Vertical traffic capacity resource allocation method based on urban area people flow heat map

Abstract

This invention discloses a method and system for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps. The method includes: constructing a standardized basic data set by collecting urban public transportation operation data, regional pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target building. Based on this data set, a macro-level pedestrian flow prediction method is used to calculate the scale and distribution characteristics of people arriving in the target area in the future, and the demand for elevators on each floor is accurately predicted by combining the pedestrian flow heat map. Based on the demand prediction results and the vertical transportation capacity supply conditions, a pre-allocation plan for transportation resources is generated, and the elevator parking planning and operation mode are dynamically adjusted. After the plan is issued and implemented, actual pedestrian flow data and elevator operation feedback information are collected in real time, and the allocation plan is continuously corrected based on data deviations, realizing adaptive and refined control of vertical transportation capacity resources.

Description

Technical Field

[0001] This invention belongs to the field of intelligent scheduling technology for vertical transportation, and more specifically, relates to a method and system for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps. Background Technology

[0002] Currently, vertical transportation facilities in urban office buildings, commercial complexes, and other buildings mainly rely on fixed operating modes, making it difficult to adapt to the dynamic changes in pedestrian flow. This has led to an increasingly prominent problem of unreasonable allocation of vertical transportation capacity. With the acceleration of urbanization, the distribution of people in urban areas exhibits significant spatial and temporal imbalances, especially in densely populated places such as office buildings. During morning and evening peak hours, the number of people entering and exiting each floor surges, while during off-peak hours, pedestrian flow is slower. This fluctuation places higher demands on the capacity supply of vertical transportation facilities.

[0003] Current vertical transportation capacity allocation methods are mostly based on fixed scheduling strategies, failing to fully consider the thermal distribution of people in urban areas and the dynamic changes in occupants on each floor of a building. They rely solely on experience to set elevator stopping floors and operating cycles, making it impossible to accurately match the actual elevator demand at different times and on different floors. During peak hours, demand is concentrated on some floors, resulting in insufficient elevator capacity and excessively long waiting times, impacting travel efficiency. Conversely, during off-peak hours, elevators operate empty or have redundant capacity, leading to energy waste and equipment wear and tear.

[0004] Meanwhile, existing technologies lack effective data support and dynamic correction mechanisms, and mostly use single data or fuzzy prediction methods. They do not integrate urban public transportation operation data, pedestrian flow heat map data and vertical transportation facility operation data, making it difficult to accurately predict the spatiotemporal distribution characteristics of elevator demand on each floor of a building, and also unable to adjust the capacity allocation plan according to real-time deviations in passenger flow.

[0005] This traditional capacity allocation model not only reduces the operational efficiency of vertical transportation facilities and affects the travel experience of passengers, but also increases equipment maintenance costs and energy consumption, failing to meet the demands of modern buildings for intelligent and efficient vertical transportation. Therefore, there is an urgent need for a method that can combine the thermal characteristics of urban pedestrian flow to accurately match the elevator demand of each floor and time period, achieving dynamic capacity allocation and adaptive control to solve the aforementioned problems of existing technologies and improve the rationality and efficiency of vertical transportation operations. Summary of the Invention

[0006] This invention aims to solve the problems of fixed vertical transportation capacity allocation in existing buildings, mismatch with real-time passenger flow, low elevator waiting efficiency, and resource waste. By integrating urban public transportation data and passenger flow heat maps, it can accurately predict and dynamically schedule the demand for elevators on each floor of the building, and adjust the remaining waiting passengers based on the real-time number of passengers getting off the elevator, thereby improving elevator operating efficiency and passenger travel experience.

[0007] To address the aforementioned deficiencies or improvement needs of existing technologies, this invention provides a method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps, comprising:

[0008] S1. Collect urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area to construct a basic data set for the pre-allocation of vertical transportation capacity;

[0009] S2. Based on the aforementioned basic data set, a macro-level passenger flow prediction method is used to calculate the passenger flow characteristics of the target area within a preset time period in the future, and the vertical transportation passenger flow demand prediction analysis of the target area is completed by combining the urban area population heat map.

[0010] S3. Based on the predicted analysis results of vertical transportation passenger flow, and combined with the capacity supply capacity of vertical transportation facilities in the target area, generate a pre-allocation plan for the capacity resources of vertical transportation facilities in the target area.

[0011] S4. The pre-allocation plan for transportation capacity resources is sent to the control terminal of the vertical transportation facilities in the target area and executed. At the same time, the actual passenger flow data and operation feedback data of the vertical transportation facilities in the target area are collected in real time. The pre-allocation plan for transportation capacity resources is dynamically corrected according to the data deviation to achieve adaptive regulation of vertical transportation capacity resources.

[0012] Furthermore, the public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area in S1 are as follows:

[0013] The urban public transportation operation data includes urban public transportation travel trajectory data, station operation data, passenger flow carrying capacity data, and passenger flow direction data;

[0014] The urban area pedestrian flow heat map data includes pedestrian density data, pedestrian distribution data, and dynamic change data of pedestrian flow in various urban areas.

[0015] The basic operational data of the vertical transportation facilities in the target area includes the quantity data, layout data, operational parameter data, and capacity-related data of the vertical transportation facilities in the target area.

[0016] Furthermore, the method for constructing the basic data set in S1 is as follows:

[0017] The collected urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area were all subjected to spatiotemporal normalization processing. The time base for data collection was set as follows: The spatial reference is the coordinates of the geographic center of the target area. Assign a spatiotemporal identifier to any data acquisition unit. ,in This refers to the acquisition time of this data unit. , These are the geographic x-coordinate and y-coordinate of the data unit, respectively.

[0018] Calculate the spatiotemporal deviation values ​​between each data unit and the spatiotemporal reference. , , Spatiotemporal calibration is performed on each data unit based on the spatiotemporal deviation value to obtain the calibrated data unit. ,in The original attribute value of the data unit;

[0019] All calibrated data units were structured and clustered according to their spatiotemporal identifiers, based on the following criteria: Time interval division and , The spatial regions are divided and clustered to form structured data clusters with spatiotemporal correlation characteristics. All structured data clusters are integrated and stored to construct the basic data set for the pre-allocation of vertical transportation capacity.

[0020] Furthermore, the macro-level passenger flow prediction method in S2 is specifically as follows:

[0021] Set the future preset duration as Based on the spatiotemporally calibrated urban public transportation operation data in the basic dataset, a preset duration is extracted. Total number of people arriving at the target building's exterior ;

[0022] Extract the real-time number of people inside the target building corresponding to the urban area pedestrian flow heat map data in the basic dataset. Then extract the personnel inflow rate of the target building per unit time. Personnel outflow rate Calculate the preset duration Changes in the number of people inside the building Get the preset duration Real-time total number of people inside the target building ;

[0023] The target building is divided into sections based on the actual floor range served by the vertical transportation facilities. Each elevator demand sub-area The value is a positive integer; retrieve the historical number of passengers in each elevator demand sub-region of the basic data set under the same time period and working conditions. , Based on the historical distribution of elevator users, a normalized elevator demand allocation relationship is constructed. Combined with the total number of people in the target building , obtained the Each elevator demand sub-area within a preset time period Predicted number of elevator passengers ;in For the first The predicted number of elevator users in each elevator demand sub-area, and meeting the following conditions. Based on the predicted number of elevator passengers in each elevator demand sub-area. Based on the core criteria and combined with the real-time changes in the number of people on each floor in the urban area's heat map of pedestrian flow, the vertical transportation demand of each floor in the target building is predicted and analyzed.

[0024] Furthermore, the process of predicting and analyzing the vertical transportation passenger flow demand in the target area in S2 is as follows:

[0025] Predicted number of elevator users based on elevator demand sub-areas on each floor Combined with the rated number of passengers transported per unit time of a single vertical transportation facility Calculate the vertical transportation capacity demand intensity corresponding to the elevator demand sub-area on each floor. ,in ;

[0026] Based on the elevator demand intensity of each floor's sub-area. The demand for vertical transportation elevators within the target building is classified into different levels to form a gradient distribution of demand intensity. Combined with the real-time changes in the number of people on each floor in the heat map of pedestrian flow, the gradient distribution of demand intensity is spatiotemporally verified to obtain the prediction results of the vertical transportation elevator demand of the target building, and to determine the priority of capacity demand and peak demand periods of each floor's elevator demand sub-area.

[0027] Furthermore, the method for generating the capacity resource pre-allocation scheme in S3 is as follows:

[0028] Based on the predicted demand for elevators in the target building's vertical transportation system, the capacity demand intensity of each floor's elevator demand sub-area is extracted. Prioritize transportation capacity demand and peak demand periods, and combine this with the basic data to centralize the number of vertical transportation facilities in the target building, the inherent service floor range, and the rated number of passengers that a single vertical transportation facility can transport per unit time. Preset the duration for the future Based on population mobility trends, it is divided into A series of consecutive scheduling time slices of varying durations ,satisfy ;

[0029] Retrieve the Historical time-sharing elevator passenger numbers for each floor's elevator demand sub-area, corresponding to each scheduling time slot. Construct this sub-region in the first... Time-sharing elevator demand function within a scheduling time slice ;in For the first Total predicted number of elevator users in each floor's elevator demand sub-area For the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. The number of passengers using the elevator during the same historical period corresponding to each scheduling time slice. For this sub-region for a preset time period Total number of passengers using the elevator throughout history Characterizing the first Within the scheduling time slice, the first The actual time-sharing elevator demand for each floor's elevator demand sub-area;

[0030] by Establish a time-sharing mapping relationship for vertical transportation facilities as constraints. ,in Indicates the first Taiwan's vertical transportation facilities in the first Service objects within a scheduling time slice , The total number of vertical transportation facilities in operation within the target building;

[0031] For each vertical transportation facility According to each scheduling time slice Determine the floor where it will be stationed and ready to be deployed. ,Will The floor is set to the floor with the highest time-sharing elevator demand within that time slot;

[0032] Simultaneously construct the runtime function Based on the time-sharing elevator demand function, time-sharing scheduling mapping relationship, and the functions of the parking and waiting floors and the operation cycle, a pre-allocation scheme for vertical transportation capacity resources with time-dimensional scheduling as the core is generated.

[0033] Furthermore, the operating cycle function is:

[0034]

[0035] in For floor operations, Characterizing the first Taiwan's vertical transportation facilities in the first A single execution cycle within a scheduling time slice.

[0036] Furthermore, the process in S4 of dynamically correcting the pre-allocation scheme of transportation resources based on data deviation is as follows:

[0037] Real-time data collection includes the actual number of people disembarking from elevators in each floor's elevator demand sub-area within the target building, as well as operational feedback data for each vertical transportation facility; among which, the first... The sub-area of ​​elevator demand on each floor is in the [number]th floor. The actual number of people disembarking within each scheduling time slot is recorded as follows: This data is collected by the elevator passenger count or the floor access control system; operational feedback data includes the corresponding scheduling time slots for each vertical transportation facility. The actual operating cycle within ;

[0038] Based on initial forecasts of time-sharing elevator demand The actual number of people who disembarked after the transport was completed Calculate the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. Number of remaining passengers to be transported within each scheduling time slot ;in, The number of people in that sub-region who have not yet completed transportation within that time slice is the core basis for dynamic adjustment; when If this occurs, it indicates that the actual transportation demand in that sub-region is not being met, and additional capacity needs to be allocated to subsequent scheduling time slots.

[0039] The remaining number of people to be transported Based on historical time-sharing elevator usage distribution ratio Allocated to all subsequent scheduling time slices The corrected time-sharing elevator demand was obtained. ;in, For the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. The historical number of passengers corresponding to each scheduling time slice;

[0040] Based on the revised time-sharing elevator demand Recalibrate the time-sharing scheduling mapping relationships of each vertical transportation facility. Synchronously correct its operating cycle function ;in, The rated number of passengers that a single vertical transportation facility can transport per unit of time. This is for rounding up. Simultaneously, the floors where each vertical transportation facility is waiting and ready to operate will be listed. Adjust to the current time slice The floors with the highest elevator values ​​are prioritized to respond to the most urgent elevator needs.

[0041] As a second aspect of the present invention, a vertical transportation capacity resource allocation system based on urban area pedestrian flow heat maps is also provided, comprising:

[0042] The data collection and aggregation construction unit is used to collect urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area, and to construct a basic data set for the pre-allocation of vertical transportation capacity;

[0043] The elevator demand prediction and analysis unit is used to calculate the passenger flow characteristics of the target area within a preset time period based on the basic data set and using a macro passenger flow prediction method. It combines the urban area population heat map to complete the vertical transportation passenger flow demand prediction and analysis of the target area.

[0044] The capacity resource pre-allocation generation unit is used to generate a capacity resource pre-allocation scheme for vertical transportation facilities in the target area based on the predicted analysis results of the vertical transportation passenger flow demand and the capacity supply capacity of the vertical transportation facilities in the target area.

[0045] The real-time feedback and adaptive correction unit is used to send the pre-allocation plan of transportation capacity resources to the control terminal of the vertical transportation facilities in the target area and execute it. At the same time, it collects the actual passenger flow data and the operation feedback data of the vertical transportation facilities in the target area in real time, and dynamically corrects the pre-allocation plan of transportation capacity resources according to the data deviation, so as to realize the adaptive regulation of vertical transportation capacity resources.

[0046] As a second aspect of the present invention, a computer-readable storage medium is also provided, on which a computer program is stored, which is executed by a processor as described in any one of the present invention, a method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps.

[0047] In summary, compared with the prior art, the above-described technical solutions conceived by this invention can achieve the following beneficial effects:

[0048] 1. The present invention provides a method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps. This method collects urban public transportation operation data, regional pedestrian flow heat map data, and basic operational data of vertical transportation facilities to construct a spatiotemporally normalized basic data set, achieving unified calibration and structured clustering of multi-source data. This step relies on real-time pedestrian flow heat maps and historical operational information to clarify the distribution patterns of people on each floor of the target building. It abandons traditional methods of equal area division and fuzzy regional segmentation, using historical elevator usage data as the core basis to provide accurate and reliable data support for subsequent elevator demand prediction. This ensures a high degree of matching between the input information and the building's vertical transportation scenario, improving the accuracy and applicability of the overall analysis.

[0049] 2. The vertical transportation capacity allocation method based on urban area pedestrian flow heat maps of this invention combines a macro-level personnel prediction model with historical time-sharing elevator usage distribution to calculate the total population size of the target building and allocate it to sub-areas on each floor. It relies on time-sharing elevator usage demand functions to accurately break down elevator usage demand at different times, and then generates a time-based pre-allocation plan based on demand intensity and peak hours. The plan only adjusts the elevator stopping floors and operating cycles without changing the physical layout, aligning with the actual scheduling logic of office buildings. This ensures that capacity deployment dynamically corresponds to elevator usage demand on each floor and at each time period, effectively alleviating peak-hour waiting pressure and improving the efficiency and stability of vertical transportation operations.

[0050] 3. The vertical transportation capacity resource allocation method based on urban area pedestrian flow heat maps of the present invention collects real-time data on the actual number of people disembarking and transported on each floor, calculates the remaining scale of people waiting to be transported, and performs closed-loop correction of elevator demand based on historical distribution, continuously optimizing the capacity allocation scheme. This correction method relies only on monitorable real-time and historical data, does not predict the destination of individual people, has rigorous logic, and is engineering-practical. It can quickly respond to deviations in actual pedestrian flow, achieving full-process adaptive control of prediction, execution, feedback, and correction, ensuring that vertical transportation capacity always matches real-time demand, and improving the system's operational stability and intelligence level. Attached Figure Description

[0051] Figure 1 This is a flowchart of a vertical transportation capacity resource allocation method based on urban area pedestrian flow heat map according to an embodiment of the present invention;

[0052] Figure 2 This is a schematic diagram of the system units in an embodiment of the present invention. Detailed Implementation

[0053] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the invention. Furthermore, the technical features involved in the various embodiments of this invention described below can be combined with each other as long as they do not conflict with each other.

[0054] Example 1

[0055] Please refer to Figure 1 This embodiment 1 provides a method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps, including:

[0056] S1. Collect urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area to construct a basic data set for the pre-allocation of vertical transportation capacity;

[0057] S2. Based on the aforementioned basic data set, a macro-level passenger flow prediction method is used to calculate the passenger flow characteristics of the target area within a preset time period in the future, and the vertical transportation passenger flow demand prediction analysis of the target area is completed by combining the urban area population heat map.

[0058] S3. Based on the predicted analysis results of vertical transportation passenger flow, and combined with the capacity supply capacity of vertical transportation facilities in the target area, generate a pre-allocation plan for the capacity resources of vertical transportation facilities in the target area.

[0059] S4. The pre-allocation plan for transportation capacity resources is sent to the control terminal of the vertical transportation facilities in the target area and executed. At the same time, the actual passenger flow data and operation feedback data of the vertical transportation facilities in the target area are collected in real time. The pre-allocation plan for transportation capacity resources is dynamically corrected according to the data deviation to achieve adaptive regulation of vertical transportation capacity resources.

[0060] This embodiment 1 further elaborates on the above steps.

[0061] (1) Data collection and collection construction

[0062] As the flow of people in urban buildings becomes increasingly complex, traditional vertical transportation scheduling relies heavily on experience-based settings and lacks multi-source data support, making it difficult to match the actual patterns of external public transportation input and internal personnel flow. To achieve matching of transport capacity allocation with personnel demand, it is necessary to first complete the unified collection and standardized processing of multi-dimensional data to form a basic data set to support subsequent analysis and scheduling.

[0063] The system first collects information related to urban public transportation operations, specifically including public transportation routes, station operational status, vehicle passenger capacity, and overall passenger flow data, reflecting the scale and trend of external passenger flow into the target area. Simultaneously, it collects information related to urban area pedestrian flow heat maps, covering pedestrian density, spatial distribution, and dynamic changes in pedestrian flow in various areas, providing a basis for judging the degree and trend of population concentration in the target area. Furthermore, it collects basic operational information on vertical transportation facilities within the target area, including the number of facilities, spatial layout, operating parameters, and capacity configuration data, to understand the supply capacity and operating conditions of the vertical transportation system itself.

[0064] After completing the collection of various types of data, the collected urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area were subjected to spatiotemporal normalization processing. The time base for data collection was set as follows. The spatial reference is the coordinates of the geographic center of the target area. Assign a spatiotemporal identifier to any data acquisition unit. ,in This refers to the acquisition time of this data unit. , These are the geographic x-coordinate and y-coordinate of the data unit, respectively.

[0065] Calculate the spatiotemporal deviation values ​​between each data unit and the spatiotemporal reference. , , Spatiotemporal calibration is performed on each data unit based on the spatiotemporal deviation value to obtain the calibrated data unit. ,in The original attribute value of the data unit;

[0066] All calibrated data units were structured and clustered according to their spatiotemporal identifiers, based on the following criteria: Time interval division and , The spatial regions are divided and clustered to form structured data clusters with spatiotemporal correlation characteristics. All structured data clusters are integrated and stored to construct the basic data set for the pre-allocation of vertical transportation capacity.

[0067] (2) Analysis of elevator demand forecast

[0068] After integrating and standardizing multi-source data, passenger flow characteristic calculations and elevator demand analysis can be conducted based on the constructed basic dataset. This effectively solves the problems of vague demand prediction and disconnect between actual passenger flow and traditional vertical transportation scheduling. Using uniformly calibrated public transportation, passenger flow heatmaps, and facility operation information, objective judgments on the future population size and distribution of target buildings can be made, providing a reliable basis for subsequent capacity allocation.

[0069] In the macro-level passenger flow forecasting stage, a forecast range for a future period is determined based on a foundational dataset. By analyzing public transportation operation information, the total number of people expected to arrive at the target building during this period is statistically analyzed. Simultaneously, combined with pedestrian flow heatmap data, the current real-time number of people inside the building is obtained. Based on the rate of change in passenger inflow and outflow per unit time, the overall change in the number of people inside the building during the forecast period is estimated, ultimately determining the total passenger size of the target building during this period. According to the actual floor range served by the vertical transportation facilities, the building is divided into several elevator demand sub-areas. Historical elevator passenger data for each sub-area under the same time period and operating conditions is retrieved. Using historical distribution ratios as the allocation basis, the total passenger size is rationally allocated to each sub-area, obtaining the predicted number of elevator passengers for each floor, ensuring that the demand allocation for each floor aligns with historical operational patterns.

[0070] Specifically, the preset duration for the future is set as follows: Based on the spatiotemporally calibrated urban public transportation operation data in the basic dataset, a preset duration is extracted. Total number of people arriving at the target building's exterior ;

[0071] Extract the real-time number of people inside the target building corresponding to the urban area pedestrian flow heat map data in the basic dataset. Then extract the personnel inflow rate of the target building per unit time. Personnel outflow rate Calculate the preset duration Changes in the number of people inside the building Get the preset duration Real-time total number of people inside the target building ;

[0072] The target building is divided into sections based on the actual floor range served by the vertical transportation facilities. Each elevator demand sub-area The value is a positive integer; retrieve the historical number of passengers in each elevator demand sub-region of the basic data set under the same time period and working conditions. , Based on the historical distribution of elevator users, a normalized elevator demand allocation relationship is constructed. Combined with the total number of people in the target building , obtained the Each elevator demand sub-area within a preset time period Predicted number of elevator passengers ;in For the first The predicted number of elevator users in each elevator demand sub-area, and meeting the following conditions. Based on the predicted number of elevator passengers in each elevator demand sub-area. Based on the core criteria and combined with the real-time changes in the number of people on each floor in the urban area's heat map of pedestrian flow, the vertical transportation demand of each floor in the target building is predicted and analyzed.

[0073] In the vertical transportation elevator demand forecasting and analysis phase, the predicted number of elevator passengers is based on the elevator demand sub-regions on each floor. Combined with the rated number of passengers transported per unit time of a single vertical transportation facility Calculate the vertical transportation capacity demand intensity corresponding to the elevator demand sub-area on each floor. ,in ;

[0074] Based on the elevator demand intensity of each floor's sub-area. The demand for vertical transportation elevators within the target building is classified into different levels to form a gradient distribution of demand intensity. Combined with the real-time changes in the number of people on each floor in the heat map of pedestrian flow, the gradient distribution of demand intensity is spatiotemporally verified to obtain the prediction results of the vertical transportation elevator demand of the target building, and to determine the priority of capacity demand and peak demand periods of each floor's elevator demand sub-area.

[0075] (3) Generation of pre-allocation of transportation capacity resources

[0076] After predicting and classifying the demand for elevators on each floor within the building, it is necessary to transform the demand results into an executable scheduling strategy, taking into account the supply conditions of the vertical transportation system itself. This will change the traditional fixed-stop, fixed-cycle operation mode and achieve dynamic matching between capacity and demand. Based on the demand prediction results obtained in the early stage, combined with the actual configuration and carrying capacity of the vertical transportation facilities, a pre-allocation plan that conforms to the pattern of personnel flow can be formulated, which can effectively improve the scheduling efficiency during peak hours and reduce elevator waiting and empty operation.

[0077] In the process of generating the pre-allocation plan for transportation resources, the transportation demand intensity of each floor's elevator demand sub-area is first extracted based on the predicted elevator demand of the target building. Prioritize transportation capacity demand and peak demand periods, and combine this with the basic data to centralize the number of vertical transportation facilities in the target building, the inherent service floor range, and the rated number of passengers that a single vertical transportation facility can transport per unit time. Preset the duration for the future Based on population mobility trends, it is divided into A series of consecutive scheduling time slices of varying durations ,satisfy ;

[0078] Retrieve the Historical time-sharing elevator passenger numbers for each floor's elevator demand sub-area, corresponding to each scheduling time slot. Construct this sub-region in the first... Time-sharing elevator demand function within a scheduling time slice ;in For the first Total predicted number of elevator users in each floor's elevator demand sub-area For the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. The number of passengers using the elevator during the same historical period corresponding to each scheduling time slice. For this sub-region for a preset time period Total number of passengers using the elevator throughout history Characterizing the first Within the scheduling time slice, the first The actual time-sharing elevator demand for each floor's elevator demand sub-area;

[0079] by Establish a time-sharing mapping relationship for vertical transportation facilities as constraints. ,in Indicates the first Taiwan's vertical transportation facilities in the first Service objects within a scheduling time slice , The total number of vertical transportation facilities in operation within the target building;

[0080] For each vertical transportation facility According to each scheduling time slice Determine the floor where it will be stationed and ready to be deployed. ,Will The floor is set to the floor with the highest time-sharing elevator demand within that time slot;

[0081] Simultaneously construct the runtime function Based on the time-sharing elevator demand function, time-sharing scheduling mapping relationship, and the functions of the parking and waiting floors and the operation cycle, a pre-allocation scheme for vertical transportation capacity resources with time-dimensional scheduling as the core is generated.

[0082] In the preferred implementation, the operating cycle function used is:

[0083]

[0084] in For floor operations, Characterizing the first Taiwan's vertical transportation facilities in the first A single execution cycle within a scheduling time slice.

[0085] (4) Real-time feedback and adaptive correction

[0086] After the pre-allocation plan is issued and put into actual operation, the actual passenger flow often deviates from the initial predictions. Relying solely on static allocation is insufficient to continuously meet the ever-changing elevator demand. Therefore, a closed-loop feedback and dynamic correction mechanism is needed to ensure the vertical transportation system remains in a state of efficient adaptation. By collecting real-time operational data and comparing the differences between predicted and actual values, the plan can be continuously adjusted to effectively solve the mismatch between predictions and reality, achieving adaptive control of vertical transportation capacity.

[0087] In actual implementation, the system will distribute the generated pre-allocation plan of transportation resources to the control terminal of the vertical transportation facilities in the target building, and put them into operation according to the set stopping floors and operating cycles. Simultaneously, it will collect real-time data on the actual number of people disembarking in each floor's elevator demand sub-area within the target building, as well as operational feedback data from each vertical transportation facility; among which, the first... The sub-area of ​​elevator demand on each floor is in the [number]th floor. The actual number of people disembarking within each scheduling time slot is recorded as follows: This data is collected by the elevator passenger count or the floor access control system; operational feedback data includes the corresponding scheduling time slots for each vertical transportation facility. The actual operating cycle within ;

[0088] Based on initial forecasts of time-sharing elevator demand The actual number of people who disembarked after the transport was completed Calculate the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. Number of remaining passengers to be transported within each scheduling time slot ;in, The number of people in that sub-region who have not yet completed transportation within that time slice is the core basis for dynamic adjustment; when If this occurs, it indicates that the actual transportation demand in that sub-region is not being met, and additional capacity needs to be allocated to subsequent scheduling time slots.

[0089] The remaining number of people to be transported Based on historical time-sharing elevator usage distribution ratio Allocated to all subsequent scheduling time slices The corrected time-sharing elevator demand was obtained. ;in, For the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. The historical number of passengers corresponding to each scheduling time slice;

[0090] Based on the revised time-sharing elevator demand Recalibrate the time-sharing scheduling mapping relationships of each vertical transportation facility. Synchronously correct its operating cycle function ;in, The rated number of passengers that a single vertical transportation facility can transport per unit of time. This is for rounding up. Simultaneously, the floors where each vertical transportation facility is waiting and ready to operate will be listed. Adjust to the current time slice The floors with the highest elevator values ​​are prioritized to respond to the most urgent elevator needs.

[0091] By continuously collecting actual data, calculating deviations, allocating remaining demand, and updating scheduling strategies, vertical transportation capacity resources are always matched with real-time elevator demand, ultimately achieving adaptive control throughout the entire process.

[0092] Example 2

[0093] Please refer to Figure 2 This embodiment 2 provides a vertical transportation capacity resource allocation system based on urban area pedestrian flow heat map, including:

[0094] The data collection and aggregation construction unit is used to collect urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area, and to construct a basic data set for the pre-allocation of vertical transportation capacity;

[0095] The elevator demand prediction and analysis unit is used to calculate the passenger flow characteristics of the target area within a preset time period based on the basic data set and using a macro passenger flow prediction method. It combines the urban area population heat map to complete the vertical transportation passenger flow demand prediction and analysis of the target area.

[0096] The capacity resource pre-allocation generation unit is used to generate a capacity resource pre-allocation scheme for vertical transportation facilities in the target area based on the predicted analysis results of the vertical transportation passenger flow demand and the capacity supply capacity of the vertical transportation facilities in the target area.

[0097] The real-time feedback and adaptive correction unit is used to send the pre-allocation plan of transportation capacity resources to the control terminal of the vertical transportation facilities in the target area and execute it. At the same time, it collects the actual passenger flow data and the operation feedback data of the vertical transportation facilities in the target area in real time, and dynamically corrects the pre-allocation plan of transportation capacity resources according to the data deviation, so as to realize the adaptive regulation of vertical transportation capacity resources.

[0098] Example 3

[0099] This embodiment 3 also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, can implement any step of a vertical transportation capacity resource allocation method based on urban area pedestrian flow heat map.

[0100] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0101] For a description of the computer-readable storage medium provided in this application, please refer to the above method embodiments; further details will not be repeated here.

[0102] Those skilled in the art will readily understand that the above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps, characterized in that, include: S1. Collect urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area to construct a basic data set for the pre-allocation of vertical transportation capacity; S2. Based on the aforementioned basic data set, a macro-level passenger flow prediction method is used to calculate the passenger flow characteristics of the target area within a preset time period in the future, and the vertical transportation passenger flow demand prediction analysis of the target area is completed by combining the urban area population heat map. S3. Based on the predicted analysis results of vertical transportation passenger flow, and combined with the capacity supply capacity of vertical transportation facilities in the target area, generate a pre-allocation plan for the capacity resources of vertical transportation facilities in the target area. S4. The pre-allocation plan for transportation capacity resources is sent to the control terminal of the vertical transportation facilities in the target area and executed. At the same time, the actual passenger flow data and operation feedback data of the vertical transportation facilities in the target area are collected in real time. The pre-allocation plan for transportation capacity resources is dynamically corrected according to the data deviation to achieve adaptive regulation of vertical transportation capacity resources. The macro-passenger flow prediction method in S2 is specifically as follows: Set the future preset duration as Based on the spatiotemporally calibrated urban public transportation operation data in the basic dataset, a preset duration is extracted. Total number of people arriving at the target building's exterior ; Extract the real-time number of people inside the target building corresponding to the urban area pedestrian flow heat map data in the basic dataset. Then extract the personnel inflow rate of the target building per unit time. Personnel outflow rate Calculate the preset duration Changes in the number of people inside the building Get the preset duration Real-time total number of people inside the target building ; The target building is divided into sections based on the actual floor range served by the vertical transportation facilities. Each elevator demand sub-area The value is a positive integer; retrieve the historical number of passengers in each elevator demand sub-region of the basic data set under the same time period and working conditions. , ; Based on the historical distribution of elevator users, a normalized elevator demand allocation relationship is constructed. Combined with the total number of people in the target building , obtained the Each elevator demand sub-area within a preset time period Predicted number of elevator passengers ;in For the first The predicted number of elevator users in each elevator demand sub-area, and meeting the following conditions. Based on the predicted number of elevator passengers in each elevator demand sub-area. Based on the core criteria and combined with the real-time changes in the number of people on each floor in the urban area's heat map of pedestrian flow, the vertical transportation demand of each floor in the target building is predicted and analyzed.

2. The method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps according to claim 1, characterized in that, The public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area mentioned in S1 are as follows: The urban public transportation operation data includes urban public transportation travel trajectory data, station operation data, passenger flow carrying capacity data, and passenger flow direction data; The urban area pedestrian flow heat map data includes pedestrian density data, pedestrian distribution data, and dynamic change data of pedestrian flow in various urban areas. The basic operational data of the vertical transportation facilities in the target area includes the quantity data, layout data, operational parameter data, and capacity-related data of the vertical transportation facilities in the target area.

3. The method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps according to claim 1, characterized in that, The method for constructing the basic data set in S1 is as follows: The collected urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area were all subjected to spatiotemporal normalization processing. The time base for data collection was set as follows: The spatial reference is the coordinates of the geographic center of the target area. Assign a spatiotemporal identifier to any data acquisition unit. ,in This refers to the acquisition time of this data unit. , These are the geographic x-coordinate and y-coordinate of the data unit, respectively. Calculate the spatiotemporal deviation values ​​between each data unit and the spatiotemporal reference. , , Spatiotemporal calibration is performed on each data unit based on the spatiotemporal deviation value to obtain the calibrated data unit. ,in The original attribute value of the data unit; All calibrated data units were structured and clustered according to their spatiotemporal identifiers, based on the following criteria: Time interval division and , The spatial regions are divided and clustered to form structured data clusters with spatiotemporal correlation characteristics. All structured data clusters are integrated and stored to construct the basic data set for the pre-allocation of vertical transportation capacity.

4. The method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps according to claim 1, characterized in that, The process of predicting and analyzing the vertical transportation passenger flow demand in the target area in S2 is as follows: Predicted number of elevator users based on elevator demand sub-areas on each floor Combined with the rated number of passengers transported per unit time of a single vertical transportation facility Calculate the vertical transportation capacity demand intensity corresponding to the elevator demand sub-area on each floor. ,in ; Based on the elevator demand intensity of each floor's sub-area. The demand for vertical transportation elevators within the target building is classified into different levels to form a gradient distribution of demand intensity. Combined with the real-time changes in the number of people on each floor in the heat map of pedestrian flow, the gradient distribution of demand intensity is spatiotemporally verified to obtain the prediction results of the vertical transportation elevator demand of the target building, and to determine the priority of capacity demand and peak demand periods of each floor's elevator demand sub-area.

5. The method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps according to claim 1, characterized in that, The method for generating the capacity resource pre-allocation scheme in S3 is as follows: Based on the predicted demand for elevators in the target building's vertical transportation system, the capacity demand intensity of each floor's elevator demand sub-area is extracted. Prioritize transportation capacity demand and peak demand periods, and combine this with the basic data to centralize the number of vertical transportation facilities in the target building, the inherent service floor range, and the rated number of passengers that a single vertical transportation facility can transport per unit time. Preset the duration for the future Based on population mobility trends, it is divided into A series of consecutive scheduling time slices of varying durations ,satisfy ; Retrieve the Historical time-sharing elevator passenger numbers for each floor's elevator demand sub-area, corresponding to each scheduling time slot. Construct this sub-region in the first... Time-sharing elevator demand function within a scheduling time slice ;in For the first Total predicted number of elevator users in each floor's elevator demand sub-area For the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. The number of passengers using the elevator during the same historical period corresponding to each scheduling time slice. For this sub-region for a preset time period Total number of passengers using the elevator throughout history Characterizing the first Within the scheduling time slice, the first The actual time-sharing elevator demand for each floor's elevator demand sub-area; by Establish a time-sharing mapping relationship for vertical transportation facilities as constraints. ,in Indicates the first Taiwan's vertical transportation facilities in the first Service objects within a scheduling time slice , The total number of vertical transportation facilities in operation within the target building; For each vertical transportation facility According to each scheduling time slice Determine the floor where it will be stationed and ready to be deployed. ,Will The floor is set to the floor with the highest time-sharing elevator demand within that time slot; Simultaneously construct the runtime function Based on the time-sharing elevator demand function, time-sharing scheduling mapping relationship, and the functions of the parking and waiting floors and the operation cycle, a pre-allocation scheme for vertical transportation capacity resources with time-dimensional scheduling as the core is generated.

6. The method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps according to claim 5, characterized in that, The operating cycle function is: in For floor operations, Characterizing the first Taiwan's vertical transportation facilities in the first A single execution cycle within a scheduling time slice.

7. The method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps according to claim 5, characterized in that, The process in S4 of dynamically correcting the pre-allocation scheme of transportation resources based on data deviation is as follows: Real-time data collection includes the actual number of people disembarking from elevators in each floor's elevator demand sub-area within the target building, as well as operational feedback data for each vertical transportation facility; among which, the first... The sub-area of ​​elevator demand on each floor is in the [number]th floor. The actual number of people disembarking within each scheduling time slot is recorded as follows: This data is collected by the elevator passenger count or the floor access control system; operational feedback data includes the corresponding scheduling time slots for each vertical transportation facility. The actual operating cycle within ; Based on initial forecasts of time-sharing elevator demand The actual number of people who disembarked after the transport was completed Calculate the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. Number of remaining passengers to be transported within each scheduling time slot ;in, The number of people in that sub-region who have not yet completed transportation within that time slice is the core basis for dynamic adjustment; when If this occurs, it indicates that the actual transportation demand in that sub-region is not being met, and additional capacity needs to be allocated to subsequent scheduling time slots. The remaining number of people to be transported Based on historical time-sharing elevator usage distribution ratio Allocated to all subsequent scheduling time slices The corrected time-sharing elevator demand was obtained. ;in, For the first The sub-area of ​​elevator demand on each floor is in the [number]th floor. The historical number of passengers corresponding to each scheduling time slice; Based on the revised time-sharing elevator demand Recalibrate the time-sharing scheduling mapping relationships of each vertical transportation facility. Synchronously correct its operating cycle function ;in, The rated number of passengers that a single vertical transportation facility can transport per unit of time. This is for rounding up; At the same time, the floors where each vertical transportation facility is stationed and ready to go will be designated as standby floors. Adjust to the current time slice The floors with the highest elevator values ​​are prioritized to respond to the most urgent elevator needs.

8. A vertical transportation capacity resource allocation system based on urban area pedestrian flow heat map, used to implement the vertical transportation capacity resource allocation method based on urban area pedestrian flow heat map as described in claim 1, characterized in that, include: The data collection and aggregation construction unit is used to collect urban public transportation operation data, urban area pedestrian flow heat map data, and basic operation data of vertical transportation facilities in the target area, and to construct a basic data set for the pre-allocation of vertical transportation capacity; The elevator demand prediction and analysis unit is used to calculate the passenger flow characteristics of the target area within a preset time period based on the basic data set and using a macro passenger flow prediction method. It combines the urban area population heat map to complete the vertical transportation passenger flow demand prediction and analysis of the target area. The capacity resource pre-allocation generation unit is used to generate a capacity resource pre-allocation scheme for vertical transportation facilities in the target area based on the predicted analysis results of the vertical transportation passenger flow demand and the capacity supply capacity of the vertical transportation facilities in the target area. The real-time feedback and adaptive correction unit is used to send the pre-allocation plan of transportation capacity resources to the control terminal of the vertical transportation facilities in the target area and execute it. At the same time, it collects the actual passenger flow data and the operation feedback data of the vertical transportation facilities in the target area in real time, and dynamically corrects the pre-allocation plan of transportation capacity resources according to the data deviation, so as to realize the adaptive regulation of vertical transportation capacity resources.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer program is executed by a processor as described in any one of claims 1-7: a method for allocating vertical transportation capacity resources based on urban area pedestrian flow heat maps.

Images