Elevator control method, device and computer equipment based on multiple scenarios

Abstract

The present application relates to a multi-scenario-based elevator control method, device and computer equipment, and relates to the field of intelligent linkage technology. The method includes: obtaining the physical characteristics, target floors and passenger flow information of the objects waiting for the elevator in the elevator lobby, analyzing the elevator usage needs and determining the scheduling plan. After the guidance information is output in the elevator lobby, the boarding video data is used to identify the resident and external waiting objects, and the resident building linkage data is generated based on the historical behavior of the resident objects to provide customized behavior guidance. For external objects, external building linkage data is generated according to their waiting behavior for analysis and management by the monitoring center. The use of this method can realize dynamic elevator control and elevator linkage, and further realize the accuracy of elevator scheduling and dynamic management of building passenger flow.

Description

Technical Field

[0001] The present application relates to the field of intelligent linkage technology, and in particular to a multi-scenario based elevator control method, device and computer equipment. Background Art

[0002] In traditional technology, elevator control methods are mainly implemented through fixed logic circuits or simple programmable controllers (PLCs). There are buttons inside and outside the elevator for passengers to send call signals. After the signal is transmitted to the control center, the control center controls the operation of the elevator according to the pre-set priority strategy (such as forward priority, shortest path priority, etc.). The entire process relies on mechanical relays or simple electrical switches to complete signal recognition and execution actions, and realize floor arrival and door opening and closing control through fixed lines. However, the elevator control method in traditional technology only controls the priority strategy of the elevator, and it is difficult to make dynamic adjustments according to the current actual situation, and it is impossible to achieve dynamic elevator control and elevator linkage. Summary of the invention

[0003] Based on this, it is necessary to provide a multi-scenario elevator control method, device and computer equipment that can realize dynamic elevator control and elevator linkage to address the above technical problems.

[0004] In a first aspect, the present application provides an elevator control method based on multiple scenarios, including:

[0005] Obtaining physical feature information and target floor information of each target waiting object in the elevator lobby, and obtaining passenger flow information of the elevator lobby;

[0006] Performing an elevator usage demand analysis based on the physical feature information, the target floor information, and the passenger flow information, and determining the dispatching information of each elevator;

[0007] Outputting the guidance information of the waiting object corresponding to each of the elevator dispatching information in the elevator waiting hall, and acquiring the video data of the object boarding the elevator corresponding to each of the elevator waiting object guidance information;

[0008] Among the target elevator waiting objects corresponding to any of the elevator climbing video data, identifying the resident elevator waiting objects and the external elevator waiting objects;

[0009] Generate resident building linkage data of any of the resident elevator waiting objects according to the historical behavior data of the resident elevator waiting objects in the target building;

[0010] Generate external building linkage data of any external elevator waiting object according to the elevator waiting behavior data of the external elevator waiting object in the elevator lobby;

[0011] Generate resident behavior guidance data of the resident waiting elevator object according to the resident building linkage data; the resident behavior guidance data is sent to the resident waiting elevator object by controlling the elevator;

[0012] According to the external building linkage data, the external behavior monitoring data of the external elevator waiting object is generated; the external behavior monitoring data is sent to the building monitoring center by controlling the elevator. In the second aspect, the present application also provides an elevator control device based on multiple scenarios, including:

[0013] A data acquisition module, used to acquire physical feature information and target floor information of each target waiting object in the elevator lobby, and to acquire passenger flow information of the elevator lobby;

[0014] A demand analysis module, used to analyze the demand for elevator use according to the physical feature information, the target floor information and the passenger flow information, and determine the dispatching information of each elevator;

[0015] An object guidance module, used for outputting the waiting object guidance information corresponding to each elevator dispatching information in the elevator waiting hall, and obtaining the object boarding video data corresponding to each waiting object guidance information;

[0016] An object recognition module is used to recognize each resident elevator waiting object and each external elevator waiting object in the part of the target elevator waiting objects corresponding to any of the object climbing the elevator video data;

[0017] A data analysis module, for generating resident building linkage data of any resident waiting for elevator object according to historical behavior data of the resident waiting for elevator in the target building;

[0018] The data analysis module is further used to generate external building linkage data of any external elevator waiting object according to the elevator waiting behavior data of the external elevator waiting object in the elevator waiting hall;

[0019] A data generation module, used for generating resident behavior guidance data of the resident waiting elevator object according to the resident building linkage data; the resident behavior guidance data is sent to the resident waiting elevator object by controlling the elevator;

[0020] The data generation module is also used to generate external behavior monitoring data of the external elevator waiting object according to the external building linkage data; the external behavior monitoring data is sent to the building monitoring center by controlling the elevator.

[0021] In a third aspect, the present application further provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements any step in a multi-scenario based elevator control method.

[0022] The above-mentioned multi-scenario-based elevator control method, device and computer equipment, by acquiring the physical characteristics information, target floor information and passenger flow information of each target waiting object in the elevator lobby, accurately analyzes the elevator usage demand and generates scheduling information, thereby realizing the intelligent and dynamic management of elevator operation. On this basis, combined with the object boarding video data, distinguish between permanent waiting objects and external waiting objects, and generate linkage guidance information based on the historical behavior data of the permanent waiting objects in the target building, provide personalized building and passage services for the permanent waiting objects, and optimize their usage experience; at the same time, generate monitoring information based on the waiting behavior data of external waiting objects in the elevator lobby, and strengthen the real-time monitoring capabilities of building safety management and abnormal behavior. Through accurate response and management of the needs of different objects, dynamic elevator control and elevator linkage can be realized, further realizing the accuracy of elevator scheduling and dynamic management of building passenger flow, comprehensively improving the efficiency of elevator scheduling, improving user experience, and providing strong guarantees for the safety and operation efficiency of the building. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the related technologies, the drawings required for use in the embodiments or the related technical descriptions are 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 work.

[0024] Figure 1 is an application environment diagram of an elevator control method based on multiple scenarios in one embodiment;

[0025] Figure 2 1 is a flow chart of an elevator control method based on multiple scenarios in an embodiment;

[0026] Figure 3 1 is a flow chart of a first method for determining elevator dispatching information in an embodiment;

[0027] Figure 4 A schematic diagram of a flow chart of a method for determining elevator scheduling constraint conditions and elevator scheduling target information in one embodiment;

[0028] Figure 5 is a flow chart of a second elevator dispatching information method in one embodiment;

[0029] Figure 6 It is a flowchart of a method for generating external building linkage data in one embodiment;

[0030] Figure 7A schematic diagram of a flow chart of a first method for obtaining foreign object risk assessment data in one embodiment;

[0031] Figure 8 is a flow chart of a second method for obtaining foreign object risk assessment data in one embodiment;

[0032] Fig. 9 1 is a flow chart of a third method for obtaining foreign object risk assessment data in one embodiment;

[0033] Fig.10 The figure is a structural block diagram of an elevator control device based on multiple scenarios in one embodiment. DETAILED DESCRIPTION

[0034] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying 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.

[0035] The present application provides a multi-scenario elevator control method, which can be applied to Figure 1 In the application environment shown. Among them, the terminal 102 communicates with the server 104 through the network. The data storage system can store the data that the server 104 needs to process. The data storage system can be integrated on the server 104, or it can be placed on the cloud or other network servers. Among them, the server 104 can be implemented with an independent server or a server cluster composed of multiple servers.

[0036] In an exemplary embodiment, Figure 2 As shown, a multi-scenario elevator control method is provided, and the method is applied to Figure 1 The server in the example is used to illustrate, including the following steps 202 to 216. Among them:

[0037] Step 202, obtaining the physical feature information and target floor information of each target waiting object in the elevator lobby, and obtaining the waiting passenger flow information in the elevator lobby.

[0038] The target waiting person may be a person who is waiting to take the elevator in the elevator lobby.

[0039] Among them, the physical feature information can be biometric data related to the target elevator waiting object, such as facial features, height, weight, body shape, etc., which is used to confirm the identity of the object and monitor its behavior.

[0040] The target floor information may be the floor selected by the elevator waiting object, that is, the elevator floor to which the object wishes to go.

[0041] The passenger flow information for elevators may be passenger flow data in the elevator lobby, including the number, distribution, and retention time of passengers waiting for the elevator.

[0042] Specifically, cameras and sensors are installed in the elevator lobby to obtain the physical characteristics of passengers. For example, facial recognition technology is used to obtain the facial information of passengers, so as to infer their age, gender and other physical characteristics; a weight sensing platform is used to determine the approximate weight of passengers or the weight of the items they carry. In addition, by installing equipment such as flow meters or thermal imaging cameras, passenger flow information in the elevator lobby can be monitored in real time. For example, if there are 30 people waiting for the elevator in the elevator lobby during a certain period of time, the target floors of these people can be recorded, such as 10 of them going to the 10th floor, 5 going to the 20th floor, and the others are distributed on different floors.

[0043] Step 204, performing an elevator usage demand analysis based on the physical feature information, the target floor information, and the passenger flow information to determine the dispatching information of each elevator.

[0044] Among them, the elevator usage demand analysis can be based on the physical characteristics of the target waiting objects, the target floor information and the waiting passenger flow information, to evaluate the demand for elevators and predict the usage frequency, required service time, energy consumption, etc. of each elevator.

[0045] The elevator dispatching information may be the elevator dispatching strategy and arrangement determined by the system based on the analysis result of the elevator usage demand.

[0046] Specifically, when analyzing the passenger's physical characteristics, information about each target floor, and passenger flow information, the machine learning model can be applied to predict the demand for elevators. In the actual operation of the machine learning model, the elevator use demand analysis is performed through the real-time collected elevator lobby data. For example, the system monitors in real time that at 8:30 a.m., there are 50 passengers in the elevator lobby, of which 20 go to the 10th floor, 15 go to the 20th floor, and the remaining passengers' target floors are distributed on other floors. Based on these data, the machine learning model predicts how many elevators are needed and how to allocate them based on historical behavior data and real-time passenger flow. For example, the model may predict that 3 elevators are needed during this period, of which 1 will give priority to serving the high-demand areas on the 10th and 20th floors, and the remaining 2 will be allocated to other floors. The elevator dispatching system will automatically adjust the elevator's stop order and passenger loading strategy based on the model's analysis of elevator use demand to ensure efficient operation, reduce waiting time and avoid overload, thereby adjusting the priority of elevator operation and obtaining the elevator dispatching information corresponding to each elevator.

[0047] Step 206: outputting the guidance information of the waiting object corresponding to each elevator dispatching information in the elevator lobby, and acquiring the video data of the object boarding the elevator corresponding to each elevator waiting object guidance information.

[0048] The guidance information for the elevator waiting object may include path guidance, elevator boarding prompts and other information provided to the target elevator waiting object.

[0049] The subject boarding video data may be a real-time video of the subject boarding the elevator captured by a camera in the elevator lobby.

[0050] Specifically, the elevator dispatch information corresponding to each elevator is displayed in real time in the elevator lobby through a large screen, LED display or voice broadcast. Assuming that the dispatch system assigns elevator A to the 10th floor and elevator B to the 20th floor according to the elevator dispatch information of elevator A, the system will display in the elevator lobby: "Elevator A goes to the 10th floor, please go to the left elevator"; "Elevator B goes to the 20th floor, please go to the right elevator". At the same time, the camera continuously records the passenger boarding process in the elevator lobby and obtains the subject boarding video data to ensure that the passengers get on the bus according to the guidance information. For example, the camera will record whether the passenger goes to the correct elevator according to the prompts, and obtain data in real time for behavior analysis.

[0051] Step 208, identifying the resident waiting objects and the external waiting objects from among the partial target waiting objects corresponding to the video data of any object boarding the elevator.

[0052] Specifically, permanent elevator waiting objects refer to passengers who frequently move around in this building, while external elevator waiting objects refer to passengers who occasionally move around in this building. By processing the object's elevator boarding video data using methods such as face recognition and RFID tags, the system can identify permanent elevator waiting objects. For example, if a passenger takes the elevator from the 1st floor to the 10th floor at 5 pm every Friday, the system will identify her as a permanent elevator waiting object. In contrast, passengers who occasionally move around in this building are identified as external elevator waiting objects in the elevator. In addition to identifying them based on the object's elevator boarding video data, the system also uses its behavioral data (such as the first appearance in the elevator lobby, no historical behavioral data, etc.) to make multiple distinctions.

[0053] Step 210: Generate resident building linkage data of any resident waiting for elevator object according to historical behavior data of the resident waiting for elevator in the target building.

[0054] The target building may be a building or floor that the elevator waiting object wants to go to. These buildings may be commercial buildings, office buildings, residential buildings, etc.

[0055] Among them, the historical behavior data can be the target waiting object's past activity records in the elevator lobby and in the building, including the time, frequency, and frequently visited floors of the elevator.

[0056] Among them, the permanent building linkage data can be linkage information generated by the system according to the historical behavior data of the permanent elevator waiting object, which is used to optimize the object's living experience in the target building.

[0057] Specifically, the historical behavior data of the resident waiting elevator object includes information such as the passenger's elevator usage time, frequency, frequently visited floors and paths. Through this data, the system can identify the regular behavior patterns of the resident waiting elevator object. For example, resident waiting elevator object A takes the elevator from the 1st floor to the 15th floor at 8 o'clock every morning and often passes through the designated security access control area. The system will generate resident building linkage data based on these behavior records and automatically set seamless access permissions for resident waiting elevator object A. When resident waiting elevator object A arrives at the elevator again and is correctly identified, there is no need for identity authentication. The elevator and access control system will automatically identify and directly provide services for it.

[0058] Step 212: Generate external building linkage data of any external elevator waiting object based on the elevator waiting behavior data of the external elevator waiting object in the elevator lobby.

[0059] Among them, the waiting behavior data can be the real-time activity data of external waiting objects in the elevator lobby, including waiting time, position changes, floor selection, etc.

[0060] Among them, the external building linkage data can be the linkage information generated by the system based on the waiting behavior data of the external elevator waiting objects, which is mainly used to evaluate the potential risks of outsiders in the building and implement monitoring.

[0061] Specifically, the waiting behavior data of the external elevator object is the activity data in the elevator lobby, including the time when the passenger enters the elevator lobby, the location of the stop, the target floor selected, the waiting time, the conversation and movement, the walking path, etc. By monitoring this data, the system will analyze its behavior pattern and predict its possible activity path, and predict that it will continue to go to different floors, stay for a long time or behave abnormally. According to the prediction results, the system will generate external building linkage data for guiding monitoring, which is used to identify the external elevator object and track it in real time. For example, if the external elevator object B enters the elevator lobby at 9 o'clock in the morning and chooses to go to the 20th floor, the system will record its activity trajectory in the elevator lobby and analyze its behavior. If this passenger wanders in the elevator lobby for a long time, the system will issue an alarm to prompt the monitoring personnel that the passenger's behavior needs to be further observed to determine whether it has abnormal or unusual activities.

[0062] Step 214: Generate resident behavior guidance data of resident elevator waiting objects according to the resident building linkage data.

[0063] The resident behavior guidance data may be guidance information generated based on the resident building linkage data and used to guide the resident elevator waiting objects to perform activities.

[0064] Specifically, according to the resident building linkage data, the system generates a conversion instruction that conforms to the resident building linkage data for the resident waiting elevator object, converts the resident building linkage data into information that the resident waiting elevator object can intuitively understand, and serves as the specific behavior guidance data of the resident waiting elevator object. The system uses the transmitting component of the elevator and a technology such as wireless communication to send it to the handheld terminal of the resident waiting elevator object, helping it to reach the target floor more conveniently and pass through different floors. For example, the resident building linkage data indicates that the resident waiting elevator object A took the elevator from the 1st floor to the 5th floor at 8 o'clock this morning, and passed through three different access control on the 5th floor. The system will recognize this behavior and generate resident behavior guidance data. When the resident waiting elevator object A takes the elevator to the target floor, the system will send the resident behavior guidance data to the handheld terminal of the resident waiting elevator object A, and prompt it through texts including but not limited to texts and charts: "Please refer to the route to reach XX position, thank you."

[0065] Step 216, generating external behavior monitoring data of external elevator waiting objects according to the external building linkage data.

[0066] Among them, the outsider behavior monitoring data can be data generated based on the waiting behavior data of outsiders waiting for the elevator, which is used to analyze and evaluate the behavior patterns, potential risks and safety hazards of outsiders, and output data for mobilizing monitoring.

[0067] Specifically, the building monitoring center generates monitoring instructions (i.e., external behavior monitoring data) that match the external building linkage data through external building linkage data, instructing external elevator waiting objects to track them comprehensively on possible paths or places where abnormal behavior may occur. For example, if it is predicted that external elevator waiting object B stays too long on atypical floors or in sensitive areas, the system will automatically start monitoring equipment leading to these areas to focus on monitoring external elevator waiting object B, and transmit the behavior data of the object to the monitoring center. The staff of the monitoring center can view the activity trajectory of the object in real time and evaluate its behavior. If the external elevator waiting object is found to have abnormal behavior (such as bypassing security access control, changing the target floor, etc.), the monitoring center will trigger corresponding alarms and security measures to ensure building safety.

[0068] In the above-mentioned multi-scenario-based elevator control method, by obtaining the physical characteristics information, target floor information and passenger flow information of each target waiting object in the elevator lobby, the elevator usage demand is accurately analyzed and scheduling information is generated, thereby realizing intelligent and dynamic management of elevator operation. On this basis, combined with the object boarding video data, the permanent waiting objects and external waiting objects are distinguished, and linkage guidance information is generated based on the historical behavior data of the permanent waiting objects in the target building, providing personalized building and passage services for the permanent waiting objects, and optimizing their usage experience; at the same time, monitoring information is generated based on the waiting behavior data of external waiting objects in the elevator lobby, strengthening the real-time monitoring capabilities of building safety management and abnormal behavior. Through accurate response and management of the needs of different objects, dynamic elevator control and elevator linkage can be realized, further realizing the accuracy of elevator scheduling and dynamic management of building passenger flow, comprehensively improving the efficiency of elevator scheduling, improving user experience, and providing strong guarantees for the safety and operation efficiency of the building.

[0069] In an exemplary embodiment, Figure 3 As shown, the elevator use demand analysis is performed based on each body feature information, each target floor information and the waiting passenger flow information to determine each elevator dispatch information, including steps 302 to 306. Among them:

[0070] Step 302, determining elevator dispatching constraint conditions and elevator dispatching target information according to the elevator waiting passenger flow information and the predicted passenger flow information of the elevator lobby.

[0071] The predicted passenger flow information may be data obtained by predicting the passenger flow that will arrive in the elevator lobby and the building based on historical data, time periods, seasonal changes, and real-time monitoring.

[0072] Among them, the elevator dispatching constraints may be restrictions and requirements that must be followed during the elevator dispatching process, including but not limited to service time restrictions, elevator load upper limits, elevator energy consumption control, safety requirements, etc.

[0073] Among them, the elevator dispatch target information can be the goals to be achieved in the elevator dispatch process, including optimizing the operating efficiency of the elevator, reducing waiting time, reducing energy consumption, improving user experience, etc.

[0074] Specifically, the system collects the current passenger flow information in the elevator lobby through real-time monitoring, such as the number of people waiting for the elevator, the target floor, and the waiting time. At the same time, combined with the predicted passenger flow information generated by the passenger flow prediction model of the elevator lobby (for example, predicting the elevator usage in a specific time period), the system determines the constraints for elevator scheduling, such as the limit on the number of elevators, the upper limit of the load of each elevator, and the priority of floor stops. The scheduling target information includes optimizing elevator waiting time, reducing passenger congestion during peak hours, and ensuring that floor demands are met in a timely manner.

[0075] For example, during the morning rush hour (8:00-9:00), there are 60 people waiting for the elevator in the elevator lobby, of which 20 choose the 10th floor, 15 choose the 20th floor, and the remaining 25 choose other floors. The system predicts that the load of the elevator will reach its maximum during this period, so the constraint condition for elevator scheduling is set to a maximum passenger capacity of 10 people / elevator, and ensure that at least 2 elevators are running during this period. At the same time, the scheduling goal is to maximize the passenger riding efficiency, reduce the waiting time of passengers, and give priority to high-demand floors (such as the 10th and 20th floors).

[0076] Step 304, initializing the parameters of the elevator scheduling algorithm according to the elevator scheduling constraints and the elevator scheduling target information, and obtaining the elevator scheduling algorithm to be used.

[0077] Among them, the elevator dispatching algorithm can be an algorithm that uses a mathematical model / neural network to optimize elevator dispatching based on elevator dispatching target information and constraints.

[0078] The elevator scheduling algorithm to be used may be a scheduling algorithm that has not been used yet but is ready to be used during the elevator scheduling process.

[0079] Specifically, based on the elevator scheduling constraints and the elevator scheduling target information, the parameters of the elevator scheduling algorithm are initialized. These parameters may include the running speed of the elevator, the priority of the target floor, the empty / full state of the elevator, etc. By setting these parameters, the elevator scheduling algorithm to be used can optimize the allocation of elevator resources while satisfying the constraints. The initialization of the algorithm will ensure that during execution, the elevator scheduling can balance multiple needs, such as reducing the waiting time of passengers and avoiding overloading of elevators.

[0080] In the specific implementation, based on the elevator scheduling constraints and elevator scheduling target information, the system sets the maximum running speed of each elevator in the elevator scheduling algorithm to 2 floors per minute, giving priority to serving passengers on the 10th and 20th floors. Empty elevators give priority to serving farther floors (such as the 20th floor), while fully loaded elevators go to closer floors (such as the 5th and 10th floors). In addition, the minimum waiting time for the elevator is set to 30 seconds to avoid unnecessary energy consumption caused by frequent elevator starts.

[0081] Step 306: Input each body feature information, each target floor information and the passenger flow information waiting for the elevator into the dispatching algorithm of the elevator to be used to obtain the dispatching information of each elevator.

[0082] Specifically, after the elevator dispatching algorithm is initialized, the system will collect various data of each target waiting object in the elevator lobby (such as the passenger's physical characteristics information, the selected target floor information, etc.) in real time, as well as the passenger flow information of the current elevator lobby, and input them into the elevator dispatching algorithm to be used. For example, the passenger's target floor information helps the algorithm determine which floors have a large demand; the passenger's physical characteristics information (such as special needs groups such as the elderly and children) will affect the priority of elevator dispatching; the passenger flow information can reflect the pressure during peak hours in real time. By processing these input data, the system will eventually generate specific elevator dispatching information, such as the start time of each elevator, the order of the stop floors, the running route of each elevator, etc., to ensure the efficiency of elevator dispatching and the smooth travel of passengers.

[0083] Specifically, if the system detects in real time that an elderly passenger enters the elevator lobby and chooses to go to the 3rd floor, the system will use the elderly passenger's physical characteristics (such as the slow speed of the elevator) as a priority dispatching factor, assign it to the empty elevator A, and ensure that elevator A can serve first. At the same time, the system decides that elevator B will go to the 10th floor first based on the passenger flow during peak hours to meet the needs of most passengers. Ultimately, the elevator dispatching information will include elevator A serving the elderly passenger, elevator B serving the 10th floor first, and the stop order and route of each elevator will be adjusted accordingly to optimize efficiency.

[0084] In this embodiment, by determining the elevator dispatching constraints and target information based on the waiting passenger flow information and the predicted passenger flow information, the system can more accurately understand the real-time load of the waiting hall and the upcoming demand. After initializing the parameters of the elevator dispatching algorithm and inputting relevant information, the dispatching efficiency of the elevator can be optimized, and the optimal elevator allocation and route selection can be achieved, thereby reducing the elevator waiting time, improving the elevator operation efficiency, and effectively allocating elevator resources to avoid excessive crowding or idle elevators during peak hours. Ultimately, through the intelligent dispatching process, the system can provide each waiting object with smoother and more timely elevator services, improving the overall user experience and the operation efficiency of the building.

[0085] In an exemplary embodiment, Figure 4 As shown, according to the passenger flow information of the elevator waiting hall and the predicted passenger flow information of the elevator waiting hall, the elevator scheduling constraint conditions and the elevator scheduling target information are determined, including steps 402 to 406. Among them:

[0086] Step 402, extracting features from the passenger flow information waiting for the elevator and the predicted passenger flow information of the elevator lobby to obtain passenger flow feature data waiting for the elevator and predicted passenger flow feature data.

[0087] Among them, the characteristic data of passenger flow waiting for elevators can be the actual behavior characteristic data obtained after feature extraction of passenger flow waiting for elevators information, including waiting time, number of arrivals, stay time, floor selection distribution, changing trend of waiting time period, etc.; the characteristic data of predicted passenger flow can be the passenger flow characteristics of the waiting hall in the future period obtained after feature extraction of predicted passenger flow information.

[0088] Specifically, the system uses neural networks (such as CNN, etc.) to extract feature information from the passenger flow information of elevator waiting halls and the predicted passenger flow information of elevator waiting halls. For example, by combining the characteristics of holidays, weekdays, weather changes, etc., the system predicts the passenger flow change trend of the elevator waiting hall and the characteristics of demand during peak hours in a specific period of time in the future. The data extracted from the passenger flow information of elevator waiting halls is used as the passenger flow feature data of elevator waiting halls, and the data extracted from the predicted passenger flow information is used as the predicted passenger flow feature data.

[0089] For example, suppose the system detects through cameras that there are 60 people waiting for the elevator in the elevator lobby during the morning rush hour, of which 25 choose the 10th floor, 20 choose the 20th floor, and the remaining 15 choose other floors. At the same time, the system combines historical data and weather conditions to predict that in the next 10 minutes, the passenger flow in the elevator lobby will increase by 30% and the demand on the 10th and 20th floors will increase significantly. By extracting features from these data, the system obtains the passenger flow feature data (current number of people waiting for the elevator and target floor) and the predicted passenger flow feature data (future passenger flow and demand forecast).

[0090] Step 404, based on the passenger flow characteristic data and the predicted passenger flow characteristic data, the estimated number of arrivals at the elevator lobby, the peak arrival rate at the elevator lobby, and the average waiting time for the elevator are calculated.

[0091] Specifically, the system estimates the total number of people who will enter the elevator lobby in a certain period of time in the future based on the characteristic data of passenger flow waiting for the elevator (such as the current number of people waiting for the elevator, demand for each floor, waiting time for the elevator, etc.) and the predicted passenger flow characteristic data (such as passenger flow changes during peak hours). Then, based on the total number of people entering the elevator lobby during a certain period of time, the system calculates the peak arrival rate, that is, the number of passengers entering the elevator lobby per minute during the peak period, combined with the set prediction time period. Finally, the system uses the predicted arrival frequency and waiting time of the total number of people entering the elevator lobby during a certain period of time to calculate the average waiting time, that is, the average time it takes for passengers to take the elevator from entering the elevator lobby. The expected number of people arriving at the elevator lobby refers to the total number of passengers expected to enter the elevator lobby within a specific time period; the peak arrival rate of the elevator lobby refers to the number of passengers arriving at the elevator lobby per minute during the peak period; and the average waiting time for the elevator refers to the average time it takes for passengers to enter the elevator lobby and actually take the elevator. Through these indicators, the system can predict the load and pressure points of elevator scheduling in different time periods. For example, the system calculates that in the next 10 minutes, about 80 people will arrive at the elevator lobby, with a peak arrival rate of 10 people per minute and an average waiting time of 2 minutes.

[0092] Step 406, determining elevator dispatch constraints based on the estimated number of people arriving at the elevator lobby, the peak arrival rate at the elevator lobby, and the average waiting time for the elevator.

[0093] Specifically, the system uses the estimated number of people arriving at the elevator lobby, the peak arrival rate of the elevator lobby, and the average waiting time for the elevator to determine the constraints of elevator scheduling and set the upper and lower limits of elevator operation, that is, the elevator constraints, which include service time constraints (requiring the elevator to complete the task of picking up and dropping off passengers within the specified time), elevator energy consumption constraints (requiring to reduce elevator energy consumption as much as possible while ensuring service quality), elevator load constraints (ensuring that the passenger capacity of each elevator does not exceed the maximum load) and elevator safety constraints (ensuring safe elevator operation and preventing risks such as overload and failure).

[0094] For example, during the morning rush hour, the system calculates that the expected number of arrivals is 80, and the peak arrival rate is 10 people per minute. Based on this data, the system decides to set elevator scheduling constraints: ensure that the passenger capacity of each elevator does not exceed 10 people (load constraint), the travel time of each elevator does not exceed 5 minutes when picking up and dropping off passengers (service time constraint), and require that the idle time of the elevator be minimized during use to reduce energy consumption (energy consumption constraint). In addition, the system monitors the operating status of the elevator to ensure that it is not overloaded or has safety hazards (safety constraint).

[0095] In this embodiment, by extracting and analyzing the features of the waiting passenger flow information and the predicted passenger flow information, the system can accurately calculate the expected number of arrivals, peak arrival rate and average waiting time in the waiting hall. These key indicators provide an important basis for elevator scheduling, ensuring that the elevator can operate efficiently within the specified service time and reasonably allocate resources under different passenger flow loads. By considering multiple constraints such as the energy consumption, load and safety of the elevator, the system can not only optimize elevator scheduling and improve the passengers' waiting experience, but also reduce energy consumption and avoid elevator overload, ensure safe operation, and ultimately achieve high efficiency and energy saving in building operation.

[0096] In an exemplary embodiment, Figure 5 As shown, each body feature information, each target floor information and the waiting passenger flow information are input into the elevator scheduling algorithm to be used, and each elevator scheduling information is obtained, including steps 502 to 506. Among them:

[0097] Step 502, based on the service time constraint, the elevator energy consumption constraint, the elevator load constraint and the elevator safety constraint, according to the physical characteristic information, the target floor information and the passenger flow information, calculate the initial elevator scheduling information.

[0098] The initial elevator dispatching information may be a dispatching strategy initially generated during the elevator dispatching process based on input demand data (such as passenger flow waiting for the elevator, target floor information, service time, etc.) and elevator constraints.

[0099] Specifically, with service time constraints, energy consumption constraints, elevator load constraints, and elevator safety constraints as calculation constraints, the system will determine the order of elevator stops based on the passenger's target floor information, such as taking into account the special needs of passengers' physical characteristics (such as the elderly, pregnant women, etc.) for elevator services, and determining the passenger capacity of each elevator and the elevators that need to be dispatched based on the passenger flow information and elevator load limits. Then, considering unexpected situations during the elevator dispatch process, it is also necessary to consider emergency elevator dispatch in the event of an accident. The system calculates the dispatch plans of each elevator under the current conditions and obtains the initial elevator dispatch information. For example, assuming that an elderly passenger chooses to go to the 10th floor, the system gives priority to elevator A for the passenger based on his physical characteristics. Elevator A ensures that the maximum passenger capacity (for example, 10 people) is not exceeded during service, and the system calculates the running time and energy consumption of elevator A to ensure that it completes the task within a reasonable time and saves energy to the greatest extent, while not causing safety problems such as overload; since elevator A takes into account special situations, other elevators need to be mutually adaptively dispatched based on the passenger flow information.

[0100] Step 504, using different scheduling information optimization algorithms to find the Pareto frontiers of each initial elevator scheduling information, and obtain each initial optimal scheduling information.

[0101] The scheduling information optimization algorithm may be an optimization algorithm used in the elevator scheduling process in order to achieve a better effect of the initial elevator scheduling information.

[0102] The initial optimal scheduling information may be the optimal preliminary scheduling solution obtained after calculation and adjustment by the scheduling information optimization algorithm.

[0103] Specifically, the system uses a variety of different optimization algorithms (such as genetic algorithm, particle swarm algorithm, simulated annealing, etc.) to optimize each initial elevator scheduling information and calculate their "Pareto frontier". The Pareto front refers to the solution set that reaches the optimal balance point between multiple scheduling objectives (such as minimizing waiting time, minimizing energy consumption, maximizing elevator utilization, etc.). Through optimization, each optimization algorithm will obtain a set of candidate optimal scheduling solutions and obtain each initial optimal scheduling information.

[0104] When optimizing, assume that the system optimizes both "elevator waiting time" and "elevator energy consumption" at the same time, and calculate multiple possible scheduling schemes through genetic algorithm and particle swarm algorithm respectively. Some schemes may give priority to reducing waiting time, but have higher energy consumption; while other schemes may give priority to reducing energy consumption, but increase waiting time. In the end, the system finds a set of scheduling schemes that best balance these two objectives, forming two sets of Pareto frontiers.

[0105] Step 506: Select the solution with the highest data uniformity information from each initial optimal scheduling information as each elevator scheduling information.

[0106] The data uniformity information may be the uniformity of data distribution in each initial optimal scheduling information.

[0107] Specifically, after obtaining multiple initial optimal scheduling information, the system calculates the data uniformity information of each solution and selects the solution with the most uniform data distribution as the final elevator scheduling information. A solution with higher data uniformity information means that it can provide more balanced performance among multiple goals, and will not focus on a specific goal, but will comprehensively consider various needs.

[0108] For example, the system obtains multiple initial optimal scheduling information, some of which focus on reducing waiting time, while others focus on reducing energy consumption. If a solution provides a balanced optimization result between the two (for example, reducing waiting time while also effectively reducing energy consumption), the system will select this solution as the final elevator scheduling information.

[0109] In this embodiment, by comprehensively considering constraints such as service time, energy consumption, load and safety, the system can calculate a preliminary elevator dispatching plan based on the physical characteristics of the waiting object, the target floor and passenger flow information. Further, by adopting a dispatching information optimization algorithm and calculating the Pareto front of each plan, the system can find the optimal dispatching plan, balance various constraints, and ensure the efficient operation of the elevator. At the same time, by selecting the solution with the highest data uniformity from the initial optimal dispatching plan, the system can avoid unbalanced elevator dispatching, thereby achieving more accurate elevator resource allocation, improving passengers' waiting experience, reducing energy consumption and improving overall dispatching efficiency.

[0110] In an exemplary embodiment, Figure 6 As shown, according to the waiting behavior data of any external waiting object in the elevator lobby, the external building linkage data of the external waiting object is generated, including steps 602 to 606. Among them:

[0111] Step 602: Analyze the behavior pattern of the external object waiting for the elevator in the elevator lobby to obtain the external object behavior prediction data.

[0112] The behavior pattern analysis may be a process of collecting and analyzing the behavior data of external waiting objects in the elevator lobby to identify the regularity and pattern of their behavior.

[0113] Among them, the external object behavior prediction data can be the analysis and modeling of the behavior data of the external waiting objects in the elevator lobby and surrounding areas to predict the results of their future behavior; for example, the predicted behavior path, target floor selection, and dwell time of the external waiting objects.

[0114] Specifically, the system uses machine learning or data mining technology to analyze the behavior patterns of external waiting objects in the elevator lobby, that is, it uses clustering algorithms, random forests, K-nearest neighbor algorithms, hidden Markov models or association rule mining to identify the behavior patterns of external waiting objects (for example, whether there is regular elevator riding behavior, frequently selected floors, waiting time, etc.). Based on these patterns, the system can predict the behaviors that external waiting objects may take in the future and obtain the behavior prediction data of external objects, such as the target floor they may choose or the time point when they arrive at the elevator lobby.

[0115] Assume that the system observes that an external object C usually arrives at the elevator lobby at 9:00 a.m. and walks in circles, peeks, and makes abnormal movements in the elevator lobby. Based on these movements, the system analyzes the behavior patterns of the external objects waiting for the elevator, and further uses the analysis data to predict the path that object C will walk in the building in the future and the actions it will take, thereby obtaining the external object behavior prediction data.

[0116] Step 604: assess the risk of the foreign object waiting for the elevator in the target building based on the foreign object behavior prediction data to obtain foreign object risk assessment data.

[0117] Among them, the risk assessment data of foreign objects can be an assessment result generated by risk analysis based on the behavior patterns, prediction data and data interaction of foreign objects waiting for the elevator with other buildings; for example, the abnormal behavior indicators of foreign objects waiting for the elevator, the difference between the behavior prediction and historical behavior, the choice preference of the target floor, the abnormal stay time, and the activity trajectory in a specific time period.

[0118] Specifically, the system uses the foreign object behavior prediction data to evaluate whether the behavior pattern of the foreign object waiting for the elevator conforms to the normal behavior pattern and whether it is likely to be associated with known risk behaviors (such as entering sensitive areas, choosing unusual floors, etc.). Risk assessment may take into account factors such as security threats and identity authentication. For example, whether the foreign object frequently chooses floors in non-public areas, or stays in the elevator hall for a long time, and finally obtains the foreign object risk assessment data through evaluation. For example, the foreign object behavior prediction data of object C shows that in addition to the 5th floor, it will also choose to go to the 24th floor (an uncommon floor), and this floor is usually only visited by specific employees. The system will evaluate the behavior of object C when going to the 24th floor as a potential risk and mark the behavior as a high-risk behavior that needs to be monitored.

[0119] Step 606: Generate external building linkage data based on the external object behavior prediction data and the external object risk assessment data.

[0120] Specifically, based on the foreign object behavior prediction data and foreign object risk assessment data, the system will generate foreign building linkage data. These data are used to link with the building monitoring system to help the system identify and track the activities of foreign objects. For example, the system will trigger the behavior monitoring of the object, mobilize monitoring equipment such as cameras and access control systems for real-time monitoring, and provide the building security center with real-time status information of foreign objects. Foreign building linkage data not only helps to track foreign personnel in real time, but also can issue alarms in time when abnormal behavior occurs to ensure building safety.

[0121] In general, based on the foreign object behavior prediction data and foreign object risk assessment data of object C, the foreign building linkage data generated by the system will trigger the monitoring of object C. When object C goes to the uncommon 24th floor, the system will automatically turn on the surveillance camera on that floor and transmit the information to the security system so that security personnel can view and evaluate its behavior at any time. If object C enters a restricted area or exhibits abnormal behavior, the system will issue an alarm in time.

[0122] In this embodiment, by analyzing the behavior patterns of external objects waiting for elevators, the system can predict their behavior in the elevator lobby and evaluate their potential risks in the target building based on these predicted data. This process not only improves the accurate monitoring of the behavior of external objects, but also effectively identifies possible safety hazards and provides risk warnings for building managers. By generating external building linkage data, the system can mobilize monitoring equipment in real time and strengthen dynamic monitoring of external objects, thereby optimizing the operational efficiency of the building while ensuring safety. This process effectively improves the safety of the building, reduces the occurrence of potential risks, and ensures the safety of personnel and facilities.

[0123] In an exemplary embodiment, Figure 7 As shown, based on the foreign object behavior prediction data, the risk of the foreign object waiting for the elevator in the target building is evaluated to obtain the foreign object risk assessment data, including steps 702 to 706. Among them:

[0124] Step 702: Identify recorded behavior data of external elevator waiting objects from other buildings that interact with the target building.

[0125] The recorded behavior data may be data information of the behavior process of external elevator waiting objects recorded and stored in real time in other buildings.

[0126] Specifically, the system can interconnect with the data interaction systems of other buildings to achieve the effect of data interaction. Specifically, the system will check the behavior records of foreign objects waiting for elevators in other buildings related to elevators, access control systems, floor access, etc. These data may include the floors that the object has visited, the length of stay, whether there are unusual behavior patterns, etc. Through these recorded behavior data, the system can further understand the behavioral background and past activities of foreign objects. Suppose that foreign object D has stayed in the elevator lobby of some buildings for a long time and has tried to enter restricted areas. The system obtains these records of object D through data interaction with these buildings to help judge the potential risks of its behavior.

[0127] Step 704, compare the external object behavior prediction data with the recorded behavior data to obtain a behavior data comparison result.

[0128] The behavior data comparison result may be a result obtained by comparing the current behavior data of the external elevator waiting object with the past behavior data of the object.

[0129] Specifically, the system compares the predicted behavior data of the external object waiting for the elevator (such as the behavior inferred based on its habits, target floor, etc.) with the behavior record data obtained from other buildings. The purpose of the comparison is to identify whether there are abnormal situations where the predicted behavior is inconsistent with the past behavior or the difference is too large, or whether there are known risk behaviors of the object in other places. For example, the system can check whether the object regularly enters a specific floor or stays in certain areas for too long. These behavior patterns can indicate risks and obtain the behavior data comparison results. In the specific example, the system predicts that object D will arrive at the 10th floor at 9:00 am and go to the 11th floor through the fire escape, but by comparing with its records in other buildings, it is found that the object has tried to enter sensitive areas (such as underground parking lots or management) in multiple locations, which indicates that its behavior is potentially risky. The system marks this behavior as suspicious and records it in the risk assessment data.

[0130] Step 706, based on the behavior data comparison result and the foreign object behavior prediction data, the risk of the foreign object waiting for the elevator in the target building is evaluated to obtain foreign object risk evaluation data.

[0131] Specifically, the system conducts a risk assessment on the behavior of the foreign object in the target building based on the behavior data comparison results and the foreign object behavior prediction data. At this time, the system will analyze whether there are suspicious or abnormal behavior patterns in the foreign object behavior prediction data, and at the same time, evaluate whether the object poses a potential security risk based on the difference information in the behavior data comparison results. If the foreign object behavior prediction data indicates that there are suspicious behavior patterns, but the difference information in the behavior data comparison results indicates that the difference is less than the security threshold, or the foreign object behavior prediction data indicates that there are no suspicious behavior patterns, but the difference information in the behavior data comparison results indicates that the difference is greater than the security threshold, then according to the security principle, the suspicious behavior pattern or difference information is selected for risk assessment; if the foreign object behavior prediction data indicates that there are suspicious behavior patterns, and the difference information in the behavior data comparison results indicates that the difference is greater than the security threshold, the suspicious behavior pattern and difference information are used for risk assessment to obtain foreign object risk assessment data.

[0132] After comparison, the system found that subject D had multiple unauthorized behavior records in other buildings, and predicted that it might choose an unusual floor in the target building. Based on this data, the system assessed the risk of subject D in the target building as "high risk" and generated corresponding risk assessment data, reminding the building management system to strengthen monitoring of the subject.

[0133] In this embodiment, by interacting with data from other buildings, the system can identify the historical behavior data of external objects waiting for elevators, and compare it with the current behavior prediction data to obtain the behavior data comparison results. Based on these comparison results, the system can more accurately assess the potential risks of external objects in the target building and identify possible abnormal behaviors or safety hazards in advance. This process improves the behavior monitoring and risk identification capabilities of external objects, ensuring that building managers can take timely measures to deal with potential security threats, thereby improving the safety and operational efficiency of the building.

[0134] In an exemplary embodiment, Figure 8 As shown, based on the behavior data comparison result and the foreign object behavior prediction data, the risk of the foreign object waiting for the elevator in the target building is evaluated to obtain the foreign object risk assessment data, including steps 802 to 806. Among them:

[0135] Step 802: when the behavior data comparison result indicates that the behavior data difference value is less than a preset risk threshold, predict the current walking path of the external elevator waiting object in the target building based on the recorded behavior data.

[0136] The preset risk threshold may be a critical value used by the system to evaluate whether the behavior of an external waiting object has potential risks.

[0137] The current walking path may be a moving track of the external elevator waiting object from entering and exiting the elevator to the final destination floor during the current visit process.

[0138] Specifically, if the behavior data comparison result indicates that the behavior data difference value is less than the preset risk threshold, it means that the behavior of the external waiting object in the target building is relatively normal or consistent with that in other buildings, and no obvious abnormality or risk signs have been identified. At this time, the system will predict the walking path of the external waiting object in the target building based on the recorded behavior data of the external waiting object in other buildings (such as the floors frequently selected, the duration of stay, etc.). The system will analyze the historical behavior pattern of the object and combine the structure of the target building (such as floor layout, common routes, etc.) to infer the path that the object may take as the current walking path.

[0139] Assume that the behavior of the foreign subject E in the target building shows a consistent pattern with that in other buildings - always going directly from the elevator hall to the 2nd floor and staying there for 5 minutes. Since its behavior in other buildings is consistent with the prediction, the system cannot identify the abnormal situation. Based on the behavior of the subject going from the elevator hall to the 2nd floor in other buildings, the system predicts that the walking path in the target building is likely to be from the elevator hall to the 2nd floor. Therefore, the system predicts that the walking path of the subject at this time is "elevator hall → 2nd floor".

[0140] Step 804, predicting the predicted risk behavior and the predicted risk target of the external object waiting for the elevator in the target building according to the current walking path and the external object behavior prediction data.

[0141] Among them, predicting risky behavior can be based on the system's behavior pattern analysis, historical data, and current behavior prediction of external elevator waiting objects, and judging their possible abnormal behaviors.

[0142] The predicted risk target may be a specific target object or target area where the system predicts that the object may cause risks to the outside after analyzing the behavior of the external elevator waiting object.

[0143] Specifically, after determining the current walking path of the external object waiting for the elevator, the system combines its external object behavior prediction data to further analyze its potential predicted risk behaviors and predicted risk targets in the target building. Specifically, the system predicts whether the object may deviate from the normal route, whether it may enter a restricted area, or perform other unusual behaviors. For example, if the historical data of the external object waiting for the elevator E shows that it often chooses to enter a high-risk area, the system will judge its possible predicted risk behaviors in the target building based on its current walking path (such as entering a restricted area, staying for a long time, smashing and damaging, and harming others). At the same time, the system will also identify the predicted risk targets that its predicted risk behaviors may target, such as server data in restricted areas, smashing glass doors, and harming specific people.

[0144] Step 806: Based on the predicted risk behavior and the predicted risk target, risk analysis is performed on the external objects waiting for elevators in the target building to obtain risk assessment data of the external objects.

[0145] Specifically, after predicting the risk behaviors and risk targets of the external objects waiting for the elevator, the system will evaluate their overall risk in the target building. The evaluation comprehensively considers the predicted risk behaviors and risk targets, combined with the building's safety management measures, monitoring coverage, and the degree of contact between different people and objects and the external objects waiting for the elevator, calculates the degree of threat that the external objects will pose to the safety of various parts of the building, and generates corresponding external object risk assessment data, including high-risk alarms, areas that need to be monitored, and security personnel's response recommendations.

[0146] In this embodiment, when the behavior data comparison results show that the behavior difference of the external elevator waiting object is less than the preset risk threshold, the system can predict the walking path of the object based on its recorded behavior data, and further evaluate its possible risk behavior and goals based on the predicted behavior data. This process can effectively identify potential safety hazards and assess the activity risks of external objects in the target building in advance. Through accurate risk prediction, the building management system can adjust the security monitoring strategy in real time, optimize resource allocation, strengthen monitoring of high-risk areas, ensure timely detection of abnormal behavior and take necessary safety measures, thereby ensuring the safe operation of the building and improving management efficiency.

[0147] In an exemplary embodiment, Fig. 9 As shown, based on the behavior data comparison result and the foreign object behavior prediction data, the risk of the foreign object waiting for the elevator in the target building is evaluated to obtain the foreign object risk assessment data, including steps 902 to 906. Among them:

[0148] Step 902 , when the behavior data comparison result indicates that the behavior data difference value is greater than a preset risk threshold, identifying the behavior data difference point between the foreign object behavior prediction data and the recorded behavior data.

[0149] The behavior data difference point may be a portion where there is a significant difference between the predicted behavior and the recorded behavior of the external waiting object.

[0150] Specifically, if the behavior data comparison result indicates that the behavior data difference value is greater than the preset risk threshold, it means that one or more predicted behaviors of the foreign object waiting for the elevator are significantly deviated from its historical behavior or normal behavior. At this time, the system needs to identify the difference between the foreign object behavior prediction data and the recorded behavior data, that is, which predicted behavior points do not match the normal behavior points or historical behavior points. For example, the foreign object waiting for the elevator may stay on the expected floor for a long time, or choose an uncommon target floor, but the foreign object waiting for the elevator does not appear in the historical data. The system analyzes and determines the specific behavior data difference points through algorithms (such as distance measurement, pattern recognition, etc.). In a special case, when the recorded behavior data is null, each data point of the foreign object behavior prediction data is used as the behavior data difference point.

[0151] Assume that the recorded behavior data of an external elevator waiting object F shows that in other buildings, the object chooses to wait for the elevator quietly in the elevator lobby, but it is predicted that the object will stomp its feet, turn around, shake its body, and look abnormally in the elevator lobby of the target building. The system discovers this behavioral difference, calculates that the difference value is greater than the preset threshold, and marks the data corresponding to the possible abnormal actions of the external elevator waiting object.

[0152] Step 904: predict abnormal behavior of the external object waiting for the elevator at a difference point of the behavior data according to the external object behavior prediction data.

[0153] The abnormal behavior of the object may be the behavior of the external waiting object that deviates from the normal and expected behavior, which usually has potential risks or characteristics that do not conform to the normal behavior.

[0154] Specifically, after identifying the difference points in the behavior data, the system infers the abnormal behavior of the object that the object may perform at these behavior data difference points based on the predicted behavior data of the external object waiting for the elevator. Specifically, the prediction model of the system will determine whether it is possible to perform atypical behaviors, such as entering restricted areas, staying for a long time, etc., based on the predicted behavior data of the external object waiting for the elevator. If it is judged that the external object waiting for the elevator has an atypical execution trend, the system further uses the rule-based reasoning method or decision tree model to further use the external object behavior prediction data to infer the abnormal behavior of the object that the object may take at the difference point in the behavior data and in a specific situation, and evaluate the potential risks. For example, the system predicts that object F goes to the 20th floor instead of the conventional 5th floor, which may be an attempt to enter a restricted area on the floor. Since this floor is the office area of ​​the technical department, usually only specific personnel can enter. The system predicts that the object may attempt to enter an unauthorized area, so this behavior is marked as abnormal behavior.

[0155] Step 906: Perform risk analysis on the external object waiting for the elevator in the target building according to the abnormal behavior of the object, and obtain risk assessment data of the external object.

[0156] Specifically, after predicting the abnormal behavior of an external object waiting for the elevator, the system will conduct a risk analysis on the external object waiting for the elevator by comprehensively considering the severity of the abnormal behavior, the possible threat to building safety, and the building's security environment (such as monitoring equipment, access control, etc.). If the predicted behavior indicates that the object poses a security threat (such as the possibility of entering a restricted area, staying too long, etc.), the system will generate corresponding external object risk assessment data, including risk levels (such as high risk, medium risk, low risk), areas or actions that require special attention, and real-time suggestions for security personnel (such as deploying monitoring in advance, immediate intervention, etc.).

[0157] In this embodiment, by identifying the behavioral data difference points of the external elevator waiting objects that have significant differences in the behavioral data comparison, the system can promptly discover the abnormal deviations between them and the expected behavior patterns and predict their possible abnormal behaviors. Based on the predictions of these abnormal behaviors, the system can conduct an in-depth analysis of the potential risks of external objects in the target building, thereby evaluating whether they will pose a threat to the safety of the building. This process not only improves the early warning capability of potential risks, but also provides building managers with a more accurate basis for decision-making, ensuring that they can quickly respond to abnormal situations, take appropriate safety measures, and effectively improve the overall safety of the building and the efficiency of emergency response.

[0158] It should be understood that, although the steps in the flowcharts involved in the above 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 is not strictly limited in order, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above embodiments may 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 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.

[0159] Based on the same inventive concept, the embodiment of the present application also provides a multi-scenario elevator control device for implementing the multi-scenario elevator control method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more multi-scenario elevator control device embodiments provided below can refer to the above limitations on a multi-scenario elevator control method, which will not be repeated here.

[0160] In an exemplary embodiment, Fig.10 As shown, a multi-scenario based elevator control device is provided, including: a data acquisition module 1002, a demand analysis module 1004, an object guidance module 1006, an object recognition module 1008, a data analysis module 1010 and a data generation module 1012.

[0161] Each module in the above-mentioned multi-scenario-based elevator control device can be implemented in whole or in part by software, hardware, or a combination thereof. Each of the above-mentioned modules can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each of the above modules.

[0162] In one embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above method embodiments when executing the computer program.

[0163] In one embodiment, a computer-readable storage medium is provided, storing a computer program, which implements the steps in the above method embodiments when executed by a processor.

[0164] In one embodiment, a computer program product or computer program is provided, the computer program product or computer program includes computer instructions, the computer instructions are stored in a computer-readable storage medium. A processor of a computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps in the above-mentioned method embodiments.

[0165] It should be noted that the user information (including but not limited to user device information, user personal 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.

[0166] A person of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing related 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 embodiments of the above-mentioned methods.

[0167] The technical features of the above embodiments may be arbitrarily combined. To make the description concise, 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, they should be considered to be within the scope of this specification.

[0168] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A multi-scenario elevator control method, characterized in that: Applied to an elevator building control center, the method comprises: Obtaining physical feature information and target floor information of each target waiting object in the elevator lobby, and obtaining passenger flow information of the elevator lobby; Performing an elevator usage demand analysis based on the physical feature information, the target floor information, and the passenger flow information, and determining the dispatching information of each elevator; The step of performing an elevator usage demand analysis based on the physical feature information, the target floor information, and the passenger flow information to determine the dispatching information of each elevator includes: Determining elevator dispatching constraint conditions and elevator dispatching target information according to the elevator waiting passenger flow information and the predicted passenger flow information of the elevator waiting hall; Initializing the parameters of the elevator scheduling algorithm according to the elevator scheduling constraint condition and the elevator scheduling target information to obtain the elevator scheduling algorithm to be used; Inputting each of the physical feature information, each of the target floor information and the waiting passenger flow information into the to-be-used elevator dispatching algorithm to obtain each of the elevator dispatching information; Outputting the guidance information of the waiting object corresponding to each of the elevator dispatching information in the elevator waiting hall, and acquiring the video data of the object boarding the elevator corresponding to each of the elevator waiting object guidance information; Among the target elevator waiting objects corresponding to any of the elevator climbing video data, identifying the resident elevator waiting objects and the external elevator waiting objects; Generate resident building linkage data of any of the resident elevator waiting objects according to the historical behavior data of the resident elevator waiting objects in the target building; Generate external building linkage data of any external elevator waiting object according to the elevator waiting behavior data of the external elevator waiting object in the elevator lobby; Generate resident behavior guidance data of the resident waiting elevator object according to the resident building linkage data; the resident behavior guidance data is sent to the resident waiting elevator object by controlling the elevator; According to the external building linkage data, external behavior monitoring data of the external elevator waiting object is generated; and the external behavior monitoring data is sent to the building monitoring center by controlling the elevator.

2. The method according to claim 1, characterized in that The step of determining elevator dispatching constraints and elevator dispatching target information according to the elevator waiting passenger flow information and the predicted passenger flow information of the elevator waiting hall includes: Extracting features of the passenger flow information waiting for the elevator and the predicted passenger flow information of the elevator lobby to obtain passenger flow feature data waiting for the elevator and predicted passenger flow feature data; Calculate the estimated number of arrivals at the elevator lobby, the peak arrival rate at the elevator lobby, and the average waiting time for the elevator according to the passenger flow characteristic data and the predicted passenger flow characteristic data; The elevator scheduling constraints are determined based on the expected number of people arriving at the elevator lobby, the peak arrival rate of the elevator lobby, and the average waiting time of the elevator lobby; the elevator scheduling constraints include service time constraints, elevator energy consumption constraints, elevator load constraints, and elevator safety constraints.

3. The method according to claim 2, characterized in that The elevator dispatching algorithm to be used includes an item dispatching information sub-algorithm and a dispatching optimization sub-algorithm; the physical feature information, the target floor information and the passenger flow information are input into the elevator dispatching algorithm to be used to obtain the elevator dispatching information, including: Based on the service time constraint, the elevator energy consumption constraint, the elevator load constraint and the elevator safety constraint, and according to the physical feature information, the target floor information and the passenger flow information, calculate each initial elevator dispatching information; Using different scheduling information optimization algorithms to find the Pareto frontier of each of the initial elevator scheduling information, and obtain each initial optimal scheduling information; A solution with the highest data uniformity information is selected from each of the initial optimal scheduling information as each of the elevator scheduling information.

4. The method according to claim 1, characterized in that: The step of generating external building linkage data of any external elevator waiting object according to the elevator waiting behavior data of the external elevator waiting object in the elevator waiting hall comprises: Performing behavior pattern analysis on the waiting behavior data of the external object waiting for the elevator in the elevator lobby to obtain the behavior prediction data of the external object; According to the foreign object behavior prediction data, the risk of the foreign object waiting for the elevator in the target building is evaluated to obtain foreign object risk evaluation data; The external building linkage data is generated according to the external object behavior prediction data and the external object risk assessment data.

5. The method according to claim 4, characterized in that The step of evaluating the risk of the foreign object waiting for the elevator in the target building according to the foreign object behavior prediction data to obtain foreign object risk evaluation data includes: Identify the recorded behavior data of the external elevator waiting object from other buildings that interact with the target building; Comparing the foreign object behavior prediction data with the recorded behavior data to obtain a behavior data comparison result; According to the behavior data comparison result and the foreign object behavior prediction data, the risk of the foreign object waiting for the elevator in the target building is evaluated to obtain the foreign object risk evaluation data.

6. The method according to claim 5, characterized in that The step of evaluating the risk of the foreign object waiting for the elevator in the target building according to the behavior data comparison result and the foreign object behavior prediction data to obtain the foreign object risk evaluation data includes: When the behavior data comparison result indicates that the behavior data difference value is less than a preset risk threshold, predicting the current walking path of the external elevator waiting object in the target building based on the recorded behavior data; Predicting the predicted risk behavior and the predicted risk target of the foreign object waiting for the elevator in the target building according to the walking path at that time and the predicted behavior data of the foreign object; According to the predicted risk behavior and the predicted risk target, a risk analysis is performed on the external object waiting for the elevator in the target building to obtain the external object risk assessment data.

7. The method according to claim 5, characterized in that The step of evaluating the risk of the foreign object waiting for the elevator in the target building according to the behavior data comparison result and the foreign object behavior prediction data to obtain the foreign object risk evaluation data includes: In the case where the behavior data comparison result indicates that the behavior data difference value is greater than a preset risk threshold, identifying the behavior data difference point between the foreign object behavior prediction data and the recorded behavior data; According to the foreign object behavior prediction data, predict the abnormal behavior of the foreign object waiting for the elevator at the difference point of the behavior data; According to the abnormal behavior of the object, a risk analysis is performed on the external object waiting for the elevator in the target building to obtain the risk assessment data of the external object.

8. An elevator control device based on multiple scenarios, characterized in that: Applied to an elevator building control center, the device includes: a data acquisition module, a demand analysis module, an object guidance module, an object recognition module, a data analysis module, and a data generation module; the device is used to implement the steps of the method described in any one of claims 1 to 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 7 are implemented.

Images