A multi-elevator intelligent scheduling method and device based on large model analysis and a medium

Abstract

The application discloses a multi-elevator intelligent scheduling method and device based on large model analysis, and a medium, and relates to the technical field of elevator control. The method comprises the following steps: obtaining floor information and corresponding number information of users and time information through a user request device; detecting the weight and number of the current users through a detection module to determine whether the number is correct, wherein the detection module comprises a sensor and a camera; in the case of passing the detection, inputting the floor information and corresponding number information and time information into a trained large model, performing time series analysis on the floor information and corresponding number information, and obtaining the request distribution of the floor interval; obtaining an elevator control strategy through an elevator control module according to the request distribution of the floor interval and the time information, and scheduling the elevator. The application realizes the formulation of an accurate elevator scheduling strategy, optimizes the running track of the elevator, and improves the response speed and overall operation efficiency through the above method.

Description

Technical Field

[0001] This application relates to the field of elevator control technology, and in particular to a method, device and medium for intelligent scheduling of multiple elevators based on large model analysis. Background Technology

[0002] With the acceleration of urbanization and the continuous emergence of high-rise buildings, elevators, as an important tool for vertical transportation, play an indispensable role in people's daily lives. However, traditional elevator scheduling methods are often based on simple rules or fixed algorithms, which cannot accurately predict and respond to complex changes in user requests, resulting in low elevator operating efficiency, excessively long user waiting times, and high energy consumption.

[0003] In recent years, with the rapid development of technologies such as big data and artificial intelligence, deep learning-based predictive models have achieved remarkable results in many fields. Particularly in the transportation sector, by collecting and analyzing large-scale data to build predictive models, accurate prediction and intelligent scheduling of traffic flow can be achieved. However, research on applying deep learning technology to elevator scheduling is relatively limited, and many challenges and gaps remain.

[0004] Currently, although some elevator systems have begun to incorporate intelligent technologies, these systems often simply apply these technologies to a single aspect of the elevator, such as floor control or fault diagnosis, without achieving comprehensive optimization of the entire elevator dispatching system. Furthermore, these systems also have many shortcomings in data collection, model training, and real-time adjustments, making it difficult to meet the high-efficiency, intelligent, and environmentally friendly requirements of modern high-rise buildings for elevator dispatching.

[0005] Based on the above analysis, the problems and shortcomings of the existing technology are as follows:

[0006] Current elevator technology cannot accurately predict and respond to complex changes in user requests, resulting in low elevator operating efficiency and high energy consumption, failing to meet the requirements of modern high-rise buildings for efficient, intelligent, and environmentally friendly elevator scheduling. Summary of the Invention

[0007] This application provides a method, device, and medium for intelligent scheduling of multiple elevators based on large model analysis. It can solve the problem that elevators cannot accurately predict and respond to complex changes in user requests in the prior art, resulting in low elevator operating efficiency, high energy consumption, and failure to meet the requirements of modern high-rise buildings for efficient, intelligent, and environmentally friendly elevator scheduling.

[0008] In a first aspect, embodiments of this application provide a multi-elevator intelligent scheduling method based on large-scale model analysis. The method includes: obtaining floor information, corresponding number of people, and time information requested by a user through a user request device, the user request device including a card swiping area, floor keys, and a cancel key, with a plus key following the floor keys; detecting the current user's weight and number of people through a detection module to determine if the number of people is correct, the detection module including a sensor and a camera; if the detection is successful, inputting the floor information, corresponding number of people, and time information into a trained large-scale model, performing time-series analysis on the floor information and corresponding number of people to obtain the request volume distribution of floor intervals, the floor intervals including a first interval and a second interval; and obtaining an elevator control strategy through an elevator control module based on the request volume distribution and time information of the floor intervals, and scheduling the elevators, the elevators using a self-healing coating material.

[0009] In one implementation of this application, the elevator includes a first elevator and a second elevator, and the elevator includes an elevator door frame. Based on the request volume distribution and time information of the floor intervals, an elevator control strategy is obtained through a user request device, and the elevator is scheduled. Specifically, if the user weight in the first interval exceeds a first preset threshold, the first elevator is scheduled to transport users in the first interval exclusively, and the second elevator is scheduled to transport users in the second interval exclusively. The user is then informed of the floor interval reached by the elevator through a display device located on the elevator door frame. If the number of people in the first interval exceeds a second preset threshold, the first elevator is scheduled to transport some users in the first interval exclusively, and the second elevator is scheduled to transport the remaining users.

[0010] In one implementation of this application, after obtaining the floor information requested by the user and the corresponding number of people through the user request device, the method further includes: obtaining the information of the card-swipe user and the requested floor information, and detecting the current user's weight and number of people through the detection module; if the detection is successful and the user weight in the first interval and the second interval does not exceed the first preset threshold, dispatching the nearest elevator to provide a dedicated delivery service to the user.

[0011] In one implementation of this application, the method further includes: obtaining emergency alarm information, dispatching the nearest elevator to the alarm floor without stopping; informing the user through a display device, and setting the floor key for the alarm floor to be unresponsive.

[0012] In one implementation of this application, before obtaining the floor information and corresponding number of people requested by the user through the user request device, the method further includes: constructing a large model, wherein the large model adopts a recurrent neural network and a long short-term memory network algorithm, and training the large model; preset a first preset threshold and a second preset threshold for the user's weight, wherein the second preset threshold is the maximum load capacity of the elevator; and preset the priority of the elevator control strategy, wherein the emergency alarm has the highest priority.

[0013] In one implementation of this application, the user request device obtains the time information requested by the user, specifically including: collecting the earliest usage time, latest usage time, number of starts, and average running time of the elevator each day; and calculating the elevator usage frequency based on the time information to obtain the peak time period for elevator operation.

[0014] In one implementation of this application, after obtaining the peak hours of elevator operation, the method further includes: during peak hours, dispatching an idle elevator to the floor with the highest demand; during off-peak hours, dispatching an idle elevator to a middle floor or the floor with the highest demand.

[0015] In one implementation of this application, the method further includes: collecting floor information, corresponding number of people and time information requested by the user in real time, and monitoring the power consumption, speed and load parameters of the elevator in real time; periodically iterating the parameters of the large model through incremental learning and online learning; after the parameter iteration of the large model is completed, updating the elevator control strategy in real time through the elevator control module to improve the elevator response speed and reduce energy consumption.

[0016] Secondly, embodiments of this application also provide a multi-elevator intelligent scheduling device based on large model analysis. The device includes at least one processor and a memory communicatively connected to the at least one processor. The memory stores instructions executable by the at least one processor, which, when executed, enable the at least one processor to: obtain floor information and corresponding number of people, as well as time information, requested by a user through a user request device, the user request device including a card swiping area, floor keys, and a cancel key, with a plus key following the floor keys; detect the current user's weight and number of people through a detection module to determine if the number of people is correct, the detection module including a sensor and a camera; if the detection passes, input the floor information, corresponding number of people, and time information into a trained large model, perform time-series analysis on the floor information and corresponding number of people to obtain the request volume distribution of floor intervals, the floor intervals including a first interval and a second interval; and obtain an elevator control strategy through an elevator control module based on the request volume distribution and time information of the floor intervals, and schedule the elevators, the elevators using a self-healing coating material.

[0017] Thirdly, this application embodiment also provides a non-volatile computer storage medium for intelligent multi-elevator scheduling based on large model analysis, storing computer-executable instructions. The computer-executable instructions are configured as follows: obtaining floor information and corresponding number of people, as well as time information, requested by a user through a user request device, the user request device including a card swiping area, floor keys, and a cancel key, with a plus key following the floor keys; detecting the current user's weight and number of people through a detection module to determine if the number of people is correct, the detection module including a sensor and a camera; if the detection is successful, inputting the floor information, corresponding number of people, and time information into a trained large model, performing time-series analysis on the floor information and corresponding number of people to obtain the request volume distribution of floor intervals, the floor intervals including a first interval and a second interval; and obtaining an elevator control strategy through an elevator control module based on the request volume distribution and time information of the floor intervals, and scheduling the elevators, the elevators using a self-healing coating material.

[0018] This application provides a multi-elevator intelligent scheduling method, device, and medium based on large-scale model analysis. It utilizes large-scale model analysis and deep learning techniques to perform time-series analysis and prediction of user request data, formulate precise elevator scheduling strategies, optimize elevator operating trajectories, and improve response speed and overall operating efficiency. Simultaneously, through real-time monitoring and energy efficiency optimization, it can also reduce the energy consumption of the elevator system, achieving the goal of green energy saving and meeting users' needs for fast, intelligent, and green travel. By adjusting and updating the operating strategy, the energy consumption of the elevator system is effectively reduced. Attached Figure Description

[0019] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0020] Figure 1 A flowchart illustrating a multi-elevator intelligent scheduling method based on large model analysis provided in this application embodiment;

[0021] Figure 2 This is a schematic diagram of the internal structure of a multi-elevator intelligent scheduling device based on large model analysis, provided as an embodiment of this application. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions of this application will be clearly and completely described below in conjunction with specific embodiments and corresponding drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments in this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0023] This application provides a method, device, and medium for intelligent scheduling of multiple elevators based on large model analysis. It solves the problem that elevators in the prior art cannot accurately predict and respond to complex changes in user requests, resulting in low elevator operating efficiency, high energy consumption, and failure to meet the requirements of modern high-rise buildings for efficient, intelligent, and environmentally friendly elevator scheduling.

[0024] The technical solutions proposed in the embodiments of this application will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 A flowchart illustrating a multi-elevator intelligent scheduling method based on large model analysis, provided as an embodiment of this application. Figure 1 As shown in the figure, the multi-elevator intelligent scheduling method based on large model analysis provided in this application embodiment specifically includes the following steps:

[0026] Step 10: Obtain the floor information requested by the user, the corresponding number of people, and the time information through the user request device. The user request device includes a card swiping area, a floor button, and a cancel button. The floor button is followed by a plus sign button.

[0027] First, it should be noted that the elevator in this embodiment differs from a regular elevator in that, in a regular elevator, the up or down button is pressed first, and then the corresponding floor button is pressed after all passengers have entered the elevator; however, in the elevator of this embodiment, the floor button can be pressed directly from outside the elevator. That is to say, the floor information and the corresponding number of passengers can be obtained before the passengers have entered the elevator. Further explanation follows.

[0028] For example, if person A wants to reach the 15th floor and presses the button for the 15th floor, and person B also wants to reach the 15th floor, then person B can directly press the plus sign key next to the button for the 15th floor; if they press the wrong button, they can directly press the cancel key.

[0029] The user request collection device can include a user interface such as a touchscreen or buttons. If it's a touchscreen smart screen, each person pressing the corresponding floor button will have their information displayed on the screen. If the user wants to cancel, they can simply click the corresponding information. If it's a standard button-type device, only the information of the last person can be canceled. This user request collection device can be installed on every floor, or, to save cost, on only the first floor.

[0030] Step 20: The current user's weight and number of people are detected by the detection module to determine if the number of people is correct. The detection module includes sensors and cameras.

[0031] In this step, it cannot be ruled out that some people may not know how to operate the system, resulting in errors in the floor information and the corresponding number of people. Therefore, sensors and cameras can be used to detect the flow of people inside and outside the elevator.

[0032] Step 30: If the detection passes, input the floor information, the corresponding number of people, and the time information into the trained large model, perform time series analysis on the floor information and the corresponding number of people to obtain the request distribution of the floor interval, which includes the first interval and the second interval.

[0033] In this step, the first interval can be the lower floors 1-10, and the second interval can be the higher floors 10-20. In practice, more intervals can be set according to the height of the floors to avoid unnecessary waiting time for people taking the elevator.

[0034] Step 40: Based on the request volume distribution and time information of the floor intervals, the elevator control module obtains the elevator control strategy and schedules the elevator. The elevator uses a self-healing coating material.

[0035] As an optional embodiment, the elevator may include a first elevator and a second elevator, and the elevator includes an elevator door frame;

[0036] In other words, in this embodiment of the application, at least two elevators must be installed.

[0037] Based on the request distribution and time information between floors, the elevator control module obtains the elevator control strategy and schedules the elevators. Specifically, this may include:

[0038] Step 401: If the weight of the user in the first section exceeds the first preset threshold, the first elevator is dispatched to transport the user in the first section, and the second elevator is dispatched to transport the user in the second section. The user is informed of the floor section to which the elevator has arrived through the display device, which is located on the elevator door frame.

[0039] For example, if the first preset threshold is 10 and the second preset threshold is 20, when more than 10 users want to go to the lower floors (1-10) and the remaining users want to go to the higher floors (10-20), then two elevators will be dispatched to take them respectively.

[0040] Step 402: If the number of people in the first section exceeds the second preset threshold, dispatch the first elevator to deliver some users in the first section, and dispatch the second elevator to deliver the remaining users.

[0041] For example, if more than 25 users need to go to the lower floors (1-10), the first elevator will be dispatched to take 20 of them to the lower floors, and the second elevator will be dispatched to take the remaining users to the lower and higher floors.

[0042] If more than the second preset threshold number of users go to the lower floor section and the higher floor section respectively, and there are only two elevators, then the first elevator will be dispatched to take 20 users to the lower floor section, and the second elevator will be dispatched to take 20 users to the higher floor section. Users who do not take the elevator need to re-enter their floor information.

[0043] As another optional embodiment, after obtaining the floor information and corresponding number of people requested by the user through the user request device, the method may further include:

[0044] The system obtains information about the card-swipe user and the requested floor information, and detects the current user's weight and number of people through a detection module. If the detection passes and the user weight in both the first and second intervals does not exceed the first preset threshold, the system dispatches the nearest elevator to provide a dedicated delivery service to the user.

[0045] This step allows for faster, more customized services to higher-level users, improving the user experience.

[0046] As another alternative embodiment, the method may further include:

[0047] Upon receiving an emergency alarm, dispatch the nearest elevator to the alarm floor without stopping; notify the user via a display device and set the floor button for the alarm floor to be unresponsive.

[0048] In this step, the emergency alarm information can come from a user calling the property management, pressing the alarm button, or being detected by monitoring devices such as cameras. At this point, the nearest elevator is dispatched to the alarm floor, and the user is notified via a display screen or voice announcement. It's understood that the elevator is currently unused and has already served all passengers. If a user intending to reach that floor doesn't pay attention to the display screen or voice announcement, they will find that the floor button is unresponsive.

[0049] It is understandable that, before obtaining the requested floor information and corresponding number of people through the user request device, the method may also include:

[0050] Step 01: Build a large model. The large model uses recurrent neural network and long short-term memory network algorithms and is trained.

[0051] In this step, to more intelligently schedule elevators, large-scale models can be introduced for analysis, employing deep learning algorithms such as Recurrent Neural Networks (RNNs) or Long Short-Term Memory (LSTM) networks. These algorithms can handle large-scale data, build targeted predictive models, and perform time-series analysis on user request data. During the learning process, feature engineering can be performed to extract key features from user request data, such as floor information and request time. Through supervised learning based on historical data, the model continuously adjusts its parameters, gradually learning and understanding user behavior patterns.

[0052] Step 02: Set a first preset threshold and a second preset threshold for the user's weight. The second preset threshold is the maximum load capacity of the elevator.

[0053] In this step, the first preset threshold and the second preset threshold can be customized according to the actual situation.

[0054] Step 03: Preset the priority of the elevator control strategy, with the emergency alarm having the highest priority.

[0055] Specifically, obtaining the time information of a user request through the user request device can include:

[0056] Step 101: Collect the earliest and latest usage times, number of starts and average running time of the elevator each day.

[0057] Step 102: Calculate the elevator usage frequency based on the time information to obtain the peak hours for elevator operation.

[0058] Furthermore, after determining the peak operating hours of the elevator, the method may also include:

[0059] Step 103: During peak hours, dispatch available elevators to the floors with the highest demand;

[0060] Step 104: During off-peak hours, dispatch available elevators to stop at middle floors or floors with the highest demand.

[0061] Preferably, the method may further include:

[0062] Step 50: Collect floor information, corresponding number of people and time information requested by users in real time, and monitor the power consumption, speed and load parameters of the elevator in real time. Iterate the parameters of the large model regularly through incremental learning and online learning.

[0063] Step 60: After the parameters of the large model are iterated, the elevator control strategy is updated in real time through the elevator control module to improve the elevator's response speed and reduce energy consumption.

[0064] To adapt to changes in real-time data, a periodic update mechanism can be established. Through incremental learning and online learning, model parameters are iterated periodically to ensure the model continuously and accurately reflects changes in user behavior. Through this holistic learning, prediction, and update mechanism, the large-scale model analysis module provides the elevator system with intelligent scheduling capabilities, not only improving elevator response speed but also flexibly adapting to constantly changing user needs. The elevator control module continuously collects real-time operating data and user feedback information to adjust and optimize scheduling strategies in real time. It can adjust the elevator's trajectory according to actual conditions to meet user needs and improve elevator response speed and overall operating efficiency.

[0065] Furthermore, to optimize the energy efficiency of elevator systems, advanced energy consumption calculation methods can be employed to monitor parameters such as elevator power consumption, speed, and load capacity in real time, and use computational models to estimate actual energy consumption. During off-peak hours, energy-saving suggestions are provided based on real-time operating data and historical energy consumption information. Energy consumption can be reduced by adjusting elevator operation strategies. To this end, several technological means can be introduced: renewable energy utilization: integrating solar photovoltaic or wind power generation systems to collect renewable energy, reducing dependence on traditional energy sources, thereby reducing the overall carbon footprint of the system; energy storage technology: combining high-efficiency battery energy storage technology to store renewable energy generated during the day for power supply during peak hours or when needed, smoothing electricity demand and improving system reliability; self-healing materials and energy-saving elevator components: using self-healing materials such as self-repairing coatings to reduce friction and wear of elevator components and improve operating efficiency. The use of energy-saving elevator components such as low-energy motors and energy recovery systems comprehensively improves the energy efficiency of the elevator system. By integrating these sustainable technological solutions, the elevator system not only achieves real-time energy consumption management and optimization but also actively incorporates the application of renewable energy and advanced materials, evolving towards a more environmentally friendly and efficient direction. This comprehensive solution helps improve the sustainability of the system and injects more green elements into urban transportation systems.

[0066] The above are embodiments of the method proposed in this application. Based on the same inventive concept, embodiments of this application also provide a multi-elevator intelligent scheduling device based on large model analysis, the structure of which is as follows: Figure 2 As shown.

[0067] Figure 2 This is a schematic diagram of the internal structure of a multi-elevator intelligent scheduling device based on large model analysis, provided as an embodiment of this application. Figure 2 As shown, the device includes:

[0068] At least one processor 201;

[0069] And a memory 202 that is communicatively connected to at least one processor;

[0070] The memory 202 stores instructions executable by at least one processor, which are executed by at least one processor 201 to enable at least one processor 201 to:

[0071] The system obtains the floor information, corresponding number of people, and time information requested by the user through a user request device, which includes a card swiping area, floor buttons, and a cancel button. A plus sign button is added after the floor button. A detection module, including sensors and a camera, detects the current user's weight and number of people to determine if the number is correct. If the detection is successful, the floor information, corresponding number of people, and time information are input into a pre-trained large model. Time-series analysis is performed on the floor information and corresponding number of people to obtain the request volume distribution for each floor interval, which includes a first interval and a second interval. Based on the request volume distribution and time information for each floor interval, an elevator control module obtains an elevator control strategy and schedules the elevator. The elevator uses a self-healing coating material.

[0072] Some embodiments of this application provide corresponding to Figure 1 A non-volatile computer storage medium for intelligent multi-elevator scheduling based on large model analysis, storing computer-executable instructions, wherein the computer-executable instructions are configured as follows:

[0073] The system obtains the floor information, corresponding number of people, and time information requested by the user through a user request device, which includes a card swiping area, floor buttons, and a cancel button. A plus sign button is added after the floor button. A detection module, including sensors and a camera, detects the current user's weight and number of people to determine if the number is correct. If the detection is successful, the floor information, corresponding number of people, and time information are input into a pre-trained large model. Time-series analysis is performed on the floor information and corresponding number of people to obtain the request volume distribution for each floor interval, which includes a first interval and a second interval. Based on the request volume distribution and time information for each floor interval, an elevator control module obtains an elevator control strategy and schedules the elevator. The elevator uses a self-healing coating material.

[0074] The various embodiments in this application are described in a progressive manner. Similar or identical parts between embodiments can be referred to mutually. Each embodiment focuses on describing the differences from other embodiments. In particular, the embodiments for IoT devices and media are basically similar to the method embodiments, so the description is relatively simple; relevant parts can be referred to the descriptions of the method embodiments.

[0075] The systems, media, and methods provided in this application are one-to-one correspondences. Therefore, the systems and media also have similar beneficial technical effects as their corresponding methods. Since the beneficial technical effects of the methods have been described in detail above, the beneficial technical effects of the systems and media will not be repeated here.

[0076] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0077] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0078] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0079] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0080] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0081] Memory may include non-persistent storage in computer-readable media, such as random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of computer-readable media.

[0082] Computer-readable media includes both permanent and non-permanent, removable and non-removable media that can store information using any method or technology. Information can be computer-readable instructions, data structures, modules of programs, or other data. Examples of computer storage media include, but are not limited to, phase-change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, CD-ROM, digital versatile optical disc (DVD) or other optical storage, magnetic tape, magnetic magnetic disk storage or other magnetic storage devices, or any other non-transferable medium that can be used to store information accessible by a computing device. As defined herein, computer-readable media does not include transient computer-readable media, such as modulated data signals and carrier waves.

[0083] It should also be noted that the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0084] The above description is merely an embodiment of this application and is not intended to limit the scope of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of the claims of this application.

Claims

1. A multi-elevator intelligent scheduling method based on large model analysis, characterized in that, The method includes: The user request device obtains the floor information, the corresponding number of people, and the time information requested by the user. The user request device includes a card swiping area, a floor key, and a cancel key. The floor key is followed by a plus sign key. The detection module detects the current user's weight and number of people to determine if the number of people is correct. The detection module includes sensors and a camera. If the detection passes, the floor information, the corresponding number of people, and the time information are input into the trained large model. The floor information and the corresponding number of people are analyzed over time to obtain the request distribution of the floor intervals. The floor intervals include a first interval and a second interval. Based on the request volume distribution and time information of the floor interval, the elevator control module obtains the elevator control strategy and schedules the elevator. The elevator uses a self-healing coating material. The elevator includes a first elevator and a second elevator, and the elevator includes an elevator door frame; Based on the request volume distribution and time information of the floor intervals, the elevator control module obtains an elevator control strategy and schedules the elevator, specifically including: If the weight of the user in the first section exceeds the first preset threshold, the first elevator is dispatched to transport the user in the first section, and the second elevator is dispatched to transport the user in the second section. The user is informed of the floor section to which the elevator has been delivered through a display device located on the elevator door frame. If the number of people in the first section exceeds the second preset threshold, the first elevator is dispatched to transport some users in the first section, and the second elevator is dispatched to transport the remaining users. After obtaining the floor information and corresponding number of people requested by the user through the user request device, the method further includes: Obtain information about the card-swipe user and the requested floor information, and use the detection module to detect the current user's weight and number of people; If the detection passes and the user weight in both the first and second sections does not exceed the first preset threshold, the nearest elevator will be dispatched to provide a dedicated delivery service to the user. The method further includes: Upon receiving an emergency alarm, dispatch the nearest elevator to the alarm floor, ensuring that the elevator does not stop en route. The system will notify the user via a display device and indicate that the floor key for the alarm floor is unresponsive. Before obtaining the floor information and corresponding number of people requested by the user through the user request device, the method further includes: A large model is constructed, which employs recurrent neural network and long short-term memory network algorithms, and the large model is trained. A first preset threshold and a second preset threshold are set for the user's weight, wherein the second preset threshold is the maximum load capacity of the elevator; The elevator control strategy has a preset priority, with the emergency alarm having the highest priority.

2. The intelligent multi-elevator scheduling method based on large model analysis according to claim 1, characterized in that, Obtaining the time information requested by the user through the user request device specifically includes: Collect the earliest usage time, latest usage time, number of starts, and average running time of the elevator each day; Based on the time information, the usage frequency of the elevator is calculated to obtain the peak operating hours of the elevator.

3. The intelligent multi-elevator scheduling method based on large model analysis according to claim 2, characterized in that, After determining the peak operating hours of the elevator, the method further includes: During the peak hours, dispatch available elevators to the floors with the highest demand; During off-peak hours, dispatch available elevators to stop on middle floors or floors with the highest demand.

4. The intelligent scheduling method for multiple elevators based on large model analysis according to claim 1, characterized in that, The method further includes: The system collects floor information, corresponding number of people, and time information requested by users in real time, and monitors the power consumption, speed, and load parameters of the elevator in real time. Through incremental learning and online learning, the parameters of the large model are iterated periodically. After the parameters of the large model are iterated, the elevator control strategy is updated in real time through the elevator control module to improve the elevator's response speed and reduce energy consumption.

5. A multi-elevator intelligent scheduling device based on large model analysis, characterized in that, The device includes: At least one processor; And, a memory communicatively connected to the at least one processor; The memory stores instructions executable by the at least one processor, which, when executed by the at least one processor, enable the at least one processor to: Perform the steps of the multi-elevator intelligent scheduling method based on large model analysis as described in any one of claims 1-4.

6. A non-volatile computer storage medium for intelligent scheduling of multiple elevators based on large model analysis, storing computer-executable instructions, characterized in that, The computer-executable instructions are set as follows: Perform the steps of the multi-elevator intelligent scheduling method based on large model analysis as described in any one of claims 1-4.

Images