Escalator control method and device, escalator system, computer equipment and storage medium

Abstract

The invention relates to an escalator control method and device, computer equipment, an escalator system and a computer readable storage medium. The method comprises the steps that a current image collected for the escalator at the current time is obtained; identifying first state information of a bearing object of the escalator in the current image, and predicting second state information of the bearing object in future prediction time based on the first state information; determining unbalance risk information corresponding to the bearing object according to the second state information; under the condition that the unbalance risk information represents that the bearing object has an unbalance risk, determining unbalance track information of the bearing object according to the second state information; and a target stair area corresponding to the unbalance track information is determined from the escalator, and a safety air bag corresponding to the target stair area is unfolded, so that unbalance protection is provided for the bearing object through the unfolded safety air bag. By adopting the method, the safety of the escalator can be improved.

Description

Technical Field

[0001] This application relates to the technical field of escalators, and particularly to an escalator control method, an escalator control device, an escalator system, a computer device, a computer-readable storage medium, and a computer program product. Background Art

[0002] Escalators generally include escalators with a certain inclination angle, horizontal moving walkways, or moving walkways with a slight inclination. The main components of an escalator mainly include steps and handrails (handrail belts) on both sides, and the handrails are provided for passengers to hold during the operation of the escalator. However, in the prior art, the safety of escalators is not good. For example, passengers may roll down on the steps, the function of the handrails is limited, and the risk of passengers being injured is relatively high. Summary of the Invention

[0003] Based on this, it is necessary to provide an escalator control method, an escalator control device, an escalator system, a computer device, a computer-readable storage medium, and a computer program product for the above technical problems to improve the safety of escalators.

[0004] In a first aspect, this application provides an escalator control method, including:

[0005] Obtain a current image collected for the escalator at the current time;

[0006] Identify first state information of the load-bearing object on the escalator in the current image, and based on the first state information, predict second state information of the load-bearing object at a future prediction time;

[0007] Determine imbalance risk information corresponding to the load-bearing object according to the second state information;

[0008] In the case where the imbalance risk information indicates that the load-bearing object has an imbalance risk, determine imbalance trajectory information of the load-bearing object according to the second state information;

[0009] Determine a target step area corresponding to the imbalance trajectory information from the escalator, and deploy the airbag corresponding to the target step area to provide imbalance protection for the load-bearing object through the deployed airbag.

[0010] In one of the embodiments, determining the imbalance risk information corresponding to the load-bearing object according to the second state information includes:

[0011] Obtain historical state information of the load-bearing object, and the historical state information is recognized from a historical image collected based on a historical time corresponding to the current time;

[0012] Perform imbalance prediction on the load-bearing object according to the second state information and the historical state information to obtain imbalance risk information corresponding to the load-bearing object.

[0013] In one embodiment, imbalance prediction is performed on the load-bearing object according to the second state information and the historical state information to obtain the imbalance risk information corresponding to the load-bearing object, including:

[0014] Obtain the pressure information of the load-bearing object on the escalator and the radar detection information of the load-bearing object on the escalator;

[0015] Fuse the second state information, the historical state information, the pressure information, and the radar detection information according to a preset weight to obtain the imbalance detection information;

[0016] Determine the imbalance risk information corresponding to the load-bearing object based on the imbalance detection information.

[0017] In one embodiment, determine the target step area corresponding to the imbalance trajectory information from the escalator and deploy the airbag corresponding to the target step area, including:

[0018] Determine the imbalance step area corresponding to the imbalance trajectory information from the escalator, and based on the imbalance step area, determine the target step area from the escalator according to the safety distance threshold;

[0019] Determine the passenger information of the escalator in the target step area;

[0020] When the passenger information indicates that the target step area is not occupied, deploy the airbag provided corresponding to the skirt board associated with the target step area.

[0021] In one embodiment, the foregoing escalator control method further includes:

[0022] When the imbalance risk information indicates that the load-bearing object has an imbalance risk, control the escalator to decelerate according to the first deceleration method;

[0023] When the imbalance risk information indicates that the load-bearing object is in a preset abnormal posture, control the escalator to decelerate according to the second deceleration method and issue a load abnormality prompt for the load-bearing object.

[0024] In one embodiment, the foregoing escalator control method further includes:

[0025] Obtain the recovery trigger condition for the airbag;

[0026] When it is determined based on the load-bearing object that the recovery trigger condition is met, recover the deployed airbag so that the recovered airbag can respond to the next activation and deployment.

[0027] In a second aspect, the present application further provides an escalator control device, including:

[0028] An acquisition module, configured to acquire a current image collected for an escalator at a current time;

[0029] A determination module, configured to identify first state information of a load-bearing object on the escalator in the current image, and based on the first state information, predict second state information of the load-bearing object at a future prediction time; determine imbalance risk information corresponding to the load-bearing object according to the second state information; in a case where the imbalance risk information indicates that the load-bearing object has an imbalance risk, determine imbalance trajectory information of the load-bearing object according to the second state information;

[0030] A control module, configured to determine a target step area corresponding to the imbalance trajectory information from the escalator, and deploy an airbag corresponding to the target step area, so as to provide imbalance protection for the load-bearing object through the deployed airbag.

[0031] In a third aspect, the present application further provides an escalator system, including an escalator and the escalator control device as described in the second aspect.

[0032] In a fourth aspect, the present application further provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the escalator control method in the foregoing first aspect are implemented.

[0033] In a fifth aspect, the present application further 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 escalator control method in the foregoing first aspect are implemented.

[0034] In a sixth aspect, the present application further provides a computer program product, including a computer program, and when the computer program is executed by a processor, the steps of the escalator control method in the foregoing first aspect are implemented.

[0035] For the foregoing escalator control method, device, computer device, escalator system, computer-readable storage medium, and computer program product, by identifying the current image, the first state information of the load-bearing object is determined, and based on the first state information, the second state information is predicted to determine the imbalance risk information corresponding to the load-bearing object, which realizes predicting whether there is an imbalance risk according to the current state of the load-bearing object on the escalator, and establishes safety monitoring of the load-bearing object on the escalator; in a case where the imbalance risk information indicates that the load-bearing object has an imbalance risk, the deployed airbag provides imbalance protection for the load-bearing object, which improves the safety of the escalator. At the same time, since the airbag to be deployed is the airbag corresponding to the target step area, and the target step area corresponds to the imbalance trajectory information determined based on the second state information, the deployed airbag can accurately protect the load-bearing object and avoid the situation that the load-bearing object fails to be protected due to deploying the wrong airbag, which further improves the safety of the escalator. Brief Description of the Drawings

[0036] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the following will briefly introduce the drawings required for use in the description of the embodiments of the present application or related technologies. Obviously, the drawings in the following description are only some embodiments of the present application. For those of ordinary skill in the art, without creative efforts, other related drawings can also be obtained based on these drawings.

[0037] Figure 1 It is a schematic flowchart of the escalator control method in one embodiment;

[0038] Figure 2 It is another schematic flowchart of the escalator control method in one embodiment;

[0039] Figure 3 It is still another schematic flowchart of the escalator control method in one embodiment;

[0040] Figure 4 It is a structural block diagram of the escalator control device in one embodiment;

[0041] Figure 5 It is the internal structure diagram of a computer device in one embodiment. Detailed Description of the Embodiments

[0042] In order to make the purpose, technical solutions and advantages of the present application clearer, the following further details the present application in conjunction with the drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application. As used herein, the term "a plurality" may refer to two or more than two unless otherwise specified.

[0043] In one embodiment, as Figure 1 shown, a method for controlling an escalator is provided. In this embodiment, it is exemplified that the method is applied to a server. The server may be a server for controlling an escalator. It can be understood that the method can also be applied to an escalator. For example, in addition to traditional components such as steps and handrails, an escalator may also include a module for controlling components such as steps and handrails. Of course, the method can also be applied to a system including an escalator and a server, such as an escalator operation control management system, and is implemented through the interaction between the escalator and the server. In this embodiment, the method includes steps S101 to S105:

[0044] Step S101: The server acquires a current image collected for the escalator at the current time.

[0045] Among them, the escalator can be, but is not limited to, an end-driven escalator, a middle-driven escalator, an escalator with a straight ladder path, an escalator with a spiral ladder path, a rotary spiral ladder path escalator, etc.

[0046] Among them, the current image can be an image collected for the escalator, and the image can represent the operating condition of the escalator at the current time. Exemplarily, the current image can include the escalator and load-bearing objects such as passengers and luggage carried by the escalator.

[0047] In some embodiments, the current time can be the current time point. Correspondingly, the current image can be an image for a time point.

[0048] In some embodiments, the current time can also be a current period of time. For example, taking every five seconds as a time period. Correspondingly, the current image can be an image for a time period, for example, an image of five consecutive seconds. Exemplarily, the current image can be one image or multiple images.

[0049] In some embodiments, the acquisition method of the current image can be obtained based on a pre-set image acquisition device. Exemplarily, the image acquisition device can be set on the escalator or above the escalator, etc. The number of image acquisition devices can be one or more.

[0050] Step S102: The server identifies the first state information of the load-bearing object on the escalator in the current image, and based on the first state information, predicts the second state information of the load-bearing object at the future prediction time.

[0051] Among them, the load-bearing object can include passengers. In some embodiments, the load-bearing object can also include shopping carts, baby carriages, pets, luggage, etc.

[0052] Among them, the first state information can be information identified by the server based on the current image, which represents the state of the load-bearing object on the escalator. Exemplarily, the first state information can include the state of a passenger on the escalator, such as the limb states of the standing posture and the positions of both hands, etc. Additionally, the gaze state of the passenger, etc. Exemplarily, the first state information can include the state information of a baby carriage, such as the positions of each wheel of the baby carriage and the state of the passenger responsible for pushing the baby carriage, etc.

[0053] Among them, the future prediction time can be relative to the current time. Similarly to the foregoing description of the current time, the future prediction time can be a future time point or a time period.

[0054] Among them, the second state information can be the predicted state information representing the load-bearing object at the future prediction time. For example, the position of the right foot of a passenger on the escalator in the next second, etc.

[0055] In some embodiments, the server may extract first state information from the current image based on artificial intelligence model-related technologies, such as convolutional neural networks, and predict second state information based on the first state information.

[0056] Step S103: The server determines imbalance risk information corresponding to the carrying object according to the second state information.

[0057] Among them, the imbalance risk information may be risk information indicating the possible risks caused by the destruction of the balance of the carrying object on the escalator.

[0058] In some embodiments, the server may also determine the imbalance risk information corresponding to the carrying object based on artificial intelligence model-related technologies, such as convolutional neural networks, according to the second state information. For example, risk features that may cause imbalance are extracted from the second state information. For example, a passenger stands on one foot on the escalator, or a young passenger plays and frolics on the escalator.

[0059] Step S104: When the imbalance risk information indicates that the carrying object has an imbalance risk, the server determines the imbalance trajectory information of the carrying object according to the second state information.

[0060] Among them, the imbalance trajectory information may be the imbalance situation that the carrying object may cause due to the imbalance risk. For example, falling or rolling on the escalator. Another example is the form and direction of the passenger about to fall.

[0061] In some embodiments, the server may also determine the imbalance trajectory information based on artificial intelligence model-related technologies.

[0062] Step S105: Determine a target step area corresponding to the imbalance trajectory information from the escalator, and deploy the airbag corresponding to the target step area to provide imbalance protection for the carrying object through the deployed airbag.

[0063] In some embodiments, the server may determine a target step area corresponding to the imbalance trajectory information from the escalator. Exemplarily, the server may determine the imbalance trajectory of the carrying object according to the imbalance trajectory information. For example, a passenger rolls from the first step to the fifth step of the escalator, so that the corresponding target step area can be obtained, such as the area from the second step to the fifth step.

[0064] In some embodiments, the target step area may correspond to one or more steps of the escalator.

[0065] In some embodiments, the target step area may correspond to all or part of the area of one or more steps.

[0066] In some possible embodiments, the server may determine the level of the imbalance risk of the load-bearing object according to the imbalance risk information. For example, it may be classified into levels one to three according to the severity and urgency of the imbalance risk. For example, when there is a baby in the stroller, the corresponding imbalance risk may be level one. Different control measures are taken according to the level of the imbalance risk of the load-bearing object. For example, when the level is one, the running speed of the escalator is reduced, when the level is two, the airbag is pre-inflated, and when the level is three, the airbag is deployed.

[0067] By identifying the current image, the first state information of the load-bearing object is determined, and based on the first state information, the second state information is predicted to determine the imbalance risk information corresponding to the load-bearing object. This realizes predicting whether there is an imbalance risk according to the current state of the load-bearing object on the escalator, and this establishes the safety monitoring of the load-bearing object on the escalator; when the imbalance risk information indicates that the load-bearing object has an imbalance risk, the deployed airbag provides imbalance protection for the load-bearing object, which improves the safety of the escalator. At the same time, since the airbag to be deployed is the airbag corresponding to the target step area, and the target step area corresponds to the imbalance trajectory information determined based on the second state information, the deployed airbag can accurately protect the load-bearing object and avoid the situation where the load-bearing object fails to be protected due to deploying the wrong airbag, which further improves the safety of the escalator.

[0068] In one embodiment, "determining the imbalance risk information corresponding to the load-bearing object according to the second state information" in the foregoing method, as Figure 2 shown, may include steps S201 to S202:

[0069] Step S201: The server obtains the historical state information of the load-bearing object, and the historical state information is obtained by identifying the historical image collected based on the historical time corresponding to the current time.

[0070] Among them, the historical time may be relative to the current time. Similarly to the foregoing description of the current time, the historical time may be a time point or a time period.

[0071] In some embodiments, the historical time may be a time point or a time period adjacent to the current time. Exemplarily, when the current time is 18:00 sharp, the historical time may be 17:59:59, and the historical time may also be from 17:59:55 to 17:59:59.

[0072] Step S202: The server performs an imbalance prediction for the load-bearing object according to the second state information and the historical state information to obtain the imbalance risk information corresponding to the load-bearing object.

[0073] In some embodiments, the server can determine the imbalance risk information from two perspectives: the current time and the historical time. Exemplarily, the second status information and the historical status information can be integrated to perform an imbalance prediction for the bearing object, thereby obtaining the imbalance risk information.

[0074] By comprehensively determining the imbalance risk information corresponding to the bearing object based on the status information of the bearing object on the escalator from two aspects, namely the second status information and the historical status information, it helps to improve the accuracy of the imbalance risk information.

[0075] In one embodiment, the step of "performing an imbalance prediction for the bearing object according to the second status information and the historical status information to obtain the imbalance risk information corresponding to the bearing object" in the foregoing method may include: the server obtains the pressure information of the bearing object on the escalator and the radar detection information of the bearing object on the escalator; fuses the second status information, the historical status information, the pressure information, and the radar detection information according to a preset weight to obtain imbalance detection information; and determines the imbalance risk information corresponding to the bearing object based on the imbalance detection information.

[0076] Among them, the pressure information may be information related to the pressure exerted by the bearing object on the escalator. For example, when a passenger stands on the step of the escalator, the corresponding pressure magnitude is detected by a pressure sensor preset on the step.

[0077] In some embodiments, radar detection devices, such as millimeter-wave radars, may be set at positions on, around, or above the escalator, and the server detects the bearing object carried by the escalator through the radar detection devices.

[0078] In some embodiments, the radar detection information may include the specific position information of the bearing object on the escalator and the morphological information of the bearing object, such as the external contour and movement changes.

[0079] Exemplarily, the server may use the second status information and the historical status information as the basis for determining the imbalance risk information, and use the pressure information and the radar detection information as a verification of the above determination basis.

[0080] Exemplarily, the preset weights corresponding to the second status information, the historical status information, the pressure information, and the radar detection information may be the same or different.

[0081] Exemplarily, the server may fuse the second status information, the historical status information, the pressure information, and the radar detection information based on normalization processing.

[0082] Based on the above technical solution, by comprehensively determining the imbalance risk information corresponding to the load-bearing object according to the second state information, historical state information, pressure information, and radar detection information, it helps to further improve the accuracy of the imbalance risk information.

[0083] In one embodiment, as Figure 3 shown, the step of "determining the target step area corresponding to the imbalance trajectory information from the escalator and deploying the airbag corresponding to the target step area" in the foregoing method may include steps S301 to S302:

[0084] Step S301: The server determines the imbalance step area corresponding to the imbalance trajectory information from the escalator, and based on the imbalance step area, determines the target step area from the escalator according to the safety distance threshold.

[0085] Step S302: The server determines the passenger information of the escalator in the target step area.

[0086] Step S303: When the passenger information indicates that there is no passenger in the target step area, the server deploys the airbag provided corresponding to the skirt board associated with the target step area.

[0087] Exemplarily, the server may use 1m in front and behind the load-bearing object as the safety distance threshold. Of course, other values can also be taken for the safety distance threshold to determine the imbalance step area.

[0088] Among them, the passenger information of the target step area may be information related to the load-bearing object carried by the escalator in the target step area. For example, there is a passenger and a suitcase in the target step area.

[0089] In some embodiments, the server may analyze the passenger information to determine whether there is a passenger in the target step area. If there is a passenger, the situation of the corresponding load-bearing object can be further analyzed. For example, whether the load-bearing object is a passenger or a non-passenger such as goods. If the load-bearing object is a non-passenger, the physical information of the load-bearing object can be determined, such as whether there are sharp protrusions in the contour appearance, the volume size, etc. According to the physical information of the load-bearing object, it is determined whether the corresponding airbag is deployed. For example, if the volume of the load-bearing object is small and does not affect the deployment of the airbag, the airbag can be deployed. Another example is that the load-bearing object is a small square table. Since the table has rectangular table corners and there is a risk of a passenger imbalance hitting the table corners and causing a safety accident, the corresponding airbag should be deployed at this time.

[0090] In some embodiments, when the passenger information indicates that the target step area is occupied, specifically, when there are passengers in the target step area, at this time, based on the aforementioned imbalance risk information and imbalance trajectory information, the second status information, imbalance risk information, and imbalance trajectory information corresponding to the passengers in the target step area can be re-determined. Accordingly, the second target step area can be obtained, and then whether to activate and deploy the airbag in the second target step area can be determined according to the passenger information in the second target step area. Thus, it is possible to avoid deploying the airbag when there are passengers in the target step area, which may affect the safety of the passengers. At the same time, the imbalance risk of the passengers in the target step area can be predicted in advance. For example, the safety impact of the imbalance risk of other passengers on the passengers in the target step area. Accordingly, the second target step area is determined, and the passengers in the target step area are also included in the scope of safety protection, which further improves the safety of the escalator.

[0091] For example, there is a passenger B in the target step area corresponding to the imbalance trajectory information of passenger A obtained through the aforementioned steps. Then, the second status information and imbalance risk information corresponding to passenger B can be re-determined, and further, the imbalance trajectory information of passenger B can be obtained. According to the imbalance trajectory information of passenger B, the corresponding second target step area can be obtained. Whether to activate and deploy the airbag in the second target step area is determined according to the passenger information in the second target step area. If there is a passenger C in the second target step area, then the imbalance trajectory information of passenger C can be re-determined. According to the imbalance trajectory information of passenger C, the corresponding third target step area can be obtained. Whether to activate and deploy the airbag in the third target step area is determined according to the passenger information in the third target step area. If there is a passenger D in the third target step area, the same principle can be applied as above, and so on in a cycle.

[0092] The above technical solution determines the target step area from the escalator. According to the passenger information in the target step area of the escalator, the corresponding airbag is activated only when the passenger information indicates that the target step area is not occupied. Thus, it is possible to avoid deploying the airbag when there are passengers in the target step area, which may affect the safety of the passengers. The passengers in the target step area are also included in the scope of safety protection, further improving the safety of the escalator.

[0093] In one embodiment, the aforementioned escalator control method further includes: when the imbalance risk information indicates that the load-bearing object has an imbalance risk, the server controls the escalator to decelerate in a first deceleration mode; when the imbalance risk information indicates that the load-bearing object is in a preset abnormal posture, the server controls the escalator to decelerate in a second deceleration mode and issues a load-bearing abnormality prompt for the load-bearing object.

[0094] Wherein, the preset abnormal posture can be a posture that is preset to indicate the abnormality of the load-bearing object.

[0095] In some embodiments, the server may classify the types of load-bearing objects and preset different abnormal postures according to different types of load-bearing objects.

[0096] For example, for passengers, abnormal postures may include standing on one foot, standing in the opposite direction to the running direction of the escalator, etc.; for load-bearing objects that are not passengers, for example, the abnormal posture of a stroller may include that the number of wheels in direct contact with the escalator steps is less than two.

[0097] In some embodiments, the preset abnormal posture may be one of the factors causing the risk of imbalance. Therefore, in the case where the load-bearing object is in the preset abnormal posture, the server may decelerate in a second deceleration manner and issue a load abnormality prompt for the load-bearing object. Exemplarily, the load abnormality prompt may include at least one of the following: playing a safety prompt audio, turning on a safety warning light, and displaying prompt text.

[0098] In some embodiments, the first deceleration method may include controlling the escalator to decelerate according to a preset first deceleration rate until it stops; the second deceleration method may include controlling the escalator to decelerate from a first operating speed to a second operating speed according to a preset second deceleration rate. The first operating speed may be the rated operating speed of the escalator, and the second operating speed is less than the first operating speed. Exemplarily, the first deceleration rate and the second deceleration rate may be the same or different.

[0099] According to the different contents represented by the imbalance risk information, the above technical solution adopts different control methods for the escalator - when the imbalance risk information indicates that there is an imbalance risk for the load-bearing object, the first deceleration method is used to control the escalator; when the load-bearing object is in the preset abnormal posture, the second deceleration method is used to control the escalator and a load abnormality prompt is issued. This realizes more refined safety control of the escalator, avoids "overprotection", and makes the safety control of the escalator match the actual imbalance risk.

[0100] In one of the embodiments, the foregoing escalator control method further includes: the server obtains a recovery trigger condition for the airbag; when it is determined that the recovery trigger condition is satisfied based on the load-bearing object, the deployed airbag is recovered to respond to the next activation and deployment through the recovered airbag.

[0101] In some embodiments, the server may update the first status information, imbalance risk information, etc. of the load-bearing object in real time, and determine whether the recovery trigger condition is satisfied according to the first status information. For example, when the imbalance risk information indicates that there is no imbalance risk, it may be determined that the recovery trigger condition is satisfied.

[0102] Exemplarily, the recovery trigger conditions for the airbag can include at least one of the following: no risk of imbalance for the carrying object, the escalator has been stopped for a time longer than a preset stop time, and no carrying object on the escalator.

[0103] By determining whether the recovery trigger conditions for the airbag are met, and if so, recovering the deployed airbag to prepare for the next risk of imbalance. This realizes the recycling of the airbag.

[0104] In one embodiment, the foregoing escalator control method may further include: the server performs carrying object recognition based on the current image, and when the recognized carrying objects are not passengers, reduces the escalator running speed or stops the escalator.

[0105] Considering that escalators are mainly for passenger travel, when it is detected that there are no passengers, the server can reduce the escalator running speed or stop the escalator. Especially when there are only goods without passengers, reducing the escalator running speed or stopping the escalator helps to avoid safety accidents.

[0106] In an exemplary embodiment, a safety device is provided, which is applied to an escalator. The safety device includes:

[0107] A camera, arranged above the escalator, for taking images of the escalator area (corresponding to the foregoing current image, historical image, etc.). The camera is connected to the image recognition unit through a network. The number of cameras can be one or more.

[0108] An image recognition unit, for analyzing whether there are any falling actions of the escalator passengers in the images taken by the camera and the positions where the falls occur (corresponding to the foregoing determination of the first state information, second state information, imbalance risk information, and imbalance trajectory information, etc.), and transmitting the results to the control unit.

[0109] Airbags, distributed at several positions on the escalator skirt board. A passenger sensor is installed at each airbag deployment point, and the inflation control of the airbags is controlled by the control unit. In some embodiments, regarding the airbag settings, based on historical data statistics, high-risk areas (platform stages) / areas with a high injury rate in the escalator can be determined, and denser airbags are arranged in high-risk areas.

[0110] A passenger sensor, for detecting whether there are passengers on the steps corresponding to the airbag arrangement positions, corresponding to the foregoing "determining the passenger information on the escalator in the target step area", etc.

[0111] A control unit, which is used to control the operation and stop of the escalator, receive the passenger fall signal from the image recognition unit, and receive the passenger sensor signal; when receiving the passenger fall signal, it controls the escalator to stop slowly, and at the same time, according to the passenger fall position and combined with the signals of the passenger sensors downward from the passenger fall position, if there is no passenger, it activates the corresponding airbag; otherwise, it does not activate the corresponding airbag. In some embodiments, when a passenger falls on the escalator, it usually rolls downward. Accordingly, the opening condition of the airbag can be set, that is, when a fall event occurs and there is no standing passenger in the downward step direction; for the special case of falling upward, it can also be judged whether to open the airbag according to this condition.

[0112] In some embodiments, the above safety device can be based on a server to realize the control of the escalator and the deployment and recovery of the airbag. For example, the actual execution entities corresponding to the image recognition unit and the control unit in the above safety device can be the server.

[0113] In some embodiments, the image recognition unit can make predictions (safety analysis) based on the standing mentality of people on the escalator. If there is a risk of falling, the control unit controls the escalator to give a prompt, such as the light being on and the bell ringing; if there is a risk, the operating state of the escalator is adjusted based on the risk level.

[0114] In some embodiments, the above safety protection device can further include a millimeter-wave radar and a pressure sensor. The control unit can be used to comprehensively determine and verify whether a passenger fall has occurred or is likely to occur through the data of the image recognition unit, the millimeter-wave radar, and the pressure sensor, corresponding to the relevant content such as the pressure information and the radar detection information described above.

[0115] In some embodiments, the control unit can verify whether a passenger fall has occurred or is likely to occur through a time window, such as confirming based on three consecutive frames of images.

[0116] In some embodiments, the control unit can determine the range of the passenger fall based on a preset safety distance threshold. For example, with the fall position as the center, the range is 1.5 meters before and after.

[0117] In some embodiments, the control unit can adopt different control schemes for the escalator based on different actual situations. Exemplarily, the control schemes of the control unit for the escalator can be divided into three levels, as shown in Table 1, giving a possible control strategy.

[0118] Table 1

[0119] Level Trigger condition Response measure Level I Detect abnormal posture Voice warning + Reduce running speed (0.5 m / s → 0.3 m / s) Level II Identify the tendency of instability Emergency braking preparation + Airbag pre-inflation Level III Confirm the falling action Graded braking + Directional airbag deployment + Alarm linkage

[0120] In some embodiments, the above safety protection device can further include an airbag recovery device, corresponding to the relevant content about airbag recovery described above. The airbag recovery device is configured with:

[0121] An electric retraction mechanism for retracting the ejected airbag;

[0122] A self-cleaning nozzle for automatically cleaning the surface when the airbag is retracted;

[0123] And an integrated rapid inflation compensation module for providing rapid inflation when the recycled airbag is ejected next time.

[0124] The above device can activate the airbag while the passenger falls, avoiding the expansion of the harm suffered by the passenger. At the same time, according to different levels of triggering conditions, different corresponding measures are controlled for the escalator to provide refined safety protection for escalator passengers; by recycling the airbag, the airbag can be reused and the cost can be reduced; through millimeter-wave radar, pressure sensing, time window verification, safety distance threshold, etc., it is comprehensively determined whether there is a safety risk for the passenger, thus establishing an anti-misoperation mechanism, that is, avoiding the misidentification of the passenger's safety risk and avoiding wrong response measures, which helps to improve the accuracy of the safety risk response and thus improve the safety of the escalator.

[0125] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are sequentially shown according to the indication of the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless there is a clear description in this article, the execution of these steps has no strict order limit, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages is not necessarily sequential, but can be executed alternately or alternately with at least a part of other steps or steps or stages in other steps.

[0126] Based on the same inventive concept, the embodiments of the present application also provide an escalator control device for implementing the escalator control method involved above. The implementation solutions provided by this device to solve problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the escalator control device provided below can refer to the limitations on the escalator control method in the above text and will not be repeated here.

[0127] In an exemplary embodiment, as Figure 4 shown, an escalator control device 400 is provided, including:

[0128] An acquisition module 401 for acquiring a current image of the escalator collected at the current time;

[0129] A determination module 402, configured to identify first state information of a load-bearing object on an escalator in a current image, and based on the first state information, predict second state information of the load-bearing object at a future prediction time; determine imbalance risk information corresponding to the load-bearing object according to the second state information; and in the case that the imbalance risk information indicates that the load-bearing object has an imbalance risk, determine imbalance trajectory information of the load-bearing object according to the second state information.

[0130] A control module 403, configured to determine a target step area corresponding to the imbalance trajectory information from the escalator, and deploy a safety airbag corresponding to the target step area, so as to provide imbalance protection for the load-bearing object through the deployed safety airbag.

[0131] In one embodiment, the determination module 402 is further configured to determine imbalance risk information corresponding to the load-bearing object according to the second state information, including: obtaining historical state information of the load-bearing object, where the historical state information is identified from a historical image collected based on a historical time corresponding to the current time; and performing an imbalance prediction on the load-bearing object according to the second state information and the historical state information, so as to obtain the imbalance risk information corresponding to the load-bearing object.

[0132] In one embodiment, the determination module 402 is further configured to perform an imbalance prediction on the load-bearing object according to the second state information and the historical state information, so as to obtain the imbalance risk information corresponding to the load-bearing object, including: obtaining pressure information of the load-bearing object on the escalator and radar detection information of the load-bearing object on the escalator; fusing the second state information, the historical state information, the pressure information, and the radar detection information according to a preset weight to obtain imbalance detection information; and determining the imbalance risk information corresponding to the load-bearing object based on the imbalance detection information.

[0133] In one embodiment, the control module 403 is further configured to determine a target step area corresponding to the imbalance trajectory information from the escalator, and deploy a safety airbag corresponding to the target step area, including: determining an imbalanced step area corresponding to the imbalance trajectory information from the escalator, and determining a target step area from the escalator based on the imbalanced step area according to a safety distance threshold; determining passenger information of the escalator in the target step area; and in the case that the passenger information indicates that the target step area is not occupied by passengers, deploying a safety airbag correspondingly arranged with a skirt board associated with the target step area.

[0134] In one embodiment, the control module 403 is further configured to, in the case that the imbalance risk information indicates that the load-bearing object has an imbalance risk, control the escalator to decelerate according to a first deceleration method; and in the case that the imbalance risk information indicates that the load-bearing object is in a preset abnormal posture, control the escalator to decelerate according to a second deceleration method and issue a load abnormality prompt for the load-bearing object.

[0135] In one embodiment, the control module 403 is further configured to obtain the recycling trigger condition for the airbag; when it is determined based on the carried object that the recycling trigger condition is met, recycle the deployed airbag to respond to the next activation and deployment through the recycled airbag.

[0136] Each module in the above escalator control device can be implemented in whole or in part by software, hardware, and their combination. The above modules can be embedded in the processor of the computer device in hardware form or be independent of it, or be stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to the above respective modules.

[0137] In an exemplary embodiment, a computer device is provided. The computer device can be a server or a terminal, and its internal structural diagram can be as Figure 5 shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, abbreviated as I / O), and a communication interface. Among them, the processor, the memory, and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the data required for executing the escalator control method, such as the current image, historical images, etc. The input / output interface of the computer device is used for the processor to exchange information with external devices. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements an escalator control method.

[0138] Those skilled in the art can understand that Figure 5 the structure shown in

[0139] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0140] In an exemplary embodiment, a computer device is provided, including a memory and a processor. A computer program is stored in the memory, and when the processor executes the computer program, it implements the steps in the above method embodiments.

[0141] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0142] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0143] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile memory and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, artificial intelligence (AI) processors, etc., without limitation.

[0144] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this application.

[0145] The above-described embodiments merely represent several implementation manners of this application. The description is relatively specific and detailed, but it should not be construed as a limitation on the patent scope of this application. It should be noted that for those of ordinary skill in the art, without departing from the concept of this application, several modifications and improvements can still be made, and these all belong to the protection scope of this application. Therefore, the protection scope of this application shall be subject to the appended claims.

Claims

1. An escalator control method, characterized in that: The method comprises: Get the current image collected for the escalator at the current time; Identifying first state information of a load-bearing object of the escalator in the current image, and predicting second state information of the load-bearing object at a future prediction time based on the first state information; Determining, according to the second state information, imbalance risk information corresponding to the bearing object; When the imbalance risk information indicates that the load-bearing object has an imbalance risk, determining the imbalance trajectory information of the load-bearing object according to the second state information; A target step area corresponding to the imbalance trajectory information is determined from the escalator, and an airbag corresponding to the target step area is deployed, so as to provide imbalance protection for the carried object through the deployed airbag.

2. The method according to claim 1, characterized in that The determining, according to the second state information, the imbalance risk information corresponding to the bearing object includes: Acquire historical status information of the bearing object, where the historical status information is obtained based on historical image recognition collected at a historical time corresponding to the current time; An imbalance prediction is performed for the bearing object according to the second state information and the historical state information to obtain imbalance risk information corresponding to the bearing object.

3. The method according to claim 2, characterized in that The performing imbalance prediction for the load-bearing object according to the second state information and the historical state information to obtain imbalance risk information corresponding to the load-bearing object includes: Acquire pressure information of the carried object on the escalator and radar detection information of the carried object on the escalator; fusing the second state information, the historical state information, the pressure information and the radar detection information according to preset weights to obtain imbalance detection information; Unbalance risk information corresponding to the load-bearing object is determined based on the imbalance detection information.

4. The method according to claim 1, characterized in that: The step of determining a target step area corresponding to the imbalance trajectory information from the escalator and deploying an airbag corresponding to the target step area includes: Determine an unbalanced step area corresponding to the unbalanced trajectory information from the escalator, and determine a target step area from the escalator based on the unbalanced step area according to a safety distance threshold; Determine the passenger carrying information of the escalator in the target step area; When the passenger information indicates that the target step area is not carrying passengers, a safety airbag arranged corresponding to the skirt panel associated with the target step area is deployed.

5. The method according to claim 1, characterized in that The method further comprises: When the imbalance risk information indicates that the carried object has an imbalance risk, controlling the escalator to decelerate according to a first deceleration mode; When the imbalance risk information indicates that the carried object is in a preset abnormal posture, the escalator is controlled to decelerate according to a second deceleration mode and a load abnormality prompt is issued for the carried object.

6. The method according to any one of claims 1 to 5, characterized in that The method further comprises: Obtaining a recovery trigger condition for the airbag; When it is determined based on the load-bearing object that the recovery trigger condition is satisfied, the deployed safety airbag is recovered so as to respond to the next activation and deployment through the recovered safety airbag.

7. An escalator control device, characterized in that: The device comprises: An acquisition module, used to acquire a current image captured for the escalator at a current time; a determination module, configured to identify first state information of a load-bearing object of the escalator in the current image, and predict second state information of the load-bearing object at a future prediction time based on the first state information; determine imbalance risk information corresponding to the load-bearing object according to the second state information; and determine imbalance trajectory information of the load-bearing object according to the second state information when the imbalance risk information indicates that the load-bearing object has an imbalance risk; A control module is used to determine a target step area corresponding to the imbalance trajectory information from the escalator, and deploy an airbag corresponding to the target step area to provide imbalance protection for the carried object through the deployed airbag.

8. An escalator system, characterized in that: The invention comprises an escalator and the escalator control device as claimed in claim 7.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images