Train emergency evacuation command method and system based on LED visible light communication

Abstract

The present application relates to the field of train emergency evacuation command, and more particularly to a train emergency evacuation command method and system based on LED visible light communication, when an emergency occurs in a train, an evacuation plan containing different position space mapping instructions is generated according to the accident type and position information; the space mapping instructions are converted into visible light modulation signals and area identification codes, and loaded onto the LED lighting lamps and lanterns at the corresponding positions to drive them to emit optical indication signals; the passenger flow density and light signal feedback at each position are monitored in real time, and the congestion probability of each position in the future preset time window is judged accordingly; if the congestion probability exceeds the probability threshold, the space mapping instructions of the corresponding position are updated. The present application can dynamically and adaptively guide passenger evacuation in adverse environments such as smoke obstruction, and effectively improve the safety and efficiency of evacuation.

Description

Technical Field

[0001] This application relates to the field of train emergency evacuation command technology, and in particular to a train emergency evacuation command method and system based on LED visible light communication. Background Technology

[0002] Currently, emergency train evacuations primarily rely on static directional signs, manual announcements, or onboard broadcast systems. However, when a train accident occurs inside a tunnel, radio signals are easily blocked or interfered with, and the broadcast system may fail. Simultaneously, dense smoke severely reduces visibility, making static signs difficult for passengers to identify effectively. Some solutions attempt to introduce LED visible light communication for dynamic guidance, such as pre-planning evacuation directions based on the accident location and emitting directional light signals via LED lights. However, these solutions typically only set the evacuation direction once in the initial stage, making it difficult to adaptively adjust to the actual flow of people during the evacuation process. This results in inconsistent evacuation efficiency and may even exacerbate congestion due to delayed instructions.

[0003] Existing dynamic evacuation plans typically assume that passengers can continuously and stably observe the optical indicator signals emitted by LED lights during evacuation, accurately perceiving subtle information such as color changes, gradual shifts in flashing frequency, or the direction of light flow. Based on this assumption, these plans achieve a smooth transition of instructions by gradually changing the state of the light signals. However, in actual train emergency evacuation scenarios, passengers are often in a state of high tension. When passengers miss crucial transition signals due to tension, smoke, or obstructed vision, misunderstandings of instructions are likely, and this can even lead to dangerous behaviors such as going the wrong way. Summary of the Invention

[0004] To address one or more problems in the prior art, the main objective of this application is to provide a train emergency evacuation command method and system based on LED visible light communication.

[0005] To achieve the aforementioned objectives, this application proposes a train emergency evacuation command method based on LED visible light communication, the method comprising: In response to the triggering of a train emergency, the system collects accident type and location information and generates an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations. The spatial mapping command is converted into a visible light modulation signal and a region identification code; According to the area identification code, the visible light modulation signal is loaded onto the LED lighting fixtures in the corresponding location information respectively; The LED lighting fixture is driven to emit an optical indication signal according to the visible light modulation signal; Real-time monitoring of pedestrian density and light signal feedback at various locations; and determination of the congestion probability at each location within a future preset time window based on the pedestrian density and light signal feedback. If the congestion probability exceeds the probability threshold based on the judgment result, the spatial mapping instruction at the corresponding location is updated.

[0006] This application also provides a train emergency evacuation command system based on LED visible light communication, including: The response acquisition module is used to respond to the triggering of train emergency events, collect accident type and location information, and generate an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations. The instruction conversion module is used to convert the spatial mapping instruction into a visible light modulation signal and a region identification code; The loading module is used to load the visible light modulation signal onto the LED lighting fixtures in the corresponding location information according to the area identification code; The driving module is used to drive the LED lighting fixture to emit an optical indication signal according to the visible light modulation signal; The monitoring module is used to monitor the pedestrian density and light signal feedback at each location in real time, and to determine the congestion probability of each location within a preset time window based on the pedestrian density and light signal feedback. The update module is used to update the spatial mapping instruction at the corresponding location if the congestion probability exceeds the probability threshold based on the judgment result.

[0007] This application also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of any of the methods described above.

[0008] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of any of the methods described above.

[0009] This application presents a train emergency evacuation command method and system based on LED visible light communication. In the event of an emergency, the train can directly utilize the existing LED lighting system within the carriages for evacuation command, without relying on radio communication or additional dedicated display equipment. It remains reliable even in extreme environments such as tunnels and areas with dense smoke. By monitoring pedestrian density and light signal feedback at various locations in real time, the system can predict congestion trends in the short term and proactively adjust the evacuation direction of corresponding areas before congestion actually occurs. This predictive dynamic adjustment avoids the lag effect of static indications or passive responses, effectively reducing the risk of crowd accumulation and trampling in bottleneck areas such as carriage connections and exits. Simultaneously, the entire closed-loop process of monitoring, prediction, and updating continuously operates, ensuring that the evacuation plan always matches the actual pedestrian flow on site, significantly improving evacuation efficiency and safety. Compared to traditional broadcasts, static light boxes, or one-time set directional lights, this method is more flexible and intelligent, adapting to rapidly changing passenger flow distribution in emergencies and providing passengers with clear, reliable, and dynamic visual guidance. Attached Figure Description

[0010] Figure 1 This is a flowchart illustrating a train emergency evacuation command method based on LED visible light communication according to an embodiment of this application. Figure 2 This is a flowchart illustrating another embodiment of the train emergency evacuation command method based on LED visible light communication in this application. Figure 3 This is a schematic block diagram of a train emergency evacuation command system based on LED visible light communication according to an embodiment of this application; Figure 4 This is a schematic block diagram of the structure of a computer device according to an embodiment of this application.

[0011] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with the embodiments and with reference to the accompanying drawings. Detailed Implementation

[0012] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0013] Reference Figure 1 This application provides a train emergency evacuation command method based on LED visible light communication, the method comprising: S1. In response to the triggering of a train emergency, collect accident type and location information, and generate an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations; S2. Convert the spatial mapping instruction into a visible light modulation signal and a region identification code; S3. Based on the area identification code, the visible light modulation signal is loaded onto the LED lighting fixtures in the corresponding location information respectively; S4. Drive the LED lighting fixture to emit an optical indication signal according to the visible light modulation signal; S5. Monitor the pedestrian density and light signal feedback at each location in real time, and determine the congestion probability of each location within a future preset time window based on the pedestrian density and light signal feedback. S6. Based on the judgment result, if the congestion probability exceeds the probability threshold, then update the spatial mapping instruction at the corresponding location.

[0014] As described in steps S1-S3 above, this method begins operation when an emergency occurs on the train, such as a fire, derailment, or stop in a tunnel. The entire process can be executed by the train's central control unit or a dedicated emergency communication controller. First, it's necessary to determine the type of accident and which carriage or area it occurred in. This step can be accomplished using the train's built-in fire detectors, smoke sensors, vehicle attitude sensors, or the driver's manual alarm device. After collecting the accident type and location information, an evacuation plan is generated. The core is assigning a spatial mapping instruction to each carriage or each area requiring guidance. Simply put, a spatial mapping instruction tells passengers in that area which direction to evacuate, such as moving forward towards the front door or backward towards the rear door. Different locations may receive completely different instructions, as carriages closer to the accident point need to move away from the danger, while carriages further away need to move towards the safety exits. Next, the spatial mapping instruction is converted into a light signal suitable for LED lighting. The spatial mapping instruction for each area is first encoded to obtain a visible light modulated signal, and a zone identification code is attached to this signal. The area identification code acts like an identification tag for each carriage or each light, used to distinguish which specific location the signal belongs to. Visible light modulation signals are electrical signals that carry information by changing the brightness, flicker frequency, or pulse width of LED lights. Their modulation frequency is higher than the flicker frequency that the human eye can distinguish, so passengers will not perceive flicker when looking at the lights normally, and the lighting function is unaffected. Then, based on the area identification code, the corresponding visible light modulation signal is loaded onto the LED lighting fixtures within that area. In this way, each LED light or group of LED lights only receives the instruction signal for its own area, making the light information emitted by different carriages different from each other.

[0015] As described in steps S4-S6 above, after the signal loading is completed, the LED lights are driven to emit optical indication signals according to the visible light modulation signal. These optical indication signals can be visual light flow direction, color changes, or flashing with a specific rhythm. Passengers can understand the current evacuation direction by seeing these light signals. Because the LED lights are already installed in the carriage, there is no need to install additional display screens or dedicated communication equipment, so this method is both practical and economical. While emitting light signals, the flow density of people and light signal feedback at each location must be monitored in real time. The flow density can be estimated by receiving the attenuation signal from the LED lights being blocked by people using photodetectors installed in the carriage. The light signal feedback refers to the change in light intensity or reception quality received by the detector. Based on this real-time data, it can be determined whether congestion will occur at each location within a very short time window in the future, such as 5 or 10 seconds. This is a predictive mechanism, rather than dealing with congestion after it has already occurred. For example, if the flow density of people in a certain carriage is rising rapidly and the light signal feedback shows that the frequency of obstruction is increasing, it can be deduced that the carriage will be severely congested in a few seconds. If the prediction results show that the probability of congestion at a certain location exceeds a pre-set probability threshold, the spatial mapping instructions for that location are proactively updated. The update might change the original forward evacuation to a backward evacuation, or to slow down and wait, or even prohibit passage. Through this proactive adjustment, the flow of people can be altered before congestion actually develops, thus preventing it from escalating. The entire process is continuously cyclical, with instructions constantly revised based on the latest actual passenger flow during evacuation, ensuring the evacuation plan always matches the actual situation. In this way, even in extreme environments such as radio signal blockage in tunnels, dense smoke, or broadcast failure, the train can still use its existing LED lighting system to dynamically and proactively guide each passenger to evacuate along the most rational path, thereby reducing the risk of congestion and stampedes and improving overall evacuation efficiency.

[0016] As described above, using this method, trains can directly utilize the existing LED lighting system within the carriages for evacuation guidance during emergencies, without relying on radio communication or additional dedicated display equipment. This remains reliable even in extreme environments such as tunnels and areas with dense smoke. By monitoring pedestrian density and light signal feedback at various locations in real time, the system can predict congestion trends in the short term and proactively adjust evacuation directions in corresponding areas before congestion actually occurs. This proactive dynamic adjustment avoids the lag effect of static instructions or passive responses, effectively reducing the risk of crowds accumulating and trampling in bottleneck areas such as carriage connections and exits. Simultaneously, the entire closed-loop process of monitoring, prediction, and updating continues, ensuring that the evacuation plan always matches the actual pedestrian flow on-site, significantly improving evacuation efficiency and safety. Compared to traditional broadcasts, static light boxes, or one-time set directional lights, this method is more flexible and intelligent, adapting to rapidly changing passenger flow distribution in emergencies and providing passengers with clear, reliable, and dynamic visual guidance.

[0017] Reference Figure 2 In one embodiment, the method for collecting accident type and location information and generating an evacuation plan includes: S11. Based on the accident type and location information, the train is divided into a danger zone, a buffer zone, and a safe zone, wherein the danger zone includes the accident location and the adjacent carriages of the accident location; S12. Based on the division results, determine the distance and path direction between each carriage and the nearest safety exit, and generate spatial mapping instructions for each carriage; S13. When the evacuation directions of the spatial mapping instructions of adjacent carriages are opposite, the boundary between the two carriages shall be marked as an uncrossable boundary.

[0018] As described above, when generating an evacuation plan, this method divides the train carriages into three distinct zones based on the collected accident type and location. The carriage where the accident occurred, along with one or two adjacent carriages, is marked as the danger zone, as it is closest to the source of the hazard. Outside the danger zone, areas closer to the exit and temporarily less affected by the accident are designated as safe zones, while areas in between serve as buffer zones. This division allows the system to adopt different command strategies for areas with different risk levels. For example, danger zones need to be cleared as quickly as possible, buffer zones can be cleared more slowly, and safe zones can guide passengers to detour. After dividing the zones, the system calculates the straight-line distance or the path distance along the train aisle from each carriage to the nearest safe exit and determines whether the most reasonable direction from that carriage to the exit is forward or backward. Based on these distances and directions, specific spatial mapping instructions can be generated for each carriage, instructing passengers whether they should evacuate towards the front or rear of the train. Because different carriages are located at varying distances from the exits, some carriages may be instructed to move forward while others are instructed to move backward, which is normal. However, if two adjacent carriages receive opposite evacuation directions—for example, carriage 3 is instructed to move backward while carriage 4 is instructed to move forward—the junction between these two carriages becomes a potential hazard. Passengers moving from opposite directions are prone to congestion or even collisions at the junction. To avoid this, the system marks a non-crossable boundary at the junction of two carriages. This boundary is not a physical barrier but a restriction at the instruction level, meaning that passengers in one carriage should not attempt to cross this boundary to enter the other carriage. In this way, although the evacuation directions of the two carriages are opposite, passengers are guided to move away from the boundary, reducing the risk of congestion at the junction. In this manner, the entire evacuation plan not only considers the spatial relationship between each carriage and the exit but also proactively prevents potential head-on collisions between adjacent carriages, making the evacuation path more rational and safer.

[0019] In one embodiment, the method for collecting accident type and location information and generating an evacuation plan further includes: Obtain the spatial mapping command for adjacent carriages; When the evacuation directions of the spatial mapping instructions of adjacent carriages point to each other, it is determined to be a head-on conflict. In response to the head-on collision, an instruction to adjust the spatial mapping of one of the carriages is given to reverse the evacuation directions of adjacent carriages.

[0020] As mentioned above, during the evacuation plan generation process, a further check is performed to determine if there are any head-on conflicts between the instructions of adjacent carriages. Specifically, after the system has generated spatial mapping instructions for each carriage, it obtains the evacuation directions of each pair of adjacent carriages. If it is found that the evacuation directions of two adjacent carriages are pointing towards each other, for example, the instruction for carriage 3 is to move backward and the instruction for carriage 4 is to move forward, then the passengers of the two carriages will move towards each other, creating a head-on conflict at the junction. If this situation is not addressed, it can easily lead to a blockage or even a stampede at the junction. Faced with such head-on conflicts, the system does not allow them to exist but actively adjusts the spatial mapping instructions of one carriage. The principle of adjustment is to make the evacuation directions of the two carriages ultimately opposite rather than opposite. For example, if the instruction for carriage 3 is changed to forward, then both carriages will move forward. Although the directions are consistent, in practice, it still needs to be determined in conjunction with the exit location. A more typical approach is to change the direction of the carriage pointing towards the other carriage to move away from the other carriage, so that the passengers of both carriages evacuate in a direction away from the junction. After this adjustment, the evacuation directions of adjacent carriages are no longer pointing in opposite directions, thus eliminating head-on conflicts. This approach resolves potential congestion points by modifying light signal commands. Moreover, the adjustment decision is based on the real-time command status of adjacent carriages, resulting in a rapid response time, making it suitable for real-time operation during emergency evacuations.

[0021] In one embodiment, the method for updating the spatial mapping instruction at the corresponding position includes: Based on the congestion probability, analyze the extent to which the congestion probability exceeds the probability threshold; Based on the amplitude, the spatial mapping instruction is divided into multiple intermediate states, each intermediate state corresponding to a sub-instruction, wherein the number of intermediate states is positively correlated with the amplitude; The time interval is determined based on the amplitude, and the space mapping instruction is updated to the next intermediate state sub-instruction sequentially according to the time interval until the target sub-instruction is reached, wherein the length of the time interval is negatively correlated with the amplitude.

[0022] As mentioned above, when the predicted congestion probability at a certain location exceeds a pre-set probability threshold, the spatial mapping instruction for that location is not immediately switched to the final target instruction. Instead, the extent to which the congestion probability exceeds the threshold is assessed. If the exceedance is small, the situation is not too urgent and can be handled gradually; if the exceedance is large, the congestion risk is high and adjustments need to be made as soon as possible. Based on the magnitude of the exceedance, the process from the current instruction to the final target instruction is broken down into several intermediate states. Each intermediate state corresponds to a sub-instruction, such as changing from normal passage to deceleration warning, from deceleration warning to standby and slowing down, and finally from standby and slowing down to prohibiting passage. Multiple transitional instructions can be inserted in between. Then, the instructions are updated step by step according to a pre-set time interval, switching to the next intermediate state after each time interval, until the target instruction is finally reached. The larger the exceedance, the shorter the time interval between each intermediate state, and the faster the entire update process. Alternatively, the number of intermediate states can be increased to make each step more subtle and allow passengers to adapt more easily to the gradual adjustment of instructions. The advantage of this approach is that when the congestion risk is low, the instructions change smoothly, preventing passengers from panicking due to sudden changes; when the congestion risk is high, the instructions switch quickly, effectively preventing crowds from continuing to flood into congested areas. Compared to abrupt, one-step adjustments, this phased approach, adjusting speed according to risk level, better meets the actual needs of emergency evacuation, accommodating both passengers' psychological adaptability and ensuring necessary response speed. When the predicted congestion probability at a certain location exceeds a pre-set probability threshold, the extent to which this probability exceeds the threshold is first assessed. The magnitude of the exceedance reflects the urgency of the current congestion risk. Based on the magnitude of the exceedance, the process from the current instruction to the final target instruction is broken down into several intermediate states, each corresponding to a sub-instruction. For example, from normal passage to deceleration warning, from deceleration warning to standby and slow down, and finally from standby and slow down to prohibit passage. Multiple transitional instructions can be inserted as needed. Subsequently, the time interval is determined according to the magnitude, updating the instructions step by step, switching to the next intermediate state after each time interval, until the final target instruction is achieved. Among these, the magnitude of the congestion probability exceeding the threshold is negatively correlated with the length of the time interval; that is, the larger the exceedance, the shorter the time interval between each intermediate state, and the faster the entire update process is completed; the smaller the exceedance, the longer the time interval, and the smoother the update process. Meanwhile, the magnitude of the exceedance is positively correlated with the number of intermediate states; that is, the larger the exceedance, the more intermediate states there are, and the more subtle the changes at each step; the smaller the exceedance, the fewer intermediate states there are, and the more direct the changes.

[0023] In one embodiment, the method for updating the spatial mapping instruction at the corresponding position further includes: Record the number of times the spatial mapping command for each carriage changes direction within a preset time window; When the number of times any carriage changes direction exceeds a preset threshold, and the passenger density of the carriage and its adjacent carriages is lower than a preset density threshold, it is determined to be a decision oscillation. In response to the determination, the prediction and instruction updates for the congestion probability of the carriage and its adjacent carriages are stopped. The spatial mapping command of the carriage and its adjacent carriages is locked to a static direction based on absolute distance, and is continuously locked for a preset stable duration, wherein the absolute distance refers to the straight-line distance from the center of the carriage to each safety exit.

[0024] As mentioned above, a subtle problem can occur during the dynamic adjustment of spatial mapping instructions: the evacuation direction of the same carriage can be changed back and forth several times in a short period of time. For example, it might be changed to forward, then backward a few seconds later, and then back to forward again a few seconds later. This situation is often not caused by actual congestion changes, but rather by the repeated jumps in prediction results due to competition between two exits that are roughly the same distance apart, a phenomenon known as decision oscillation. To prevent this oscillation from continuing indefinitely, this embodiment records the number of times the evacuation direction of each carriage has been changed within a preset time window, such as the past 30 seconds. Simultaneously, the passenger density of that carriage and its adjacent carriages is observed. If the number of direction changes exceeds a pre-set threshold, and the passenger density in these carriages is not particularly high, it indicates that the oscillation is not caused by extreme congestion, but rather by a problem with the decision-making logic itself. Once decision oscillation is determined to have occurred, congestion probability predictions and instruction updates for these carriages are discontinued. Continuing to predict would only exacerbate the chaotic direction changes. Instead, the spatial mapping instructions for these carriages are locked to a static direction based on absolute distance. Absolute distance refers to the straight-line distance from the center of each carriage to each of the front and rear safety exits. The locked direction is directed towards the exit closest to it. This static direction remains stable and does not change with real-time passenger density. The locking action lasts for a preset stable period, such as two minutes, to allow the evacuation process to stabilize. After the stable period ends, if the situation permits, normal dynamic prediction and updates are resumed. In this way, even if decision-making falters, evacuation command will not fall into an endless state of chaotic repetition; passengers will always see a consistent and unchanging guiding direction, thus ensuring basic order during the evacuation.

[0025] It's worth noting that during implementation, the following situation might occur: A train is stopped in a winding tunnel. A particular carriage, such as carriage 5, is approximately 150 meters from the front emergency exit and 160 meters from the rear emergency exit—the distances to the two exits are very close. Initially, the system assigns evacuation directions based on the distance of each carriage to the nearest exit. Carriage 5 is instructed to move forward, carriage 4 in front of it is also instructed to move forward, and carriage 6 behind it is instructed to move backward. This seemingly reasonable plan will encounter problems after evacuation has been underway for some time. As the crowd moves forward, the passenger density in carriage 4 increases rapidly because too many passengers are accumulating at the front exit. The system detects this trend and predicts that carriage 4 will become severely congested in a few seconds. Therefore, it proactively updates the instructions for carriage 4, changing it to evacuate backward. Passengers who were originally moving forward turn around and meet the flow of people evacuating backward from carriage 6 in carriage 5. The passenger density in carriage 5 rapidly increased, and the system predicted impending congestion there, changing the evacuation order for carriage 5 to forward. The passenger flow then reversed course again, exacerbating congestion in carriage 4, prompting the system to change the evacuation order back to the rear. This cycle repeated itself, with the evacuation direction constantly shifting between forward and backward, creating a periodic oscillation. This oscillation wasn't caused by an inability to alleviate the actual congestion, but rather by the close proximity of the two exits. Each prediction and adjustment focused only on the immediate congestion, ignoring the chain reaction that its actions would trigger in adjacent carriages. Once the oscillation began, it often didn't subside on its own; instead, it continued, causing passengers to see flashing lights that moved back and forth, leading to confusion and panic.

[0026] To address this situation, this method employs a decision-making oscillation detection and locking mechanism. Specifically, it records the number of times the evacuation direction of each carriage is changed within a given period. If the number of direction changes for a carriage exceeds a preset threshold, and the passenger density in that carriage and its adjacent carriages is not high, it indicates that the current situation is not one of extreme congestion, but rather a problem with the decision-making logic itself. In this case, the prediction of congestion probability and the update of instructions for these carriages are proactively stopped, and no further direction adjustments are made. Simultaneously, the evacuation direction of these carriages is locked to a static direction based on absolute distance. That is, each carriage points to the exit closer to its two exits in a straight line, and this direction no longer changes with real-time passenger density. The locking lasts for a preset stable period, allowing the entire evacuation process to calm down before deciding whether to resume dynamic adjustments based on the situation. In this way, even if the train is in a special alignment such as a curved tunnel, and even if the distance between the two exits is almost equal, the evacuation command will not fall into endless oscillations. Passengers will always see a stable and unchanging directional guide, thus ensuring basic order and safety during the evacuation.

[0027] In one embodiment, passengers' visual state differs significantly from normal during actual evacuation. Under normal circumstances, people can steadily observe surrounding light signals, accurately discerning subtle color changes, gradual shifts in flashing frequency, or the direction of light flow. However, in an emergency, panic causes a sharp increase in blinking frequency, from the usual 15-20 times per minute to 60 times per minute or even higher, with each blink lasting longer. Simultaneously, visual attention becomes highly narrowed, similar to tunnel vision; passengers often only focus on the door or exit directly in front, rarely looking up to carefully observe the changes in LED lights on the ceiling. When spatial mapping instructions switch gradually in stages, such as transitioning from a slow-flashing green state to a fast-flashing red state, there are intermediate transitional phases like deceleration warnings and waiting / gradual movement. If the critical transition moment happens to occur in the instant a passenger blinks or their gaze shifts, these intermediate states may be completely missed. What passengers actually see is not a smooth transition, but a direct jump from one state to another, such as going directly from normal passage to a fast-flashing red "no passage" sign. This sudden change can easily trigger panic-induced sudden stops or even reversing.

[0028] To address this problem caused by the discontinuity of human visual sampling, this method also includes: The step of dividing the space mapping instruction into multiple intermediate states includes: A superimposed optical indication signal is generated for each intermediate state. The superimposed optical indication signal contains the base signal of the current stage and the auxiliary signal of the adjacent stage. The duration of each intermediate state is controlled to be no less than the preset minimum gaze duration; When the detected pedestrian flow speed at the location decreases by more than a preset speed change threshold within the updated preset time window, the signal reverts to the previous intermediate state, and the duration of the current stage is extended by a preset extension time.

[0029] As mentioned above, in the process of breaking down spatial mapping instructions into multiple intermediate states and gradually switching between them, a special design is incorporated into the light signal emitted in each intermediate state to ensure that passengers can accurately perceive the changes in instructions even under stress or poor visibility. Specifically, in addition to the base signal of the current stage, the light signal of each stage also superimposes an auxiliary signal from the adjacent stage. For example, if the current stage is a solid green light indicating normal passage, and the next stage is a slow yellow flashing light indicating a deceleration warning, then a very weak slow yellow flashing component is superimposed on the solid green light, allowing passengers to sense the impending change in direction or state in advance. This superposition does not interfere with the correct understanding of the current instruction but serves as a warning. Furthermore, the duration of each intermediate state cannot be too short; it must be at least longer than the time it takes for a person to blink normally or for their gaze to briefly shift in an emergency. A minimum gaze duration is set, such as 0.5 or 0.8 seconds, to ensure that even if passengers blink frequently due to panic or their gaze wavers, they have at least one complete opportunity to capture the light signal content of the current stage. During the gradual switching process, the movement speed of people at that location is also monitored simultaneously. If, within a pre-defined time window after an updated instruction, the flow of people noticeably slows down—for example, by exceeding a pre-set speed change threshold—this usually indicates that passengers are confused or panicked by the change in instructions, potentially leading to slowing down, hesitation, or even moving in the wrong direction. In this case, instead of continuing to transition, the system proactively reverts to the previous intermediate state's light signal and extends the current signal's duration by a pre-defined time, allowing passengers more time to adjust to the change before attempting to transition to the next stage. Through this layered warning system, ensuring minimum attention time, and the mechanism of extending the transition during speed decreases, even if passengers are panicked, blinking frequently, have limited vision, or are distracted, they can reliably receive the complete transition instructions, reducing the sense of abrupt change caused by missing intermediate states, thereby lowering the risk of chaos and accidents during evacuation.

[0030] In one embodiment, the step of driving the LED lighting fixture to emit an optical indication signal according to the visible light modulation signal includes: According to the evacuation direction in the spatial mapping instruction, control the LED lighting fixtures in the same area to be lit sequentially along the evacuation direction; The visual flow patterns of LED lighting fixtures in different areas are controlled to flow in opposite directions, which is used to distinguish the evacuation directions of different areas.

[0031] As mentioned above, when driving LED lights to emit optical indication signals, a dynamic light pattern is used to help passengers intuitively understand the evacuation direction. Specifically, based on the evacuation direction specified by the current carriage's spatial mapping instructions, multiple LED lights in the same area are controlled to illuminate sequentially along that direction. For example, if the evacuation direction is forward, the lights closest to the front of the carriage will illuminate first, then sequentially illuminate backward, making it appear to the human eye as if light points are flowing from back to front. Passengers, seeing the direction of the light pattern, naturally know which direction to move in, without needing to identify colors or patterns. Simultaneously, to prevent passengers from different carriages from wandering around, the flowing light patterns in adjacent areas are controlled to be opposite directions. For example, the light pattern in carriage 3 flows from back to front, indicating that passengers should move forward; while the light pattern in carriage 4 flows from front to back, indicating that passengers should move backward. The flowing light patterns in the two directions create a clear directional contrast at the carriage boundaries, allowing passengers to immediately see the evacuation direction of their own carriage and reducing the likelihood of misjudgment due to light signal interference from adjacent carriages.

[0032] In one feasible embodiment, the method for updating the spatial mapping instruction at the corresponding position further includes: The time series of the light signal feedback or the crowd density is obtained, and the actual direction of crowd movement at the current location is determined based on the time series of the light signal feedback or the crowd density. Obtain the evacuation direction from the space mapping instruction to be updated; Compare the actual direction of pedestrian movement with the evacuation direction in the spatial mapping instruction to be updated, and determine whether they are opposite. If the actual direction of pedestrian movement is opposite to the evacuation direction, the location will be marked as an instruction failure zone, and the LED lighting fixtures at the current location will be switched to the preset emergency warning light mode. A command failure signal is sent to the management terminal to trigger the re-collection of accident type and location information, and the evacuation plan is updated based on the re-collection results.

[0033] As mentioned above, during actual evacuation, the data obtained from light signal feedback or crowd density monitoring is not only used to predict congestion but also to determine the actual direction of passenger movement. Specifically, the light signal feedback or crowd density data collected over a period of time is arranged into a sequence in chronological order. From this sequence, it is analyzed whether the current passenger flow in the carriage is moving forward or backward, i.e., the actual direction of passenger movement. Simultaneously, the evacuation direction specified in the upcoming updated spatial mapping instructions is obtained; for example, if the instruction requires passengers to move forward. Then, the actual direction of passenger movement is compared with the evacuation direction specified in the instruction to see if they are opposite. If the actual passenger flow is moving backward, but the instruction requires forward movement, the two are opposite. There could be many reasons for this. Perhaps the smoke sensor misreported the location of the fire source, causing the system to believe the danger was ahead when it was actually behind. Perhaps the fire spread too quickly, making the originally safe direction dangerous, and passengers instinctively or visually chose to escape in the opposite direction. Regardless of the reason, continuing to issue light signals according to the original instruction and forcibly requiring passengers to move in the opposite direction will only exacerbate the chaos and may even lead to more serious consequences. Therefore, if the actual flow of people is detected to be opposite to the commanded direction, this location is marked as a command failure zone. Simultaneously, the LED lights in this area are switched to a preset emergency warning light mode, such as a high-frequency flashing red light. This light signal is not for directional guidance, but to alert passengers to danger and to stop moving in the current direction. In addition, a command failure signal is sent to the driver's cab, dispatch center, or on-site command personnel, triggering a re-collection of accident type and location information. This may involve rereading data from various sensors or requesting manual verification of the actual situation. Based on the re-collected results, an evacuation plan is regenerated and the corresponding spatial mapping commands are updated. In this way, when it is found that the commands issued are seriously contradictory to the actual behavior of passengers, the system will not blindly adhere to the original commands or simply change the commands to follow the flow of people. Instead, it will acknowledge that the current commands may have failed, switch to warning mode, and request a reassessment, thereby preventing passengers from being led to more dangerous areas due to erroneous commands.

[0034] Reference Figure 3 This application also provides a train emergency evacuation command system based on LED visible light communication, including: The response acquisition module 1 is used to collect accident type and location information in response to the triggering of a train emergency, and generate an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations. Instruction conversion module 2 is used to convert the spatial mapping instruction into a visible light modulation signal and a region identification code; Loading module 3 is used to load the visible light modulation signal onto the LED lighting fixtures in the corresponding location information according to the area identification code; Drive module 4 is used to drive the LED lighting fixture to emit an optical indication signal according to the visible light modulation signal; Monitoring module 5 is used to monitor the crowd density and light signal feedback at each location in real time, and to determine the congestion probability of each location within a preset time window based on the crowd density and light signal feedback. The update module 6 is used to update the spatial mapping instruction at the corresponding location if the congestion probability exceeds the probability threshold based on the judgment result.

[0035] As described above, it is understood that each component of the train emergency evacuation command system based on LED visible light communication proposed in this application can realize the function of any of the train emergency evacuation command methods based on LED visible light communication as described above, and the specific structure will not be repeated.

[0036] Reference Figure 4 This application also provides a computer device, which may be a server, and its internal structure may be as follows: Figure 4 As shown, the computer device includes a processor, memory, network interface, and database connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and database. The internal memory provides the environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores monitoring data and other data. The network interface is used for communication with external terminals via a network connection. When the computer program is executed by the processor, it implements a train emergency evacuation command method based on LED visible light communication.

[0037] The processor described above executes the train emergency evacuation command method based on LED visible light communication, including: in response to the triggering of a train emergency, collecting accident type and location information, and generating an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations; converting the spatial mapping instructions into visible light modulation signals and area identification codes; loading the visible light modulation signals onto LED lighting fixtures within the corresponding location information according to the area identification codes; driving the LED lighting fixtures to emit optical indication signals according to the visible light modulation signals; monitoring the pedestrian density and light signal feedback at each location in real time, and determining the congestion probability of each location within a future preset time window based on the pedestrian density and light signal feedback; and updating the spatial mapping instructions for the corresponding location if the congestion probability exceeds a probability threshold based on the determination result.

[0038] One embodiment of this application also provides a computer-readable storage medium storing a computer program. When executed by a processor, the computer program implements a train emergency evacuation command method based on LED visible light communication, including the following steps: in response to the triggering of a train emergency, collecting accident type and location information, generating an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations; converting the spatial mapping instructions into visible light modulation signals and area identification codes; loading the visible light modulation signals onto LED lighting fixtures within the corresponding location information according to the area identification codes; driving the LED lighting fixtures to emit optical indication signals according to the visible light modulation signals; monitoring the pedestrian density and light signal feedback of each location information in real time, and determining the congestion probability of each location within a future preset time window based on the pedestrian density and light signal feedback; and updating the spatial mapping instructions for the corresponding location if the congestion probability exceeds a probability threshold based on the determination result.

[0039] Those skilled in the art will understand that all or part of the processes in the methods of the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments of the above methods. Any references to memory, storage, databases, or other media used in this application and in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link DRAM (SLDRAM), RAMbus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0040] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, apparatus, article, or method. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, apparatus, article, or method that includes that element.

[0041] The above description is only a preferred embodiment of this application and does not limit the patent scope of this application. Any equivalent structural or procedural changes made based on the content of this application's specification and drawings, or direct or indirect applications in other related technical fields, are similarly included within the patent protection scope of this application.

Claims

1. A train emergency evacuation command method based on LED visible light communication, characterized in that, The method includes: In response to the triggering of a train emergency, the system collects accident type and location information and generates an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations. The spatial mapping command is converted into a visible light modulation signal and a region identification code; According to the area identification code, the visible light modulation signal is loaded onto the LED lighting fixtures in the corresponding location information respectively; The LED lighting fixture is driven to emit an optical indication signal according to the visible light modulation signal; Real-time monitoring of pedestrian density and light signal feedback at various locations; and determination of the congestion probability at each location within a future preset time window based on the pedestrian density and light signal feedback. If the congestion probability exceeds the probability threshold based on the judgment result, the spatial mapping instruction at the corresponding location is updated.

2. The train emergency evacuation command method based on LED visible light communication according to claim 1, characterized in that, The method for collecting accident type and location information and generating an evacuation plan includes: Based on the accident type and location information, the train is divided into a danger zone, a buffer zone, and a safe zone, wherein the danger zone includes the accident location and the adjacent carriages at the accident location; Based on the division results, the distance and path direction between each carriage and the nearest safety exit are determined, and spatial mapping instructions for each carriage are generated. When the evacuation directions of the spatial mapping instructions of adjacent carriages are opposite, the boundary between the two carriages is marked as an uncrossable boundary.

3. The train emergency evacuation command method based on LED visible light communication according to claim 2, characterized in that, The method for collecting accident type and location information and generating an evacuation plan further includes: Obtain the spatial mapping command for adjacent carriages; When the evacuation directions of the spatial mapping instructions of adjacent carriages point to each other, it is determined to be a head-on conflict. In response to the head-on collision, an instruction to adjust the spatial mapping of one of the carriages is given to reverse the evacuation directions of adjacent carriages.

4. The train emergency evacuation command method based on LED visible light communication according to claim 1, characterized in that, The method for updating the spatial mapping instruction at the corresponding position includes: Based on the congestion probability, analyze the extent to which the congestion probability exceeds the probability threshold; Based on the amplitude, the spatial mapping instruction is divided into multiple intermediate states, each intermediate state corresponding to a sub-instruction, wherein the number of intermediate states is positively correlated with the amplitude; The time interval is determined based on the amplitude, and the space mapping instruction is updated to the next intermediate state sub-instruction sequentially according to the time interval until the target sub-instruction is reached, wherein the length of the time interval is negatively correlated with the amplitude.

5. The train emergency evacuation command method based on LED visible light communication according to claim 4, characterized in that, The method further includes: updating the spatial mapping instruction at the corresponding position. Record the number of times the spatial mapping command for each carriage changes direction within a preset time window; When the number of times any carriage changes direction exceeds a preset threshold, and the passenger density of the carriage and its adjacent carriages is lower than a preset density threshold, it is determined to be a decision oscillation. In response to the determination, the prediction and instruction updates for the congestion probability of the carriage and its adjacent carriages are stopped. The spatial mapping command of the carriage and its adjacent carriages is locked to a static direction based on absolute distance, and is continuously locked for a preset stable duration, wherein the absolute distance refers to the straight-line distance from the center of the carriage to each safety exit.

6. The train emergency evacuation command method based on LED visible light communication according to claim 4, characterized in that, The step of dividing the space mapping instruction into multiple intermediate states includes: A superimposed optical indication signal is generated for each intermediate state. The superimposed optical indication signal contains the base signal of the current stage and the auxiliary signal of the adjacent stage. The duration of each intermediate state is controlled to be no less than the preset minimum gaze duration; When the detected pedestrian flow speed at the location decreases by more than a preset speed change threshold within the updated preset time window, the signal reverts to the previous intermediate state, and the duration of the current stage is extended by a preset extension time.

7. The train emergency evacuation command method based on LED visible light communication according to claim 1, characterized in that, The step of driving the LED lighting fixture to emit an optical indication signal according to the visible light modulation signal includes: According to the evacuation direction in the spatial mapping instruction, control the LED lighting fixtures in the same area to be lit sequentially along the evacuation direction; The visual flow patterns of LED lighting fixtures in different areas are controlled to flow in opposite directions, which is used to distinguish the evacuation directions of different areas.

8. A train emergency evacuation command system based on LED visible light communication, characterized in that, include: The response acquisition module is used to respond to the triggering of train emergency events, collect accident type and location information, and generate an evacuation plan, wherein the evacuation plan includes spatial mapping instructions for different locations. The instruction conversion module is used to convert the spatial mapping instruction into a visible light modulation signal and a region identification code; The loading module is used to load the visible light modulation signal onto the LED lighting fixtures in the corresponding location information according to the area identification code; The driving module is used to drive the LED lighting fixture to emit an optical indication signal according to the visible light modulation signal; The monitoring module is used to monitor the pedestrian density and light signal feedback at each location in real time, and to determine the congestion probability of each location within a preset time window based on the pedestrian density and light signal feedback. The update module is used to update the spatial mapping instruction at the corresponding location if the congestion probability exceeds the probability threshold based on the judgment result.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

Images