Rail Transit Crowd Evacuation Method and Device Based on Internet of Things

Abstract

The present invention provides a rail transit crowd evacuation method and device based on the Internet of Things. The method comprises the following steps: collecting operating parameters of rail transit equipment; predicting hazards based on the operating parameters; calculating crowd density upon receiving a warning signal; and invoking the Dijkstra algorithm to plan the nearest escape route based on the operating parameters, the warning signal, and the crowd density. The present invention enables dynamic planning of the nearest escape route, avoiding existing and future danger points, and achieving safe and rapid crowd evacuation.

Description

Technical Field

[0001] The present invention belongs to the field of rail transit safety technology, and specifically relates to a rail transit crowd evacuation method and device based on the Internet of Things. Background Art

[0002] Currently, emergency evacuation in emergencies is receiving increasing attention worldwide. However, urban rail transit systems remain a complex and challenging issue due to system complexity, the uncontrollable nature of personnel, and the unpredictability of emergencies. When emergencies occur, finding a single optimal evacuation plan is often impossible due to the myriad influencing factors. Even minor changes in evacuation measures and psychological factors can significantly impact the outcome.

[0003] Existing technologies often rely on on-site drawings and pre-designed evacuation plans for fixed crowd management. Even with the addition of crowd-counting cameras to divert crowds, this still overlooks many real-world scenarios. For example, if a dynamically planned route encounters a malfunctioning device, or an accident causes the device to overheat, posing a potential explosion risk, the dynamic algorithm will not plan an escape route for passengers, but a dangerous and thorny path. Summary of the Invention

[0004] In order to overcome the above technical defects, the present invention provides a rail transit crowd evacuation method and device based on the Internet of Things, which can dynamically plan the nearest escape route.

[0005] In order to solve the above problems, the present invention is implemented according to the following technical solutions:

[0006] A rail transit crowd evacuation method based on the Internet of Things, comprising the following steps:

[0007] Collect operating parameters of rail transit equipment;

[0008] predicting hazards based on the operating parameters;

[0009] When a warning signal is obtained, the crowd density is calculated;

[0010] The Dijkstra algorithm is called and the nearest escape route is planned in combination with the operating parameters, the warning signal and the crowd density.

[0011] As a further improvement of the present invention, the present invention also includes a method for calculating crowd density:

[0012] Get the number of people;

[0013] Get the area of the evacuation passage;

[0014] Calculating the population density according to the number of people and the area of the evacuation passage, where the population density is equal to the number of people divided by the area;

[0015] As a further improvement of the present invention, the warning signal includes:

[0016] The first type of warning is used to notify of danger;

[0017] Category II warnings are used to warn of hazards that require treatment within forty-eight hours;

[0018] The third type of warning is used to warn of hazards that need to be dealt with within twelve hours;

[0019] Category 4 warnings are used to warn of hazards that need to be addressed within two hours;

[0020] The fifth type of warning is used to warn of dangers that require immediate attention.

[0021] As a further improvement of the present invention, the step of calling the Dijkstra algorithm and planning the nearest escape path in combination with the warning signal and the crowd density includes the following steps:

[0022] obtaining a first weight according to a category of the warning signal;

[0023] obtaining a second weight according to the operating parameter;

[0024] Obtaining a third weight according to the crowd density;

[0025] The Dijkstra algorithm is called, and the first weight, the second weight, and the third weight are combined to calculate the shortest escape path.

[0026] As a further improvement of the present invention, the step of collecting operating parameters of rail transit equipment includes the steps of:

[0027] The rail transit equipment is accessed using the MQTT / HTTP protocol to obtain the operating parameters.

[0028] As a further improvement of the present invention, the step of predicting the danger according to the operating parameters comprises the steps of:

[0029] The operating parameters and whether a fault occurs under the operating parameters are used as inputs of a risk prediction model, and the risk prediction model is trained.

[0030] As a further improvement of the present invention, the present invention further comprises the steps of:

[0031] The nearest escape path is sent to an IoT application or IoT system.

[0032] As a further improvement of the present invention, the step of sending the nearest escape path to an Internet of Things application or an Internet of Things system includes:

[0033] The IoT application or the IoT system is accessed through a message service API and obtains the nearest escape route.

[0034] Compared with the existing technology, the present invention has the following beneficial effects: by collecting the operating parameters of rail transit equipment in real time, the operating conditions of rail transit are predicted, and the Dijkstra algorithm is used to plan the nearest escape path in combination with the crowd density of the evacuation channel. Based on this, it can avoid that when a danger has occurred inside the rail transit, secondary dangers that may occur on the escape path or congestion on the escape path are not predicted, causing secondary harm to passengers or causing passengers to walk on a road that is not conducive to escape. The operating parameters and crowd density of the present invention are updated in real time, so that the planning of the escape path can also be updated synchronously, and the nearest escape path can be planned in real time and dynamically. For large hub subway stations, existing and future dangerous points can be avoided to achieve safe and rapid evacuation of people.

[0035] In addition, the present invention also provides a rail transit crowd evacuation device based on the Internet of Things, comprising:

[0036] Operation parameter acquisition module, used to collect operation parameters of rail transit equipment;

[0037] A hazard prediction module, configured to predict hazards based on the operating parameters;

[0038] The path planning module is used to call the Dijkstra algorithm and plan the nearest escape path in combination with the operating parameters, the warning signal and the crowd density.

[0039] As a further improvement of the present invention, the present invention further comprises:

[0040] The third-party software access module is used to send the nearest escape route to the Internet of Things application or Internet of Things system. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] The specific embodiments of the present invention will be further described in detail below with reference to the accompanying drawings, wherein:

[0042] Figure 1 This is a flow chart of Example 1. DETAILED DESCRIPTION

[0043] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood that the preferred embodiments described herein are only used to illustrate and explain the present invention, and are not used to limit the present invention.

[0044] Example 1

[0045] This embodiment discloses a rail transit crowd evacuation method based on the Internet of Things, such as Figure 1 As shown, the steps include:

[0046] S1. Collect the operating parameters of rail transit equipment, including: escalator operation status gateway, rolling shutter gateway, electronic guidance gateway, guide light box gateway, etc.

[0047] S2. Predict dangers based on operating parameters. When danger is predicted, a warning signal is issued. In rail transit hubs, accidents such as fires and explosions may occur. After fires and explosions damage rail transit equipment, the rail transit equipment may malfunction, thereby causing a secondary fire or explosion. Alternatively, the rail transit equipment may operate poorly, causing its own malfunctions and leading to fires and explosions. Based on this, it is necessary to predict the dangers of rail transit equipment based on operating parameters.

[0048] S3. When a warning signal is received, calculate the crowd density. When danger is likely to occur, promptly monitor the crowd density on the current evacuation channel to prepare for escape route planning.

[0049] S4. Call the Dijkstra algorithm and plan the nearest escape route based on the operating parameters, warning signals and crowd density.

[0050] In the above embodiment, a method for calculating crowd density is also included:

[0051] S31. Obtaining the number of people. Obtaining the number of people can be achieved through an infrared sensor or a people counting camera.

[0052] S32. Obtain the area of the evacuation passage. The layout and area of all evacuation passages in the rail transit station are pre-stored on the Internet of Things platform. When needed, they can be called from the Internet of Things platform.

[0053] S33. Calculate the crowd density based on the number of people and the area of the evacuation passage. The crowd density is equal to the number of people divided by the area.

[0054] Specifically, the warning signals include: first-class warnings, second-class warnings, third-class warnings, fourth-class warnings and fifth-class warnings, among which the first-class warnings are used to notify dangers; the second-class warnings are used to warn of dangers that need to be dealt with within forty-eight hours; the third-class warnings are used to warn of dangers that need to be dealt with within twelve hours; the fourth-class warnings are used to warn of dangers that need to be dealt with within two hours; the fifth-class warnings are used to warn of dangers that need to be dealt with immediately; the alarm signals can be transmitted to the subway's monitoring background. For the first-class warnings, maintenance personnel can carry out timely maintenance of rail transit equipment to avoid dangers caused by failures of rail transit equipment. For the second-class warnings to the fifth-class warnings that may cause dangers, the operating personnel can have an overall and macro control of the people and objects on the scene based on this embodiment, and promptly notify the staff to make dynamic adjustments to ensure the personal safety and property safety of passengers and staff.

[0055] Specifically, step S4 includes the following steps:

[0056] S41. Obtain a first weight according to the category of the warning signal. The higher the warning level, the greater the generated weight. For example, the weight of the fifth category warning is the largest.

[0057] S42. Obtain a second weight based on the operating parameters, that is, when the rail transit equipment is in normal condition, the obtained second weight is smaller, and when the rail transit equipment is in failure and may cause further fire or other dangers, the second weight is larger.

[0058] S43. Obtain a third weight according to the crowd density. When the crowd density is small, the obtained third weight is small. When the crowd density is large, the obtained third weight is large.

[0059] S44. Call the Dijkstra algorithm and calculate the nearest escape path based on the first weight, the second weight, and the third weight. Specifically, if there are multiple warning signals on a path, multiple first weights are obtained and accumulated. If multiple rail transit equipment on a path fails or has the possibility of failure, multiple second weights are obtained and accumulated. When using the Dijkstra algorithm, a weight is added to each path. A path with a large weight increases the probability of being impassable or is excluded. That is, even if it is the shortest path, if there is a rail transit equipment failure on the path, which may further cause danger, or there are many alarm signals on the path, or there are already a large number of passengers on the path, which may cause congestion, the path will still be excluded. For some paths that may not be the shortest, the rail transit equipment on the path is operating normally, the probability of further causing secondary danger is low, or the passenger flow on the path is small and can be evacuated quickly, the path can still be determined as the nearest escape path. For other contents of the Dijkstra algorithm, please refer to the prior art and will not be described in detail here.

[0060] Furthermore, step S1 includes the steps of:

[0061] S11. Use the MQTT / HTTP protocol to access rail transit equipment to obtain operating parameters. The MQTT protocol can provide communication security for a large number of low-power IoT devices with unreliable working network environments. The MQTT protocol has the following features: 1. Simple implementation; 2. Providing QoS for data transmission; 3. Lightweight and low bandwidth occupation; 4. Ability to transmit any type of data; 5. Maintainable sessions. Based on this, the operating parameters of rail transit equipment can be collected in seconds, which meets the requirements of high safety factor and fast response for the rail transit system.

[0062] In the above embodiment, step S2 includes the steps of:

[0063] S21. Use operating parameters and whether a fault occurs under the operating parameters as inputs to the hazard prediction model, and train the hazard prediction model. The operating parameters and whether a fault occurs can be predicted based on historical operating conditions. Through this step, it is possible to quickly identify whether the rail transit equipment is in a fault state based on the real-time operating parameters of the rail transit equipment, providing conditions for subsequent hazard prediction.

[0064] In order to enable passengers to obtain the nearest escape route in real time, this embodiment further includes the steps of:

[0065] S5. Send the nearest escape route to an IoT application or IoT system. IoT applications include mini-programs, official accounts, mobile apps, etc., and IoT systems include web applications. These IoT applications and IoT systems are commonly used by passengers in daily life. When danger occurs, passengers can quickly obtain escape route guidance through these IoT applications or IoT systems.

[0066] Specifically, step S5 includes:

[0067] S51. The IoT application is accessed through the message service API and obtains the nearest escape route.

[0068] Specifically, step S51 includes the following processes:

[0069] 1. Application application: In this embodiment, an application system is applied, and the sandbox environment debugging AppID, key and ticket are automatically generated.

[0070] 2. Access debugging: Set the message callback address, call the login authentication API and the message broadcast API, and jointly debug the data transmission between the application system and this embodiment.

[0071] 3. Release and launch: After the application has completed access and debugging in the sandbox environment, it can apply for release. It is necessary to upload the application product information and test report. If necessary, the application access address and test environment must be provided. After the administrator reviews and approves the application, the application is launched in the sandbox environment.

[0072] 4. Application Deployment: Apply for the official AppID, key, and ticket for the production environment based on the project ID. Enter the message callback address for the application in the actual project. Note that the ticket and API access domain name for the production environment and the sandbox environment are different. Please replace the ticket configured in the code, obtain the Weiling API access domain name for the production environment, and perform complete functional verification in the production environment.

[0073] 5. Application maintenance: After the application is deployed in the production environment, if the function changes or the application ticket expires, it is necessary to generate a new ticket in the same production environment, perform complete functional verification in the production environment, and then re-release the iterative version of the application.

[0074] In summary, this embodiment has the following beneficial effects:

[0075] 1. This embodiment dynamically plans the nearest escape route through three links (warning signals, operating parameters, and crowd density), avoiding existing or potentially dangerous routes to achieve safe and rapid evacuation of the crowd.

[0076] 2. This embodiment not only facilitates the access of devices and applications, but also provides various types of data access capabilities, such as edge gateways, video gateways, and API gateways. As a data distribution center for IoT devices, it optimizes the building space, facility systems, and application services within large rail transit stations based on usage scenarios and business logic, integrates and distributes all warnings, configures relevant rules, and determines equipment failures based on historical equipment operation status. It then reasonably identifies risk points for dynamic escape route planning.

[0077] 3. For third-party application systems that complete data access through the message service API of this embodiment, this embodiment provides simple and easy-to-use online debugging tools and deployment services without having to consider issues such as underlying infrastructure, communication protocols and security, and can quickly complete data access and environment deployment of the application system; after authorization by this embodiment, the application system can obtain data reported by the device, can quickly call the interface authentication, data service and other capabilities provided by this embodiment, and can also transmit data to the Internet of Things platform of this embodiment and third-party application systems through the message service API, and realize the interconnection and interoperability of various types of hardware devices and application systems based on the rule engine provided by this embodiment.

[0078] Example 2

[0079] This embodiment provides a rail transit crowd evacuation device based on the Internet of Things, including: an operating parameter acquisition module, a danger prediction module and a path planning module, wherein the operating parameter acquisition module is used to collect the operating parameters of rail transit equipment; the danger prediction module is used to predict danger based on the operating parameters; the path planning module is used to call the Dijkstra algorithm and plan the nearest escape path based on the operating parameters, warning signals and crowd density.

[0080] In order to enable passengers to obtain the nearest escape route in real time, this embodiment further includes: a third-party software access module, which is used to send the nearest escape route to the Internet of Things application or Internet of Things system.

[0081] For the specific implementation process of this embodiment, please refer to Example 1, which will not be described in detail here.

[0082] The above description is merely a preferred embodiment of the present invention and does not constitute any form of limitation to the present invention. Therefore, any modifications, equivalent changes, and modifications made to the above embodiments based on the technical essence of the present invention without departing from the content of the technical solution of the present invention shall still fall within the scope of the technical solution of the present invention.

Claims

1. A rail transit crowd evacuation method based on the Internet of Things, characterized in that: Including steps: Using the MQTT / HTTP protocol to access the rail transit equipment to obtain the operating parameters, the rail transit equipment includes: escalator operation status gateway, rolling shutter gateway, electronic guidance gateway, and guide light box gateway; predicting hazards based on the operating parameters; When a warning signal is obtained, the crowd density is calculated; The Dijkstra algorithm is called and the nearest escape route is planned in combination with the operating parameters, the warning signal and the crowd density.

2. The rail transit crowd evacuation method according to claim 1, characterized in that: It also includes the method for calculating crowd density: Get the number of people; Get the area of the evacuation passage; The population density is calculated based on the number of people and the area of the evacuation passage, where the population density is equal to the number of people divided by the area.

3. The rail transit crowd evacuation method according to claim 1, characterized in that: The warning signals include: The first type of warning is used to notify of danger; Category II warnings are used to warn of hazards that require treatment within forty-eight hours; The third type of warning is used to warn of hazards that need to be dealt with within twelve hours; Category 4 warnings are used to warn of hazards that need to be addressed within two hours; The fifth type of warning is used to warn of dangers that require immediate attention.

4. The rail transit crowd evacuation method according to claim 3, characterized in that: The step of calling the Dijkstra algorithm and planning the nearest escape route in combination with the warning signal and the crowd density includes the following steps: obtaining a first weight according to a category of the warning signal; obtaining a second weight according to the operating parameter; Obtaining a third weight according to the crowd density; The Dijkstra algorithm is called, and the first weight, the second weight, and the third weight are combined to calculate the shortest escape path.

5. The rail transit crowd evacuation method according to claim 1, characterized in that: The step of predicting the danger according to the operating parameters comprises the steps of: The operating parameters and whether a fault occurs under the operating parameters are used as inputs of a risk prediction model, and the risk prediction model is trained.

6. The rail transit crowd evacuation method according to claim 1, characterized in that: Also includes the steps: The nearest escape path is sent to an IoT application or IoT system.

7. The rail transit crowd evacuation method according to claim 6, characterized in that: The step of sending the nearest escape path to an IoT application or IoT system includes: The IoT application or the IoT system is accessed through a message service API and obtains the nearest escape route.

8. A rail transit crowd evacuation device based on the Internet of Things, characterized in that: The rail transit crowd evacuation method according to any one of claims 1 to 7 comprises: Operation parameter acquisition module, used to collect operation parameters of rail transit equipment; A hazard prediction module, configured to predict hazards based on the operating parameters; The path planning module is used to call the Dijkstra algorithm and plan the nearest escape path in combination with the operating parameters, the warning signal and the crowd density.

9. The rail transit crowd evacuation device according to claim 8, characterized in that: Also includes: The third-party software access module is used to send the nearest escape route to the Internet of Things application or Internet of Things system.

Images