Intelligent management system for urban service operation platform

Abstract

The application relates to the technical field of urban intelligent evacuation, in particular to an intelligent management system for a city service operation platform. The system comprises a path planning module, a crowded condition monitoring module, an escalator monitoring module, an evacuation capacity evaluation module and a path correction module. The path correction module obtains spatial posture data of a monitoring target by constructing an escalator inclined coordinate system, calculates an optimal path score in combination with real-time crowded distribution of an evacuation channel, and adaptively corrects an initial path based on a weighted model. By identifying abnormal behaviors in the escalator area and in combination with the enabling condition of the standby evacuation channel, the evacuation capacity score of the whole evacuation channel is obtained, dynamic path scheduling in high-density crowds and parameter adjustment are realized. The application builds an evacuation strategy optimization mechanism of a perception, decision-making and feedback closed loop, and effectively improves the safety evacuation efficiency and risk control capability in complex urban scenes.

Description

Technical Field

[0001] This invention relates to the field of urban intelligent evacuation technology, and in particular to an intelligent management system for urban service operation platforms. Background Technology

[0002] With the widespread use of urban underground spaces, ensuring evacuation safety has become a crucial component of urban service operations. Related research indicates that in emergencies such as fires, using escalators in conjunction with stairs as evacuation routes can shorten maximum evacuation time by approximately 23% to 33% compared to relying solely on stairs. Furthermore, installing fireproof baffles at the bottom of escalators can improve evacuation efficiency by 6% to 7%. However, current research on escalators as emergency evacuation routes in most scenarios remains limited to evacuation time simulations, lacking real-time monitoring mechanisms and dynamic evaluation systems for the risks of escalator use, and failing to fully consider the impact of sudden behaviors such as climbing and falls on evacuation safety.

[0003] On the other hand, mainstream path planning strategies are mostly based on static shortest paths or simulated paths. Although some studies have attempted to use simulation models, artificial intelligence or reinforcement learning methods for real-time path optimization and dynamically adjust evacuation strategies in conjunction with personnel distribution, most of them lack a closed-loop design that integrates with visual recognition technology. They cannot achieve real-time linkage between congestion, risk and the opening and closing status of backup channels, nor can they perform adaptive calibration of path weights based on on-site feedback.

[0004] In addition, current sanitation operation systems and urban operation platforms rely heavily on manual inspections and static deployments, failing to integrate intelligent visual monitoring with multi-path collaborative scheduling, resulting in insufficient evacuation efficiency and difficulty in identifying safety risks in a timely manner.

[0005] Therefore, there is an urgent need for a comprehensive underground space evacuation system that integrates real-time visual behavior recognition, escalator risk assessment, dynamic crowding assessment, coordinated activation of backup passages, and adaptive adjustment of path scoring.

[0006] Chinese patent document CN107241841A discloses a mobile application system for urban lighting operation management. Based on the operation platform of the urban operation management system, the handheld terminal has the following functions: information query function, control strategy setting function, alarm push function, GIS map positioning function, work order dispatch function, equipment management function, etc.

[0007] This invention manages the operation of urban lighting systems through data communication between handheld terminals and central servers. While it possesses certain real-time and remote control capabilities, it still suffers from the following shortcomings: the system relies on manual operation and preset strategies, lacking the ability to perceive and respond to complex dynamic factors in the operational scenario; lighting strategies are mainly based on time control, light control, and latitude and longitude control, with limited intelligence and insufficient ability to integrate and schedule multi-source data; work order management mainly relies on subjective feedback and operational procedures from personnel, failing to achieve intelligent linkage between fault diagnosis, task assignment, and path planning. Therefore, it is evident that existing intelligent management platforms are insufficient to meet the comprehensive decision-making needs of multiple scenarios, multiple elements, and multiple objectives in urban service management. Summary of the Invention

[0008] Therefore, the present invention provides an intelligent management system for urban service operation platforms to overcome the problem of low resource allocation efficiency caused by the single source of path scheduling and the lack of feedback adjustment in the prior art due to unreasonable path selection.

[0009] To achieve the above objectives, the present invention provides an intelligent management system for an urban service operation platform, comprising:

[0010] The path planning module is used to determine the initial evacuation path based on the distribution status of the monitored targets and the layout of evacuation routes;

[0011] A congestion monitoring module, which is connected to the path planning module, is used to monitor the target distribution density and distribution location of any evacuation exit in the initial evacuation path in order to analyze the congestion situation of each evacuation exit.

[0012] An escalator monitoring module, which is connected to the crowding monitoring module, is used to identify abnormal behavior of the monitored target by detecting key attitude points, and calculate the safety risk index of the escalator based on the abnormal behavior to determine the current evacuation feasibility.

[0013] An evacuation capacity assessment module, which is connected to the escalator monitoring module, is used to determine whether to activate the backup evacuation channel based on the current flow status of the monitored target, analyze the opening and closing status of the backup evacuation channel, and obtain the evacuation capacity of the entire evacuation channel based on the congestion level and the number of backup evacuation channels when the backup evacuation channel is activated.

[0014] The path correction module is connected to the path planning module, the escalator monitoring module, and the evacuation capacity assessment module, respectively. It selects the optimal evacuation path based on the weighted calculation results and the initial evacuation path and broadcasts it.

[0015] Furthermore, the congestion monitoring module includes an underground area congestion calculation unit and an underground area congestion analysis unit, wherein,

[0016] The underground area congestion calculation unit is used to monitor the real-time congestion of each upward evacuation exit in the underground area.

[0017] The underground area congestion analysis unit is used to compare the upward standard congestion threshold with the upward real-time congestion, and determine the congestion status of the upward evacuation exit based on the comparison results.

[0018] Furthermore, the escalator monitoring module includes an escalator status sensing unit, a riding behavior recognition unit, and a risk prediction unit, wherein...

[0019] The escalator status sensing unit is used to obtain the escalator usage density during escalator operation.

[0020] The elevator riding behavior recognition unit is used to identify the category of dangerous behavior and the frequency of dangerous behavior during elevator riding.

[0021] The risk prediction unit is used to determine the category of the current evacuation status of the escalator based on the escalator usage density and the results of identifying dangerous behaviors while riding the escalator and to calculate the escalator safety risk value.

[0022] Furthermore, the elevator riding behavior recognition unit includes a key point construction subunit and a key point detection subunit, wherein,

[0023] The key point construction sub-unit is used to establish a three-dimensional coordinate system and extract the key points of the monitoring target.

[0024] The key point detection subunit identifies the category of dangerous behavior of the monitored target based on the key points of the joints, including climbing behavior recognition and falling behavior recognition.

[0025] Furthermore, the risk prediction unit includes an escalator safety risk value calculation subunit and an analysis subunit, wherein,

[0026] The escalator safety risk value calculation subunit calculates the escalator safety risk value based on the detected dangerous behavior categories and frequencies and the escalator usage.

[0027] The analysis subunit compares the calculated escalator safety risk value with the preset escalator safety risk value threshold, and determines the category of the current evacuation status of the escalator based on the comparison result.

[0028] Furthermore, climbing behavior recognition includes,

[0029] Calculate the real-time relative height between the monitored target's hand and the top of the escalator;

[0030] Compare the real-time relative altitude with the standard relative altitude range;

[0031] If the real-time relative height is not within the standard relative height range and the duration exceeds the preset duration for dangerous behavior, it is judged as climbing behavior.

[0032] Furthermore, fall behavior recognition includes,

[0033] Calculate the angle between the spine line and the horizontal plane to obtain the real-time angle;

[0034] Compare the real-time angle with the standard angle.

[0035] If the real-time angle is less than the standard angle, obtain the descent velocity of the center of gravity for several consecutive frames, and compare the descent velocity with a descent velocity threshold.

[0036] If the rate of descent of the center of gravity exceeds the descent speed threshold, it is determined to be a fall.

[0037] Furthermore, the evacuation capacity assessment module includes a ground area congestion analysis unit and a full evacuation route score calculation unit, wherein,

[0038] The ground area congestion analysis unit is used to continuously monitor the real-time ground congestion of each ground evacuation exit in the ground area, and compare the real-time ground congestion with the ground standard congestion threshold. Based on the comparison results, it determines whether to activate the backup evacuation passage and the number of backup evacuation passages corresponding to each main evacuation passage when activated.

[0039] The full evacuation route score calculation unit is used to obtain the real-time congestion level of each main evacuation route going up, the real-time congestion level of the escalator ground, and the corresponding number of backup evacuation routes when the backup evacuation routes are activated, and to calculate the evacuation capacity corresponding to the overall congestion score of the full evacuation routes.

[0040] Furthermore, the path correction module includes a quantization comparison unit and a path correction unit, wherein,

[0041] The quantitative comparison unit is used to obtain the ranking results of the overall congestion score of the entire evacuation route;

[0042] The total evacuation route is a collection of main evacuation routes and backup evacuation routes formed by the one-to-one correspondence of the upward evacuation exit, escalator, and ground evacuation exit.

[0043] The path correction unit is used to determine the initial evacuation path based on the priority ranking result of the comprehensive congestion score of the entire evacuation route.

[0044] Furthermore, the path correction unit includes a first correction unit and a second correction unit, wherein,

[0045] The first correction unit is used to determine the overall congestion score of the entire evacuation route based on the number of the second backup evacuation route when the backup evacuation route is not activated, and select the optimal evacuation route and broadcast it based on the priority ranking result of the overall congestion score of the entire evacuation route.

[0046] The second correction unit is used to determine the overall congestion score of all evacuation routes based on the number of first backup evacuation routes when the backup evacuation routes are activated, and to select and announce the optimal evacuation route based on the priority ranking result of the overall congestion score of all evacuation routes.

[0047] Compared with existing technologies, the advantages of this invention are as follows: The path planning module calculates initial path scores based on the Euclidean distance from the monitored target to each evacuation exit and the evacuation capacity score, ensuring that the initially selected path is both short and feasible. The evacuation capacity score is obtained by fusing multiple parameters such as congestion density and frequency of dangerous behaviors, avoiding path selection bias caused by using distance as a single indicator. Visual recognition and coordinate mapping technologies are used to accurately convert the two-dimensional coordinates of the monitored target in image space into actual site coordinates, improving the accuracy of path planning. The congestion monitoring module and the escalator monitoring module work together to achieve real-time identification of the congestion status and risk level of any passage. The evacuation capacity assessment module further decides whether to activate backup passages and assesses the overall load capacity of the system's global evacuation passages. The path correction module selects the optimal path in real time based on the dynamic weighted results and broadcasts it in multiple ways, effectively improving the system's adaptive evacuation capability in emergencies and enhancing the intelligent response capability of the urban service operation platform in complex crowd flow scenarios.

[0048] Furthermore, the crowding calculation unit accurately identifies the number of people monitored in each frame of the image and matches it with the visible area to obtain the crowd density at the evacuation exit, thereby determining whether it exceeds the set threshold. The analysis unit combines the density and threshold results to determine in real time whether there is a risk of blockage in the passage, providing an objective basis for subsequent path adjustments and effectively improving the rationality and safety of passage use.

[0049] Furthermore, by combining escalator density with the frequency of dangerous behaviors, an escalator safety risk value is generated. The risk prediction unit integrates multiple data sources and significantly improves the accuracy of abnormal situation response through model fusion. It can effectively determine whether the current escalator is available, avoid arranging evacuation in potentially high-risk passages, and ensure the safety of the crowd.

[0050] Furthermore, by analyzing spatial angle changes and velocity sequences, the method can accurately capture the trend of rapid changes in the center of gravity. This method can filter out false alarms and only trigger identification when both angle and velocity are abnormal, effectively improving the real-time performance and reliability of escalator accident early warning. Attached Figure Description

[0051] Figure 1This is a schematic diagram of the structure of an intelligent management system for an urban service operation platform according to an embodiment of the present invention;

[0052] Figure 2 This is a connection diagram of the congestion monitoring module according to an embodiment of the present invention;

[0053] Figure 3 This is a logic diagram for climbing behavior recognition in an embodiment of the present invention;

[0054] Figure 4 This is a logic diagram for recognizing fall behavior in an embodiment of the present invention. Detailed Implementation

[0055] To make the objectives and advantages of the present invention clearer, the present invention will be further described below with reference to embodiments; it should be understood that the specific embodiments described herein are merely for explaining the present invention and are not intended to limit the present invention.

[0056] Preferred embodiments of the present invention will now be described with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are merely illustrative of the technical principles of the present invention and are not intended to limit the scope of protection of the present invention.

[0057] It should be noted that in the description of this invention, the terms "upper", "lower", "left", "right", "inner", "outer", etc., which indicate directions or positional relationships, are based on the directions or positional relationships shown in the accompanying drawings. This is only for the convenience of description and is not intended to indicate or imply that the device or element must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, it should not be construed as a limitation of this invention.

[0058] Furthermore, it should be noted that, in the description of this invention, unless otherwise explicitly specified and limited, the terms "installation," "connection," and "linking" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection of two components. For the technical monitoring targets in this art, the specific meaning of the above terms in this invention can be understood according to the specific circumstances.

[0059] Please see Figure 1 As shown, this is a structural diagram of an intelligent management system for an urban service operation platform according to an embodiment of the present invention. The present invention provides an intelligent management system for an urban service operation platform, comprising:

[0060] The path planning module is used to determine the initial evacuation path based on the distribution status of the monitored targets and the layout of evacuation routes;

[0061] A congestion monitoring module, which is connected to the path planning module, is used to monitor the target distribution density and distribution location of any evacuation exit in the initial evacuation path in order to analyze the congestion situation of each evacuation exit.

[0062] An escalator monitoring module, which is connected to the crowding monitoring module, is used to identify abnormal behavior of the monitored target by detecting key attitude points, and calculate the safety risk index of the escalator based on the abnormal behavior to determine the current evacuation feasibility.

[0063] An evacuation capacity assessment module, which is connected to the escalator monitoring module, is used to determine whether to activate the backup evacuation channel based on the current flow status of the monitored target, analyze the opening and closing status of the backup evacuation channel, and obtain the evacuation capacity of the entire evacuation channel based on the congestion level and the number of backup evacuation channels when the backup evacuation channel is activated.

[0064] The path correction module is connected to the path planning module, the escalator monitoring module, and the evacuation capacity assessment module, respectively. It selects the optimal evacuation path based on the weighted calculation results and the initial evacuation path and broadcasts it.

[0065] In this embodiment, the path planning module is based on the Euclidean distance D from the target population to each evacuation exit. i The current evacuation capacity C of the evacuation exit i The path score for each evacuation route when the backup route is not open is calculated using the following formula:

[0066]

[0067] Where α is the distance weighting coefficient;

[0068] β is the weighting coefficient for evacuation capacity;

[0069] α+β=1;

[0070] The initial settings were α = 0.9 and β = 0.1, and the evacuation exit with the highest score was selected as the initial evacuation route.

[0071] Among them, the spatial location of the monitored target is obtained based on the visual recognition algorithm and the Euclidean distance from it to each evacuation exit is calculated;

[0072] A deep learning-based target detection network is used to identify the two-dimensional pixel coordinates of the monitored target in the image frame, and the coordinates (x, y) are mapped to the actual physical coordinates (x, y) of the site by combining the camera installation angle.

[0073] Using the known position of the evacuation exit in the coordinate system (x i y i ), calculate the Euclidean distance from the target to the i-th evacuation exit.

[0074] Visual density detection devices are deployed at each evacuation exit, both above and below ground. These devices integrate the types, frequencies, and congestion scores of dangerous behaviors fed back by the behavior recognition module. The evacuation capacity score is then calculated to determine the evacuation capacity of the current evacuation route.

[0075] Evacuation capability score C i The larger the value, the stronger the evacuation capacity and the smoother the evacuation channels.

[0076] When planning routes, distance is taken into account when selecting routes, while evacuation capacity parameters are set based on historical evacuation route data.

[0077] The path planning module calculates initial path scores based on the Euclidean distance from the monitored targets to each evacuation exit and the evacuation capacity score, ensuring that the initially selected paths are both short and feasible. The evacuation capacity score is obtained by fusing multiple parameters such as congestion density and frequency of dangerous behaviors, avoiding path selection bias caused by using distance as a single indicator. Visual recognition and coordinate mapping technology are used to accurately convert the two-dimensional coordinates of the monitored targets in image space into actual site coordinates, improving the accuracy of path planning. The congestion monitoring module and the escalator monitoring module work together to achieve real-time identification of the congestion status and risk level of any passage. The evacuation capacity assessment module further makes decisions on whether to activate backup passages and assesses the overall load capacity of the system's global evacuation passages. The path correction module selects the optimal path in real time based on the dynamic weighted results and broadcasts it in multiple ways, effectively improving the system's adaptive evacuation capability in emergency situations and enhancing the intelligent response capability of the urban service operation platform in complex crowd flow scenarios.

[0078] See Figure 2 The diagram shown is a connection schematic of the congestion monitoring module according to an embodiment of the present invention.

[0079] Specifically, the congestion monitoring module includes an underground area congestion calculation unit and an underground area congestion analysis unit, wherein,

[0080] The underground area congestion calculation unit is used to monitor the real-time congestion of each upward evacuation exit in the underground area.

[0081] The underground area congestion analysis unit is used to compare the upward standard congestion threshold with the upward real-time congestion, and determine the congestion status of the upward evacuation exit based on the comparison results.

[0082] In this embodiment, a smart visual acquisition camera at a set angle is installed above each upward evacuation exit. The camera is connected to the computing subunit of the congestion monitoring module and continuously acquires video data of the area covered by the evacuation exit.

[0083] The underground area congestion calculation unit uses a visual algorithm that combines target detection and behavior recognition to identify and number the monitoring targets in the image, and performs continuous tracking in the image sequence to eliminate duplicate counts;

[0084] Let A be the area of ​​the detection zone covered by the field of view of the upward evacuation exit. D The unit is m 2 The system identifies N human bodies in the video frames acquired per second. D Then the uplink real-time congestion ρ D It is calculated using the following formula.

[0085]

[0086] Where, N D A is the deduplication count of all detected targets in the current frame. D The actual area within the field of view obtained after conversion from physical distance measurement;

[0087] The underground area congestion analysis unit is used to compare the upward standard congestion threshold with the upward real-time congestion. The upward standard congestion threshold is set at 4 people / m². 2 ;

[0088] If the real-time congestion level of the upward escalator exceeds the standard congestion level threshold for the upward escalator, the escalator will be monitored.

[0089] If the real-time uplink congestion is less than or equal to the uplink standard congestion threshold, evacuation will proceed using the initial evacuation path.

[0090] The crowding calculation unit accurately identifies the number of people in each frame of the image and matches them with the visible area to obtain the crowd density at the evacuation exit, thereby determining whether it exceeds the set threshold. The analysis unit combines the density and threshold results to determine in real time whether there is a risk of blockage in the passage, providing an objective basis for subsequent path adjustments and effectively improving the rationality and safety of passage use.

[0091] Specifically, the escalator monitoring module includes an escalator status sensing unit, a riding behavior recognition unit, and a risk prediction unit, wherein...

[0092] The escalator status sensing unit is used to obtain the escalator usage density during escalator operation.

[0093] The elevator riding behavior recognition unit is used to identify the category of dangerous behavior and the frequency of dangerous behavior during elevator riding.

[0094] The risk prediction unit is used to determine the category of the current evacuation status of the escalator based on the escalator usage density and the results of identifying dangerous behaviors while riding the escalator and to calculate the escalator safety risk value.

[0095] In this embodiment, the escalator status sensing unit uses binocular stereo cameras installed above and to the side of the escalator, combined with an infrared counting module, to obtain the total number N of users in each time period of the escalator in real time. E Simultaneously obtain the effective area A of all passenger-carrying platform sections of the escalator. E The unit is m 2 The escalator usage density ρ can then be calculated using the following formula. E ,

[0096]

[0097] The escalator behavior recognition unit uses visual behavior recognition cameras located at the top and bottom of the escalator to collect dynamic posture information of passengers. It then uses the OpenPose skeleton recognition network to extract key nodes, constructing a continuous temporal coordinate sequence throughout the entire escalator ride and obtaining the frequency f of dangerous behaviors per unit time. risk ;

[0098] The risk prediction unit is responsible for summarizing the escalator usage density μ and the frequency of dangerous behaviors f. risk The safety risk value R of the escalator is calculated using the following formula.

[0099]

[0100] Wherein, ω1 is the weight of escalator usage density in the escalator safety risk value;

[0101] ω2 represents the weight of the frequency of dangerous behaviors in the escalator safety risk value;

[0102] μ0 is the standard escalator usage density threshold, representing the maximum number of passengers that can be safely carried per unit area. In this embodiment, the value is taken as 3.5 people / m². 2 ;

[0103] f norm The standard dangerous behavior implementation frequency threshold refers to the number of dangerous behaviors allowed per person per minute. In this embodiment, the value is 0.002.

[0104] By combining escalator density with the frequency of dangerous behaviors, an escalator safety risk value is generated. The risk prediction unit integrates multiple data sources and significantly improves the accuracy of abnormal situation response through model fusion. It can effectively determine whether the current escalator is available, avoid arranging evacuation in potentially high-risk passages, and ensure the safety of the crowd.

[0105] Specifically, the elevator riding behavior recognition unit includes a key point construction subunit and a key point detection subunit, wherein,

[0106] The key point construction sub-unit is used to establish a three-dimensional coordinate system and extract the key points of the monitoring target.

[0107] The key point detection subunit identifies the category of dangerous behavior of the monitored target based on the key points of the joints, including climbing behavior recognition and falling behavior recognition.

[0108] In this embodiment, a three-dimensional coordinate system (X, Y, Z) is defined with the escalator's direction of movement as the X-axis, the escalator's vertical upward direction as the Y-axis, and the passenger's lateral direction as the Z-axis.

[0109] Extract the key skeleton points of the monitoring target:

[0110] Using a deep neural network model, the 3D coordinates of key nodes are extracted for each elevator-riding target detected in the image.

[0111] Center point of the neck P1, center point of the left shoulder P2, center point of the right shoulder P3, center point of the spine P4, center point of the left hand P5, center point of the right hand P6, center point of the pelvis P7.

[0112] Based on key nodes, construct skeleton connection relationships and establish a skeleton model;

[0113] The key point detection subunit performs temporal analysis on the key points of the skeleton and determines whether there is dangerous behavior by the spatial position changes of consecutive frames.

[0114] By defining a three-axis coordinate system, the coordinates of key nodes during elevator rides are extracted in real time, and the behavior category is determined based on the skeleton connection relationship. This enhances the accuracy of identifying abnormal elevator ride behaviors while maintaining the stability and robustness of the recognition algorithm in complex action environments, providing refined support for dangerous behavior detection.

[0115] Specifically, the risk prediction unit includes an escalator safety risk value calculation subunit and an analysis subunit, wherein,

[0116] The escalator safety risk value calculation subunit calculates the escalator safety risk value based on the detected dangerous behavior categories and frequencies and the escalator usage.

[0117] The analysis subunit compares the calculated escalator safety risk value with the preset escalator safety risk value threshold, and determines the category of the current evacuation status of the escalator based on the comparison result.

[0118] See Figure 3 As shown, it is a logic decision diagram for climbing behavior recognition in an embodiment of the present invention;

[0119] Specifically, climbing behavior recognition includes,

[0120] Calculate the real-time relative height between the monitored target's hand and the top of the escalator;

[0121] Compare the real-time relative altitude with the standard relative altitude range;

[0122] If the real-time relative height is not within the standard relative height range and the duration exceeds the preset duration for dangerous behavior, it is judged as climbing behavior.

[0123] In this embodiment, the key point construction subunit uses depth image recognition to identify the left-hand center point P5 and right-hand center point P6 of the current elevator passenger, and obtains their spatial three-dimensional coordinates (X). L Y L Z L ), (X R Y R Z R ));

[0124] Simultaneously, the top edge point P of the escalator handrail in the same horizontal direction as the monitored target in the current evacuation route is obtained through escalator parameters and image recognition. top Height value Y top ;

[0125] Calculate the center point P of the passenger's hand in the current frame. LR Real-time relative height H with the top of the escalator real Specifically:

[0126]

[0127] Among them, the center point of the hand P LR The midpoint of the line connecting the left-hand center point P5 and the right-hand center point P6;

[0128] Set the standard relative height range H for safety control std In this embodiment, it is set to -[-0.2, 0.2], with the unit being m;

[0129] The real-time relative altitude is compared with the standard relative altitude range.

[0130] If the real-time relative height is less than or equal to the minimum value of the standard relative height range, it is determined to be a climbing tendency, and the duration is further obtained.

[0131] If the real-time relative height is within the standard relative height range, it is considered as non-abnormal behavior;

[0132] If the real-time relative height is greater than or equal to the maximum value of the standard relative height range, it is determined to be a climbing tendency. The duration is then obtained to determine whether it is a climbing behavior in dangerous behavior.

[0133] Set a preset duration of 5 seconds for the dangerous behavior, and compare the duration of the dangerous behavior with the preset duration.

[0134] If the duration exceeds the preset duration for dangerous behavior, it is judged as climbing behavior among dangerous behaviors;

[0135] If the duration is less than or equal to the preset duration of the dangerous behavior, it is determined to be a non-abnormal behavior.

[0136] By calculating the relative height between a passenger's hand and the top edge of the escalator in real time and combining this with duration analysis, a climbing behavior judgment model is constructed. Using only spatial distance and time logic as the judgment criteria, it can effectively identify dangerous actions and distinguish them from ordinary standing behavior, providing data support for behavior monitoring and risk warning in escalator areas.

[0137] See Figure 4 As shown, it is a logic decision diagram for fall behavior recognition in an embodiment of the present invention;

[0138] Specifically, fall behavior recognition includes,

[0139] Calculate the angle between the spine line and the horizontal plane to obtain the real-time angle;

[0140] Compare the real-time angle with the standard angle.

[0141] If the real-time angle is less than the standard angle, obtain the descent velocity of the center of gravity for several consecutive frames, and compare the descent velocity with a descent velocity threshold.

[0142] If the rate of descent of the center of gravity exceeds the descent speed threshold, it is determined to be a fall.

[0143] In this embodiment, the center point P1 of the neck and the center point P7 of the pelvis are obtained, and a spinal line vector is formed based on these two points.

[0144]

[0145] Using the horizontal direction as a reference plane, the real-time angle, i.e., the angle θ between the spine line and the horizontal plane, is calculated through vector projection. The calculation formula is as follows:

[0146]

[0147] in, The vertical upward unit vector is (0, 1, 0);

[0148] Set the standard angle as θ std =40°, compare the real-time angle with the standard angle.

[0149] If the real-time angle is greater than the standard angle, it is determined to be a non-abnormal behavior;

[0150] If the real-time angle is less than or equal to the standard angle, it is determined to be a tendency to fall. Further, the center of gravity descent speed of several consecutive frames is obtained to determine whether it is a fall behavior in dangerous behavior.

[0151] Specifically, the set of centroids of the monitored target along the Y-axis [y1, y2, ..., y] within 5 seconds is obtained at a frame rate of 30fps. 150 ];

[0152] The velocity sequence is calculated using the inter-frame difference method, and the calculation formula is as follows.

[0153]

[0154] 149 sets of inter-frame centroid points were calculated;

[0155] The center of gravity is the midpoint of the line connecting the center point of the neck, P1, and the center point of the pelvis, P7.

[0156] The descent velocity of the center of gravity in several consecutive frames is obtained. A descent velocity threshold of 0.6 m / s is set, and the descent velocity of the center of gravity is compared with the descent velocity threshold.

[0157] If the rate of descent of the center of gravity exceeds the descent speed threshold, or if the rate of descent of the center of gravity is greater than the normal level, it is judged as a fall, which is a dangerous behavior.

[0158] If the descent speed of the center of gravity is less than or equal to the descent speed threshold, the descent speed of the center of gravity is at a normal level and is not abnormal behavior.

[0159] By analyzing spatial angle changes and velocity sequences, this method can accurately capture the trend of rapid changes in the center of gravity. It can filter out false alarms and only trigger identification when both angle and velocity are abnormal, effectively improving the real-time performance and reliability of escalator accident warnings.

[0160] Specifically, the evacuation capacity assessment module includes a ground area congestion analysis unit and a full evacuation route score calculation unit, wherein,

[0161] The ground area congestion analysis unit is used to continuously monitor the real-time ground congestion of each ground evacuation exit in the ground area, and compare the real-time ground congestion with the ground standard congestion threshold. Based on the comparison results, it determines whether to activate the backup evacuation passage and the number of backup evacuation passages corresponding to each main evacuation passage when activated.

[0162] The full evacuation route score calculation unit is used to obtain the real-time congestion level of each main evacuation route, the escalator safety risk value, and the corresponding number of backup evacuation routes when the backup evacuation route is activated, and to calculate the evacuation capacity corresponding to the overall congestion score of the full evacuation route.

[0163] In this embodiment, let A be the area of ​​the detection zone covered by the field of view of the ground evacuation exit.U The unit is m 2 The system identifies N human bodies in the video frames acquired per second. U Then the real-time ground congestion ρ U It can be calculated using the following formula:

[0164]

[0165] Where, N U A is the deduplication count of all detected targets in the current frame. U The actual area within the field of view obtained after conversion from physical distance measurement;

[0166] Take the ground standard congestion threshold ρ U，std 3.5 people / m 2 The ground area congestion analysis unit compares the standard ground congestion threshold with the real-time ground congestion level.

[0167] If the real-time ground congestion exceeds the standard ground congestion threshold, the current main evacuation route is not capable of evacuating the current number of people, and the backup route needs to be activated.

[0168] If the real-time ground congestion level is less than or equal to the ground standard congestion threshold, the current main evacuation route has the capacity to evacuate the current number of people, and the backup route will not be activated.

[0169] When activating a backup evacuation route, the number of backup routes at activation is set to the number of the first backup evacuation routes. The number of backup evacuation routes (n) that need to be activated for the current main evacuation route is determined by the following formula. b ,

[0170]

[0171] Wherein, δ represents the amount of pedestrian density that each backup evacuation route can alleviate, and the system preset is 0.8;

[0172] This indicates a rounding up operation, ensuring that at least one backup channel is activated whenever the threshold is exceeded;

[0173] For example, when the ρ of a certain main passage corresponds to a ground evacuation exit U =4.6, substituting, we get

[0174]

[0175] At this point, immediately activate its two paired backup evacuation routes and then activate n. b =2 inputs are passed to the full evacuation route fraction calculation unit;

[0176] The formula for calculating the overall congestion score of all evacuation routes is as follows:

[0177]

[0178] C i,adjusted =100*T

[0179] Among them, ω3, ω4, and ω5 are preset weights corresponding to the three indicators of real-time congestion level of the upward movement, escalator safety risk value, and the number of corresponding backup evacuation channels, respectively.

[0180] ρ D,max The maximum tolerable value set for historical statistics on ground congestion;

[0181] R ,max The maximum tolerable value set for historical statistics of escalator safety risk values;

[0182] n max The maximum number of backup evacuation routes that can be opened corresponding to the main evacuation route;

[0183] C i,adjusted The evacuation capacity corresponding to the overall congestion score of all evacuation routes;

[0184] Take ω3=0.3, ω4=0.4, ω5=0.3;

[0185] The threshold for comparing the overall congestion score of all evacuation routes is set at 0.5;

[0186] The overall congestion score of all evacuation routes is compared with the threshold for comparison.

[0187] If the overall congestion score of the entire evacuation route is greater than the threshold for comparing the overall congestion score of the entire evacuation route, and the evacuation capacity of the initial route meets the evacuation requirements, the division method of the initial route will not be adjusted, and the initial evacuation route will be the optimal evacuation route.

[0188] If the overall congestion score of the entire evacuation route is less than or equal to the threshold for comparing the overall congestion score of the entire evacuation route, the evacuation capacity of the initial route cannot meet the evacuation requirements. After evacuation, the weight coefficient of the evacuation capacity will be dynamically adjusted to update the initial evacuation route to the optimal evacuation route.

[0189] For example, when ρ D =3.2, ρ D,max =5.0, R=40, R ,max =100, n b =2,n max When C = 4, i,adjusted=0.29, which is less than the threshold of 0.5 for the comprehensive congestion score comparison of the entire evacuation route. At this time, the weight coefficient of the evacuation capacity needs to be dynamically adjusted to meet the evacuation requirements of the monitoring target. After evacuation, the weight coefficient of the evacuation capacity is dynamically adjusted with a fixed upward adjustment value of 10% of the original weight coefficient of the evacuation capacity.

[0190] A dynamic evacuation capacity adjustment mechanism is established, which integrates real-time congestion density in the ground area, escalator risk values, and the number of backup passages in use to form a comprehensive congestion score for all evacuation passages, accurately assessing the current path carrying capacity; when the score is below the threshold, the weight is automatically increased to optimize the path scoring model, making the system's evacuation decisions more closely match the actual evacuation scenario on site.

[0191] Specifically, the path correction module includes a quantization comparison unit and a path correction unit, wherein,

[0192] The quantitative comparison unit is used to obtain the ranking results of the overall congestion score of the entire evacuation route;

[0193] The total evacuation route is a collection of main evacuation routes and backup evacuation routes formed by the one-to-one correspondence of the upward evacuation exit, escalator, and ground evacuation exit.

[0194] The path correction unit is used to determine the initial evacuation path based on the priority ranking result of the comprehensive congestion score of the entire evacuation route.

[0195] In this embodiment, the evacuation path corresponding to the highest priority congestion score of the entire evacuation route is selected as the optimal evacuation path. The congestion score of the entire evacuation route from the monitored target to each route is obtained, and the score is sorted from high to low to form a priority list. The priority is proportional to the sequence number in the priority list.

[0196] The higher the priority, the stronger the evacuation capability.

[0197] By establishing a ranking mechanism based on congestion comprehensive scoring, the priority of each evacuation route in the current state is clarified, and the ranking result serves as the basis for route correction, effectively avoiding the risk of initial route failure; in emergency scenarios, the evacuation strategy can be updated in real time, improving response efficiency and route utilization.

[0198] Specifically, the path correction unit includes a first correction unit and a second correction unit, wherein...

[0199] The first correction unit is used to determine the overall congestion score of the entire evacuation route based on the number of the second backup evacuation route when the backup evacuation route is not activated, and select the optimal evacuation route and broadcast it based on the priority ranking result of the overall congestion score of the entire evacuation route.

[0200] The second correction unit is used to determine the overall congestion score of all evacuation routes based on the number of first backup evacuation routes when the backup evacuation routes are activated, and to select and announce the optimal evacuation route based on the priority ranking result of the overall congestion score of all evacuation routes.

[0201] In this embodiment, when the backup evacuation route is not activated, n b When the value is 0, the number of backup passages when activated is the number of the second backup evacuation passages.

[0202] Dynamic directional signs display evacuation routes in real time; LED or LCD screens installed at passage entrances and major turning points simultaneously display evacuation routes and directional arrows.

[0203] The optimal evacuation route is announced via a voice broadcasting system deployed in the evacuation area, using speakers on the ceiling or walls.

[0204] By constructing a path correction response mechanism, dynamic route selection is based on the scoring and ranking of the entire evacuation route under different conditions, and multi-channel broadcasting is carried out through directional signs, display screens and voice systems; this achieves full coverage and real-time notification of evacuation route information, and enhances the system's ability to guide high-density population areas.

[0205] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it is readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will all fall within the scope of protection of the present invention.

[0206] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention; various modifications and variations can be made to the present invention for technical monitoring objectives in this field. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the protection scope of the present invention.

Claims

1. An intelligent management system for a city service operation platform, characterized in that, Comprising, a path planning module configured to determine an initial evacuation path according to a monitored target distribution state and a layout of evacuation channels; a congestion condition monitoring module connected to the path planning module and configured to monitor a target distribution density and a target distribution position of any evacuation exit in the initial evacuation path to analyze a congestion condition of each evacuation exit; an escalator monitoring module connected to the congestion condition monitoring module and configured to identify abnormal behaviors of the monitored targets through key posture point detection, calculate a safety risk index of the escalator based on the abnormal behaviors, and determine a current evacuation feasibility; an evacuation capacity evaluation module connected to the escalator monitoring module and configured to determine whether to enable a backup evacuation channel according to a current flow state of the monitored targets, analyze an opening and closing state of the backup evacuation channel, and obtain an overall evacuation channel evacuation capacity based on a congestion degree and a number of backup evacuation channels when the backup evacuation channel is enabled; a path correction module connected to the path planning module, the escalator monitoring module, and the evacuation capacity evaluation module, respectively, and configured to select an optimal evacuation path based on a weighted calculation result and the initial evacuation path and broadcast the optimal evacuation path; the evacuation capacity evaluation module includes a ground area congestion analysis unit and an overall evacuation channel score calculation unit, wherein the ground area congestion analysis unit is configured to continuously monitor a ground real-time congestion degree of each ground evacuation exit in a ground area, compare the ground real-time congestion degree with a ground standard congestion degree threshold, and determine whether to enable a backup evacuation channel and a number of backup evacuation channels corresponding to each main evacuation channel when the backup evacuation channel is enabled based on a comparison result; the overall evacuation channel score calculation unit is configured to obtain an uplink real-time congestion degree of each main evacuation channel, an escalator ground real-time congestion degree, and a number of corresponding backup evacuation channels when the backup evacuation channel is enabled, and calculate an overall evacuation channel congestion comprehensive score corresponding to an evacuation capacity; the path correction module includes a quantification comparison unit and a path correction unit, wherein the quantification comparison unit is configured to obtain a ranking result of the overall evacuation channel congestion comprehensive score; wherein the overall evacuation channel is a set of main evacuation channels and backup evacuation channels corresponding to each of an uplink evacuation exit, an escalator, and a ground evacuation exit; the path correction unit is configured to select an optimal evacuation path based on a priority ranking result of the overall evacuation channel congestion comprehensive score and broadcast the optimal evacuation path. 2.The intelligent management system for urban service operation platform according to claim 1, characterized in that, the congestion condition monitoring module includes an underground area congestion degree calculation unit and an underground area congestion degree analysis unit, wherein the underground area congestion degree calculation unit is configured to monitor an uplink real-time congestion degree of each uplink evacuation exit in an underground area; the underground area congestion degree analysis unit is configured to compare an uplink standard congestion degree threshold with the uplink real-time congestion degree and determine a congestion condition of the uplink evacuation exit based on a comparison result. 3.The intelligent management system for urban service operation platform according to claim 1, characterized in that, the escalator monitoring module includes an escalator state perception unit, a boarding behavior recognition unit, and a risk prediction unit, wherein the escalator state perception unit is configured to obtain an escalator usage density in an escalator operating state; the boarding behavior recognition unit is configured to identify a category of dangerous behaviors and a dangerous behavior implementation frequency in a boarding process; The risk prediction unit is configured to identify the escalator use density and the dangerous behavior of taking the escalator, and calculate an escalator safety risk value to determine the category of the current evacuation state of the escalator. 4.The intelligent management system for urban service operation platform according to claim 3, characterized in that, The escalator behavior identification unit includes a key point construction subunit and a key point detection subunit. The key point construction subunit is configured to establish a three-dimensional coordinate system and extract the key point of the joint of the monitoring target. The key point detection subunit identifies the category of the dangerous behavior of the monitoring target according to the key point of the joint, including climbing behavior identification and falling behavior identification. 5.The intelligent management system for urban service operation platform according to claim 3, characterized in that, The risk prediction unit includes an escalator safety risk value calculation subunit and an analysis subunit. The escalator safety risk value calculation subunit calculates the escalator safety risk value based on the detected dangerous behavior category and frequency and the escalator use amount. The analysis subunit compares the calculated escalator safety risk value with a preset escalator safety risk value threshold, and determines the category of the current evacuation state of the escalator based on the comparison result. 6.The intelligent management system for urban service operation platform according to claim 4, characterized in that, The climbing behavior identification includes, calculating the real-time relative height of the hand of the monitoring target and the top of the escalator; comparing the real-time relative height with a standard relative height interval; if the real-time relative height is not within the standard relative height interval and the duration exceeds the preset dangerous behavior time, the climbing behavior is determined. 7.The intelligent management system for urban service operation platform of claim 4, wherein, The falling behavior identification includes, calculating the angle between the spine line and the horizontal plane to obtain a real-time angle; comparing the real-time angle with a standard angle, if the real-time angle is less than the standard angle, obtaining the gravity center drop speed of a plurality of consecutive frames, and comparing the gravity center drop speed with a drop speed threshold, if the gravity center drop speed is greater than the drop speed threshold, the falling behavior is determined. 8.The intelligent management system for urban service operation platform according to claim 7, characterized in that, The path correction unit includes a first correction unit and a second correction unit. The first correction unit is configured to determine the full evacuation channel congestion comprehensive score based on the number of second backup evacuation channels when the backup evacuation channel is not enabled, to select the optimal evacuation path based on the priority ranking result of the full evacuation channel congestion comprehensive score and broadcast. The second correction unit is configured to determine the full evacuation channel congestion comprehensive score based on the number of first backup evacuation channels when the backup evacuation channel is enabled, to select the optimal evacuation path based on the priority ranking result of the full evacuation channel congestion comprehensive score and broadcast. The first backup evacuation channel number is the number of evacuation channels when the backup evacuation channel is enabled. The second backup evacuation channel number is the number of evacuation channels when the backup evacuation channel is not enabled.

Images