Transportation hub passenger flow control method based on holographic trajectory and related device

Abstract

The invention discloses a transportation junction passenger flow control method based on a holographic trajectory and a related device, and relates to the technical field of intelligent transportation, and the method comprises the steps: carrying out the trajectory perception of a moving object in a transportation junction, and generating a current time sequence trajectory of the moving object in a three-dimensional space; calling a constructed traffic prediction model used for predicting the traffic sharing rate, wherein the traffic sharing rate represents the sharing rate of different traffic modes; and inputting the current time sequence track into a traffic prediction model to obtain a current traffic sharing rate output by the traffic prediction model for the traffic hub. According to the method, the current traffic sharing rate of the traffic hub is predicted by sensing the time sequence track of the moving object, so that the transport capacity demands of different traffic modes are predicted, the traffic transport capacity resources can be effectively linked, and the control effect is improved.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a method and related devices for passenger flow control at a transportation hub based on holographic trajectories. Background Art

[0002] At present, large transportation hubs (such as airports, railway stations, long-distance bus stations and buses) often see passenger flow exceeding the usual level during holidays or special events, which increases the pressure on passenger flow. This requires timely on-site management, order maintenance and road guidance.

[0003] The traditional method is to analyze the passenger flow at the entrance and exit sections, but this single-point data analysis cannot fully grasp the temporal and spatial distribution of passenger flow, thus affecting the linkage of transportation capacity resources. Summary of the invention

[0004] In view of the above problems, this application provides a method and related device for passenger flow control at a transportation hub based on holographic trajectories, so as to achieve the purpose of comprehensively grasping the temporal and spatial distribution of passenger flow and effectively linking transportation capacity resources. The specific plan is as follows: The first aspect of the present application provides a method for controlling passenger flow at a transportation hub based on a holographic trajectory, and the method for controlling passenger flow at a transportation hub based on a holographic trajectory comprises: By sensing the trajectory of the moving object in the transportation hub, a current time-series trajectory of the moving object in the three-dimensional space is generated; Retrieving a traffic prediction model that has been constructed to predict a traffic sharing rate, wherein the traffic sharing rate represents a sharing rate of different traffic modes; The current time series trajectory is input into the traffic prediction model to obtain the current traffic share rate output by the traffic prediction model for the traffic hub.

[0005] In a possible implementation, the generating of the current time-series trajectory of the moving object in the three-dimensional space by performing trajectory sensing on the moving object in the transportation hub includes: Sensing and tracking a first time-series trajectory of the moving object in a two-dimensional space through a holographic trajectory sensing device; Acquire a coordinate transformation matrix corresponding to the holographic trajectory sensing device, wherein the coordinate transformation matrix represents a coordinate transformation relationship of the holographic trajectory sensing device from the two-dimensional space to the three-dimensional space; Converting the first time series trajectory into a second time series trajectory in the three-dimensional space according to the coordinate conversion matrix; Acquire a topological relationship between the holographic trajectory sensing devices, and determine a set of time series trajectories having an associated relationship in the second time series trajectories based on the topological relationship; The Hungarian algorithm is used to identify the matching time series trajectories in the time series trajectory set and perform trajectory fusion to obtain the current time series trajectory.

[0006] In a possible implementation, the process of constructing the traffic prediction model includes: Obtain a first historical time series trajectory of the transportation hub at a first historical time; Performing data cleaning on the first historical time series trajectory to obtain a first sample time series trajectory; Extracting first feature vectors corresponding to different transportation modes from the first sample time series trajectory; Using the first feature vector as an input of a first deep learning network, and taking the traffic share rate labeling of the first sample time series trajectory as a target, iteratively training the first deep learning network; The first deep learning network after training is used as the traffic prediction model.

[0007] In a possible implementation, the passenger flow control method for a transportation hub based on holographic trajectories further includes: The current time-series trajectory is subjected to three-dimensional rendering simulation to realize a holographic twin of the passenger flow of the transportation hub.

[0008] In a possible implementation, the passenger flow control method for a transportation hub based on holographic trajectories further includes: Obtaining the current passenger flow and transportation capacity of the transportation hub and outputting them; Traffic scheduling is performed based on the current passenger flow, the traffic capacity situation and the current traffic sharing rate.

[0009] In a possible implementation, the passenger flow control method for a transportation hub based on holographic trajectories further includes: Obtaining a second historical time series trajectory and traffic operation conditions of the transportation hub at a second historical time; Performing data cleaning on the second historical time series trajectory to obtain a second sample time series trajectory; Extracting a second feature vector under the traffic operation condition from the second sample time series trajectory; Using the second feature vector as an input of a second deep learning network, performing end-to-end iterative training on the second deep learning network, and ending the training when a trajectory prediction result of the second deep learning network approaches the second sample time series trajectory; The second deep learning network after training is used as the trajectory simulation model of the transportation hub.

[0010] The second aspect of the present application provides a traffic hub passenger flow control device based on a holographic trajectory, and the traffic hub passenger flow control device based on a holographic trajectory includes: A trajectory sensing module, used to generate a current time-series trajectory of a moving object in a three-dimensional space by sensing the trajectory of the moving object in the transportation hub; A model training module, used to construct a traffic prediction model for predicting a traffic sharing rate, wherein the traffic sharing rate represents the sharing rate of different traffic modes; The traffic prediction module is used to retrieve the traffic prediction model; input the current time series trajectory into the traffic prediction model to obtain the current traffic share rate output by the traffic prediction model for the traffic hub.

[0011] The third aspect of the present application provides a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements the method for passenger flow control at a transportation hub based on holographic trajectories according to the first aspect or any implementation method of the first aspect.

[0012] A fourth aspect of the present application provides an electronic device, comprising at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the method for passenger flow control at a transportation hub based on holographic trajectories according to the above-mentioned first aspect or any implementation method of the first aspect.

[0013] The fifth aspect of the present application provides a computer storage medium, which carries one or more computer programs. When the one or more computer programs are executed by an electronic device, the electronic device can implement the passenger flow control method for a transportation hub based on holographic trajectories according to the above-mentioned first aspect or any implementation method of the first aspect.

[0014] Through the above technical solution, the present application provides a method and related device for passenger flow control in a transportation hub based on holographic trajectories. By sensing the trajectory of moving objects in the transportation hub, the current time-series trajectory of the moving objects in three-dimensional space is generated; the constructed traffic prediction model for predicting the traffic sharing rate is retrieved, and the traffic sharing rate represents the sharing rate of different modes of transportation; the current time-series trajectory is input into the traffic prediction model to obtain the current traffic sharing rate output by the traffic prediction model for the transportation hub. The present application predicts the current traffic sharing rate of the transportation hub by sensing the time-series trajectory of the moving object, thereby predicting the capacity demand of different modes of transportation, which can effectively link the transportation capacity resources and improve the control effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] The above and other features, advantages and aspects of the embodiments of the present disclosure will become more apparent with reference to the following detailed description in conjunction with the accompanying drawings. Throughout the accompanying drawings, the same or similar reference numerals represent the same or similar elements. It should be understood that the drawings are schematic and the originals and elements are not necessarily drawn to scale.

[0016] Figure 1 A flow chart of a method for controlling passenger flow at a transportation hub based on holographic trajectories provided in an embodiment of the present application; Figure 2 A partial flow chart of a method for controlling passenger flow at a transportation hub based on holographic trajectories provided in an embodiment of the present application; Figure 3 Another part of the flow chart of a method for controlling passenger flow at a transportation hub based on holographic trajectories provided in an embodiment of the present application; Figure 4 A schematic diagram of the structure of a passenger flow control device for a transportation hub based on holographic trajectories provided in an embodiment of the present application; Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following describes the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. The terms used in the implementation method section of the present application are only used to explain the specific embodiments of the present application, and are not intended to limit the present application.

[0018] The embodiments of the present application are described below in conjunction with the accompanying drawings. Those skilled in the art will appreciate that, with the development of technology and the emergence of new scenarios, the technical solutions provided in the embodiments of the present application are also applicable to similar technical problems.

[0019] The terms "first", "second" etc. in the specification of the application and the above-mentioned drawings are used to distinguish similar objects, and need not be used to describe a specific order or sequential order. It should be understood that the terms used in this way can be interchangeable in appropriate circumstances, and this is only to describe the distinction mode adopted by the objects of the same attributes when describing in the embodiments of the application. In addition, the terms "including" and "having" and any of their variations are intended to cover non-exclusive inclusions, so that the process, method, system, product or equipment comprising a series of units need not be limited to those units, but may include other units that are not clearly listed or inherent to these processes, methods, products or equipment.

[0020] See also Figure 1 , Figure 1 A flow chart of a method for controlling passenger flow at a transportation hub based on holographic trajectories provided in an embodiment of the present application. Figure 1As shown, a method for passenger flow control at a transportation hub based on holographic trajectories provided in an embodiment of the present application may include steps S101 to S103, and these steps are described in detail below.

[0021] S101, generating a current time-series trajectory of a moving object in a three-dimensional space by sensing the trajectory of the moving object in the transportation hub.

[0022] In the embodiment of the present application, the moving objects may be passengers, pick-up personnel or staff, etc., and the trajectory of each moving object in the transportation hub is perceived in real time, and the time-series trajectory of each moving object in the real three-dimensional space at the current moment, that is, the current time-series trajectory, can be generated.

[0023] In a possible implementation, by setting up holographic trajectory sensing equipment that covers all passenger gathering and distribution scenes at transportation hubs, the holographic trajectory of passengers in scenes including passenger arrival floors, taxis, online ride-hailing cars, buses, coaches, subway entrances and exits, and waiting halls can be sensed and analyzed in real time. Figure 2 , Figure 2 A partial flow chart of a method for controlling passenger flow at a transportation hub based on holographic trajectories provided in an embodiment of the present application. Figure 2 As shown, an embodiment of the present application provides a method for passenger flow control in a transportation hub based on holographic trajectories, wherein step S101 "generates the current time trajectory of the moving object in the three-dimensional space by performing trajectory perception on the moving object in the transportation hub" may include steps S1011 to S1015, and these steps are described in detail below.

[0024] S1011, sensing and tracking the first temporal trajectory of the moving object in the two-dimensional space through a holographic trajectory sensing device.

[0025] In an embodiment of the present application, multiple holographic trajectory sensing devices can be deployed at different locations of a transportation hub, and each holographic trajectory sensing device can sense and track moving objects within its field of view, thereby generating a time-series trajectory of the moving object in the two-dimensional space where the holographic trajectory sensing device is located, i.e., a first time-series trajectory.

[0026] Based on this, the holographic trajectory data of passengers in the transportation hub can be perceived through the holographic trajectory sensing device, so as to track the movement trajectory of groups of people.

[0027] S1012, obtaining a coordinate transformation matrix corresponding to the holographic trajectory perception device, where the coordinate transformation matrix represents a coordinate transformation relationship of the holographic trajectory perception device from a two-dimensional space to a three-dimensional space.

[0028] In the embodiment of the present application, for each holographic sensing device, its coordinate transformation relationship from two-dimensional space to three-dimensional space can be pre-calibrated, and the coordinate transformation relationship is represented by a coordinate transformation matrix, which represents the mapping between the two-dimensional coordinates of the moving object sensed by the holographic sensing device and the real geographic coordinates. Specifically, the two-dimensional coordinates of the reference points in the holographic sensing device are usually established by pre-calibration, and these points also have corresponding references in the real geographic coordinates. The coordinate transformation matrix can be calculated using these reference points.

[0029] S1013: Convert the first time series trajectory into a second time series trajectory in three-dimensional space according to the coordinate conversion matrix.

[0030] In the embodiment of the present application, for each holographic sensing device, the first time-series track sensed by it can be converted from two-dimensional space to three-dimensional space through a coordinate conversion matrix, so as to obtain the corresponding second time-series track, thereby achieving accurate three-dimensional spatial positioning.

[0031] S1014, obtaining a topological relationship between holographic trajectory perception devices, and determining a set of time-series trajectories having an associated relationship in the second time-series trajectory based on the topological relationship.

[0032] In the embodiment of the present application, since the perception range of a single holographic trajectory sensing device cannot cover the entire transportation hub, and there is also an intersection of perception ranges between different holographic trajectory sensing devices, the same moving object may be sensed by multiple holographic trajectory sensing devices at the same time, or may be sensed by different holographic trajectory sensing devices in succession. In this regard, in the embodiment of the present application, firstly, a topological relationship between multiple holographic trajectory sensing devices on the map is established, such as adjacent, connected, intersecting, and containing relationships; then, based on the topological relationship, the temporal and spatial correlation of the second time series trajectories sensed by different holographic trajectory sensing devices is analyzed, and motion features are extracted to determine a set of time series trajectories with correlations sensed by different holographic trajectory sensing devices.

[0033] S1015, using the Hungarian algorithm to identify matching time series trajectories in the time series trajectory set and perform trajectory fusion to obtain the current time series trajectory.

[0034] In an embodiment of the present application, a cost matrix is ​​constructed by the Hungarian algorithm, in which each element represents the matching cost or similarity between two second time-series trajectories from different holographic trajectory sensing devices in the time-series trajectory set, so as to determine the optimal trajectory matching relationship, and the matching second time-series trajectories are fused according to the trajectory matching relationship to obtain a unified and continuous time-series trajectory, i.e., the current time-series trajectory.

[0035] S102, retrieve a traffic prediction model that has been constructed to predict a traffic sharing rate, where the traffic sharing rate represents the sharing rate of different traffic modes.

[0036] In the embodiment of the present application, a traffic prediction model is obtained in advance based on deep learning technology training. The traffic prediction model is used to predict the proportion of transportation modes used for transportation transfer services for passengers arriving at transportation hubs, that is, the share of different transportation modes, and then guide large passenger flow diversion and transportation capacity scheduling. The arrival data of railway trains at the hub are gathered to predict the capacity demand of operating vehicles such as taxis, online car-hailing, subways, buses, and coaches, as well as passenger waiting flow data.

[0037] See also Figure 3 , Figure 3 Another part of the flow chart of a method for controlling passenger flow at a transportation hub based on holographic trajectories provided in an embodiment of the present application. Figure 3 As shown, an embodiment of the present application provides a method for passenger flow control in a transportation hub based on holographic trajectories, wherein the process of constructing a traffic prediction model may include steps S201 to S205, and these steps are described in detail below.

[0038] S201, obtaining a first historical time series trajectory of a transportation hub at a first historical time.

[0039] In an embodiment of the present application, a time series trajectory perceived and fused by multiple holographic perception devices at a transportation hub in historical time can be obtained, that is, a first historical time series trajectory corresponding to a first historical time.

[0040] S202: Perform data cleaning on the first historical time series trajectory to obtain a first sample time series trajectory.

[0041] In the embodiment of the present application, data cleaning is performed on the first historical time series trajectory to remove invalid or abnormal time series trajectories therein, thereby obtaining a first sample time series trajectory.

[0042] S203: extracting first feature vectors corresponding to different transportation modes from the first sample time series trajectory.

[0043] In the embodiment of the present application, time characteristics and spatial characteristics for describing different transportation modes are constructed, and feature vectors corresponding to different transportation modes, namely, first feature vectors, are extracted from the first sample time series trajectory.

[0044] S204: Using the first feature vector as an input of a first deep learning network, and taking the traffic share rate labeling of the first sample time series trajectory as a target, the first deep learning network is iteratively trained.

[0045] In an embodiment of the present application, sequence prediction technology in deep learning is used to learn and train the motion features in the first sample time series trajectory, so as to train the first deep learning network, analyze the mapping relationship between different motion features and transportation modes, and construct a traffic prediction model.

[0046] S205, using the first deep learning network after training as a traffic prediction model.

[0047] In the embodiment of the present application, a dynamic adjustment mechanism is added to the traffic prediction model to feedback and adjust the prediction value according to the real-time holographic passenger flow density data and train arrival passenger data.

[0048] S103, inputting the current time series trajectory into the traffic prediction model to obtain the current traffic sharing rate output by the traffic prediction model for the traffic hub.

[0049] In the embodiment of the present application, the current time series trajectory can be input into the traffic prediction model to obtain the current traffic share of different modes of transportation, that is, the current traffic share. In addition, based on the current traffic share, the train arrival passenger data and the real-time time series trajectory of the passengers can be aggregated to dynamically predict the capacity demand of each mode of transportation in the future.

[0050] Therefore, by predicting passenger flow and traffic sharing rate, we can scientifically guide the dispatch and management of passenger transfer service capacity, such as public transportation, subway, coach, taxi, online car-hailing, etc., to achieve rapid evacuation of passengers and efficient operation of the transportation network. Secondly, during peak hours or special events, early warning of large passenger flows and prediction of passenger trajectory can help large transportation hubs prepare more targeted safety precautions in advance.

[0051] In a possible implementation, the twin simulation technology can be used to realize the twin of the holographic passenger flow trajectory of the three-dimensional scene. In this regard, the embodiment of the present application provides a method for passenger flow control at a transportation hub based on the holographic trajectory, which also includes the following steps: Perform three-dimensional rendering simulation on the current time-series trajectory to realize the holographic twin of passenger flow in the transportation hub.

[0052] In an embodiment of the present application, a three-dimensional virtual model corresponding to the real world is constructed, and the current time trajectory of the moving objects in the transportation hub is fed back to the three-dimensional virtual model for rendering and simulation, thereby realizing a holographic twin of the passenger flow of the transportation hub.

[0053] In a possible implementation, the information release device can be used to guide and coordinate the matching of passenger and transport resources supply and demand, and dynamically dispatch with taxi, online car-hailing and other transport dispatch systems. In this regard, a method for passenger flow control at a transportation hub based on holographic trajectories provided in an embodiment of the present application also includes the following steps: Obtain the current passenger flow and traffic capacity of the transportation hub and output them; perform traffic dispatch based on the current passenger flow, traffic capacity and current traffic sharing rate.

[0054] In the embodiment of the present application, the current passenger flow and traffic capacity of the transportation hub can be sensed, and the information release device can be used to display and output, so as to guide passengers in choosing transportation modes, reduce the waiting time of passengers, and improve travel efficiency. In addition, traffic dispatch can be carried out based on the current passenger flow, traffic capacity and current traffic sharing rate to quickly solve the capacity demand of the transportation hub.

[0055] In a possible implementation, a trajectory simulation model can be established through a deep learning end-to-end architecture to achieve twin trajectory simulation. In this regard, a method for passenger flow control at a transportation hub based on holographic trajectory provided in an embodiment of the present application also includes the following steps: Obtain a second historical time series trajectory and traffic operation conditions of a transportation hub at a second historical time; perform data cleaning on the second historical time series trajectory to obtain a second sample time series trajectory; extract a second eigenvector under the traffic operation conditions from the second sample time series trajectory; use the second eigenvector as input to a second deep learning network, perform end-to-end iterative training on the second deep learning network, and terminate the training when the trajectory prediction result of the second deep learning network approaches the second sample time series trajectory; use the second deep learning network after the training as a trajectory simulation model of the transportation hub.

[0056] In an embodiment of the present application, a time series trajectory perceived and fused by a holographic perception device at a transportation hub in historical time can be obtained, that is, a second historical time series trajectory corresponding to a second historical time. Then, data cleaning is performed on the second historical time series trajectory to remove invalid or abnormal time series trajectories therein, thereby obtaining a second sample time series trajectory. Furthermore, a temporal feature and a spatial feature are constructed to describe the transportation hub under different traffic operation conditions (such as train numbers, ticket checking locations, boarding locations, etc.), and a feature vector corresponding to multiple traffic operation conditions is extracted from the second sample time series trajectory, that is, a second feature vector. Furthermore, the second feature vector is used as the input of the second deep learning network, and segment-to-end iterative training is performed by learning the trajectory behavior and interaction relationship of the moving object. The training is terminated when the trajectory prediction result of the second deep learning network approaches the input, thereby obtaining a trajectory simulation model.

[0057] In subsequent use, the traffic operation conditions to be generated can be input into the trajectory simulation model, and the trajectory simulation model can output the corresponding time-series trajectory containing different moving objects, and simulate and predict the behavior trajectory simulation of individual or group passengers under similar traffic operation conditions in a visual way, helping managers understand and optimize the hub passenger flow control status from a macro and micro perspective. Based on the end-to-end learning architecture of deep learning, the deep learning network can directly learn the prediction and reasoning results from a large number of original time-series trajectories, avoiding the limitations of manually designed features, and can effectively improve the performance and generalization ability of the trajectory simulation model.

[0058] In addition, for the second deep learning network, the MSE loss function can be used to measure the difference between the trajectory prediction result and the second sample time series trajectory. A smaller loss value indicates that the model's prediction is closer to the actual situation, so the model can be further optimized and adjusted. The MSE loss function is shown in the following formula (1): (1) in, is the mean square error, is the result of the trajectory process, is the second sample timing trace.

[0059] Through the above description, the embodiment of the present application provides a method for passenger flow control in a transportation hub based on holographic trajectories, which can realize the accurate perception of the movement trajectory and real-time movement trajectory of passenger flow in large transportation hub scenes, and integrate the three-dimensional virtual model of the transportation hub to build a holographic digital twin of passenger flow from a macro perspective, providing managers with insights into passenger flow dynamics and passenger flow routes. It aims to optimize hub passenger flow control, balance the contradiction between transportation connection capacity and demand, and optimize the allocation of transportation resources. On the other hand, real-time monitoring and intelligent early warning of abnormal conditions such as passenger congestion and crowd retention can improve the efficiency and safety of transportation operations.

[0060] The above introduces a method for passenger flow control at a transportation hub based on a holographic trajectory provided in an embodiment of the present application. The following will introduce a device for executing the above-mentioned method for passenger flow control at a transportation hub based on a holographic trajectory.

[0061] See also Figure 4 , Figure 4 A schematic diagram of the structure of a traffic hub passenger flow control device based on holographic trajectory provided in an embodiment of the present application. Figure 4 As shown, an embodiment of the present application provides a passenger flow control device for a transportation hub based on a holographic trajectory, comprising: The trajectory sensing module 10 is used to generate the current time sequence trajectory of the moving object in the three-dimensional space by sensing the trajectory of the moving object in the transportation hub; A model training module 20 is used to construct a traffic prediction model for predicting a traffic sharing rate, where the traffic sharing rate represents the sharing rate of different traffic modes; The traffic prediction module 30 is used to retrieve the traffic prediction model; input the current time series trajectory into the traffic prediction model to obtain the current traffic share rate output by the traffic prediction model for the traffic hub.

[0062] In a possible implementation, the trajectory perception module 10 is specifically configured to: A first time-series trajectory of a moving object in a two-dimensional space is sensed and tracked through a holographic trajectory sensing device; a coordinate transformation matrix corresponding to the holographic trajectory sensing device is obtained, and the coordinate transformation matrix represents the coordinate transformation relationship of the holographic trajectory sensing device from the two-dimensional space to the three-dimensional space; the first time-series trajectory is converted into a second time-series trajectory in the three-dimensional space according to the coordinate transformation matrix; the topological relationship between the holographic trajectory sensing devices is obtained, and a set of time-series trajectories with an associated relationship in the second time-series trajectory is determined based on the topological relationship; the Hungarian algorithm is used to identify matching time-series trajectories in the time-series trajectory set and perform trajectory fusion to obtain the current time-series trajectory.

[0063] In a possible implementation, the model training module 20 is specifically used to: Obtain the first historical time series trajectory of the transportation hub at the first historical time; perform data cleaning on the first historical time series trajectory to obtain a first sample time series trajectory; extract the first feature vector corresponding to different transportation modes from the first sample time series trajectory; use the first feature vector as the input of the first deep learning network, and iteratively train the first deep learning network with the traffic share rate of the first sample time series trajectory as the target; use the first deep learning network after training as a traffic prediction model.

[0064] In a possible implementation, the above-mentioned traffic hub passenger flow control device based on holographic trajectory further includes: The holographic twin module is used to perform three-dimensional rendering simulation of the current time-series trajectory to realize the holographic twin of the passenger flow in the transportation hub.

[0065] In a possible implementation, the above-mentioned traffic hub passenger flow control device based on holographic trajectory further includes: The information release module is used to obtain and output the current passenger flow and traffic capacity of the transportation hub; and to perform traffic scheduling based on the current passenger flow, traffic capacity and current traffic sharing rate.

[0066] In a possible implementation, the above-mentioned traffic hub passenger flow control device based on holographic trajectory further includes: The trajectory simulation module is used to obtain the second historical time series trajectory and traffic operation conditions of the transportation hub at the second historical time; perform data cleaning on the second historical time series trajectory to obtain a second sample time series trajectory; extract the second feature vector under the traffic operation condition from the second sample time series trajectory; use the second feature vector as the input of the second deep learning network, perform end-to-end iterative training on the second deep learning network, and terminate the training when the trajectory prediction result of the second deep learning network approaches the second sample time series trajectory; and use the second deep learning network after the training as the trajectory simulation model of the transportation hub.

[0067] It should be noted that the detailed functions of each module in the embodiment of the present application can be found in the corresponding public part of the above-mentioned embodiment of the passenger flow control method for the transportation hub based on holographic trajectory, and will not be repeated here.

[0068] The present application also provides an electronic device in an embodiment. Figure 5 , Figure 5 A schematic diagram of the structure of an electronic device provided in an embodiment of the present application. The electronic device in the embodiment of the present application may include but is not limited to fixed terminals such as mobile phones, laptops, PDAs (personal digital assistants), PADs (tablet computers), desktop computers, etc. Figure 5 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0069] like Figure 5 As shown, the electronic device may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage device 508 to a random access memory (RAM) 503. When the electronic device is powered on, various programs and data required for the operation of the electronic device are also stored in the RAM 503. The processing device 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0070] Typically, the following devices may be connected to the I / O interface 505: an input device 506 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; an output device 507 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 508 including, for example, a memory card, a hard disk, etc.; and a communication device 509. The communication device 509 may allow the electronic device to communicate with other devices wirelessly or by wire to exchange data. Although Figure 5An electronic device having various devices is shown, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead.

[0071] Also provided in an embodiment of the present application is a computer program product, including computer-readable instructions. When the computer-readable instructions are executed on an electronic device, the electronic device implements any one of the methods for passenger flow control at a transportation hub based on holographic trajectories provided in an embodiment of the present application.

[0072] A computer-readable storage medium is also provided in an embodiment of the present application. The storage medium carries one or more computer programs. When one or more computer programs are executed by an electronic device, the electronic device can implement any of the transportation hub passenger flow control methods based on holographic trajectories provided in the embodiments of the present application.

[0073] It should also be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed over multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the drawings of the device embodiments provided by the present application, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines.

[0074] Through the description of the above implementation mode, the technicians in the field can clearly understand that the present application can be implemented by means of software plus necessary general hardware, and of course, it can also be implemented by special hardware including special integrated circuits, special CPUs, special memories, special components, etc. In general, all functions completed by computer programs can be easily implemented by corresponding hardware, and the specific hardware structure used to implement the same function can also be various, such as analog circuits, digital circuits or special circuits. However, for the present application, software program implementation is a better implementation mode in more cases. Based on such an understanding, the technical solution of the present application is essentially or the part that contributes to the prior art can be embodied in the form of a software product, which is stored in a readable storage medium, such as a computer floppy disk, a U disk, a mobile hard disk, a ROM, a RAM, a disk or an optical disk, etc., including a number of instructions to enable a computer device (which can be a personal computer, a training device, or a network device, etc.) to execute the methods described in each embodiment of the present application.

[0075] In the above embodiments, all or part of the embodiments may be implemented by software, hardware, firmware or any combination thereof. When implemented by software, all or part of the embodiments may be implemented in the form of a computer program product.

[0076] The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium. For example, the computer instructions may be transmitted from a website site, a computer, a training device, or a data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, training device, or data center. The computer-readable storage medium may be any available medium that a computer can store or a data storage device such as a training device, a data center, etc. that includes one or more available media integrations. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive (SSD)), etc.

Claims

1. A method for passenger flow control in a transportation hub based on holographic trajectories, characterized in that: The passenger flow control method of the transportation hub based on holographic trajectory includes: By sensing the trajectory of the moving object in the transportation hub, a current time-series trajectory of the moving object in the three-dimensional space is generated; Retrieving a traffic prediction model that has been constructed to predict a traffic sharing rate, wherein the traffic sharing rate represents a sharing rate of different traffic modes; The current time series trajectory is input into the traffic prediction model to obtain the current traffic share rate output by the traffic prediction model for the traffic hub.

2. The method for passenger flow control at a transportation hub based on holographic trajectory according to claim 1 is characterized in that: The method of generating a current time-series trajectory of a moving object in a three-dimensional space by sensing the trajectory of the moving object in the transportation hub includes: Sensing and tracking a first time-series trajectory of the moving object in a two-dimensional space through a holographic trajectory sensing device; Acquire a coordinate transformation matrix corresponding to the holographic trajectory sensing device, wherein the coordinate transformation matrix represents a coordinate transformation relationship of the holographic trajectory sensing device from the two-dimensional space to the three-dimensional space; Converting the first time series trajectory into a second time series trajectory in the three-dimensional space according to the coordinate conversion matrix; Acquire a topological relationship between the holographic trajectory sensing devices, and determine a set of time series trajectories having an associated relationship in the second time series trajectories based on the topological relationship; The Hungarian algorithm is used to identify the matching time series trajectories in the time series trajectory set and perform trajectory fusion to obtain the current time series trajectory.

3. The method for passenger flow control at a transportation hub based on holographic trajectory according to claim 1 is characterized in that: The construction process of the traffic prediction model includes: Obtain a first historical time series trajectory of the transportation hub at a first historical time; Performing data cleaning on the first historical time series trajectory to obtain a first sample time series trajectory; Extracting first feature vectors corresponding to different transportation modes from the first sample time series trajectory; Using the first feature vector as an input of a first deep learning network, and taking the traffic share rate labeling of the first sample time series trajectory as a target, iteratively training the first deep learning network; The first deep learning network after training is used as the traffic prediction model.

4. The method for passenger flow control at a transportation hub based on holographic trajectory according to claim 1 is characterized in that: The passenger flow control method of the transportation hub based on holographic trajectory also includes: The current time-series trajectory is subjected to three-dimensional rendering simulation to realize a holographic twin of the passenger flow of the transportation hub.

5. The method for passenger flow control at a transportation hub based on holographic trajectory according to claim 1 is characterized in that: The passenger flow control method of the transportation hub based on holographic trajectory also includes: Obtaining the current passenger flow and transportation capacity of the transportation hub and outputting them; Traffic scheduling is performed based on the current passenger flow, the traffic capacity situation and the current traffic sharing rate.

6. The method for passenger flow control at a transportation hub based on holographic trajectory according to claim 1 is characterized in that: The passenger flow control method of the transportation hub based on holographic trajectory also includes: Obtaining a second historical time series trajectory and traffic operation conditions of the transportation hub at a second historical time; Performing data cleaning on the second historical time series trajectory to obtain a second sample time series trajectory; Extracting a second feature vector under the traffic operation condition from the second sample time series trajectory; Using the second feature vector as an input of a second deep learning network, performing end-to-end iterative training on the second deep learning network, and ending the training when a trajectory prediction result of the second deep learning network approaches the second sample time series trajectory; The second deep learning network after training is used as the trajectory simulation model of the transportation hub.

7. A passenger flow control device for a transportation hub based on holographic trajectory, characterized in that: The passenger flow control device of the transportation hub based on holographic trajectory includes: A trajectory sensing module, used to generate a current time-series trajectory of a moving object in a three-dimensional space by sensing the trajectory of the moving object in the transportation hub; A model training module, used to construct a traffic prediction model for predicting a traffic sharing rate, wherein the traffic sharing rate represents the sharing rate of different traffic modes; The traffic prediction module is used to retrieve the traffic prediction model; input the current time series trajectory into the traffic prediction model to obtain the current traffic share rate output by the traffic prediction model for the traffic hub.

8. A computer program product, characterized in that It includes computer-readable instructions, and when the computer-readable instructions are executed on an electronic device, the electronic device implements the passenger flow control method for a transportation hub based on holographic trajectories as described in any one of claims 1 to 6.

9. An electronic device, characterized in that: The method comprises at least one processor and a memory connected to the processor, wherein: The memory is used to store computer programs; The processor is used to execute the computer program so that the electronic device can implement the passenger flow control method for a transportation hub based on holographic trajectories as described in any one of claims 1 to 6.

10. A computer storage medium, characterized in that: The storage medium carries one or more computer programs, and when the one or more computer programs are executed by an electronic device, the electronic device can implement the method for passenger flow control in a transportation hub based on holographic trajectories as described in any one of claims 1 to 6.

Images