A control method, device, medium and train for a train

Abstract

The present invention discloses a control method, device, medium and train for a train, which is applicable to the technical field of train driving safety. By analyzing the driver's face information to determine the current state of the train, when the train is in an active state, obtain the operation state of the train, determine the driver's driving state through face information analysis, and then comprehensively determine the driver's driving behavior based on the current state, operation state and driving state, and adopt corresponding warning and control mechanisms through the supervision of the driving behavior. Activating the train according to the face information does not require separate key insertion, saving the driver's key operation time. According to the face information and the comprehensively determined driving behavior, the train then performs corresponding warning mechanism and control mechanism processing, avoiding the wrong touch caused by the driver continuously pressing the vigilance case or the foot pedal button device, simplifying the driver's operation steps, and improving driving safety.

Description

Technical Field

[0001] The present invention relates to the technical field of train driving safety, and particularly to a control method, device, medium and train for a train. Background Art

[0002] As one of the main factors leading to traffic accidents, fatigue driving poses a great threat to the lives and property safety of drivers and pedestrians. Therefore, how to effectively prevent fatigue driving and minimize various losses caused thereby has great practical significance.

[0003] During the train running process, in order to prevent the driver from fatigue driving, a vigilance button and a vigilance pedal device are set, and the driver needs to intermittently operate the button and the device (for example, operate once every 6 - 30 s). This method is rather cumbersome for the driver. In case of an emergency, the driver may ignore the current vigilance operation or wrongly touch the relevant operations of the emergency, resulting in other events during the running process and making the running unsafe.

[0004] Therefore, how to improve the safety of train running is an urgent problem to be solved by those skilled in the art. Summary of the Invention

[0005] The purpose of the present invention is to provide a control method, device, medium and train for a train, which can avoid the wrong touch caused by the driver continuously pressing the vigilance button or the pedal button device, simplify the operation steps of the driver, and improve the driving safety.

[0006] To solve the above technical problems, the present invention provides a control method for a train, including:

[0007] Collect the face information of the driver according to a time interval, and determine the current state of the train according to the face information collected for the first time, where the current state includes an activation state and a non - activation state;

[0008] When the train is in the activation state, obtain the operation state of the train, and determine the driving state of the driver according to the face information;

[0009] Determine the driving behavior of the driver according to the current state, operation state and driving state;

[0010] Adopt corresponding warning mechanisms and control mechanisms for the train according to the driving behavior.

[0011] Preferably, determining the current state of the train according to the face information collected for the first time includes:

[0012] Match the face information with the face information database pre - stored in the train to determine the authority of the driver;

[0013] When the permission is an operation permission, the current state is determined based on the relationship between the continuous departure time of the driver's face information from the recognition area of the train and the first preset time;

[0014] Correspondingly, determining the current state according to the relationship between the continuous departure time and the first preset time includes:

[0015] When the continuous departure time is greater than the first preset time, it is determined that the current state is an inactive state;

[0016] When the continuous departure time is less than or equal to the first preset time, it is determined that the current state is an active state.

[0017] Preferably, the operation state of the train at least includes the traction level operation state and the braking level operation state of the train.

[0018] Preferably, determining the driving state of the driver according to the face information includes:

[0019] Extracting the feature information corresponding to the dangerous behavior according to the collected face information;

[0020] Classifying the feature information to determine the driving state of the driver;

[0021] Correspondingly, classifying the feature information to determine the driving state of the driver includes:

[0022] Classifying the feature information through a classifier to obtain classification information, where the classification information at least includes drowsiness information, smoking information, and classification information corresponding to dangerous actions;

[0023] When there is at least one type of classification information, it is determined that the driving state of the driver is dangerous driving;

[0024] When there is no classification information, it is determined that the driving state of the driver is safe driving.

[0025] Preferably, determining the driving behavior of the driver according to the current state, operation state, and driving state includes:

[0026] Respectively obtaining the state information corresponding to the current state, operation state, and driving state;

[0027] Performing a logical operation according to each state information to determine the driving behavior.

[0028] Preferably, adopting a corresponding warning mechanism and a control mechanism for the train according to the driving behavior includes:

[0029] Obtaining the driving time corresponding to the driver's current driving behavior;

[0030] Determining the corresponding warning level according to the driving behavior and / or driving time;

[0031] Determine the corresponding early warning mechanism according to the early warning level and perform early warning processing;

[0032] Determine the corresponding control mechanism according to the early warning time of the early warning mechanism.

[0033] Preferably, determining the corresponding control mechanism according to the early warning time of the early warning mechanism includes:

[0034] When the early warning time is greater than the second preset time, drive the alarm mechanism to perform alarm processing;

[0035] When the early warning time is greater than the third preset time, drive the brake relay to perform braking and decelerating processing on the train, where the third preset time is greater than the second preset time, and the second preset time is greater than the first preset time.

[0036] To solve the above technical problems, the present invention also provides a control device for a train, including:

[0037] An acquisition module, configured to acquire the face information of the driver according to a time interval, where the current state of the train is determined according to the face information acquired for the first time, and the current state includes an activation state and a non-activation state;

[0038] A first determination module, configured to obtain the operation state of the train when the train is in the activation state, and determine the driving state of the driver according to the face information;

[0039] A second determination module, configured to determine the driving behavior of the driver according to the current state, the operation state, and the driving state;

[0040] A processing module, configured to adopt the corresponding early warning mechanism and the control mechanism for the train according to the driving behavior.

[0041] To solve the above technical problems, the present invention also provides a control device for a train, including:

[0042] A memory, configured to store a computer program;

[0043] A processor, configured to implement the steps of the control method for the train as described above when executing the computer program.

[0044] To solve the above technical problems, the present invention also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the control method for the train as described above are implemented.

[0045] To solve the above technical problems, the present invention also provides a train, including the above control device for the train.

[0046] A train control method provided by the present invention includes: collecting the driver's face information at time intervals, where the current state of the train is determined based on the face information collected for the first time, and the current state includes an activated state and a non-activated state; when the train is in the activated state, obtaining the operation state of the train and determining the driver's driving state based on the face information; determining the driver's driving behavior according to the current state, operation state and driving state; and adopting corresponding warning mechanisms and train control mechanisms according to the driving behavior. This method determines the state of the train through the analysis of the driver's face information, determines the driver's driving state through the analysis of the face information, then comprehensively determines the driver's driving behavior according to the current state, operation state and driving state, and adopts corresponding warning and control mechanisms through the supervision of the driving behavior. The train is activated according to the face information without the need for separate key insertion, saving the driver's key operation time. According to the face information and the comprehensively determined driving behavior, corresponding warning mechanisms and control mechanism processes are performed on the train, avoiding incorrect touches caused by the driver continuously pressing the vigilance case or the foot button device, simplifying the driver's operation steps, and improving driving safety.

[0047] In addition, the present invention also provides a train control device, medium and train, which have the same beneficial effects as the above train control method. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] To more clearly illustrate the embodiments of the present invention, the following will briefly introduce the drawings required for use in the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0049] Figure 1 It is a flowchart of a train control method provided by an embodiment of the present invention;

[0050] Figure 2 It is a schematic diagram of a train control technology provided by an embodiment of the present invention;

[0051] Figure 3 It is a structural diagram of a train control device provided by an embodiment of the present invention;

[0052] Figure 4 It is a structural diagram of another train control device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0053] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0054] The core of the present invention is to provide a control method, device, medium and train for a train, which can avoid the wrong touch caused by the driver continuously pressing the vigilance case or the foot pedal button device, simplify the operation steps of the driver, and improve the driving safety.

[0055] In order to enable those skilled in the art to better understand the solution of the present invention, the present invention will be further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0056] It should be noted that the train control method provided by the present invention can also be applied to other rail vehicles or vehicles used for transportation, etc., and the specific application scenarios are not limited herein. Since the train is activated by the driver inserting the key to activate the vehicle and obtain the train control right, there is a risk of loss or misappropriation of the key. The present invention is also applicable to the current activation scenario.

[0057] Figure 1 As shown in the flowchart of a train control method provided by an embodiment of the present invention, Figure 1 as described, the method includes:

[0058] S11: Collect the driver's face information according to a time interval, where the current state of the train is determined according to the first collected face information, and the current state includes an activation state and a non-activation state;

[0059] S12: When the train is in the activation state, obtain the operation state of the train and determine the driving state of the driver according to the face information;

[0060] S13: Determine the driving behavior of the driver according to the current state, operation state and driving state;

[0061] S14: Take corresponding warning mechanisms and control mechanisms for the train according to the driving behavior.

[0062] Specifically, the face information of the driver is collected according to a time interval. There is no limit on the collection device and the number of devices. It can be collected through the camera on the train, which can be an infrared camera, or an artificial intelligence (AI) camera, etc. Similarly, there is no limit on the installation position of the corresponding camera device. It can be installed at the position directly facing the driver's face in the cab. The number of installed cameras can be one or multiple cameras to facilitate capturing the driver's face information comprehensively.

[0063] Capturing face information includes capturing the driver's eye information, mouth information, etc. It can also be the face information obtained by separately capturing and then combining. The present invention does not make a limit, as long as accurate face information can be obtained.

[0064] Determine the current state of the train according to the face information collected for the first time. It should be noted that the first collection in this embodiment is the first face information of this driver collected after the current state of the train changes. For example, when the current state of the train is in the activated state, the first face information of this driver collected, or the first face information of this driver collected when switching to the non-activated state, and it is different from the face information pre-stored in the face information database.

[0065] As an embodiment, determining the current state of the train according to the face information collected for the first time includes:

[0066] Match the face information with the face information database pre-stored in the train to determine the driver's authority;

[0067] When the authority is the operation authority, determine the current state according to the relationship between the continuous departure time of the driver's face information in the recognition area of the train and the first preset time;

[0068] Correspondingly, determining the current state according to the relationship between the continuous departure time and the first preset time includes:

[0069] When the continuous departure time is greater than the first preset time, determine that the current state is the non-activated state;

[0070] When the continuous departure time is less than or equal to the first preset time, determine that the current state is the activated state.

[0071] Specifically, analyze the face information of the driver collected, and match it with the face information database pre-stored in the train to determine whether the target driver is this driver. If so, determine that this driver has the operation authority for the train. If not, determine that this driver does not have the operation authority for this train, so the subsequent train operations will not be started.

[0072] When the permission is an operation permission, the current state is determined based on the relationship between the continuous departure time of the driver's face information from the recognition area of the train and the first preset time. When the continuous departure time is greater than the first preset time, the current state is determined to be the inactive state, and the train activation is cancelled. When the continuous departure time is less than or equal to the first preset time, the current state is determined to be the active state. For example, when the driver departs from the recognition area for more than t1 time, the train activation is cancelled.

[0073] It can be understood that the matching process is the same as the face information analysis process, and algorithms such as deep learning or machine learning can be used for matching, or AI algorithms can be used for matching, which is not limited herein.

[0074] When the train is in the active state, the operation state of the train is obtained. Specifically, when the train activates, its operation state is valid. If the current state of the train is the inactive state, the operation state of the train is invalid.

[0075] As an embodiment, the operation state of the train at least includes the traction level operation state and the braking level operation state of the train.

[0076] Correspondingly, through the Train Control and Management System (TCMS) of the train, various control devices of the train are connected through the network, a master control device is set up for unified control and information sharing. The TCMS system gives full play to the reliability and safety of the vehicle level control function. The level operations set for the traction and braking of the train can be set according to the actual situation, which is not limited herein. The operation state in this embodiment includes but is not limited to the mentioned traction level operation state and the braking level operation state, and may also include other level operation states.

[0077] The driving state of the driver is determined based on the face information. The face information is analyzed to obtain the feature information of the face, and classification is performed according to the feature information to determine the corresponding driving state. The information extraction and classification processes are not limited in this embodiment and can be set according to the actual situation with corresponding extraction algorithms and classifiers. The extraction algorithm can use deep learning or machine learning, and can also use AI algorithms to extract features. The classifier can be based on deep learning, etc., and can also be classified based on traditional classification algorithms.

[0078] It should be noted that the feature information extracted from the face information can be the squinting state in the driver's eye information, the yawning state in the driver's mouth information, etc., or determined as the dozing state through the combination of two pieces of feature information. It can also be the smoking action of the driver, and the cigarette butt information is used as an auxiliary to extract the picture information with the cigarette butt, etc. It can also be the shaking head movement when the driver shakes his head and loses concentration. It is not limited here. The more feature information is extracted, the more accurately the current driving state of the current driver can be determined.

[0079] Determine the driving behavior of the driver based on the current state, operation state, and driving state obtained in steps S11 and S12. It can be understood that the specific classification and determination of these three states are used to determine the driving behavior through the corresponding mapping relationship. It can be classified into valid and invalid according to the state, and 1 and 0 are set respectively. Logical operations are performed on the corresponding different state values to determine the driving behavior. It can also be classified into more than two states according to the state. Under each state, according to its weight value, the weight values obtained from different state classifications in the three states are added to obtain the total weight score. When the weight score is in a certain weight range, the driving behavior is determined, etc.

[0080] As an embodiment, determining the driving behavior of the driver according to the current state, operation state, and driving state includes:

[0081] Obtain the state information corresponding to the current state, operation state, and driving state respectively;

[0082] Perform logical operations according to the state information to determine the driving behavior.

[0083] Specifically, in this embodiment, the driving behavior is determined according to the relationship of logical operations. The driving behavior finally obtained by the logical operations is divided into two types, 1 and 0, and the two are respectively mapped to different driving behaviors, such as high-risk driving behaviors and low-risk driving behaviors, or risky driving behaviors and risk-free driving behaviors.

[0084] The operation order corresponding to the three states in the logical operation is not specifically limited, and the specific operation methods of AND and OR are not limited, and can be set according to the actual situation. For example, the driving behavior is determined by the current state AND (operation state OR driving state). The above three states are divided into valid or invalid, 1 and 0. When the current state is 0, it means that the train is in an unactivated state, and all subsequent states are 0. The driving behavior obtained necessarily is a low-risk driving behavior. Therefore, the operation order can be determined according to the priority and set according to the actual situation.

[0085] According to different driving behaviors, corresponding warning mechanisms and train control mechanisms are adopted. Combining the above embodiments, the driving behaviors are divided into low-risk and high-risk driving behaviors, and the warning mechanisms corresponding to them have two levels. Corresponding warning mechanisms are set according to the two levels, which can be buzzer sounding, reminder on the control page, etc. The output frequencies of different levels are different, and the output frequency corresponding to high risk is greater than that corresponding to low risk. According to the driving behavior, corresponding control mechanisms are adopted for the train. If the warning mechanism lasts for a long time and the driver does not take any measures (does not turn off the warning mechanism button), the train control system will automatically decelerate until it stops.

[0086] A train control method provided by an embodiment of the present invention includes: collecting the driver's face information according to a time interval, where the current state of the train is determined according to the first collected face information, and the current state includes an activated state and a non-activated state; when the train is in the activated state, obtaining the operation state of the train and determining the driving state of the driver according to the face information; determining the driving behavior of the driver according to the current state, operation state and driving state; and adopting corresponding warning mechanisms and train control mechanisms according to the driving behavior. This method determines the state of the train by analyzing the driver's face information, and determines the driving state of the driver by analyzing the face information. Then, according to the current state, operation state and driving state, the driving behavior of the driver is comprehensively determined, and corresponding warning and control mechanisms are adopted through the supervision of the driving behavior. The train is activated according to the face information without the need for separate key insertion, saving the driver's key operation time. According to the face information and the comprehensively determined driving behavior, corresponding warning mechanisms and control mechanism processing are performed on the train, avoiding incorrect touches caused by the driver continuously pressing the vigilance button or the foot button device, simplifying the driver's operation steps, and improving driving safety.

[0087] Based on the above embodiments, determining the driving state of the driver according to the face information in step S12 includes:

[0088] Extracting feature information corresponding to dangerous behaviors according to the collected face information;

[0089] Classifying the feature information to determine the driving state of the driver;

[0090] Correspondingly, classifying the feature information to determine the driving state of the driver includes:

[0091] Classifying the feature information through a classifier to obtain classification information, where the classification information at least includes drowsiness information, smoking information, and classification information corresponding to dangerous actions;

[0092] When there is at least one type of classification information, it is determined that the driving state of the driver is dangerous driving;

[0093] When there is no classification information, it is determined that the driving state of the driver is safe driving.

[0094] Specifically, the feature information corresponding to the dangerous behavior is extracted according to the collected face information. Since the expressions or facial information in the face information are rich, the feature information corresponding to the dangerous behaviors such as the eye information, mouth information, and smoking actions of the driver is obtained. Then, the driving state of the driver is determined by classifying the feature information. The classification can be performed through deep learning, machine learning, etc. or a classifier using traditional algorithms, which is not limited herein.

[0095] The classification information at least includes types corresponding to drowsiness information, smoking information, dangerous actions, etc. When there is at least one type of classification information, it is determined that the corresponding driving state is dangerous driving. Among them, determining dangerous driving is for one type of classification information or a combination of multiple types of classification information. When there is no classification information, that is, when the classifier classifies the feature information and does not obtain the corresponding classification result, or the obtained classification information does not meet the conditions of the current classification, it is determined as safe driving.

[0096] The driving state of the driver is determined according to the face information provided by the embodiments of the present invention, and the driving state of the driver is determined through the classification state. By extracting the feature information and then performing classification, the classification accuracy of the driving state is improved.

[0097] Based on the above embodiments, the corresponding warning mechanism and the control mechanism for the train according to the driving behavior in step S14 include:

[0098] Obtain the driving time corresponding to the driver's current driving behavior;

[0099] Determine the corresponding warning level according to the driving behavior and / or driving time;

[0100] Determine the corresponding warning mechanism according to the warning level and perform warning processing;

[0101] Determine the corresponding control mechanism according to the warning time of the warning mechanism.

[0102] Specifically, obtain the driving time corresponding to the driver's current driving behavior, and use the duration of the current driving behavior as the driving time. Determine the corresponding warning level through the driving behavior or driving time, or determine the corresponding warning level through the mapping relationship between the driving behavior and the driving time.

[0103] In combination with the above embodiments, the current driving behaviors include low-risk driving and high-risk driving. The low-level warning mechanism can be determined based on low-risk driving, and the high-level warning mechanism can be determined based on high-risk driving. It is also possible to classify driving behaviors into different levels, such as level one, level two, etc., and corresponding warning mechanisms are provided according to different levels. Similarly, the warning level is determined according to the corresponding relationship between driving behavior and driving time. When the driving behavior is low-risk driving, its warning level can be further defined as a low-level warning, a medium-level warning, or a high-level warning according to the length of driving time.

[0104] The warning mechanism can be a buzzer sounding, a reminder on the control page, or a vibration of the driver's seat, etc., to remind the driver. It is also possible to upload the driver's driving behavior to the cloud and remind the driver through external devices of the control center.

[0105] The control mechanism of the train is determined according to the warning time of the warning mechanism. It can be understood that after the warning mechanism is activated, if the driver is always unaware of the warning mechanism or ignores it after noticing, and does not take any actions to respond to the warning mechanism (such as turning off the warning mechanism), then alarm processing will be carried out according to the length of the warning time. The length of this time can be that an alarm mechanism is triggered after exceeding a certain threshold. When the warning time has not been processed all the time, after the alarm mechanism is triggered, and when the warning time exceeds the critical threshold, the braking relay is driven to perform braking deceleration on the train until it stops and other operations.

[0106] As an embodiment, determining the corresponding control mechanism according to the warning time of the warning mechanism includes:

[0107] When the warning time is greater than the second preset time, drive the alarm mechanism to perform alarm processing;

[0108] When the warning time is greater than the third preset time, drive the braking relay to perform braking deceleration on the train, where the third preset time is greater than the second preset time, and the second preset time is greater than the first preset time.

[0109] Specifically, when the warning time is greater than the second preset time, drive the alarm mechanism to give an alarm. When it is greater than the third preset time, drive the braking relay to perform deceleration processing. Among them, the third preset time is greater than the second preset time, and the second preset time is greater than the first preset time.

[0110] For example, after the warning level is determined, if it lasts for more than t2 time, drive the penalty buzzer to give a sound alarm prompt. If it lasts for more than t3 time, drive the penalty braking relay, and apply braking to the vehicle circuit to decelerate until it stops. Among them, t1 < t2 < t3, and the time can also be adjusted according to the actual situation.

[0111] The process of adopting corresponding warning mechanisms and train control mechanisms according to driving behaviors provided by the embodiments of the present invention is used to remind the driver to drive safely and change the train control mechanism in a timely manner according to driving behaviors, avoiding incorrect touches caused by the driver continuously pressing the vigilance button or the foot pedal button device, simplifying the driver's operation steps, and improving driving safety.

[0112] As an embodiment, Figure 2 It is a schematic diagram of a train control technology provided by the embodiments of the present invention, as Figure 2 shown, which is composed of a visual analysis module, a vehicle TCMS, and a vehicle circuit.

[0113] The visual analysis module is responsible for face permission management and recognition, and outputs auxiliary contacts (activation contacts) in an activated state and safe driving instructions; the vehicle TCMS system comprehensively judges the driver's operation information and conducts penalty warnings; the vehicle circuit is responsible for building the vehicle activation circuit. When the visual analysis module detects the face of a driver with permission (the face already entered in the visual analysis module), it closes the auxiliary contacts in the activated state, activates the activation relay of the train through the vehicle circuit, and the train is activated; the visual analysis module captures the driver's face information in real time. If the face information is out of the recognition area for more than t1 time, the train activation is cancelled. The visual analysis module detects the face information of a driver with permission and evaluates in real time whether the driver's driving state is dangerous (drowsy, smoking, dangerous actions, etc.), and sends the diagnosis result and safe driving instructions to the train TCMS system through a protocol;

[0114] The TCMS system collects the states of ① the activation relay is valid, ② the safe driving is valid, and ③ the effective operation is valid (including traction level operation and braking level operation), comprehensively judges the driver's driving behavior (logical formula: ① AND (② OR ③)), and conducts hierarchical warnings. If it lasts for more than t2 time, it drives the penalty buzzer for a sound alarm prompt; if it lasts for more than t3 time, it drives the penalty braking relay, and the vehicle circuit applies braking to decelerate to a stop.

[0115] For the introduction of a train control technology provided by the present invention, please refer to the above method embodiments. The present invention will not be elaborated here, and it has the same beneficial effects as the above train control method.

[0116] The above has described in detail the various embodiments corresponding to the train control method. On this basis, the present invention also discloses a train control device corresponding to the above method. Figure 3 It is a structural diagram of a train control device provided by the embodiments of the present invention. As Figure 3 shown, the train control device includes:

[0117] The acquisition module 11 is used to acquire the driver's face information according to a time interval, and determine the current state of the train based on the face information acquired for the first time, where the current state includes an activation state and a non-activation state;

[0118] The first determination module 12 is used to obtain the operation state of the train and determine the driving state of the driver according to the face information when the train is in the activation state;

[0119] The second determination module 13 is used to determine the driving behavior of the driver according to the current state, operation state and driving state;

[0120] The processing module 14 is used to adopt corresponding warning mechanisms and control mechanisms for the train according to the driving behavior.

[0121] Since the embodiments of the device part correspond to the above embodiments, the embodiments of the device part are described with reference to the embodiments of the above method part and will not be elaborated here.

[0122] For the introduction of a train control device provided by the present invention, please refer to the above method embodiments. The present invention will not be elaborated here, and it has the same beneficial effects as the above train control method.

[0123] Figure 4 This is a structural diagram of another train control device provided by the embodiments of the present invention. As Figure 4 shown, the device includes:

[0124] The memory 21 is used to store computer programs;

[0125] The processor 22 is used to implement the steps of the train control method when executing the computer program.

[0126] The train control device provided in this embodiment may include but is not limited to smart phones, tablet computers, notebook computers or desktop computers, etc.

[0127] Among them, the processor 22 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 22 may be implemented in at least one of the following hardware forms: Digital Signal Processor (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 22 may also include a main processor and a coprocessor. The main processor is a processor used to process data in the wake state, also known as the Central Processing Unit (CPU); the coprocessor is a low-power processor used to process data in the standby state. In some embodiments, the processor 22 may be integrated with a Graphics Processing Unit (GPU), and the GPU is responsible for rendering and drawing the content to be displayed on the display screen. In some embodiments, the processor 22 may further include an artificial intelligence processor, and the AI processor is used to process computational operations related to machine learning.

[0128] The memory 21 may include one or more computer-readable storage media, and the computer-readable storage media may be non-transitory. The memory 21 may further include high-speed random access memory and non-volatile memory, such as one or more disk storage devices and flash storage devices. In this embodiment, the memory 21 is at least used to store the following computer program 211. After the computer program is loaded and executed by the processor 22, it can implement the relevant steps of the train control method disclosed in any of the foregoing embodiments. In addition, the resources stored in the memory 21 may further include an operating system 212 and data 213, etc., and the storage method may be temporary storage or permanent storage. Among them, the operating system 212 may include Windows, Unix, Linux, etc. The data 213 may include, but is not limited to, the data involved in the train control method, etc.

[0129] In some embodiments, the train control device may further include a display screen 23, an input / output interface 24, a communication interface 25, a power supply 26, and a communication bus 27.

[0130] Those skilled in the art can understand that Figure 4 the structure shown in

[0131] does not constitute a limitation on the train control device, and it may include more or fewer components than those shown in the figure.

[0132] For the introduction of a train control device provided by the present invention, please refer to the above method embodiments, and the present invention will not be elaborated herein again. It has the same beneficial effects as the above train control method.

[0133] Furthermore, the present invention also provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor 22, the steps of the train control method as described above are implemented.

[0134] It can be understood that if the method in the above embodiments is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and executes all or part of the steps of the methods described in the various embodiments of the present invention. And the aforementioned storage media include: USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs and other various media that can store program codes.

[0135] For the introduction of a computer-readable storage medium provided by the present invention, please refer to the above method embodiments, and the present invention will not be elaborated herein again. It has the same beneficial effects as the above train control method.

[0136] In addition, a train provided by the present application includes the above train control device. For the introduction of a train provided by the present invention, please refer to the above method embodiments, and the present invention will not be elaborated herein again. It has the same beneficial effects as the above train control method.

[0137] The above has made a detailed introduction to a train control method, a train control device, a medium, and a train provided by the present invention. The various embodiments in the specification are described in a progressive manner. Each embodiment focuses on the differences from other embodiments. The same or similar parts among the various embodiments can be referred to each other. For the device disclosed in the embodiments, since it corresponds to the method disclosed in the embodiments, the description is relatively simple. For the relevant parts, please refer to the description in the method part. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements and modifications can still be made to the present invention, and these improvements and modifications also fall within the protection scope of the claims of the present invention.

[0138] It should also be noted that in this specification, relational terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprising", "including" or any other variant thereof are intended to cover non-exclusive inclusion, such that a process, method, article or device comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "comprising an..." does not exclude the presence of additional identical elements in the process, method, article or device comprising the said element.

Claims

1. A control method for a train, characterized in that Including: Collecting the driver's face information according to a time interval, wherein the current state of the train is determined according to the first collected face information, and the current state includes an activation state and a non-activation state; When the train is in the activation state, obtaining the operation state of the train and determining the driving state of the driver according to the face information; Determining the driving behavior of the driver according to the current state, the operation state and the driving state; Adopting corresponding warning mechanisms and control mechanisms for the train according to the driving behavior, specifically including: obtaining the driving time corresponding to the current driving behavior of the driver; determining a corresponding warning level according to the driving behavior and / or the driving time; determining a corresponding warning mechanism according to the warning level for warning processing; determining the corresponding control mechanism according to the warning time of the warning mechanism.

2. The control method of the train according to claim 1, wherein, The determining the current state of the train according to the first collected face information includes: Matching the face information with the face information database pre-stored in the train to determine the driver's authority; When the authority is an operation authority, determining the current state according to the relationship between the continuous departure time of the driver's face information in the recognition area of the train and a first preset time; Correspondingly, the determining the current state according to the relationship between the continuous departure time and the first preset time includes: When the continuous departure time is greater than the first preset time, determining the current state as the non-activation state; When the continuous departure time is less than or equal to the first preset time, determining the current state as the activation state.

3. The control method of the train according to claim 1 or 2, characterized in that, The operation state of the train at least includes the traction level operation state and the braking level operation state of the train.

4. The control method of the train according to claim 3, characterized in that, The determining the driving state of the driver according to the face information includes: Extracting feature information corresponding to dangerous behaviors according to the collected face information; Classifying the feature information to determine the driving state of the driver; Correspondingly, the classifying the feature information to determine the driving state of the driver includes: Classifying the feature information through a classifier to obtain classification information, where the classification information at least includes classification information corresponding to drowsiness information, smoking information and dangerous actions; When there is at least one type of the classification information, determining the driving state of the driver as dangerous driving; When there is no such classification information, determining the driving state of the driver as safe driving.

5. The control method of the train according to claim 4, characterized in that, The determining the driving behavior of the driver according to the current state, the operation state and the driving state includes: Respectively obtaining the state information corresponding to the current state, the operation state and the driving state; Performing a logical operation according to each state information to determine the driving behavior.

6. The control method of the train according to claim 2, characterized in that, The determining the corresponding control mechanism according to the warning time of the warning mechanism includes: When the warning time is greater than a second preset time, driving an alarm mechanism to perform alarm processing; When the warning time is greater than a third preset time, drive a braking relay to perform a braking and deceleration process on the train, where the third preset time is greater than the second preset time, and the second preset time is greater than the first preset time.

7. A control device for a train, characterized in that, It includes: An acquisition module, configured to acquire the driver's face information according to a time interval, where the current state of the train is determined according to the first acquired face information, and the current state includes an activation state and a non-activation state; A first determination module, configured to obtain the operation state of the train and determine the driver's driving state according to the face information when the train is in the activation state; A second determination module, configured to determine the driver's driving behavior according to the current state, the operation state, and the driving state; A processing module, configured to adopt corresponding warning mechanisms and control mechanisms for the train according to the driving behavior, specifically including: obtaining the driving time corresponding to the driver's current driving behavior; determining a corresponding warning level according to the driving behavior and / or the driving time; determining a corresponding warning mechanism according to the warning level for warning processing; determining a corresponding control mechanism according to the warning time of the warning mechanism.

8. A control device for a train, characterized in that, It includes: A memory, configured to store a computer program; A processor, configured to implement the steps of the train control method according to any one of claims 1 to 6 when executing the computer program.

9. A computer-readable storage medium, characterized in that, A computer program is stored on the computer-readable storage medium, and when the computer program is executed by a processor, the steps of the train control method according to any one of claims 1 to 6 are implemented.

10. A train, characterized in that, It includes the train control device according to claim 8.

Images