Elevator stopping scheduling method and device, computer equipment and storage medium

Abstract

The invention relates to an elevator stopping scheduling method and device, computer equipment and a storage medium, and the method comprises the steps that current to-be-taken elevator information corresponding to all floors is obtained through first image equipment corresponding to elevator halls of all the floors; the current elevator waiting information comprises figure information of the elevator waiting user; current operation information of each elevator is determined through second image equipment in each elevator car; when the person information has the preset feature information, based on the current operation information, a first elevator taken by the corresponding elevator waiting user meeting the preset feature information is determined; the target elevator is dispatched to a first floor where the to-be-taken user is located; the current elevator waiting information and the current operation information are input into an elevator dispatching model, and an elevator stopping dispatching result of a second floor except the first floor is obtained; the elevator stopping scheduling result is used for indicating the stopping floors of the second elevator except the first elevator. By adopting the method, the rationality of elevator stopping scheduling can be improved.

Description

Technical Field

[0001] The present application relates to the field of elevator control technology, and in particular to an elevator stop scheduling method, device, computer equipment and storage medium. Background Art

[0002] With the development of the field of intelligent algorithm technology, intelligent algorithms are increasingly used in the field of elevator control, especially for the Elevator Group Control System (ECGS), which often uses intelligent algorithms to achieve more accurate elevator dispatching control.

[0003] ECGS refers to the use of an automatic control system to dispatch and coordinate the operation of each elevator (usually 3 or more) installed in a building as an organic whole. The system aims to improve the operating efficiency of the vertical transportation system, provide services to passengers with shorter waiting time and running time, thereby improving service quality and reducing energy consumption.

[0004] However, in the related art, the elevator dispatching of the elevator group control system controlled by intelligent algorithms at least has the problem of unreasonable elevator operation distribution. Summary of the invention

[0005] Based on this, the purpose of this application is to solve at least one of the above-mentioned technical defects, especially the technical defect of unreasonable elevator operation distribution in the prior art. This application provides an elevator stop scheduling method, device, computer equipment and storage medium.

[0006] In a first aspect, the present application provides an elevator stop scheduling method, the method comprising:

[0007] The current waiting elevator information corresponding to each floor is obtained through the first image devices corresponding to the elevator halls of each floor; the current waiting elevator information includes the character information of the user waiting to take the elevator;

[0008] Determine the current operation information of each elevator through the second imaging device in each elevator bridge;

[0009] In the case where the character information has preset characteristic information, based on the current operation information, a first elevator for the user to take the elevator that meets the preset characteristic information is determined; and the target elevator is dispatched to the first floor where the user to take the elevator is located;

[0010] The current waiting elevator information and the current operation information are input into the pre-trained elevator dispatching model. Through the elevator dispatching model, the elevator stop dispatching result of the second floor except the first floor is obtained; the elevator stop dispatching result is used to indicate the stop floor of the second elevator except the first elevator.

[0011] In one embodiment, the target waiting elevator information includes the space information required for taking the elevator, and the current operation information includes the remaining space information of the bridge compartment;

[0012] Through the elevator dispatching model, the elevator stop dispatching results for the second floor except the first floor are obtained, including:

[0013] Through the elevator dispatching model, based on the required space information and the remaining space information, the predicted information of the stay time of each second elevator for each floor is obtained;

[0014] Based on the dwell time prediction information, the floor stop results of each second elevator are obtained.

[0015] In one embodiment, obtaining the current waiting elevator information corresponding to each floor includes:

[0016] Acquire an elevator image through a first imaging device;

[0017] According to the elevator image, obtaining the body shape feature of the person and / or the volume feature of the object;

[0018] The required spatial information is determined based on the body shape features of the person and / or the volume features of the object.

[0019] In one embodiment, the method further comprises:

[0020] Determine the elevator status of each floor through the first imaging device;

[0021] If the boarding status of a floor is a status indicating cancellation of boarding, the elevator stop information of the floor is confirmed as information indicating cancellation of elevator stop.

[0022] In one embodiment, determining the elevator status of each floor through the first imaging device includes:

[0023] Acquiring a person video having person features from a first imaging device;

[0024] Perform behavior detection on the person video to obtain the behavior detection result;

[0025] When the behavior detection result indicates that the person has left the elevator hall, the elevator riding state is confirmed as a state indicating cancellation of the elevator riding.

[0026] In one embodiment, the method further comprises:

[0027] Get the historical elevator information for the current time period;

[0028] Based on the current waiting elevator information and the historical elevator information, the target waiting elevator information is obtained;

[0029] The target waiting elevator information and the current operation information are input into the pre-trained elevator dispatching model, and the elevator stop dispatching result of the second floor except the first floor is obtained through the elevator dispatching model.

[0030] In one embodiment, the training method of the elevator dispatching model includes:

[0031] Obtain the satisfaction degree of the elevator stop scheduling results;

[0032] Based on the satisfaction level, determining a loss value for the elevator dispatching model;

[0033] According to the loss value, the elevator scheduling model is iteratively trained to obtain a trained elevator scheduling model.

[0034] In a second aspect, the present application provides an elevator stop scheduling device, the device comprising:

[0035] The elevator information module is used to obtain the current elevator information corresponding to each floor through the first image devices corresponding to the elevator halls of each floor; the current elevator information includes the character information of the user waiting to take the elevator;

[0036] An operation information module, used to determine the current operation information of each elevator through the second image device in each elevator bridge;

[0037] The first elevator module is used to determine the first elevator for the user to take the elevator corresponding to the preset characteristic information based on the current operation information when the character information has the preset characteristic information; and dispatch the target elevator to the first floor where the user to take the elevator is located;

[0038] The second elevator module is used to input the current waiting elevator information and the current operation information into a pre-trained elevator scheduling model, and obtain the elevator stop scheduling result for the second floor other than the first floor through the elevator scheduling model; the elevator stop scheduling result is used to indicate the stop floor of the second elevator other than the first elevator.

[0039] In a third aspect, the present application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the above method when executing the computer program.

[0040] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which implements the steps of the above method when the computer program is executed by a processor.

[0041] It can be seen from the above technical solutions that the embodiments of the present application have the following advantages:

[0042] The elevator stop scheduling method, device, computer equipment and storage medium provided by the present application can determine the current waiting elevator information and the current operation information in the elevator bridge car by combining with the image device, and can further determine whether the character information contains preset feature information. If the preset feature information exists, the corresponding waiting elevator users can be given priority to take the elevator. For example, priority elevator service can be provided to users with limited mobility, thereby reflecting the personalized service of the elevator group control system and improving the rationality of the elevator operation arrangement. At the same time, the present application can process and predict the current waiting elevator information and the current operation information through the elevator scheduling model to obtain the stop schedule of other floors. In this way, the stop scheduling arrangement of other floors can be accurately determined by combining AI video images and machine learning technology, which is conducive to improving the rationality of elevator stop scheduling. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.

[0044] Figure 1 A schematic diagram of a process of an elevator stop scheduling method provided in an embodiment of the present application Figure 1 ;

[0045] Figure 2 A schematic diagram of a process of an elevator stop scheduling method provided in an embodiment of the present application Figure 2 ;

[0046] Figure 3 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 3 ;

[0047] Figure 4 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 4 ;

[0048] Figure 5 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 5 ;

[0049] Figure 6 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 6 ;

[0050] Figure 7 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 7 ;

[0051] Figure 8 A schematic diagram of the structure of an elevator stop scheduling device provided in an embodiment of the present application;

[0052] Fig. 9 A schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0053] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0054] With the development of the field of intelligent algorithm technology, intelligent algorithms are increasingly used in the field of elevator control, especially for the Elevator Group Control System (ECGS), which often uses intelligent algorithms to achieve more accurate elevator dispatching control.

[0055] ECGS refers to the use of an automatic control system to dispatch and coordinate the operation of each elevator (usually 3 or more) installed in a building as an organic whole. The system aims to improve the operating efficiency of the vertical transportation system, provide services to passengers with shorter waiting time and running time, thereby improving service quality and reducing energy consumption.

[0056] Elevator AI group control technology integrates multiple sensors, data acquisition equipment and intelligent analysis systems to collect real-time data such as elevator operation status, passenger call information, floor passenger flow, etc. After processing, these data are input into the AI ​​algorithm model, which calculates the optimal elevator scheduling plan based on preset control rules and optimization goals, and adjusts the elevator's operation status in real time.

[0057] However, in the related art, the technology has the following problems:

[0058] (1) Insufficient adaptability: Although AI group control technology has strong learning and optimization capabilities, it may not be adaptable enough in extreme or special situations. For example, in unexpected or emergency situations, the system may not be able to respond quickly, resulting in obstruction of elevator operation or threat to passenger safety.

[0059] (2) Limited flexibility: The control strategies and optimization objectives of AI group control systems are usually implemented based on preset algorithms and models. However, in actual applications, the operating environment and passenger needs of the elevator system may change. If the system cannot flexibly adjust the control strategies and optimization objectives to adapt to these changes, it may cause system performance to deteriorate or fail to meet passenger needs.

[0060] That is, the existing elevator dispatching that controls the elevator group control system through intelligent algorithms at least has the problem of unreasonable elevator operation distribution.

[0061] Based on this, the present application provides an elevator stop scheduling method, device, computer equipment and storage medium. When there are passengers with preset characteristic information, the present application can give priority to the corresponding waiting elevator users to take the elevator, thereby reflecting the personalized service of the elevator group control system and improving the rationality of the elevator operation arrangement. At the same time, the present application can process and predict the current waiting elevator information and the current operation information through the elevator scheduling model to obtain the stop schedule of other floors. In this way, combined with AI video images and machine learning technology, the stop scheduling arrangement of other floors can be accurately determined, which is conducive to improving the rationality of elevator stop scheduling.

[0062] In an exemplary embodiment, Figure 1 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 1 ,like Figure 1 As shown, a method for scheduling elevator stops is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. In this embodiment, the method includes S101 to S104. Among them:

[0063] S101. Obtain the current information of the elevator user corresponding to each floor through the first imaging device corresponding to the elevator hall of each floor; the current information of the elevator user includes the personal information of the user waiting to take the elevator.

[0064] Among them, the elevator hall refers to the area where users wait for the elevator. The first imaging device may refer to a monitoring device installed in the elevator hall, which can be used to detect the user's elevator behavior, that is, it can be used to obtain the user's behavior information while waiting for the elevator. The current waiting elevator information may refer to the user's current behavior information while waiting for the elevator. For example, the user's behavior of waiting for the elevator in the elevator hall can be used as the current elevator information. At the same time, the user's information about leaving the elevator hall and canceling the elevator ride can also be used as the current waiting elevator information, that is, the elevator state corresponding to the current waiting elevator information represents the cancellation of the elevator ride. The current waiting elevator information may also include the character feature information of the user waiting for the elevator, for example, it may be the character's body feature information, so as to determine the elevator space and other elevator information required by the user waiting for the elevator.

[0065] It can be understood that the floors referred to here may be floors where elevator calls exist. If no elevator is called for a certain floor, the floor data for this floor is not needed.

[0066] Exemplarily, the server can obtain the user's elevator behavior information detected by the first image device in the elevator hall of each floor. For example, when it is detected that the user is waiting for the elevator, the behavior detection video of the first image device installed in the elevator hall of each floor can be obtained, and the current waiting elevator information can be obtained by analyzing the behavior detection video. The detection of the user's waiting elevator behavior can be triggered automatically by the first image device when the human feature is detected, or it can be triggered by the user clicking the elevator button. For example, after the user presses the up or down elevator button, the server can trigger the user's elevator behavior detection, so as to obtain the current waiting elevator information. The current waiting elevator information can include the feature information of the person of the waiting elevator user. Further, the elevator space information required by the waiting elevator user can be calculated based on the feature information of the person, so that the elevator space information can be used to better perform the scheduling of the elevator group control.

[0067] S102. Determine the current operation information of each elevator through the second imaging device in each elevator bridge compartment.

[0068] The second imaging device may refer to a monitoring device installed in the elevator car, which may be used to detect the riding behavior in the elevator car, that is, to obtain the operation information of the elevator car. The current operation information may refer to the space information of the elevator car, for example, the space occupied by the user in the elevator car may be used as the current operation information. The current operation information may also include the characteristic information of the person in the elevator car, for example, the body characteristic information of the person, so as to determine the space occupied by the elevator in the elevator car and other information.

[0069] Exemplarily, the server can obtain the elevator operation space information of each elevator car from the second image device. For example, while obtaining the current elevator information to be taken from the first image device, the server can obtain the space information in the elevator car through the second image device. Furthermore, the server can determine the remaining space information in each elevator car, thereby better scheduling the elevator group control.

[0070] S103. When the character information has preset characteristic information, determine the first elevator for the user to take the elevator that meets the preset characteristic information based on the current operation information; and dispatch the target elevator to the first floor where the user to take the elevator is located.

[0071] The preset characteristic information may refer to information with special characteristics that are set in advance, for example, it may be characteristics of a person with travel difficulties, such as sitting in a wheelchair, carrying crutches, etc., or characteristics of a pregnant woman, carrying large items, etc. The first elevator may refer to an elevator that can be taken by a user with the preset characteristic information. For example, if the user to be taken is in a wheelchair, the first elevator that meets the wheelchair space can be determined. The first floor refers to the floor where the user with the preset characteristic information is located.

[0072] Exemplarily, the server can determine whether the user waiting for the elevator has preset characteristic information. If the character information has preset characteristic information, the server can find the elevator that meets the preset characteristic information corresponding to the user waiting for the elevator according to the current operation information, and use it as the first elevator. The server can dispatch the first elevator to the floor where the user with the preset characteristic information is located, that is, the first floor. In this way, personalized elevator services can be provided to users with preset characteristic information, and elevator services can be provided preferentially to users with inconvenient travel. For example, for passengers carrying large luggage or strollers, sufficient space can be reserved in advance, and corresponding guidance information can be displayed inside the elevator to ensure that they can enter the elevator smoothly.

[0073] S104. Input the current waiting elevator information and the current operation information into a pre-trained elevator dispatching model, and obtain the elevator stop dispatching result for the second floor other than the first floor through the elevator dispatching model; the elevator stop dispatching result is used to indicate the stop floor of the second elevator other than the first elevator.

[0074] The elevator dispatch model may refer to a neural network model for dispatching group-controlled elevators, for example, a model based on a neural network, a recurrent neural network, and a deep neural network. The second floor may refer to a floor other than the first floor. The second elevator may refer to a floor other than the first elevator. The elevator stop dispatch result may refer to the elevator dispatch result for each second floor.

[0075] For example, the server can input the current waiting elevator information and the current operation information into the pre-trained elevator dispatch model, and obtain the elevator stop dispatch result of the second floor, that is, the stop result information of each second elevator through the prediction result of the elevator dispatch model. In this way, the server can determine the stop order of each second elevator on each second floor.

[0076] Through the machine learning of the elevator dispatching model, the stopping result of the second elevator at the second floor can be accurately determined. Combined with the personalized elevator service in the above step S103, the rationality of the elevator stop dispatching can be improved.

[0077] In this embodiment, by combining with the image device, the current waiting elevator information and the current operation information in the elevator bridge can be determined, and it can be further determined whether the character information contains preset feature information. If the preset feature information exists, the corresponding waiting elevator users can be given priority to take the elevator. For example, priority elevator services can be provided to users with limited mobility, thereby reflecting the personalized services of the elevator group control system and improving the rationality of the elevator operation arrangement. At the same time, the present application can process and predict the current waiting elevator information and the current operation information through the elevator scheduling model to obtain the stop arrangement of other floors. In this way, the stop scheduling arrangement of other floors can be accurately determined by combining AI video images and machine learning technology, which is conducive to improving the rationality of elevator stop scheduling.

[0078] In some specific embodiments, by deploying high-definition cameras and AI image recognition technology in elevator halls and public areas, the system can capture and analyze the number of residents waiting for elevators and their distribution in real time. Combined with advanced video computing algorithms, the system can quickly identify the waiting status of each passenger and possible floor requirements, thereby formulating an elevator scheduling strategy that is more in line with the current actual situation. This scheduling method based on real-time data effectively avoids the imbalance phenomenon of "busier people are busier and idle people are more idle" that may occur in traditional systems, and ensures the efficient allocation of elevator resources.

[0079] Advanced cameras and sensor networks are deployed in the elevator hall and inside the elevator. These devices can capture and analyze the body characteristics of passengers, the size of the items they carry, and the real-time layout inside the elevator. With the help of AI video analysis technology, the system can quickly calculate the elevator space required for each passenger and predict the number of additional passengers that the elevator can accommodate after it stops. In this way, the system can ensure that each elevator stop is as close to full as possible, rather than leaving some space vacant or overloaded, thereby maximizing the space utilization of the elevator.

[0080] By identifying the needs of different passengers, the system can provide more personalized services. For example, for passengers carrying large luggage or baby strollers, the system may reserve enough space in advance and display corresponding guidance information inside the elevator to ensure that they can enter the elevator smoothly. In addition, the system can also provide priority elevator services for specific users (such as elderly people with limited mobility or disabled people) through linkage with the building management system, further improving the rationality of elevator stop scheduling.

[0081] In an exemplary embodiment, the target waiting elevator information includes the required space information for taking the elevator, and the current operation information includes the remaining space information of the bridge compartment;

[0082] Through the elevator dispatching model, the elevator stop dispatching results for the second floor except the first floor are obtained, including:

[0083] Through the elevator dispatching model, based on the required space information and the remaining space information, the predicted information of the stay time of each second elevator for each floor is obtained;

[0084] Based on the dwell time prediction information, the floor stop results of each second elevator are obtained.

[0085] The required space information may refer to the space required by the users waiting to take the elevator, and the remaining space information may refer to the remaining space in the elevator bridge.

[0086] Exemplarily, the server can process the required space information and the remaining space information through the elevator scheduling model to obtain the time information that each second elevator needs to stay on each floor. For example, if the remaining space is larger than the required space, the required stay time may be shorter; if the remaining space is smaller than the required space, the required stay time may be longer. The elevator scheduling model can accurately predict the required stay time, and then the floor stop sequence of each second elevator can be arranged based on the stop time prediction information, so that the stop sequence of the second elevators can be arranged with the highest efficiency, thereby improving the efficiency of users taking the elevator and improving the rationality of elevator scheduling.

[0087] Advanced cameras and sensor networks are deployed in the elevator hall and inside the elevator. These devices can capture and analyze the body characteristics of passengers, the size of the items they carry, and the real-time layout inside the elevator. With the help of AI video analysis technology, the system can quickly calculate the elevator space required for each passenger and predict the number of additional passengers that the elevator can accommodate after it stops. In this way, the system can ensure that each elevator stop is as close to full as possible, rather than leaving some space vacant or overloaded, thereby maximizing the space utilization of the elevator.

[0088] In this embodiment, through the elevator scheduling model, based on the required space information and the remaining space information, the dwell time prediction information of each second elevator for each floor is obtained; based on the dwell time prediction information, the floor stop result of each second elevator can be obtained, thereby improving the operating efficiency of the group-controlled elevators and further improving the rationality of elevator scheduling.

[0089] In an exemplary embodiment, Figure 2 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 2 ,like Figure 2 As shown, in Figure 1 Based on the above, the step S101 is further described. In the step S101, the current waiting elevator information corresponding to each floor is obtained, which may specifically include:

[0090] S201. Acquire an elevator image through a first imaging device.

[0091] S202: Obtaining a person's body shape feature and / or an object's volume feature according to the elevator riding image.

[0092] S203: Determine required spatial information based on the body shape features of the person and / or the volume features of the object.

[0093] The elevator image may refer to an image of a user waiting to take the elevator. The body shape feature of a person refers to the body shape feature of a person. The object volume feature may be used to indicate the size of an object. The object volume feature may include the volume feature of a robot. For example, if there is a food delivery robot taking the elevator, the volume feature of the food delivery robot may be determined.

[0094] Exemplarily, the first imaging device can perform video monitoring of the elevator hall, and the server can obtain the video image uploaded by the first imaging device, and determine the elevator image corresponding to the user taking the elevator from the video image. The server can calculate and determine the body shape features and / or volume features of the person in the elevator image through the elevator image. In this way, the server can determine the elevator space required for taking the elevator based on information such as the body shape features and / or volume features of the object, and further based on the determined required elevator space, in this way, the elevator that meets the required elevator space can be better dispatched to the floor corresponding to the required elevator space, thereby improving the operating efficiency of the elevator and improving the rationality of group control elevator scheduling.

[0095] Optionally, based on the real-time recognition of space utilization and remaining space information, the system can dynamically adjust the elevator's parking strategy. When the system detects that there are a large number of passengers waiting on a certain floor and there is enough space inside the elevator to accommodate them, the elevator will be given priority to stop to reduce the waiting time of passengers.

[0096] Optionally, the specific needs of different types of passengers can also be taken into account. For example, for special purposes that require a larger elevator space (such as decoration and transportation), such passengers can be automatically guided to use a dedicated freight elevator during busy elevator hours to avoid affecting the elevator use of daily residential users. This customized service strategy not only ensures the elevator riding experience of residential users, but also promotes the rational use of elevator space resources.

[0097] In this embodiment, an image of the elevator is obtained through the first imaging device, and the body shape features and / or volume features of the person can be obtained based on the image of the elevator. Further, based on the body shape features and / or volume features of the person, the required spatial information can be effectively and accurately determined, so that the group-controlled elevator can be dispatched in combination with the required spatial information, thereby effectively improving the operating efficiency of the elevator, avoiding the situation where some elevator users can get on the elevator while others cannot, and improving the rationality of the scheduling of the group-controlled elevator.

[0098] In an exemplary embodiment, Figure 3 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 3 ,like Figure 3 As shown, in Figure 1 On the basis of the above, the elevator stop scheduling method is further described, and the method also includes:

[0099] S301, determining the elevator status of each floor through the first imaging device;

[0100] S302. If the boarding status of a floor is a status indicating cancellation of boarding, the elevator stop information of the floor is confirmed as information indicating cancellation of elevator stop.

[0101] The elevator status may refer to whether there are users waiting for the elevator.

[0102] For example, the server can obtain multiple elevator images of the elevator hall from the first image device, and the server can determine whether each floor needs to take the elevator through the multiple elevator images. If there is a floor where the elevator is canceled, the elevator can be canceled from stopping at that floor. In this way, if the passenger cancels the elevator request or leaves temporarily before the elevator arrives, the system will immediately update the elevator's stop plan to avoid unnecessary stops and improve the elevator's operating efficiency.

[0103] In an exemplary embodiment, determining the elevator status of each floor through the first image device includes:

[0104] Acquiring a person video having person features from a first imaging device;

[0105] Perform behavior detection on the person video to obtain the behavior detection result;

[0106] When the behavior detection result indicates that the person has left the elevator hall, the elevator riding state is confirmed as a state indicating cancellation of the elevator riding.

[0107] The character video may refer to a video with character information. The behavior detection result may be a result of detecting the behavior of the character.

[0108] Exemplarily, the server can obtain a person video with a person detected from the first image device; and the server can use a preset behavior detection algorithm to perform behavior recognition on the person video to determine the behavior information of the person, that is, the behavior detection result of the person. If the behavior detection result indicates that the person has left the elevator hall, and the time when the person has left is greater than the preset time threshold, the user's elevator state can be confirmed as a state representing the cancellation of the elevator ride, and further, the elevator stop on this floor can be indicated. The time threshold referred to here can be 1 minute, 2 minutes, etc., which can be set according to actual conditions.

[0109] In this way, for passengers who temporarily cancel their elevator needs, the system can quickly identify and adjust the elevator operation plan accordingly to avoid unnecessary stops, thereby further improving the elevator's operating efficiency.

[0110] In this embodiment, behavior detection is performed on a person video to obtain a behavior detection result; when the behavior detection result indicates that the person has left the elevator hall, the elevator state can be confirmed as a state indicating cancellation of the elevator ride, thereby reducing unnecessary stops of the elevator, improving the operating efficiency of the elevator, and improving the rationality of elevator scheduling.

[0111] In an exemplary embodiment, Figure 4A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 4 ,like Figure 4 As shown, in Figure 1 Based on the above, the elevator stop scheduling method is further described, and the method also includes:

[0112] S401. Obtain historical elevator riding information for the current time period.

[0113] S402. Based on the current waiting-to-take elevator information and the historical elevator riding information, obtain the target waiting-to-take elevator information.

[0114] S403, input the target waiting elevator information and the current operation information into the pre-trained elevator dispatching model, and obtain the elevator stop dispatching result of the second floor except the first floor through the elevator dispatching model.

[0115] The historical elevator riding information may refer to the historical elevator riding data of the current time period. The target elevator waiting information may refer to the data combining the current elevator waiting information and the historical elevator riding information.

[0116] Exemplarily, the server can obtain historical elevator riding data for the current time period from the database. For example, during the peak elevator riding time period, the number of people who need to take the elevator on each floor can be determined from the historical elevator riding information, and the historical elevator stay time can be determined. Furthermore, based on the historical number of people in the current time period, the elevator scheduling can be reasonably adjusted.

[0117] The server can combine the current waiting elevator information and the historical elevator riding information to obtain the target waiting elevator information. For example, based on the current elevator riding information, it can determine whether it conforms to the trend of historical elevator riding data. For example, during peak elevator riding hours, the server can determine based on the number of people in the current elevator riding information whether there is a trend of more and more people taking the elevator. If so, the historical elevator riding information can be combined to predict the next target waiting elevator information. If not, the target waiting elevator information can be determined based on the current elevator riding information.

[0118] In addition, the server can input the target waiting elevator information and current operation information into the pre-trained elevator dispatch model, and predict the elevator stop dispatch result of the second floor except the first floor through the elevator dispatch model, so as to be conducive to more reasonable dispatch of group control elevators. For example, during the peak period of elevator riding, when the number of elevator users is increasing, the amount of elevator space required for each floor during this period can be determined by combining historical elevator riding information. In this way, the elevator dispatch information of each floor can be effectively predicted, thereby improving the operation efficiency of the elevator.

[0119] In actual applications, intelligent prediction can be achieved, which can predict the elevator usage trend in the future, including peak hours, popular floors, etc., based on historical data and current real-time information. Based on this, the system can automatically adjust the elevator's stop strategy, such as increasing the elevator's stop frequency or optimizing the stop sequence during peak hours to reduce the average waiting time of passengers.

[0120] In this embodiment, through the above steps S401 to S403, combined with historical elevator information, it is possible to more effectively predict and determine the elevator space required for the current time period, and make advance judgments on the scheduling of group-controlled elevators, thereby improving the operating efficiency of the elevators in the current time period and improving the rationality of the scheduling of group-controlled elevators.

[0121] In an exemplary embodiment, the training method of the elevator scheduling model includes:

[0122] Obtain the satisfaction degree of the elevator stop scheduling results;

[0123] Based on the satisfaction level, determining a loss value for the elevator dispatching model;

[0124] According to the loss value, the elevator scheduling model is iteratively trained to obtain a trained elevator scheduling model.

[0125] The satisfaction level may be a satisfaction value obtained by evaluating the dispatching of the elevator. The loss value may refer to a loss parameter used for model training.

[0126] Exemplarily, the server can obtain the results of the satisfaction survey set up in the elevator, and each time the satisfaction can be iterated into the current neural network calculation. According to these iterations, the current docking strategy is determined, and then the floors that each elevator needs to dock are predicted based on the docking strategy. For example, the server can obtain evaluation results such as the elevator waiting time, the elevator docking time, and the running time of the elevator to the target floor to determine the user's satisfaction with the elevator stop scheduling result. The server can determine the loss value for the elevator scheduling model based on the satisfaction through the loss function. Furthermore, the server can iteratively train the elevator scheduling model based on the loss value to obtain a trained elevator scheduling model. In this way, effective iterative training of the elevator scheduling model can be achieved, thereby improving the rationality of elevator scheduling.

[0127] In this embodiment, the loss value for the elevator scheduling model can be determined by the satisfaction level of the elevator stop scheduling result; and the elevator scheduling model can be iteratively trained according to the loss value to obtain a trained elevator scheduling model, thereby improving the optimization model for group control elevator scheduling and improving the rationality of group control elevator scheduling.

[0128] In some exemplary embodiments, Figure 5A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 5 ,exist Figure 1 Based on the above, the elevator stop scheduling method is further described, and the method also includes:

[0129] S501, Data Collection: Through the installation of sensors 501a inside and outside the elevator, AI cameras 501b, existing monitoring systems 501c, and other data sources 501d equipment, the elevator operation data and passenger travel information are collected in real time. These data include but are not limited to the elevator passenger capacity, arrival floors, dwell time, elevator speed, direction, floor, cumulative operation time, amplitude, leveling status, etc. Ensure that the collected data is accurate and complete, and provide a reliable basis for subsequent data processing and analysis.

[0130] S502, data preprocessing, including:

[0131] S502a, data cleaning: clean the collected raw data to remove noise, outliers and duplicate data.

[0132] S502b, data deduplication: perform deduplication processing on possible duplicate data to ensure the uniqueness of the data.

[0133] S502c, data filling: For missing data, reasonable filling is performed based on context information or historical data to ensure data integrity.

[0134] S503, feature extraction: extract useful features from the preprocessed data, which can reflect the use of the elevator and the travel needs of passengers. For example, the average stay time of the elevator, the maximum passenger capacity, the arrival time distribution of passengers and other features can be extracted.

[0135] Figure 6 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 6 ,like Figure 6 As shown, the method also includes:

[0136] Continue with the above step S503;

[0137] S601, external entity model establishment and training, including:

[0138] S601a, select the model: according to the needs of elevator group control, use convolutional neural network, recurrent neural network and deep neural network to build the model;

[0139] S601b, model training: use the extracted feature data to train the model so that the model can accurately predict the operating status of the elevator and the travel needs of passengers.

[0140] S601c, Model evaluation: Evaluate the model through methods such as cross-validation to ensure the accuracy and generalization ability of the model.

[0141] S602: Formulate external entity scheduling strategy, including:

[0142] S602a, Personalized ride: By identifying the needs of different passengers, the system can provide more personalized services. For example, for passengers with large luggage or baby strollers, the system may reserve enough space in advance and display corresponding guidance information inside the elevator to ensure that they can enter the elevator smoothly.

[0143] S602b. Special needs: By linking with the building management system, priority elevator service can be provided to specific users (such as elderly people with limited mobility or disabled people), further demonstrating humanistic care.

[0144] S602c, Strategy optimization: According to the actual operation of the elevator and the feedback from passengers, the scheduling strategy is continuously optimized to improve the overall performance of the system.

[0145] S602d, Intelligent Dispatch: Formulate elevator dispatch strategies based on the trained model. The system will automatically adjust the elevator's route and stop floors based on real-time data and prediction results to optimize the elevator's operating efficiency and passengers' travel experience.

[0146] Figure 7 A schematic diagram of a process for an elevator stop scheduling method provided in an embodiment of the present application Figure 7 ,like Figure 7 As shown, the method also includes:

[0147] Continue with the above step S602;

[0148] S701, real-time monitoring and feedback.

[0149] S702, HD cameras and AI image recognition: Through the deployment of HD cameras and AI image recognition technology in elevator halls and public areas, the system can capture and analyze the number of residents waiting for elevators and their distribution in real time. Combined with advanced video computing algorithms, the system can quickly identify the waiting status and possible floor requirements of each passenger, thereby formulating an elevator scheduling strategy that is more in line with the current actual situation. This scheduling method based on real-time data effectively avoids the imbalance phenomenon of "busier people are busier and idle people are more idle" that may occur in traditional systems, and ensures the efficient allocation of elevator resources.

[0150] S703, identifying special passengers;

[0151] S704. Real-time analysis of passenger quantity and distribution, including: S704a. Timely adjustment of cancellation requests.

[0152] S705. Accurate control identification and utilization optimization, including: S705a. Real-time space utilization and remaining space information; S705b. Identification of elevator demand.

[0153] Based on the real-time recognition of space utilization and remaining space information, the system can dynamically adjust the elevator's parking strategy. When the system detects that there are a large number of passengers waiting on a certain floor and there is enough space inside the elevator to accommodate them, the elevator will be given priority to stop to reduce the waiting time of passengers. At the same time, if the passenger cancels the elevator request or leaves temporarily before the elevator arrives, the system will immediately update the elevator's parking plan to avoid unnecessary stops and improve the elevator's operating efficiency.

[0154] S706, AI scheduling calculation and strategy update.

[0155] S707. Predictions based on historical and real-time data.

[0156] S708, Intelligent prediction and dynamic adjustment: With intelligent prediction function, it can predict the elevator usage trend in the future, including peak hours, popular floors, etc., based on historical data and current real-time information. Based on this, the system can automatically adjust the elevator's stop strategy, such as increasing the elevator's stop frequency or optimizing the stop sequence during peak hours to reduce the average waiting time of passengers. At the same time, for passengers who temporarily cancel their elevator needs, the system can also quickly identify and adjust the elevator operation plan accordingly to avoid unnecessary stops, thereby further improving the elevator's operating efficiency.

[0157] S709, Real-time monitoring of elevator status: Real-time monitoring of the elevator's operating status to ensure the safe operation of the elevator. Perform AI scheduling calculations in real time based on the residents' waiting conditions and update the scheduling strategy.

[0158] S710, Abnormal detection and alarm: The AI ​​algorithm is used to analyze the operation data of the elevator in real time, and timely detect and alarm various abnormal events such as overspeed, squatting at the bottom, rushing to the top, opening the door and walking, and stopping at non-level floors.

[0159] S711. User feedback collection: Collect passengers’ travel experience feedback as a basis for optimizing scheduling strategies.

[0160] S712, System maintenance and upgrade: Regularly maintain and inspect the elevator group control system to ensure the stable operation of the system. According to technological progress and changes in user needs, upgrade and transform the system to adapt to new application scenarios and needs.

[0161] The entire system is also equipped with powerful data analysis and visualization tools that can continuously collect and analyze various data during elevator operation, including but not limited to passenger waiting time, elevator full load rate, failure rate, etc. These data provide valuable decision-making support for property managers, enabling them to promptly discover and solve potential problems, continuously optimize elevator scheduling strategies, and improve overall service levels.

[0162] For example, Figures 5 to 7 The specific implementation methods can be implemented by referring to the above-mentioned embodiments or a combination of multiple embodiments, which will not be described in detail here.

[0163] In this embodiment, through real-time monitoring and precise scheduling, this scheduling method based on real-time data effectively avoids the imbalance phenomenon of "busier people are busier and idle people are more idle" that may occur in traditional systems, and ensures the efficient allocation of elevator resources. Improve the operating efficiency of elevators through intelligent prediction and dynamic adjustment. Through customized services and space optimization, this customized service strategy not only guarantees the elevator experience of residential users, but also promotes the rational use of elevator space resources. Through precise space identification and utilization optimization, in this way, the system can ensure that each elevator stop is as close to full load as possible, rather than partial space vacancy or overload, thereby maximizing the space utilization of the elevator. Improve the operating efficiency of the elevator through dynamic docking strategies and real-time adjustments. Provide priority elevator services for specific users (such as elderly or disabled people with limited mobility) through personalized ride experience, further demonstrating humanistic care.

[0164] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0165] The elevator stop scheduling device provided in the embodiment of the present application is described below. The elevator stop scheduling device and the above-mentioned elevator stop scheduling method have the same inventive concept, and the implementation solution for solving the problem provided by the device is similar to the implementation solution recorded in the above-mentioned method. Therefore, the specific limitations in one or more elevator stop scheduling device embodiments provided below can refer to the limitations on the elevator stop scheduling method above. The elevator stop scheduling device described below and the elevator stop scheduling method described above can be referred to each other, and will not be repeated here.

[0166] In an exemplary embodiment, Figure 8 A schematic diagram of the structure of an elevator stop scheduling device provided in an embodiment of the present application is shown in FIG. Figure 8 As shown, the elevator stop scheduling device 80 includes: an elevator information module 810, an operation information module 820, a first elevator module 830, and a second elevator module 840, wherein:

[0167] The elevator information module 810 is used to obtain the current elevator information corresponding to each floor through the first image devices corresponding to the elevator halls of each floor; the current elevator information includes the character information of the user waiting to take the elevator;

[0168] The operation information module 820 is used to determine the current operation information of each elevator through the second image device in each elevator bridge;

[0169] The first elevator module 830 is used to determine the first elevator for the user to take the elevator corresponding to the preset characteristic information based on the current operation information when the character information has the preset characteristic information; and dispatch the target elevator to the first floor where the user to take the elevator is located;

[0170] The second elevator module 840 is used to input the current waiting elevator information and the current operation information into a pre-trained elevator scheduling model, and obtain the elevator stop scheduling result for the second floor other than the first floor through the elevator scheduling model; the elevator stop scheduling result is used to indicate the stop floor of the second elevator other than the first elevator.

[0171] In an exemplary embodiment, the target waiting elevator information includes the space information required for taking the elevator, and the current operation information includes the remaining space information of the bridge car.

[0172] The second elevator module is used to obtain the dwell time prediction information of each second elevator for each floor based on the required space information and the remaining space information through the elevator scheduling model; and obtain the floor stop result of each second elevator based on the dwell time prediction information.

[0173] In an exemplary embodiment, the elevator information module is used to obtain an elevator image through a first imaging device; obtain a person's body shape features and / or an object's volume features based on the elevator image; and determine required spatial information based on the person's body shape features and / or the object's volume features.

[0174] In an exemplary embodiment, the elevator information module is also used to determine the elevator status of each floor through the first image device; if the elevator status of a floor is a state indicating cancellation of the elevator, the elevator stop information of the floor is confirmed as information indicating cancellation of the elevator stop.

[0175] In an exemplary embodiment, the elevator information module is used to obtain a person video with person features from a first imaging device; perform behavior detection on the person video to obtain a behavior detection result; and when the behavior detection result indicates that the person has left the elevator hall, confirm the elevator status as a status indicating cancellation of the elevator ride.

[0176] In an exemplary embodiment, the second elevator module is also used to obtain historical elevator riding information for the current time period; obtain target elevator riding information based on current elevator waiting information and historical elevator riding information; input the target elevator waiting information and current operation information into a pre-trained elevator scheduling model, and obtain the elevator stop scheduling result for the second floor other than the first floor through the elevator scheduling model.

[0177] In an exemplary embodiment, the device also includes a model training module.

[0178] The model training module is used to obtain the satisfaction level of the elevator stop scheduling results; based on the satisfaction level, the loss value of the elevator scheduling model is determined; according to the loss value, the elevator scheduling model is iteratively trained to obtain a trained elevator scheduling model.

[0179] In an exemplary embodiment, the present application also provides a computer-readable storage medium, in which a computer program is stored. When the computer program is executed by one or more processors, the one or more processors execute the steps of the elevator stop scheduling method in any of the above embodiments.

[0180] In an exemplary embodiment, the present application also provides a computer device having a computer program stored therein, wherein when the computer-readable instructions are executed by one or more processors, the one or more processors execute the steps of the elevator stop scheduling method as described in any one of the above embodiments.

[0181] In an exemplary embodiment, the present application further provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of any of the elevator stop scheduling methods in the above embodiments.

[0182] Indicatively, Fig. 9 As shown, Fig. 9 This is a schematic diagram of the internal structure of a computer device provided in an embodiment of the present application. The computer device 900 may be provided as a server. Fig. 9 The computer device 900 includes a processing component 902, which further includes one or more processors, and a memory resource represented by a memory 901 for storing instructions executable by the processing component 902, such as an application. The application stored in the memory 901 may include one or more modules, each corresponding to a set of instructions. In addition, the processing component 902 is configured to execute the instructions to perform the text recognition method of any of the above embodiments.

[0183] The computer device 900 may further include a power supply component 903 configured to perform power management of the computer device 900, a wired or wireless network interface 904 configured to connect the computer device 900 to a network, and an input / output (I / O) interface 905. The computer device 900 may operate based on an operating system stored in the memory 901, such as Windows Server TM, Mac OS X TM, Unix TM, Linux TM, Free BSD TM, or the like.

[0184] Those skilled in the art will understand that Fig. 9 The structure shown in the figure is only a block diagram of a part of the structure 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 certain components, or have a different arrangement of components.

[0185] It should be noted that the user information (including but not limited to user device information, user personal information, elevator information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0186] Finally, it should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0187] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The various embodiments can be combined as needed, and the same or similar parts can refer to each other.

[0188] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. An elevator stop scheduling method, characterized in that: The method comprises: Through the first image devices corresponding to the elevator halls of the respective floors, the current waiting elevator information corresponding to the respective floors is obtained; the current waiting elevator information includes the character information of the waiting elevator user; Determining the current operation information of each elevator by means of a second imaging device in each elevator bridge compartment; In the case where the character information has preset characteristic information, based on the current operation information, a first elevator for the user to take the elevator corresponding to the preset characteristic information is determined; and the target elevator is dispatched to the first floor where the user to take the elevator is located; The current waiting elevator information and the current operation information are input into a pre-trained elevator scheduling model, and the elevator stop scheduling result of the second floor other than the first floor is obtained through the elevator scheduling model; the elevator stop scheduling result is used to indicate the stop floor of the second elevator other than the first elevator.

2. The method according to claim 1, characterized in that The target waiting elevator information includes the space information required for taking the elevator, and the current operation information includes the remaining space information of the bridge compartment; The step of obtaining the elevator stop scheduling result for the second floor other than the first floor through the elevator scheduling model includes: Obtaining, by means of the elevator dispatching model, stop time prediction information of each of the second elevators for each of the floors based on the required space information and the remaining space information; Based on the dwell time prediction information, the floor stop result of each of the second elevators is obtained.

3. The method according to claim 2, characterized in that The obtaining of the current waiting elevator information corresponding to each of the floors includes: Acquire an elevator image through the first imaging device; Obtaining a person's body shape feature and / or an object's volume feature according to the elevator image; The required spatial information is determined based on the body shape features of the person and / or the volume features of the object.

4. The method according to claim 1, characterized in that: The method further comprises: Determining the elevator status of each of the floors through the first imaging device; If the elevator riding status of a floor is a status indicating cancellation of the elevator riding, the elevator stop information of the floor is confirmed as information indicating cancellation of the elevator stop.

5. The method according to claim 4, characterized in that Determining the elevator status of each floor through the first image device includes: Acquire a person video having person features from the first image device; Performing behavior detection on the person video to obtain a behavior detection result; When the behavior detection result indicates that the person has left the elevator hall, the elevator riding state is confirmed as a state indicating cancellation of the elevator riding.

6. The method according to claim 1, characterized in that The method further comprises: Get the historical elevator information for the current time period; Based on the current waiting elevator information and the historical elevator information, obtaining target waiting elevator information; The target waiting elevator information and the current operation information are input into a pre-trained elevator dispatching model, and the elevator stop dispatching result of the second floor except the first floor is obtained through the elevator dispatching model.

7. The method according to claim 1, characterized in that The training method of the elevator scheduling model includes: Obtain the satisfaction degree of the elevator stop scheduling results; Based on the satisfaction level, determining a loss value for the elevator scheduling model; The elevator scheduling model is iteratively trained according to the loss value to obtain a trained elevator scheduling model.

8. An elevator stop dispatching device, characterized in that: The device comprises: The elevator information module is used to obtain the current elevator information corresponding to each floor through the first image devices corresponding to the elevator halls of each floor; the current elevator information includes the character information of the user waiting to take the elevator; An operation information module, used to determine the current operation information of each elevator through a second imaging device in each elevator bridge compartment; A first elevator module is used to determine, when the character information has preset characteristic information, based on the current operation information, a first elevator for a waiting user to take the elevator corresponding to the preset characteristic information; and dispatch the target elevator to the first floor where the waiting user is located; The second elevator module is used to input the current waiting elevator information and the current operation information into a pre-trained elevator scheduling model, and obtain the elevator stop scheduling result of the second floor other than the first floor through the elevator scheduling model; the elevator stop scheduling result is used to indicate the stop floor of the second elevator other than the first elevator.

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 7 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 7 are implemented.

Images