' facial recognition data, motion data, etc.

[0064] Data life cycle management, which sets life cycles for different types of data, sets automatic cleaning rules, and regularly deletes long-unused user data. For example, by comparing the interval from the time when a user was last recognized to the current time with the set life cycle, inactive users are determined.

[0065] The intelligent walking path contains multiple monitoring nodes. Missing values may occur at each monitoring point due to reasons such as occlusion, excessive targets, and misjudgment in recognition. Therefore, rules or models are used to detect abnormal situations, mark the detected abnormalities and missing data, and fill them through methods such as interpolation.

[0066] Through the monitoring device of the intelligent walking path, the flow information of the intelligent walking path is collected, and the flow information is represented by a flow crowding coefficient.

[0067] The acquisition logic of the flow crowding coefficient is as follows: According to the recognition devices at each monitoring node, the number of users recognized at each node is obtained in real time, and the number of users recognized at each node is marked as: SL i , where i = 1, 2, 3,..., I, I is a positive integer, and i is the numbering of the intelligent walking path monitoring nodes;

[0068] Set the threshold for the number of users recognized by the monitoring node, and mark the threshold for the number of users recognized by the monitoring node as: SL yz , set the threshold for the overall number of users recognized by the intelligent walking path, and mark the threshold for the overall number of users recognized by the intelligent walking path as: TOT;

[0069] It should be noted that the threshold for the number of users recognized by the monitoring node is set by the staff in the professional field, and is specifically determined according to the data processing capacity of each monitoring node and the upper limit of the number of users that the detection device can accurately recognize.

[0070] Determine the load level of each node through the ratio of the number of users recognized by each monitoring node to the threshold for the number of users recognized by the monitoring node, and mark the load level of each node as: FZ i , where

[0071] Determine the overall system load level through the number of users recognized by each monitoring node, and mark the overall system load level as: FZtot , where

[0072] calculate the crowding coefficient of the pedestrian flow, and the calculation formula is: where YJ rl is the crowding coefficient of the pedestrian flow.

[0073] It can be seen from the formula that the larger the crowding coefficient of the pedestrian flow, the more people may be recognized by each monitoring node, indicating that the pedestrian flow at the current moment may be larger, and each monitoring node may need to process more movement data of users. Therefore, it is easier to miss recognition, resulting in the system consuming a large amount of computing resources when filling in missing values, which may lead to a decline in the user experience of recognizing the intelligent walking path.

[0074] According to the data processing ability of the monitoring device, analyze the ability of the intelligent walking path to accommodate users, and represent the ability of the intelligent walking path to accommodate users through the retention hazard coefficient;

[0075] The acquisition logic of the retention hazard coefficient is as follows: establish a unique ID for each user using the intelligent walking path through face recognition technology, and record the number of people in the intelligent walking path in real time. Mark the number of people in the intelligent walking path as: JL, where the number of people in the intelligent walking path is the number of people recognized by face recognition entering the intelligent walking path minus the number of people recognized by face recognition leaving the intelligent walking path;

[0076] Set the retention time threshold, determine the time point when the user enters the intelligent walking path through face recognition. If the user is not recognized by any monitoring node within the retention time threshold, it is considered that the user may be detained in the intelligent walking path, and mark the number of users who may be detained in the intelligent walking path as: ZL;

[0077] Set the leaving time threshold, determine the time point when the user enters the intelligent walking path through face recognition. If the user is not recognized by any monitoring node within the leaving time threshold, it is considered that the user may have left the intelligent walking path midway, and mark the number of users who may have left the intelligent walking path midway as: LK;

[0078] It should be noted that the retention time threshold and the leaving time threshold are determined by professional staff in the field. The retention time threshold is a relatively short time period to ensure that users not recognized within a short time will not be misjudged as leaving. The leaving time threshold is a relatively long time period used to judge the situation where users do not appear in the walking path for a long time, considering that users may leave midway or there may be data missing.

[0079] Calculate the retention hazard coefficient, and the calculation formula is: where YH zl is the retention hazard coefficient.

[0080] As can be seen from the formula, the larger the coefficient of potential risk of congestion, the more people may be staying on the smart path, indicating that there are potential risks on the current smart path. When the number of users of the smart path continues to increase, it may exceed the threshold of the overall processing and identification of users on the smart path, resulting in a decline in the user experience of identifying the smart path.

[0081] By comprehensively analyzing the coefficient of crowding and the coefficient of potential risk of congestion, a data analysis model is established to generate an early warning evaluation coefficient. The calculation formula of the early warning evaluation coefficient is: where pg yz is the early warning evaluation coefficient, and α1 and α2 are the proportionality coefficients of the coefficient of crowding and the coefficient of potential risk of congestion, and α1 and α2 are greater than 0.

[0082] Set the threshold of the early warning evaluation coefficient, and compare the real-time early warning evaluation coefficient of the smart path with the threshold of the early warning evaluation coefficient. If the early warning evaluation coefficient is greater than the threshold of the early warning evaluation coefficient, an early warning signal is generated, indicating that the current number of users of the smart path is large. Continuing to open the smart path to the public may affect the user experience of using the smart path. If the early warning evaluation coefficient is less than the threshold of the early warning evaluation coefficient, no early warning signal is generated, indicating that the current usage status of the smart path is good.

[0083] In this embodiment, by analyzing the flow of people at different monitoring nodes on the smart path in real time and combining the computing power of the smart path monitoring device, the ability of the smart path to accommodate users in real time is evaluated, which helps to take timely measures to avoid congestion on the path, ensure the comfort and safety of users, and help identify and prevent data loss or misjudgment problems caused by overload of monitoring devices based on real-time flow analysis.

[0084] Embodiment 2

[0085] The above embodiment evaluates the ability of the smart path to accommodate users in real time. In this embodiment, the data collected from different monitoring nodes is analyzed. From the perspective of data integrity and consistency, the accuracy of the data provided by the smart path is measured. From the perspective of the relationship between monitoring nodes, the connection strength between monitoring nodes is measured to determine potential hazards on the smart path.

[0086] Among them, by setting a monitoring time interval, the data of adjacent monitoring nodes within the monitoring time interval is monitored to judge the integrity and consistency of the data of adjacent monitoring nodes.

[0087] It should be noted that the monitoring time interval is a specific time length set by staff in the professional field, and the monitoring time interval can reflect the activities of users between adjacent nodes.

[0088] The integrity of the data is represented by the data coverage coefficient. The acquisition logic of the data coverage coefficient is as follows: Based on the number of identified users between adjacent monitoring nodes and the frequency of user movement, determine the data generated by the expected users in the monitoring time interval, and mark the number of data generated by the expected users in the monitoring time interval as: YQ. Obtain the number of user data collected by the monitoring devices in the actual adjacent monitoring nodes during the monitoring time interval, and mark the number of user data collected by the monitoring devices in the actual adjacent monitoring nodes during the monitoring time interval as: SJ. Compare the number of user data collected by the monitoring devices in the actual adjacent monitoring nodes with the number of data generated by the expected users to obtain the data coverage coefficient, and mark the data coverage coefficient as: FG sj 。

[0089] It should be noted that each time a user passes through a monitoring node, a corresponding amount of data will be generated, such as different types of motion data, different types of identity information data, etc. The more the user traffic in the monitoring time interval and the greater the frequency of the user moving between adjacent monitoring nodes, the more data the user will generate.

[0090] The consistency of the data is represented by the speed logic coefficient. The acquisition logic of the speed logic coefficient is as follows: Record the time points when the monitoring devices identify the users in the monitoring time interval, and obtain the distance between adjacent monitoring nodes. Based on the time points of the users at adjacent monitoring nodes, determine the time taken by the user to move from the previous monitoring node to the next monitoring node. Divide the distance between adjacent monitoring nodes by the time taken by the user to move from the previous monitoring node to the next monitoring node to obtain the average speed of the user between adjacent monitoring nodes;

[0091] Set the average speed threshold and mark the average speed threshold as: V yz Obtain the average speed of all users in the adjacent monitoring nodes during the monitoring time interval. Compare the average speed of all users in the adjacent monitoring nodes with the average speed threshold to obtain the average speed of the users greater than the average speed threshold, and mark the average speed of the users greater than the average speed threshold as: V m , m = 1, 2, 3,..., M, M is a positive integer, and m is the number of the average speed of the users greater than the average speed threshold;

[0092] It should be noted that the average speed threshold is set by the staff in the professional field. Based on the distance between the actual adjacent monitoring nodes, estimate the average speed of the users between the adjacent detection nodes, and the average speed threshold conforms to the physical motion law.

[0093] Calculate the speed logic coefficient, and the calculation formula is: Among them, SD lj is the speed logic coefficient.

[0094] As can be seen from the formula, the larger the speed logic coefficient, the more unreasonable the speed changes of more users may be among adjacent monitoring nodes, indicating that the number of users whose speed exceeds the set average speed threshold is larger. Therefore, abnormal situations may occur in adjacent monitoring nodes.

[0095] According to the relationship between monitoring nodes, measure the connection strength between monitoring nodes. By collecting the location information, timestamps, and movement data of users from the monitoring nodes, construct a node association relationship graph, where the monitoring nodes in the intelligent walking path are the nodes of the node association relationship graph, and the movement paths of users between adjacent monitoring nodes are the edges of the node association relationship graph.

[0096] Represent the connection strength between monitoring nodes by the connection strength coefficient. The acquisition logic of the connection strength coefficient is as follows: Obtain the user flow and movement frequency of adjacent nodes in the intelligent walking path within the monitoring time interval. By calculating the average value of the number of users identified by adjacent monitoring nodes, obtain the user flow of adjacent nodes. Mark the user flow of different adjacent nodes in the intelligent walking path within the monitoring time interval as: LL q , where SL i-1 is the number of users identified by the (i - 1)-th monitoring node, q = 1, 2, 3, ……, Q, Q is a positive integer, and q is the number of adjacent monitoring nodes;

[0097] Determine the movement frequency of users by the number of times of repeated identification of users by adjacent monitoring nodes within the monitoring time interval, and mark the movement frequency of users as: CS q ;

[0098] According to the user flow and movement frequency within the monitoring time interval, calculate the connection strength between two monitoring nodes, and determine the connection strength coefficient through the method of weighted summation. The calculation formula of the connection strength coefficient is: QD q = aLL q + bCS q ; where QD q is the connection strength coefficient of the q-th adjacent monitoring node.

[0099] As can be seen from the formula, the larger the connection strength coefficient of adjacent monitoring nodes, the larger the possible pedestrian flow between adjacent monitoring nodes, and the more frequent the back-and-forth movement of people may be. Therefore, adjacent monitoring nodes are prone to cause congestion, further increasing the pressure on the computing resources of adjacent monitoring nodes and prone to triggering safety accidents.

[0100] Based on the perspective of data and the relationship between monitoring nodes, establish a data analysis model for the data coverage coefficient, speed logic coefficient, and connection strength coefficient to generate a node evaluation coefficient. The calculation formula of the node evaluation coefficient is: where pgjd is the node evaluation coefficient, and β1, β2, and β3 are the proportionality coefficients of the data coverage coefficient, the speed logic coefficient, and the connection strength coefficient, and β1, β2, and β3 are greater than 0.

[0101] As can be seen from the formula, the smaller the data coverage coefficient, the larger the speed logic coefficient and the connection strength coefficient, the larger the node evaluation coefficient, indicating that the potential hazards of adjacent nodes may be greater. On the contrary, the larger the data coverage coefficient, the smaller the speed logic coefficient and the connection strength coefficient, the smaller the node evaluation coefficient, indicating that the potential hazards of adjacent nodes may be smaller.

[0102] Set the node evaluation coefficient threshold, compare the node evaluation coefficient with the node evaluation coefficient threshold, set the warning signal quantity threshold, obtain the number of warning signals within the monitoring time interval, and compare the number of warning signals within the monitoring time interval with the warning signal quantity threshold to generate the following situations:

[0103] If the node evaluation coefficient of adjacent monitoring nodes of the smart walkway is greater than the node evaluation coefficient threshold, and the number of warning signals of the smart walkway is greater than the warning signal quantity threshold, then generate a first abnormal signal, indicating that there are relatively large potential hazards in the overall smart walkway, and accordingly, conduct quality inspection and maintenance in a timely manner to improve the computing resources of the smart walkway monitoring equipment;

[0104] If the node evaluation coefficient of adjacent monitoring nodes of the smart walkway is greater than the node evaluation coefficient threshold, and the number of warning signals of the smart walkway is less than the warning signal quantity threshold, then generate a quality inspection signal, indicating that there are potential hazards within the adjacent monitoring nodes, and it is necessary to conduct quality inspection on the adjacent monitoring nodes;

[0105] If there is no node evaluation coefficient of adjacent monitoring nodes of the smart walkway greater than the node evaluation coefficient threshold, and the number of warning signals of the smart walkway is greater than the warning signal quantity threshold, then generate a second abnormal signal, indicating that the smart walkway has insufficient capacity to accommodate users, and it is necessary for on-site staff to conduct inspections and evacuate the people staying in the smart walkway;

[0106] If there is no node evaluation coefficient of adjacent monitoring nodes of the smart walkway greater than the node evaluation coefficient threshold, and the number of warning signals of the smart walkway is less than the warning signal quantity threshold, then no other signals are generated, indicating that the current smart walkway can still maintain the normal experience of users to a certain extent.

[0107] In this embodiment, by comprehensively analyzing the data collected from specific adjacent monitoring nodes of the smart walkway and the relationships between adjacent monitoring nodes, the size of potential hazards existing in adjacent monitoring nodes is determined, and according to the number of warning signals generated by the smart walkway within the monitoring time interval, the operating state of the smart walkway is classified, which helps to improve the efficiency of safety management and resource allocation, and also significantly improves the user experience, providing strong support for the scientific decision-making and long-term management of the smart walkway.

[0108] Example 3

[0109] The present invention provides a schematic structural diagram of an intelligent walkway Internet of Things integrated management system as shown in Figure 1 , specifically including a data acquisition module, a warning evaluation module, an operation evaluation module, and a classification module, with signal connections between the modules;

[0110] The data acquisition module is used to collect the motion data and pedestrian flow information of users in real time through the monitoring devices of each monitoring node in the intelligent walkway, and transmit the collected data to the warning evaluation module and the operation evaluation module through a wireless network;

[0111] The warning evaluation module is used to calculate the real-time accommodation capacity of the intelligent walkway according to the processing capacity of the monitoring device and the current pedestrian flow information, and generate a real-time warning evaluation coefficient of the intelligent walkway;

[0112] The operation evaluation module is used to analyze the data integrity and consistency of adjacent monitoring nodes according to the data within the monitoring time interval, draw a node association relationship diagram, and generate a node evaluation coefficient of adjacent monitoring nodes within the monitoring time interval;

[0113] The classification module is used to classify the operation status of the intelligent walkway according to the hidden danger evaluation and the statistical result of the warning signal, and generate a management report.

[0114] The above formulas are all dimensionless and take their numerical values for calculation. The formulas are obtained by software simulation of a large amount of collected data to get a formula closest to the actual situation. The preset parameters in the formulas are set by those skilled in the art according to the actual situation.

[0115] The above embodiments can be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented using software, the above embodiments can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer programs are loaded or executed on a computer, the processes or functions described in the embodiments of the present application are generated in whole or in part. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions can be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center in a wired or wireless (such as infrared, wireless, microwave, etc.) manner. The computer-readable storage medium can be any available medium that can be accessed by a computer, or a data storage device such as a server or data center that includes one or more collections of available media. The available media can be magnetic media (such as floppy disks, hard disks, magnetic tapes), optical media (such as DVDs), or semiconductor media. The semiconductor media can be a solid-state drive.

[0116] It should be understood that in various embodiments of the present application, the order numbers of the above processes do not indicate the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.

[0117] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered to exceed the scope of the present application.

[0118] Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes of the systems, devices, and units described above can refer to the corresponding processes in the foregoing method embodiments, and will not be described herein again.

[0119] In several embodiments provided in the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection between each other can be through some interfaces. The indirect coupling or communication connection of the devices or units can be in electrical, mechanical, or other forms.

[0120] If the above functions are implemented in the form of software function units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or a part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present application. The foregoing storage medium includes: various media such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs that can store program codes.

[0121] The above is only the specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art within the technical scope disclosed in the present application can easily think of changes or substitutions, which should all be covered by the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.

Claims

1. A smart trail Internet of Things integrated management method, characterized in that: The specific steps include: S1: Through the monitoring equipment of the smart trail, the pedestrian flow information of the smart trail is collected in real time, and the current capacity of the smart trail to accommodate users is analyzed based on the data processing capability of the monitoring equipment; S2: Measure the user experience on the smart trail based on the pedestrian flow information and the ability of the smart trail to accommodate users, and generate warning signals or safety signals; S3: Analyze the integrity and consistency of the data of adjacent monitoring nodes in the smart trail within the monitoring time interval, and analyze the connection strength between the monitoring nodes in the smart trail by drawing the node association relationship diagram of the smart trail; The integrity of the data is represented by a data coverage coefficient, which is obtained by comparing the number of user data collected by monitoring devices in actual adjacent monitoring nodes with the number of data generated by users expected by the system; The consistency of the data is represented by the speed logic coefficient. The logic for obtaining the speed logic coefficient is as follows: the distance between adjacent monitoring nodes is compared with the time it takes for the user to travel from the previous monitoring node to the next monitoring node to obtain the average speed of the user at the adjacent monitoring nodes; an average speed threshold is set to obtain the average speed of all users at the adjacent monitoring nodes within the monitoring time interval; the average speed of all users at the adjacent monitoring nodes is compared with the average speed threshold to obtain the average speed of users whose speed is greater than the average speed threshold; the speed logic coefficient is calculated by a formula; the speed logic coefficient represents the severity of the speed change of users at adjacent monitoring nodes; Analyze the connection strength between each monitoring node in the smart trail, including; By collecting the user's location information, timestamp and motion data from the monitoring nodes, a node association graph is constructed, wherein the monitoring nodes in the smart trail are nodes of the node association graph, and the user's motion path between adjacent monitoring nodes is the edge of the node association graph; The connection strength between monitoring nodes is represented by the connection strength coefficient. The logic of obtaining the connection strength coefficient is as follows: obtain the user flow and movement frequency of adjacent nodes of the smart trail within the monitoring time interval, and obtain the user flow of adjacent nodes by calculating the average number of users identified by adjacent monitoring nodes; determine the frequency of user movement by the number of times adjacent monitoring nodes repeatedly identify users within the monitoring time interval, and calculate the connection strength coefficient between two monitoring nodes by weighted summation based on the user flow and movement frequency within the monitoring time interval; S4: Conduct a comprehensive evaluation of adjacent monitoring nodes of the smart trail within the monitoring time interval, establish a data analysis model based on the data coverage coefficient, speed logic coefficient and connection strength coefficient, and generate a node evaluation coefficient; set a node evaluation coefficient threshold and a warning signal number threshold, compare the node evaluation coefficient with the node evaluation coefficient threshold, and compare the number of warning signals with the warning signal number threshold; generate an abnormal signal, generate a quality inspection signal, or do not generate other signals based on the comparison results.

2. According to claim 1, a smart trail Internet of Things integrated management method is characterized in that: Collect the flow of people on the smart trail, including: The crowd flow information is represented by the crowd flow coefficient; The logic for obtaining the crowd congestion coefficient is as follows: according to the identification device of each monitoring node, the number of users identified by each node is obtained in real time, a threshold value for the number of users identified by the monitoring node is set, and a threshold value for the number of users identified by the overall processing of the smart trail is set; The load level of each node is determined by the ratio of the number of users identified by each monitoring node to the threshold number of users identified by the monitoring node. The overall system load level is determined by the number of users identified by each monitoring node, and the crowding coefficient is calculated by the formula.

3. According to claim 1, a smart trail Internet of Things integrated management method is characterized in that: Analyze the current smart trail’s ability to accommodate users, including: The ability of the smart trail to accommodate users is expressed by the retention risk coefficient; The logic for obtaining the retention risk coefficient is as follows: a unique ID is established for each user using the smart trail through face recognition technology, and the number of people in the smart trail is obtained by subtracting the number of people leaving the smart trail from the number of people entering the smart trail through face recognition; Set a retention time threshold to determine the time point from when the user enters the smart trail through face recognition. If the user is not recognized by any monitoring node within the retention time threshold, it is considered that the user may be stranded in the smart trail, and the number of users who may be stranded in the smart trail is obtained; Set a departure time threshold. If the user is not recognized by any monitoring node within the departure time threshold, it is considered that the user may have left the smart trail midway. The number of users who left the smart trail midway is obtained, and the retention risk coefficient is calculated through the formula.

4. The method for integrated management of the Internet of Things for smart trails according to claim 1, characterized in that: Measuring the user experience of the smart trail, including: Comprehensively analyze crowd flow coefficient and detention risk coefficient, establish data analysis model, and generate early warning assessment coefficient; Set the warning assessment coefficient threshold, compare the real-time warning assessment coefficient of the smart trail with the warning assessment coefficient threshold, if the warning assessment coefficient is greater than the warning assessment coefficient threshold, generate a warning signal, if the warning assessment coefficient is less than the warning assessment coefficient threshold, no warning signal is generated.

5. According to claim 1, the method for integrated management of the Internet of Things for smart trails is characterized in that: Analyze the integrity and consistency of adjacent monitoring node data, including: The integrity of the data is represented by the data coverage coefficient. The logic for obtaining the data coverage coefficient is as follows: according to the number of users identified between adjacent monitoring nodes and the frequency of user movement, the data generated by the expected users of the system within the monitoring time interval is determined, the number of user data collected by the monitoring devices in the actual adjacent monitoring nodes within the monitoring time interval is obtained, and the number of user data collected by the monitoring devices in the actual adjacent monitoring nodes is compared with the number of data generated by the expected users of the system to obtain the data coverage coefficient; The consistency of the data is represented by the speed logic coefficient. The logic for obtaining the speed logic coefficient is as follows: within the monitoring time interval, the time point when the monitoring device recognizes the user is recorded, and the distance between adjacent monitoring nodes is obtained. According to the time point when the user is at the adjacent monitoring node, the time taken by the user from the previous monitoring node to the next monitoring node is determined. The distance between adjacent monitoring nodes is compared with the time taken by the user from the previous monitoring node to the next monitoring node to obtain the average speed of the user at the adjacent monitoring nodes. Set the average speed threshold, obtain the average speed of all users in adjacent monitoring nodes within the monitoring time interval, compare the average speed of all users in adjacent monitoring nodes with the average speed threshold, obtain the average speed of users whose average speed is greater than the average speed threshold, and calculate the speed logic coefficient through the formula.

6. The method for integrated management of the Internet of Things for smart trails according to claim 1, characterized in that: Classify the operation status of the smart trail, including: Set the node evaluation coefficient threshold, compare the node evaluation coefficient with the node evaluation coefficient threshold, set the warning signal quantity threshold, obtain the number of warning signals in the monitoring time interval, compare the number of warning signals in the monitoring time interval with the warning signal quantity threshold, and generate the following situations: If the node evaluation coefficient of the adjacent monitoring node of the smart trail is greater than the node evaluation coefficient threshold, and the number of warning signals of the smart trail is greater than the warning signal number threshold, a first abnormal signal is generated; If the node evaluation coefficient of the adjacent monitoring node of the smart trail is greater than the node evaluation coefficient threshold, and the number of warning signals of the smart trail is less than the warning signal number threshold, a quality inspection signal is generated; If the node evaluation coefficient of the smart trail does not exist in the adjacent monitoring node greater than the node evaluation coefficient threshold, and the number of warning signals of the smart trail is greater than the warning signal number threshold, a second abnormal signal is generated; If there is no adjacent monitoring node in the smart trail whose node evaluation coefficient is greater than the node evaluation coefficient threshold, and the number of warning signals of the smart trail is less than the warning signal number threshold, no other signals will be generated.

7. An intelligent trail Internet of Things integrated management system, used to implement an intelligent trail Internet of Things integrated management method according to any one of claims 1 to 6, characterized in that: It includes data acquisition module, early warning assessment module, operation assessment module and classification module, and the signal connections between the modules; The data collection module is used to collect the user's movement data and crowd flow information in real time through the monitoring equipment of each monitoring node in the smart trail, and transmit the collected data to the early warning evaluation module and the operation evaluation module through the wireless network; The early warning assessment module is used to calculate the real-time capacity of the smart trail based on the processing capacity of the monitoring equipment and the current pedestrian flow information, and generate the real-time early warning assessment coefficient of the smart trail; An evaluation module is run to analyze the data integrity and consistency of adjacent monitoring nodes based on the data within the monitoring time interval, draw a node association relationship diagram, and generate node evaluation coefficients of adjacent monitoring nodes within the monitoring time interval; The classification module is used to classify the operating status of the smart trail and generate a management report based on the hidden danger assessment and early warning signal statistics.

Images