High-rise building elevator management system and method based on space-time information platform

Abstract

The invention provides a high-rise building elevator management system and method based on a space-time information platform. The high-rise building elevator management method comprises the steps that elevator state data of elevators in a building are obtained; the passenger flow in an elevator waiting hall and a car is monitored in real time through the machine vision technology, and passenger state data are generated; based on a spatio-temporal information platform, a digital twin model of the elevator system is generated according to the elevator state data; according to the passenger state data and the elevator state data, a preset first algorithm is used for conducting intelligent decision making on elevator dispatching, and a first dispatching strategy is output; according to the first scheduling strategy, a preset second algorithm is applied to simulate an elevator running path in the digital twin model, the elevator scheduling strategy is dynamically adjusted so as to reduce waiting time and energy consumption of passengers, and a second scheduling strategy is obtained; and managing the elevator in the building according to the second scheduling strategy. By combining machine vision, a digital twinning technology and an intelligent algorithm, the elevator dispatching efficiency and the passenger experience can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of smart buildings, and in particular to a high-rise building elevator management system and method based on a spatiotemporal information platform. Background Art

[0002] With the acceleration of urbanization and the continuous increase in high-rise buildings, elevators, as an important tool for vertical transportation, have become increasingly important in people's daily lives. However, traditional elevator management methods usually rely on simple rules or fixed algorithms, which makes it difficult for them to accurately predict and respond to complex changes in user requests. This limitation leads to problems such as low elevator operation efficiency and long user waiting time. Summary of the invention

[0003] Based on the above problems, the present invention proposes a high-rise building elevator management system and method based on a spatiotemporal information platform. By combining machine vision, digital twin technology and intelligent algorithms, an innovative elevator management method is provided, which can effectively improve the elevator dispatching efficiency and passenger experience.

[0004] In view of this, one aspect of the present invention proposes a high-rise building elevator management method based on a spatiotemporal information platform, comprising: Get elevator status data of elevators in the building; Use machine vision technology to monitor passenger flow in the elevator lobby and car in real time and generate passenger status data; Based on the spatiotemporal information platform, a digital twin model of the elevator system is generated according to the elevator status data; According to the passenger status data and the elevator status data, a preset first algorithm is used to make intelligent decisions on elevator scheduling and output a first scheduling strategy; According to the first scheduling strategy, a preset second algorithm is applied to simulate the elevator operation path in the digital twin model, and the elevator scheduling strategy is dynamically adjusted to reduce passenger waiting time and energy consumption, thereby obtaining a second scheduling strategy; The elevators in the building are managed according to the second scheduling strategy.

[0005] Optionally, the step of using machine vision technology to monitor the passenger flow in the elevator lobby and the elevator car in real time and generate passenger status data includes: Acquire first image data of an elevator lobby and second image data of an elevator car; Analyze the first image data in combination with a preset elevator waiting passenger behavior model to obtain elevator waiting passenger status data; Analyze the second image data in combination with a preset in-car passenger behavior model to obtain in-car passenger status data; The elevator waiting passenger status data and the in-car passenger status data are marked as the passenger status data.

[0006] Optionally, the step of generating a digital twin model of an elevator system based on the elevator state data based on the spatiotemporal information platform includes: A three-dimensional scene coordinate system is established based on the spatiotemporal information platform, wherein the three-dimensional scene coordinate system includes: establishing a global coordinate system with the center of the bottom floor of the building as the origin; establishing a local coordinate system with the center of the bottom of each elevator shaft as the origin; and mapping and converting the global coordinate system and the local coordinate system; Constructing a static model of the elevator system, including: constructing a three-dimensional model of elevator components such as an elevator car, a guide rail, a counterweight system, and a hoistway in the three-dimensional scene coordinate system according to the three-dimensional elevator data and the three-dimensional elevator shaft data; calibrating the relative position relationship and motion constraint relationship between the various elevator components; constructing an elevator component material library, and assigning corresponding material attributes to each elevator component; Constructing a dynamic model of the elevator system, including: establishing a physical motion model of the elevator system, including a car motion model, a traction system model, and a counterweight system model; establishing an environmental model of the elevator system according to the elevator internal environment data, including a temperature field model, an airflow field model, and a noise field model; establishing a component state model of the elevator system according to the elevator accessory data, including the working state, wear state, and fault state of each component; The static model and the dynamic model are integrated to generate a digital twin model of the elevator system, including: establishing a corresponding relationship between the physical quantities in the dynamic model and the geometric features in the static model; updating the digital twin model in real time according to the elevator status data collected in real time; and establishing a two-way data interaction mechanism between the digital twin model and the physical elevator system.

[0007] Optionally, the step of using a preset first algorithm to make intelligent decisions on elevator scheduling based on the passenger status data and the elevator status data and outputting a first scheduling strategy includes: Extracting the elevator waiting passenger status data of each floor from the elevator waiting passenger status data in the passenger status data; Generate elevator car status data according to the in-car passenger status data in the passenger status data and the elevator status data; Extracting a first feature set from the passenger status data of each floor and the elevator car status data; Intelligent decision making is performed on elevator scheduling based on the first feature set and the first algorithm, and a first scheduling strategy is output.

[0008] Optionally, the second algorithm is an ant colony algorithm; the step of applying a preset second algorithm to simulate the elevator running path in the digital twin model according to the first scheduling strategy, dynamically adjusting the elevator scheduling strategy to reduce passenger waiting time and energy consumption, and obtaining the second scheduling strategy includes: Constructing a graph structure model of an elevator scheduling scenario, including: mapping floor nodes, elevator positions, and target floors as vertices of a graph; mapping possible elevator operation paths as edges of the graph; and assigning initial pheromone concentrations to the edges according to the first scheduling strategy; Initialize the second algorithm parameters, including: setting the number of ants n to match the number of currently scheduled tasks; setting the maximum number of iterations max_iter; setting the pheromone volatility coefficient ρ1; setting the state transition probability calculation parameters α1 and β1; Construct a fitness function, including: calculating the average waiting time of passengers; calculating the total energy consumption of the elevator system; setting the waiting time weight w1 and energy consumption weight w2 according to the actual scheduling scenario; defining the fitness as the weighted sum: f1=w1×waiting time+w2×energy consumption; Execute the path search and optimization process, including: in the digital twin model, randomly assign an initial node to each ant; calculate the selection probability of the next node according to the state transition probability formula: according to the pheromone concentration τ ij and heuristic information η ij Calculate the state transition probability p ij = (τ ij ^α1 × η ij ^β1) / Σ(τ ij ^α1 × η ij ^β1); Update global pheromone concentration: pheromone volatilization τ ij =(1-ρ1)×τ ij ;Pheromone increase Δτ ij = Q / Lk (Q is a constant, Lk is the fitness value of path k); Dynamically adjust the optimization strategy: monitor the real-time state changes in the digital twin model; dynamically adjust the heuristic information according to the state changes; adaptively adjust the α1 and β1 parameter values; update the local optimal solution and the global optimal solution in each iteration; Generate the second scheduling strategy: select the global optimal solution as the final scheduling solution; convert the optimized path into specific scheduling instructions; output detailed scheduling execution steps.

[0009] Optionally, the first algorithm is a fuzzy neural network algorithm; the step of making intelligent decisions on elevator scheduling according to the first feature set and the first algorithm and outputting a first scheduling strategy includes: Preprocessing the first feature set; The first algorithm is obtained by constructing a fuzzy neural network structure, including: input layer configuration: setting the number of neurons consistent with the feature dimension and defining the domain range of the input variable; fuzzy layer design: designing membership functions for each input variable and determining the number of fuzzy rules; reasoning layer implementation: establishing a fuzzy rule base and setting rule weights; output layer construction: defining the output variable set and designing a defuzzification method; Inputting the preprocessed first feature set into the first algorithm; Execute the fuzzification process, including: calculating the membership of input variables; activating relevant fuzzy rules; Implement fuzzy reasoning, including: executing rule reasoning; aggregating the outputs of multiple rules to generate comprehensive decision results; Perform defuzzification, including: Applying the centroid method: Calculating the crisp value of the output variable and generating specific scheduling instructions; Output mapping conversion: Mapping the crisp value to the scheduling action and generating the execution sequence; Generate the first scheduling strategy, including: output scheduling priority: assign service order to each elevator and determine the target floor sequence; generate execution plan: plan operation path and set time nodes; formulate emergency plan.

[0010] Optionally, the first algorithm is a fuzzy neural network algorithm; before the step of using the preset first algorithm to make intelligent decisions on elevator scheduling according to the passenger status data and the elevator status data and outputting a first scheduling strategy, the step of optimizing the first algorithm by using a third algorithm is further included, specifically: Initialize the parameter optimization space, including: determine the fuzzy neural network parameters to be optimized: membership function parameters of fuzzy rules, connection weights of neural networks, threshold parameters of neurons; set the value range and constraints of each parameter; establish a parameter encoding scheme to discretize the continuous parameter space; Construct an optimization objective function, including: design evaluation indicators: scheduling decision accuracy, system response time, computing resource consumption; define the objective function: f2 = q1×accuracy + q2×(1 / response time) + q3×(1 / resource consumption); set the weights of each indicator q1, q2, q3; Configure the third algorithm, including: initialize the ant colony: the number of ants m is adapted to the parameter dimension, and the initial parameter combination is randomly assigned; set the algorithm control parameters: pheromone volatility coefficient ρ2, local search probability p_local, global search probability p_global; define the state transition rule: select parameter values ​​based on the roulette strategy, and consider the constraint relationship between parameters; Execute the parameter optimization process, including: evaluate the current parameter combination: test the fuzzy neural network performance on the validation data set and calculate the objective function value; update the local optimal solution: record the optimal parameter combination found by each ant and update the local pheromone concentration; update the global optimal solution: compare and update the global optimal parameter combination and update the global pheromone concentration; apply the adaptive mechanism: dynamically adjust the search step size and adjust the control parameters according to the optimization progress; Implement convergence control, including: setting termination conditions: reaching the maximum number of iterations, objective function value convergence, parameter change less than the threshold; applying early stopping mechanism: monitoring optimization effect and avoiding overfitting; Update the fuzzy neural network, including: use the optimized parameters to update the network: reconstruct the membership function, update the connection weights, and adjust the threshold parameters; verify the optimization effect: evaluate the performance on the test data set and compare the changes in indicators before and after optimization.

[0011] Optionally, the method for constructing the elevator waiting passenger behavior model includes: Collect basic behavior data, including: obtaining image sequence data, i.e. recording the movement trajectory of passengers waiting for the elevator, capturing posture change information, collecting facial expression data and gesture action data; collecting operation behavior data, i.e. recording key operation sequence, obtaining card swiping information, collecting voice command data; collecting environmental parameters, i.e. recording the crowdedness of the waiting area, monitoring the environmental noise level, and collecting lighting condition data; Extracting behavioral features from basic behavioral data, including: processing spatiotemporal features, i.e. analyzing motion trajectory features, extracting location distribution features, and calculating speed and acceleration features; identifying interactive features, i.e. extracting human-computer interaction patterns, analyzing crowd interaction features, and identifying group behavior patterns; analyzing emotional features, i.e. identifying facial expression changes, analyzing body language features, and evaluating emotional states; Establish a behavior classification system based on the extracted behavior characteristics, including: defining basic behavior types, i.e. normal waiting behavior, emergency travel behavior, and special demand behavior; constructing a composite behavior model, i.e. identifying behavior sequence associations, extracting behavior combination characteristics, and establishing behavior transfer rules; designing abnormal behavior identification, i.e. defining abnormal behavior characteristics, establishing an early warning trigger mechanism, and formulating a response strategy; Construct a probabilistic state transition model based on behavioral characteristics and behavioral classification system, including: establishing state space, i.e. defining the set of behavioral states, designing state feature vectors, and determining state transition conditions; calculating transition probability, i.e. applying Bayesian reasoning based on historical data statistics, and updating the probability matrix; realizing state prediction, i.e. predicting the probability of the next state, evaluating the reliability of prediction, and dynamically adjusting the prediction model; Implement model adaptive optimization and obtain the passenger waiting behavior model, including: designing a feedback mechanism, i.e. collecting prediction error data, analyzing error distribution characteristics, and adjusting model parameters; performing online learning, i.e. updating the behavior feature library, optimizing classification rules, and improving prediction accuracy; and implementing scenario adaptation, i.e. identifying scenario changes, adjusting model parameters, and updating prediction strategies.

[0012] Optionally, the method for constructing the in-car passenger behavior model includes: Collect multimodal data in the car, including: obtaining visual data, i.e. collecting passenger posture data, recording passenger position distribution data, and identifying face orientation information; collecting audio data, i.e. recording voice command information, collecting environmental sound characteristics, and identifying abnormal sound events; recording sensor data, i.e. collecting weight change data, monitoring vibration information, and obtaining temperature and humidity parameters; Extract passenger characteristics from the collected multimodal data in the car, including: analyzing spatial characteristics, i.e. calculating passenger density distribution, extracting standing pattern characteristics, and identifying moving path characteristics; identifying interactive behaviors, i.e. analyzing human-computer interaction patterns, extracting interpersonal interaction characteristics, and identifying group behavior patterns; evaluating emotional states, i.e. analyzing facial expression changes, identifying body language characteristics, and evaluating tension indicators; Establish a behavior classification model based on passenger characteristics, including: defining basic behavior categories, i.e. normal riding behavior, emergency behavior, and special demand behavior; constructing complex behavior patterns, i.e. identifying behavior sequence rules, extracting behavior combination features, and establishing behavior transfer rules; designing anomaly detection mechanisms, i.e. defining abnormal behavior features, establishing warning thresholds, and formulating emergency response strategies; Combining passenger characteristics and classification models, we obtain the passenger behavior model in the car, including: building a state transition network, i.e. defining the state space, calculating the transition probability, and predicting the next state; applying time series prediction, i.e. analyzing the historical behavior sequence, predicting the future behavior trend, and evaluating the prediction reliability; performing multimodal fusion, i.e. integrating multi-source data information, optimizing the prediction results, and improving the prediction accuracy; Design a safety monitoring mechanism for the in-car passenger behavior model, including: achieving real-time monitoring, i.e. monitoring the degree of congestion, detecting abnormal behavior, and assessing safety risks; establishing an early warning system, i.e. setting multi-level early warning thresholds, defining early warning trigger conditions, and formulating early warning response strategies; and performing emergency response, i.e. identifying emergency situations, initiating emergency plans, and recording event logs.

[0013] Another aspect of the present invention provides a high-rise building elevator management system based on a spatiotemporal information platform, which is used to execute a high-rise building elevator management method based on a spatiotemporal information platform, comprising: a server, a communication module and an elevator; The server is configured to: Get elevator status data of elevators in the building; Use machine vision technology to monitor passenger flow in the elevator lobby and car in real time and generate passenger status data; Based on the spatiotemporal information platform, a digital twin model of the elevator system is generated according to the elevator status data; According to the passenger status data and the elevator status data, a preset first algorithm is used to make intelligent decisions on elevator scheduling and output a first scheduling strategy; According to the first scheduling strategy, a preset second algorithm is applied to simulate the elevator operation path in the digital twin model, and the elevator scheduling strategy is dynamically adjusted to reduce passenger waiting time and energy consumption, thereby obtaining a second scheduling strategy; The elevators in the building are managed according to the second scheduling strategy.

[0014] The technical solution of the present invention is adopted, and the high-rise building elevator management method based on the spatiotemporal information platform includes: obtaining the elevator status data of the elevators in the building; using machine vision technology to monitor the passenger flow in the elevator lobby and the car in real time to generate passenger status data; based on the spatiotemporal information platform, generating a digital twin model of the elevator system according to the elevator status data; based on the passenger status data and the elevator status data, using a preset first algorithm to make intelligent decisions on elevator scheduling and output a first scheduling strategy; according to the first scheduling strategy, applying a preset second algorithm to simulate the elevator operation path in the digital twin model, dynamically adjusting the elevator scheduling strategy to reduce passenger waiting time and energy consumption, and obtaining a second scheduling strategy; managing the elevators in the building according to the second scheduling strategy. The solution of the present invention provides an innovative elevator management method by combining machine vision, digital twin technology and intelligent algorithms, which can effectively improve the scheduling efficiency of elevators and passenger experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a flow chart of a high-rise building elevator management method based on a spatiotemporal information platform provided by an embodiment of the present invention; Figure 2 It is a schematic block diagram of a high-rise building elevator management system based on a spatiotemporal information platform provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to more clearly understand the above-mentioned purpose, features and advantages of the present invention, the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. It should be noted that the embodiments of the present application and the features in the embodiments can be combined with each other without conflict.

[0017] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Therefore, the protection scope of the present invention is not limited to the specific embodiments disclosed below.

[0018] The terms "first", "second", etc. in the specification and claims of this application and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but optionally includes steps or units that are not listed, or optionally includes other steps or units inherent to these processes, methods, products or devices.

[0019] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.

[0020] Refer to the following Figure 1 to Figure 2 A high-rise building elevator management system and method based on a spatiotemporal information platform are described according to some embodiments of the present invention.

[0021] like Figure 1 As shown, one embodiment of the present invention provides a high-rise building elevator management method based on a spatiotemporal information platform, comprising: Obtain elevator status data of elevators in buildings (including elevator 3D data, elevator shaft 3D data, elevator internal environment data, elevator accessory data, etc.); It is understandable that a laser scanner can be used to perform a three-dimensional scan of the elevator and its shaft to obtain accurate spatial data; a three-dimensional model of the elevator and its shaft can be generated by combining the laser scanning data with the building information model (BIM) software; sensors (such as ultrasonic sensors, infrared sensors, etc.) are installed in the elevator shaft to monitor the state and structural changes of the shaft in real time; images of the elevator shaft are captured by a camera, and the three-dimensional information of the shaft is extracted through image processing algorithms; environmental sensors such as temperature, humidity, and light are installed in the elevator car to monitor the environmental parameters in the elevator in real time; air quality sensors are used to monitor the air quality in the elevator, including indicators such as carbon dioxide and volatile organic compounds; smart sensors are installed on the elevator's ancillary equipment (such as door control systems, control panels, etc.) to monitor their working status and performance in real time; data from various sensors are aggregated through a data integration platform to form status data of elevator accessories; a data management system is established to integrate and analyze the acquired elevator status data to form a visual elevator status report; and digital twin technology is used to combine real-time data with three-dimensional models to reflect the operating status and environmental changes of the elevator in real time. Through the above methods, various status data of elevators in the building can be fully obtained, providing a basis for the intelligent management and scheduling of elevators.

[0022] Use machine vision technology to monitor passenger flow in the elevator lobby and car in real time and generate passenger status data; Based on the spatiotemporal information platform, a digital twin model of the elevator system is generated according to the elevator status data; According to the passenger status data and the elevator status data, a preset first algorithm is used to make intelligent decisions on elevator scheduling and output a first scheduling strategy; According to the first scheduling strategy, a preset second algorithm is applied to simulate the elevator operation path in the digital twin model, and the elevator scheduling strategy is dynamically adjusted to reduce passenger waiting time and energy consumption, thereby obtaining a second scheduling strategy; The elevators in the building are managed according to the second scheduling strategy.

[0023] The solution of the present invention provides an innovative elevator management method by combining machine vision, digital twin technology and intelligent algorithms, which can effectively improve the elevator dispatching efficiency and passenger experience.

[0024] In some possible implementations of the present invention, the step of using machine vision technology to monitor the passenger flow in the elevator lobby and the car in real time and generate passenger status data includes: Acquire first image data of an elevator lobby and second image data of an elevator car; Analyze the first image data in combination with a preset elevator waiting passenger behavior model to obtain elevator waiting passenger status data; In this step, the input data of the waiting passenger in the first image data (such as pressing the up / down key, inputting the target floor number, swiping the elevator card, etc.) and the key feature data of the waiting passenger (such as face data, key behavior data, key item data, etc.) are identified; based on the input data of the waiting passenger, the key feature data of the waiting passenger and the behavior model of the waiting passenger, the status data of the waiting passenger (such as whether waiting for the elevator, whether the waiting passenger is going up or down, the destination floor, age, gender, body shape, health status, data of personal items, etc.) are obtained.

[0025] Analyze the second image data in combination with a preset in-car passenger behavior model to obtain in-car passenger status data; In this step, the passenger input data in the car (such as pressing a floor button, inputting a target floor number, speaking a floor number, swiping an elevator card, etc.) and the passenger key feature data in the car (such as facial data, key behavior data, key item data, etc.) in the second image data are identified; based on the passenger input data in the car, the passenger key feature data in the car and the passenger behavior model in the car, the passenger status data in the car (such as destination floor, age, gender, body shape, health status, carry-on item data, etc.) are obtained.

[0026] The elevator waiting passenger status data and the in-car passenger status data are marked as the passenger status data.

[0027] In this embodiment, a target detection algorithm is used to identify individual passengers in the first image data and / or the second image data to determine the number of passengers, posture (such as standing, sitting, walking, etc.), gender, body shape, age, health status, personal belongings, etc., and the movement trajectory of the passengers is tracked through a tracking algorithm. At the same time, combined with a preset elevator waiting passenger behavior model and / or car passenger behavior model, the passenger status data of the elevator waiting passengers and / or the car passengers (such as whether they are waiting for the elevator, whether they are entering or exiting the car, the destination floor of the passengers in the car, whether the elevator waiting passengers are going up or down, etc.) is determined.

[0028] In this embodiment, the status data of passengers waiting for the elevator include but are not limited to: the number of people going up, the number of people going down, age, gender, body shape, health status, data of personal belongings, destination floor, etc.; the status data of passengers in the car include but are not limited to: the number of people, age, gender, body shape, health status, data of personal belongings, destination floor, etc. In this embodiment, machine vision technology is used to obtain passenger image information through image acquisition sensors in the elevator lobby and the car, analyze and process the images, identify the location, posture, behavior and other characteristics of the passengers, so as to accurately count the number of people waiting for the elevator and the number of people in the car and other passenger status data that can indicate the intention of the passengers.

[0029] The solution of this embodiment uses machine vision technology to accurately count the passenger status data in the elevator lobby and the elevator car, thereby providing important decision support for elevator scheduling; it upgrades traditional simple passenger detection to a comprehensive status analysis; through the introduction of behavioral models, it improves the ability to understand passenger intentions; the dimensions of feature recognition are very comprehensive and can support more intelligent scheduling decisions.

[0030] In some possible embodiments of the present invention, it may also include: predicting the flow direction and flow change trend of passengers according to the distribution of passengers in the elevator lobby and the car, combined with the floor layout and the direction of elevator operation, to provide a more accurate decision-making basis for elevator scheduling; updating the passenger flow status information in real time, and when a significant change in passenger flow is detected, timely adjusting the elevator operation mode and scheduling strategy (for example, increasing the elevator operation frequency or adjusting the zoning operation strategy during peak hours); analyzing the behavior of passengers waiting for the elevator / in the car to determine whether the passengers are waiting for the elevator normally and whether they have abnormal behavior (such as jumping in the car, pulling the door, etc.), and for abnormal behavior, an alarm signal should be promptly issued to the elevator dispatch center and relevant management departments.

[0031] In some possible implementations of the present invention, the step of generating a digital twin model of an elevator system based on the elevator state data based on the spatiotemporal information platform includes: A three-dimensional scene coordinate system is established based on the spatiotemporal information platform, wherein the three-dimensional scene coordinate system includes: establishing a global coordinate system with the center of the bottom floor of the building as the origin; establishing a local coordinate system with the center of the bottom of each elevator shaft as the origin; and mapping and converting the global coordinate system and the local coordinate system; Constructing a static model of the elevator system, including: constructing a three-dimensional model of elevator components such as an elevator car, a guide rail, a counterweight system, and a hoistway in the three-dimensional scene coordinate system according to the three-dimensional elevator data and the three-dimensional elevator shaft data; calibrating the relative position relationship and motion constraint relationship between the various elevator components; constructing an elevator component material library, and assigning corresponding material attributes to each elevator component; Constructing a dynamic model of the elevator system, including: establishing a physical motion model of the elevator system, including a car motion model, a traction system model, and a counterweight system model; establishing an environmental model of the elevator system according to the elevator internal environment data, including a temperature field model, an airflow field model, and a noise field model; establishing a component state model of the elevator system according to the elevator accessory data, including the working state, wear state, and fault state of each component; The static model and the dynamic model are integrated to generate a digital twin model of the elevator system, including: establishing a corresponding relationship between the physical quantities in the dynamic model and the geometric features in the static model; updating the digital twin model in real time according to the elevator status data collected in real time; and establishing a two-way data interaction mechanism between the digital twin model and the physical elevator system; The digital twin model also includes the following functional modules: Status monitoring module: real-time monitoring and display of the operating status of the elevator system; Fault diagnosis module: Fault diagnosis based on historical data analysis and real-time data comparison; Performance evaluation module: evaluates the operating efficiency and service quality of the elevator system; Prediction and warning module: predicts possible failures and performance degradation.

[0032] The solution of this embodiment realizes the precise spatial positioning of the elevator system by establishing a unified three-dimensional scene coordinate system; facilitates the coordinated scheduling of multiple elevators through the mapping of the global coordinate system and the local coordinate system, and realizes the accurate three-dimensional modeling and spatial relationship expression of the components of the elevator system; realizes the real-time simulation and prediction of the elevator motion state, which can reflect the environmental changes and component state changes of the elevator system, and support the dynamic performance evaluation of the elevator system; provides all-round state monitoring and fault diagnosis capabilities; supports predictive maintenance and discovers potential problems in advance; provides reliable data support and simulation verification environment for elevator scheduling decisions; breaks through the limitations of static management in traditional elevator management, realizes an intelligent management mode that combines virtual and real, and provides data support for the optimization and upgrading of the elevator system.

[0033] In some possible implementations of the present invention, the step of using a preset first algorithm to make intelligent decisions on elevator scheduling based on the passenger status data and the elevator status data and outputting a first scheduling strategy includes: Extracting the status data of passengers waiting for elevators on each floor from the waiting passenger status data in the passenger status data (including the status data of passengers waiting for elevators going up (such as the destination floor, age, gender, body shape, health status, data of belongings, etc.) and the status data of passengers waiting for elevators going down (such as the destination floor, age, gender, body shape, health status, data of belongings, etc.)); Generate elevator car status data (including elevator car operation status data (such as current floor, current operation direction, request frequency of each floor, current car environment parameters, current operation parameters, etc.) and the number of passengers in the car (such as the total number of people in the car, the number of people leaving the car at each destination floor, age, gender, body shape, health status, personal belongings data, etc.) according to the in-car passenger status data in the passenger status data and the elevator status data; Extracting a first feature set from the passenger status data of each floor and the elevator car status data; Intelligent decision making is performed on elevator scheduling based on the first feature set and the first algorithm, and a first scheduling strategy is output.

[0034] In an embodiment, the first algorithm is a fuzzy neural network algorithm; the first algorithm includes an input layer, a first rule set, a first function, and an output layer; the input parameters received by the input layer include the current number of people waiting for the elevator, the number of passengers in the car, the frequency of floor requests, and the current state of the elevator; the first rule set defines multiple rules, such as "if there are a large number of people waiting for the elevator and a small number of people in the car, the elevator will be scheduled first"; the first function uses a triangular or trapezoidal membership function to quantify the fuzziness of the input parameters; the output layer outputs a scheduling strategy (including but not limited to: scheduling priority and recommended elevator target floors, etc.).

[0035] The solution of this embodiment intelligently adjusts the elevator dispatching strategy according to real-time passenger demand and elevator status to improve the service efficiency of the elevator; reduces the waiting time of passengers and improves passenger satisfaction; can quickly respond to different passenger demands and elevator status according to real-time data changes to ensure the flexibility and adaptability of the elevator system; this elevator management method based on the spatiotemporal information platform, combined with the application of intelligent algorithms, can effectively improve the management efficiency and service quality of high-rise building elevators; not only considers the traditional number of people and floors, but also includes passenger characteristics; handles uncertainty through fuzzy quantization; and makes decisions based on real-time status data.

[0036] In some possible implementations of the present invention, the second algorithm is an ant colony algorithm; the step of applying a preset second algorithm to simulate the elevator operation path in the digital twin model according to the first scheduling strategy, dynamically adjusting the elevator scheduling strategy to reduce passenger waiting time and energy consumption, and obtaining the second scheduling strategy includes: Constructing a graph structure model of an elevator scheduling scenario, including: mapping floor nodes, elevator positions, and target floors as vertices of a graph; mapping possible elevator operation paths as edges of the graph; and assigning initial pheromone concentrations to the edges according to the first scheduling strategy; Initialize the second algorithm parameters, including: setting the number of ants n to match the number of currently scheduled tasks; setting the maximum number of iterations max_iter; setting the pheromone volatility coefficient ρ1; setting the state transition probability calculation parameters α1 and β1; Construct a fitness function, including: calculating the average waiting time of passengers; calculating the total energy consumption of the elevator system; setting the waiting time weight w1 and energy consumption weight w2 according to the actual scheduling scenario; defining the fitness as the weighted sum: f1=w1×waiting time+w2×energy consumption; Execute the path search and optimization process, including: in the digital twin model, randomly assign an initial node to each ant; calculate the selection probability of the next node according to the state transition probability formula: according to the pheromone concentration τ ij and heuristic information η ij (related to path length and elevator load) Calculate the state transition probability p ij = (τ ij ^α1 × η ij ^β1) / Σ(τ ij ^α1 ×η ij ^β1); Update global pheromone concentration: pheromone volatilization τ ij =(1-ρ1)×τ ij ;Pheromone increase Δτ ij = Q / Lk (Q is a constant, Lk is the fitness value of path k); Dynamically adjust the optimization strategy: monitor the real-time state changes in the digital twin model; dynamically adjust the heuristic information according to the state changes; adaptively adjust the α1 and β1 parameter values; update the local optimal solution and the global optimal solution in each iteration; Generate the second scheduling strategy: select the global optimal solution as the final scheduling solution; convert the optimized path into specific scheduling instructions; output detailed scheduling execution steps.

[0037] In this embodiment, the components of heuristic information are: factors related to the path length (such as the distance from the current floor to the target floor, the number of floors stopped in the path, the number of turns in the path (the number of times the running direction is changed)) and factors related to the elevator load (such as the current car load rate, the number of passengers expected to get on and off in the path, the remaining capacity of the car, etc.). The calculation formula of heuristic information is: η ij =1 / (w11×distance+w21×load rate+w31×number of turns); where w11, w21, and w31 are weight coefficients; distance, load rate, and number of turns need to be normalized; η ij The larger the value, the higher the priority of the path. The dynamic adjustment of heuristic information includes: adjusting the weight according to different time periods (paying more attention to load balancing during peak hours and more attention to energy saving efficiency during off-peak hours) and adjusting according to special circumstances (reducing the load weight for special passengers, increasing the distance weight in emergencies, and reducing the speed weight for elderly people). The synergy of heuristic information and pheromones: State transition probability calculation p ij = (τ ij ^α1×η ij ^β1) / Σ(τ ij ^α1×η ij ^β1); τ ijis the pheromone concentration, α1 is the pheromone importance factor, and β1 is the heuristic information importance factor. This scheme can optimize the rationality of path selection, improve the real-time performance of scheduling decisions, enhance the adaptability of the algorithm, and achieve multi-objective trade-off scheduling optimization.

[0038] The solution of this embodiment can significantly reduce the average waiting time of passengers, reduce the overall energy consumption of the elevator system, and improve the efficiency of elevator dispatching; it can quickly respond to changes in dispatching scenarios, has good dynamic optimization capabilities, and avoids local optimal solutions; it deeply integrates the traditional ant colony algorithm with the elevator dispatching scenario, realizes a dynamic parameter adjustment mechanism, and provides more accurate dispatching optimization capabilities.

[0039] In some possible implementations of the present invention, the first algorithm is a fuzzy neural network algorithm; the step of making intelligent decisions on elevator scheduling based on the first feature set and the first algorithm and outputting a first scheduling strategy includes: Preprocess the first feature set, including: feature standardization (normalizing numerical features and encoding categorical features); feature combination construction (generating time window features and constructing feature interaction terms); feature importance evaluation (calculating feature weights and screening key features); The first algorithm is obtained by constructing a fuzzy neural network structure, including: input layer configuration (setting the number of neurons consistent with the feature dimension and defining the domain range of the input variable); fuzzy layer design (designing membership functions for each input variable and determining the number of fuzzy rules); reasoning layer implementation (establishing a fuzzy rule base and setting rule weights); output layer construction (defining the output variable set and designing a defuzzification method); Inputting the preprocessed first feature set into the first algorithm; Execute the fuzzification process, including: calculating the membership of the input variables (applying Gaussian membership function to generate fuzzy feature vectors); activating relevant fuzzy rules (matching rule conditions and calculating rule triggering strength); Implement fuzzy reasoning, including: executing rule reasoning (applying Mamdani reasoning mechanism to calculate rule output); rule combination (aggregating the output of multiple rules to generate comprehensive decision results); Perform defuzzification, including: applying the centroid method (calculating the clear value of the output variable and generating specific scheduling instructions); output mapping conversion (mapping the clear value into the scheduling action and generating the execution sequence); Generate the first scheduling strategy, including: output scheduling priority (assign service order to each elevator and determine the target floor sequence); generate execution plan (plan operation path and set time nodes); formulate emergency plan (consider emergencies and prepare equipment selection plan).

[0040] In this embodiment, the fuzzy neural network realizes intelligent dispatching of elevators through fuzzification, rule reasoning, learning optimization and intelligent decision-making in elevator dispatching to improve the transportation efficiency and service quality of elevators.

[0041] In some possible implementations of the present invention, the first algorithm is a fuzzy neural network algorithm; before the step of using the preset first algorithm to make intelligent decisions on elevator scheduling based on the passenger status data and the elevator status data and outputting a first scheduling strategy, the step of optimizing the first algorithm using a third algorithm is also included, specifically: Initialize the parameter optimization space, including: determine the fuzzy neural network parameters to be optimized: membership function parameters of fuzzy rules, connection weights of neural networks, threshold parameters of neurons; set the value range and constraints of each parameter; establish a parameter encoding scheme to discretize the continuous parameter space; Construct an optimization objective function, including: design evaluation indicators: scheduling decision accuracy, system response time, computing resource consumption; define the objective function: f2 = q1×accuracy + q2×(1 / response time) + q3×(1 / resource consumption); set the weights of each indicator q1, q2, q3; Configure the third algorithm, including: initialize the ant colony: the number of ants m is adapted to the parameter dimension, and the initial parameter combination is randomly assigned; set the algorithm control parameters: pheromone volatility coefficient ρ2, local search probability p_local, global search probability p_global; define the state transition rule: select parameter values ​​based on the roulette strategy, and consider the constraint relationship between parameters; Execute the parameter optimization process, including: evaluate the current parameter combination: test the fuzzy neural network performance on the validation data set and calculate the objective function value; update the local optimal solution: record the optimal parameter combination found by each ant and update the local pheromone concentration; update the global optimal solution: compare and update the global optimal parameter combination and update the global pheromone concentration; apply the adaptive mechanism: dynamically adjust the search step size and adjust the control parameters according to the optimization progress; Implement convergence control, including: setting termination conditions: reaching the maximum number of iterations, objective function value convergence, parameter change less than the threshold; applying early stopping mechanism: monitoring optimization effect and avoiding overfitting; Update the fuzzy neural network, including: use the optimized parameters to update the network: reconstruct the membership function, update the connection weights, and adjust the threshold parameters; verify the optimization effect: evaluate the performance on the test data set and compare the changes in indicators before and after optimization.

[0042] The solution of this embodiment can improve the decision-making accuracy of the fuzzy neural network, reduce the system response time, and reduce the consumption of computing resources; it can realize dynamic optimization of parameters, improve the robustness of the algorithm, and enhance the adaptability to environmental changes; it can accelerate the convergence speed of parameter optimization, avoid falling into local optimality, and reduce the computational overhead of the optimization process; it can provide a reliable parameter optimization solution, ensure the stability of the optimization results, and support online optimization and updating.

[0043] In some possible implementations of the present invention, the method for constructing the elevator waiting passenger behavior model includes: Collect basic behavior data, including: obtaining image sequence data, i.e. recording the movement trajectory of passengers waiting for the elevator, capturing posture change information, collecting facial expression data and gesture action data; collecting operation behavior data, i.e. recording key operation sequence, obtaining card swiping information, collecting voice command data; collecting environmental parameters, i.e. recording the crowdedness of the waiting area, monitoring the environmental noise level, and collecting lighting condition data; Extracting behavioral features from basic behavioral data, including: processing spatiotemporal features, i.e. analyzing motion trajectory features, extracting location distribution features, and calculating speed and acceleration features; identifying interactive features, i.e. extracting human-computer interaction patterns, analyzing crowd interaction features, and identifying group behavior patterns; analyzing emotional features, i.e. identifying facial expression changes, analyzing body language features, and evaluating emotional states; Establish a behavior classification system based on the extracted behavior characteristics, including: defining basic behavior types, i.e. normal waiting behavior, emergency travel behavior, and special demand behavior; constructing a composite behavior model, i.e. identifying behavior sequence associations, extracting behavior combination characteristics, and establishing behavior transfer rules; designing abnormal behavior identification, i.e. defining abnormal behavior characteristics, establishing an early warning trigger mechanism, and formulating a response strategy; Construct a probabilistic state transition model based on behavioral characteristics and behavioral classification system, including: establishing state space, i.e. defining the set of behavioral states, designing state feature vectors, and determining state transition conditions; calculating transition probability, i.e. applying Bayesian reasoning based on historical data statistics, and updating the probability matrix; realizing state prediction, i.e. predicting the probability of the next state, evaluating the reliability of prediction, and dynamically adjusting the prediction model; It is understandable that by constructing a probabilistic state transition model (state space and transition probability), the next possible behavior of the passenger can be predicted, dynamic prediction of the passenger behavior sequence can be achieved, and advance planning and optimization of elevator scheduling can be supported; the probabilistic state transition model can be used to deal with the randomness and uncertainty of passenger behavior, and the state transition probability can be updated through Bayesian reasoning to improve the reliability and robustness of the prediction results; the potential laws and patterns of passenger behavior can be discovered, typical behavior sequences and transfer paths can be identified, and an in-depth understanding of passenger behavior can be supported; a probabilistic basis can be provided for elevator scheduling decisions, supporting proactive services based on predictions, and optimizing resource allocation and scheduling efficiency; behaviors that deviate from normal state transition patterns can be identified, potential abnormal situations can be discovered in a timely manner, and early warning and intervention mechanisms can be provided; transition probabilities can be updated through continuous observation to adapt to dynamic changes in passenger behavior patterns and improve the generalization ability of the model.

[0044] Implement model adaptive optimization and obtain the passenger waiting behavior model, including: designing a feedback mechanism, i.e. collecting prediction error data, analyzing error distribution characteristics, and adjusting model parameters; performing online learning, i.e. updating the behavior feature library, optimizing classification rules, and improving prediction accuracy; and implementing scenario adaptation, i.e. identifying scenario changes, adjusting model parameters, and updating prediction strategies.

[0045] The solution of this embodiment can improve the accuracy of behavior recognition, enhance the ability to predict behavior, and realize timely detection of abnormal behavior; it can quickly respond to scene changes, realize dynamic optimization of models, and improve prediction reliability; it can reduce behavior recognition delays, speed up abnormal behavior responses, and improve decision support efficiency; it can adapt to the characteristics of different populations, support multi-scenario applications, and have transfer learning capabilities.

[0046] In some possible implementations of the present invention, the method for constructing the in-car passenger behavior model includes: Collect multimodal data in the car, including: obtaining visual data, i.e. collecting passenger posture data, recording passenger position distribution data, and identifying face orientation information; collecting audio data, i.e. recording voice command information, collecting environmental sound characteristics, and identifying abnormal sound events; recording sensor data, i.e. collecting weight change data, monitoring vibration information, and obtaining temperature and humidity parameters; Extract passenger characteristics from the collected multimodal data in the car, including: analyzing spatial characteristics, i.e. calculating passenger density distribution, extracting standing pattern characteristics, and identifying moving path characteristics; identifying interactive behaviors, i.e. analyzing human-computer interaction patterns, extracting interpersonal interaction characteristics, and identifying group behavior patterns; evaluating emotional states, i.e. analyzing facial expression changes, identifying body language characteristics, and evaluating tension indicators; Establish a behavior classification model based on passenger characteristics, including: defining basic behavior categories, i.e. normal riding behavior, emergency behavior, and special demand behavior; constructing complex behavior patterns, i.e. identifying behavior sequence rules, extracting behavior combination features, and establishing behavior transfer rules; designing anomaly detection mechanisms, i.e. defining abnormal behavior features, establishing warning thresholds, and formulating emergency response strategies; Combining passenger characteristics and classification models, we obtain the passenger behavior model in the car, including: building a state transition network, i.e. defining the state space, calculating the transition probability, and predicting the next state; applying time series prediction, i.e. analyzing the historical behavior sequence, predicting the future behavior trend, and evaluating the prediction reliability; performing multimodal fusion, i.e. integrating multi-source data information, optimizing the prediction results, and improving the prediction accuracy; Design a safety monitoring mechanism for the in-car passenger behavior model, including: achieving real-time monitoring, i.e. monitoring the degree of congestion, detecting abnormal behavior, and assessing safety risks; establishing an early warning system, i.e. setting multi-level early warning thresholds, defining early warning trigger conditions, and formulating early warning response strategies; and performing emergency response, i.e. identifying emergency situations, initiating emergency plans, and recording event logs.

[0047] The solution of this embodiment can improve the accuracy of behavior recognition, enhance the ability to detect anomalies, and achieve accurate status prediction; it can promptly discover safety hazards, quickly respond to emergencies, and improve operational safety; it can optimize passenger experience, provide personalized services, and enhance service intelligence; it can improve operational efficiency, reduce management costs, and support intelligent decision-making.

[0048] See also Figure 2 ,Another embodiment of the present invention provides a high-rise building elevator management system based on a spatiotemporal information platform, which is used to perform a high-rise building elevator management method based on a spatiotemporal information platform, including: a server, a communication module and an elevator; The server is configured to: Get elevator status data of elevators in the building; Use machine vision technology to monitor passenger flow in the elevator lobby and car in real time and generate passenger status data; Based on the spatiotemporal information platform, a digital twin model of the elevator system is generated according to the elevator status data; According to the passenger status data and the elevator status data, a preset first algorithm is used to make intelligent decisions on elevator scheduling and output a first scheduling strategy; According to the first scheduling strategy, a preset second algorithm is applied to simulate the elevator operation path in the digital twin model, and the elevator scheduling strategy is dynamically adjusted to reduce passenger waiting time and energy consumption, thereby obtaining a second scheduling strategy; The elevators in the building are managed according to the second scheduling strategy.

[0049] It should be known that Figure 2 The block diagram of the high-rise building elevator management system based on the spatiotemporal information platform is only for illustration, and the number of modules shown does not limit the protection scope of the present invention. The high-rise building elevator management system based on the spatiotemporal information platform provided in this embodiment can be used to execute the corresponding embodiments of the high-rise building elevator management method based on the spatiotemporal information platform. For the specific implementation process, please refer to the description of the embodiments of each method, which will not be repeated here.

[0050] It should be noted that, for the aforementioned method embodiments, for the sake of simplicity, they are all expressed as a series of action combinations, but those skilled in the art should be aware that the present application is not limited by the described order of actions, because according to the present application, certain steps can be performed in other orders or simultaneously. Secondly, those skilled in the art should also be aware that the embodiments described in the specification are all preferred embodiments, and the actions and modules involved are not necessarily required by the present application.

[0051] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0052] In the several embodiments provided in the present application, it should be understood that the disclosed device can be implemented in other ways. For example, the device embodiments described above are only schematic, such as the division of the above-mentioned units, which is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, and the indirect coupling or communication connection of devices or units can be electrical or other forms.

[0053] The units described above as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0054] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of software functional units.

[0055] If the above-mentioned integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable memory. Based on this understanding, the technical solution of the present application is essentially or the part that contributes to the prior art or all or part of the technical solution can be embodied in the form of a software product, and the computer software product is stored in a memory, including a number of instructions to enable a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the above-mentioned methods of each embodiment of the present application. The aforementioned memory includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, disk or CD-ROM and other media that can store program codes.

[0056] A person skilled in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing related hardware through a program, and the program can be stored in a computer-readable memory, and the memory can include: a flash drive, a read-only memory (English: Read-Only Memory, abbreviated as: ROM), a random access memory (English: Random Access Memory, abbreviated as: RAM), a magnetic disk or an optical disk, etc.

[0057] The embodiments of the present application are introduced in detail above. Specific examples are used in this article to illustrate the principles and implementation methods of the present application. The description of the above embodiments is only used to help understand the method of the present application and its core idea. At the same time, for general technical personnel in this field, according to the idea of ​​the present application, there will be changes in the specific implementation method and application scope. In summary, the content of this specification should not be understood as a limitation on the present application.

[0058] Although the present invention is disclosed as above, the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions without departing from the spirit and scope of the present invention, and can make various changes and modifications, including the combination of the above-mentioned different functions and implementation steps, including software and hardware implementation methods, all of which are within the scope of protection of the present invention.

Claims

1. A high-rise building elevator management method based on a spatiotemporal information platform, characterized in that: include: Get elevator status data of elevators in the building; Use machine vision technology to monitor passenger flow in the elevator lobby and car in real time and generate passenger status data; Based on the spatiotemporal information platform, a digital twin model of the elevator system is generated according to the elevator status data; According to the passenger status data and the elevator status data, a preset first algorithm is used to make intelligent decisions on elevator scheduling and output a first scheduling strategy; According to the first scheduling strategy, a preset second algorithm is applied to simulate the elevator operation path in the digital twin model, and the elevator scheduling strategy is dynamically adjusted to reduce passenger waiting time and energy consumption, thereby obtaining a second scheduling strategy; The elevators in the building are managed according to the second scheduling strategy.

2. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 1 is characterized in that: The step of using machine vision technology to monitor the passenger flow in the elevator lobby and the car in real time and generate passenger status data includes: Acquire first image data of an elevator lobby and second image data of an elevator car; Analyze the first image data in combination with a preset elevator waiting passenger behavior model to obtain elevator waiting passenger status data; Analyze the second image data in combination with a preset in-car passenger behavior model to obtain in-car passenger status data; The elevator waiting passenger status data and the in-car passenger status data are marked as the passenger status data.

3. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 2 is characterized in that: The step of generating a digital twin model of the elevator system based on the spatiotemporal information platform according to the elevator status data comprises: A three-dimensional scene coordinate system is established based on the spatiotemporal information platform, wherein the three-dimensional scene coordinate system includes: establishing a global coordinate system with the center of the bottom floor of the building as the origin; establishing a local coordinate system with the center of the bottom of each elevator shaft as the origin; and mapping and converting the global coordinate system and the local coordinate system; Constructing a static model of the elevator system, including: constructing a three-dimensional model of elevator components such as an elevator car, a guide rail, a counterweight system, and a hoistway in the three-dimensional scene coordinate system according to the three-dimensional elevator data and the three-dimensional elevator shaft data; calibrating the relative position relationship and motion constraint relationship between the various elevator components; constructing an elevator component material library, and assigning corresponding material attributes to each elevator component; Constructing a dynamic model of the elevator system, including: establishing a physical motion model of the elevator system, including a car motion model, a traction system model, and a counterweight system model; establishing an environmental model of the elevator system according to the elevator internal environment data, including a temperature field model, an airflow field model, and a noise field model; establishing a component state model of the elevator system according to the elevator accessory data, including the working state, wear state, and fault state of each component; The static model and the dynamic model are integrated to generate a digital twin model of the elevator system, including: establishing a corresponding relationship between the physical quantities in the dynamic model and the geometric features in the static model; updating the digital twin model in real time according to the elevator status data collected in real time; and establishing a two-way data interaction mechanism between the digital twin model and the physical elevator system.

4. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 3 is characterized in that: The step of using a preset first algorithm to make intelligent decisions on elevator scheduling based on the passenger status data and the elevator status data and outputting a first scheduling strategy includes: Extracting the elevator waiting passenger status data of each floor from the elevator waiting passenger status data in the passenger status data; Generate elevator car status data according to the in-car passenger status data in the passenger status data and the elevator status data; Extracting a first feature set from the passenger status data of each floor and the elevator car status data; Intelligent decision making is performed on elevator scheduling based on the first feature set and the first algorithm, and a first scheduling strategy is output.

5. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 4 is characterized in that: The second algorithm is an ant colony algorithm; the step of applying a preset second algorithm to simulate the elevator running path in the digital twin model according to the first scheduling strategy, dynamically adjusting the elevator scheduling strategy to reduce passenger waiting time and energy consumption, and obtaining the second scheduling strategy includes: Constructing a graph structure model of an elevator scheduling scenario, including: mapping floor nodes, elevator positions, and target floors as vertices of a graph; mapping possible elevator operation paths as edges of the graph; and assigning initial pheromone concentrations to the edges according to the first scheduling strategy; Initialize the second algorithm parameters, including: setting the number of ants n to match the number of currently scheduled tasks; setting the maximum number of iterations max_iter; setting the pheromone volatility coefficient ρ1; setting the state transition probability calculation parameters α1 and β1; Construct a fitness function, including: calculating the average waiting time of passengers; calculating the total energy consumption of the elevator system; setting the waiting time weight w1 and energy consumption weight w2 according to the actual scheduling scenario; defining the fitness as the weighted sum: f1=w1×waiting time+w2×energy consumption; Execute the path search and optimization process, including: in the digital twin model, randomly assign an initial node to each ant; calculate the selection probability of the next node according to the state transition probability formula: according to the pheromone concentration τ ij and heuristic information η ij Calculate the state transition probability p ij = (τ ij ^α1 × η ij ^β1) / Σ(τ ij ^α1 × η ij ^β1); Update global pheromone concentration: pheromone volatilization τ ij =(1-ρ1)×τ ij ;Pheromone increase Δτ ij = Q / Lk (Q is a constant, Lk is the fitness value of path k); Dynamically adjust the optimization strategy: monitor the real-time state changes in the digital twin model; dynamically adjust the heuristic information according to the state changes; adaptively adjust the α1 and β1 parameter values; update the local optimal solution and the global optimal solution in each iteration; Generate the second scheduling strategy: select the global optimal solution as the final scheduling solution; convert the optimized path into specific scheduling instructions; output detailed scheduling execution steps.

6. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 5 is characterized in that: The first algorithm is a fuzzy neural network algorithm; the step of making intelligent decisions on elevator scheduling based on the first feature set and the first algorithm and outputting a first scheduling strategy includes: Preprocessing the first feature set; The first algorithm is obtained by constructing a fuzzy neural network structure, including: input layer configuration: setting the number of neurons consistent with the feature dimension and defining the domain range of the input variable; fuzzy layer design: designing membership functions for each input variable and determining the number of fuzzy rules; reasoning layer implementation: establishing a fuzzy rule base and setting rule weights; output layer construction: defining the output variable set and designing a defuzzification method; Inputting the preprocessed first feature set into the first algorithm; Execute the fuzzification process, including: calculating the membership of input variables; activating relevant fuzzy rules; Implement fuzzy reasoning, including: executing rule reasoning; aggregating the outputs of multiple rules to generate comprehensive decision results; Perform defuzzification, including: Applying the centroid method: Calculating the crisp value of the output variable and generating specific scheduling instructions; Output mapping conversion: Mapping the crisp value to the scheduling action and generating the execution sequence; Generate the first scheduling strategy, including: output scheduling priority: assign service order to each elevator and determine the target floor sequence; generate execution plan: plan operation path and set time nodes; formulate emergency plan.

7. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 6 is characterized in that: The first algorithm is a fuzzy neural network algorithm; before the step of using the preset first algorithm to make intelligent decisions on elevator scheduling based on the passenger status data and the elevator status data and outputting the first scheduling strategy, it also includes the step of optimizing the first algorithm using a third algorithm, specifically: Initialize the parameter optimization space, including: determine the fuzzy neural network parameters to be optimized: membership function parameters of fuzzy rules, connection weights of neural networks, threshold parameters of neurons; set the value range and constraints of each parameter; establish a parameter encoding scheme to discretize the continuous parameter space; Construct an optimization objective function, including: design evaluation indicators: scheduling decision accuracy, system response time, computing resource consumption; define the objective function: f2 = q1×accuracy + q2×(1 / response time) + q3×(1 / resource consumption); set the weights of each indicator q1, q2, q3; Configure the third algorithm, including: initialize the ant colony: the number of ants m is adapted to the parameter dimension, and the initial parameter combination is randomly assigned; set the algorithm control parameters: pheromone volatility coefficient ρ2, local search probability p_local, global search probability p_global; define the state transition rule: select parameter values ​​based on the roulette strategy, and consider the constraint relationship between parameters; Execute the parameter optimization process, including: evaluate the current parameter combination: test the fuzzy neural network performance on the validation data set and calculate the objective function value; update the local optimal solution: record the optimal parameter combination found by each ant and update the local pheromone concentration; update the global optimal solution: compare and update the global optimal parameter combination and update the global pheromone concentration; apply the adaptive mechanism: dynamically adjust the search step size and adjust the control parameters according to the optimization progress; Implement convergence control, including: setting termination conditions: reaching the maximum number of iterations, objective function value convergence, parameter change less than the threshold; applying early stopping mechanism: monitoring optimization effect and avoiding overfitting; Update the fuzzy neural network, including: use the optimized parameters to update the network: reconstruct the membership function, update the connection weights, and adjust the threshold parameters; verify the optimization effect: evaluate the performance on the test data set and compare the changes in indicators before and after optimization.

8. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 7 is characterized in that: The method for constructing the elevator waiting passenger behavior model includes: Collect basic behavior data, including: obtaining image sequence data, i.e. recording the movement trajectory of passengers waiting for the elevator, capturing posture change information, collecting facial expression data and gesture action data; collecting operation behavior data, i.e. recording key operation sequence, obtaining card swiping information, collecting voice command data; collecting environmental parameters, i.e. recording the crowdedness of the waiting area, monitoring the environmental noise level, and collecting lighting condition data; Extracting behavioral features from basic behavioral data, including: processing spatiotemporal features, i.e. analyzing motion trajectory features, extracting location distribution features, and calculating speed and acceleration features; identifying interactive features, i.e. extracting human-computer interaction patterns, analyzing crowd interaction features, and identifying group behavior patterns; analyzing emotional features, i.e. identifying facial expression changes, analyzing body language features, and evaluating emotional states; Establish a behavior classification system based on the extracted behavior characteristics, including: defining basic behavior types, i.e. normal waiting behavior, emergency travel behavior, and special demand behavior; constructing a composite behavior model, i.e. identifying behavior sequence associations, extracting behavior combination characteristics, and establishing behavior transfer rules; designing abnormal behavior identification, i.e. defining abnormal behavior characteristics, establishing an early warning trigger mechanism, and formulating a response strategy; Construct a probabilistic state transition model based on behavioral characteristics and behavioral classification system, including: establishing state space, i.e. defining the set of behavioral states, designing state feature vectors, and determining state transition conditions; calculating transition probability, i.e. based on historical data statistics, applying Bayesian reasoning, and updating the probability matrix; achieving state prediction, i.e. predicting the probability of the next state, evaluating the reliability of prediction, and dynamically adjusting the prediction model; Implement model adaptive optimization and obtain the passenger waiting behavior model, including: designing a feedback mechanism, i.e. collecting prediction error data, analyzing error distribution characteristics, and adjusting model parameters; performing online learning, i.e. updating the behavior feature library, optimizing classification rules, and improving prediction accuracy; and implementing scenario adaptation, i.e. identifying scenario changes, adjusting model parameters, and updating prediction strategies.

9. The high-rise building elevator management method based on the spatiotemporal information platform according to claim 8 is characterized in that: The method for constructing the in-car passenger behavior model includes: Collect multimodal data in the car, including: obtaining visual data, i.e. collecting passenger posture data, recording passenger position distribution data, and identifying face orientation information; collecting audio data, i.e. recording voice command information, collecting environmental sound characteristics, and identifying abnormal sound events; recording sensor data, i.e. collecting weight change data, monitoring vibration information, and obtaining temperature and humidity parameters; Extract passenger characteristics from the collected multimodal data in the car, including: analyzing spatial characteristics, i.e. calculating passenger density distribution, extracting standing pattern characteristics, and identifying moving path characteristics; identifying interactive behaviors, i.e. analyzing human-computer interaction patterns, extracting interpersonal interaction characteristics, and identifying group behavior patterns; evaluating emotional states, i.e. analyzing facial expression changes, identifying body language characteristics, and evaluating tension indicators; Establish a behavior classification model based on passenger characteristics, including: defining basic behavior categories, i.e. normal riding behavior, emergency behavior, and special demand behavior; constructing complex behavior patterns, i.e. identifying behavior sequence rules, extracting behavior combination features, and establishing behavior transfer rules; designing anomaly detection mechanisms, i.e. defining abnormal behavior features, establishing warning thresholds, and formulating emergency response strategies; Combining passenger characteristics and classification models, we obtain the passenger behavior model in the car, including: building a state transition network, i.e. defining the state space, calculating the transition probability, and predicting the next state; applying time series prediction, i.e. analyzing the historical behavior sequence, predicting the future behavior trend, and evaluating the prediction reliability; performing multimodal fusion, i.e. integrating multi-source data information, optimizing the prediction results, and improving the prediction accuracy; Design a safety monitoring mechanism for the in-car passenger behavior model, including: achieving real-time monitoring, i.e. monitoring the degree of congestion, detecting abnormal behavior, and assessing safety risks; establishing an early warning system, i.e. setting multi-level early warning thresholds, defining early warning trigger conditions, and formulating early warning response strategies; and performing emergency response, i.e. identifying emergency situations, initiating emergency plans, and recording event logs.

10. A high-rise building elevator management system based on a spatiotemporal information platform, used to execute the high-rise building elevator management method based on a spatiotemporal information platform as claimed in any one of claims 1 to 9, characterized in that: include: servers, communication modules and elevators; The server is configured to: Get elevator status data of elevators in the building; Use machine vision technology to monitor passenger flow in the elevator lobby and car in real time and generate passenger status data; Based on the spatiotemporal information platform, a digital twin model of the elevator system is generated according to the elevator status data; According to the passenger status data and the elevator status data, a preset first algorithm is used to make intelligent decisions on elevator scheduling and output a first scheduling strategy; According to the first scheduling strategy, a preset second algorithm is applied to simulate the elevator operation path in the digital twin model, and the elevator scheduling strategy is dynamically adjusted to reduce passenger waiting time and energy consumption, thereby obtaining a second scheduling strategy; The elevators in the building are managed according to the second scheduling strategy.

Images