A passenger flow prediction method for transportation hubs considering multiple collection and distribution modes

Abstract

This application relates to the field of artificial intelligence, and in particular to a method for predicting passenger flow at a transportation hub that takes into account multiple distribution modes, including: collecting multimodal passenger flow data and external factor data, preprocessing the data to obtain raw data; constructing a prediction model, the prediction model including a multi-channel time series enhancement module, a spatiotemporal coding and channel fusion module, and an optimization and prediction module; inputting the multimodal passenger flow data and external factor data into the trained prediction model to obtain predicted values ​​of passenger flow distribution for multiple modes of transportation in the transportation hub. This application not only focuses on the dynamic spatiotemporal dependencies of multiple modes, but also integrates external factors such as holidays, weather conditions, and time information, enabling refined predictions of passenger flow for multiple modes of transportation in the transportation hub.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence, and in particular to a method for predicting passenger flow at a transportation hub taking into account multiple distribution modes. Background Art

[0002] In recent years, with the rapid development of urbanization and the economy worldwide, passenger flow at large integrated transportation hubs has increased significantly. With the vigorous development of intelligent transportation systems, passenger travel needs are becoming increasingly diverse. The complex and volatile nature of passenger flow and the diverse distribution patterns of hubs present unique challenges and opportunities for transportation planning and management. Accurate passenger flow forecasting can provide an important foundation for optimizing operational strategies and ensuring efficient resource allocation. However, obtaining accurate, refined, and instructive forecasts remains a challenging task. Convolutional neural networks (CNNs) convert passenger flow data into image representations to extract temporal features. The use of convolutional layers can significantly improve parallel computing power and efficiency. However, relatively simple models may not fully capture the nonlinear relationships and complex patterns in temporal series data. The self-attention mechanism enables the Transformer to consider all elements in a series and create various correlations, attracting significant research attention. However, the window size directly limits the contextual dependencies in long-sequence processing, hindering training and inference. Some studies divide transportation centers into different regions to predict passenger flow distribution, extracting spatial features based on graph convolutional neural networks (GCNs). In addition, some studies have considered multi-source data, including mobile phone data, special events, weather conditions and smart card data for comprehensive prediction.

[0003] However, most existing research considers overall passenger flow variations within a transportation hub only from a temporal perspective, neglecting the impact of other modes of transportation in the surrounding area. Passengers arriving at or departing from a train station often use multiple modes of transportation. Ignoring their interactions results in a failure to identify specific traffic patterns. Refined multimodal forecasting enables managers to understand the specific needs of various modes, thereby improving service quality and effectively identifying potential safety hazards. However, when considering the interactions of multiple modes, the goal becomes to effectively model their complex spatiotemporal correlations. Current research still faces the following challenges: In the spatial dimension, passenger flow exhibits significant interdependence and transitivity between different transportation entities. Changes in traffic conditions can alter the connections between different modes. Some studies have used CNNs to capture local spatial correlations. A significant limitation is that they ignore the irregularities of real-world traffic structures, resulting in the loss of critical topological information. A better approach to circumvent this problem is to construct the transportation network as a graph. Specifically, GCNs typically use adjacency matrices or Laplacian matrices to describe the graph structure. However, the multiple modes of transportation around a transportation hub are unevenly distributed, and their spatial correlations change dynamically over time in complex ways. Traffic maps using static or adaptive adjacency matrices cannot dynamically reflect the true spatial relationships at each moment. Therefore, constructing data-driven dynamic traffic maps is of practical significance. In the temporal dimension, traffic conditions fluctuate cyclically and variably. Consequently, multimodal passenger flow data exhibits significant volatility and continuous interactions. Unlike focusing solely on overall passenger flow, fine-grained prediction is more challenging but can achieve more detailed predictions of passenger flow distribution. Deep learning models can learn regular temporal patterns through continuous training. However, special circumstances such as holidays require special handling. Some research incorporates external factors into model training to adapt to anomalies. Factors such as weather, road conditions, and holidays can be integrated into the network along with temporal data for joint learning. The temporal interval of passenger flow also affects the difficulty of capturing temporal features. Within a certain range, larger intervals introduce more volatility and lose more detail, making accurate future predictions more challenging. The strong volatility and data spikes of multimodal passenger flow at train stations in particular pose a challenge to prediction. Management authorities demand extremely high accuracy during peak periods to enable appropriate emergency response measures. Comprehensive temporal feature enhancement solutions are needed to better serve multimodal predictions.

[0004] Therefore, how to accurately predict passenger flow at transportation hubs with multiple distribution modes is an urgent problem that needs to be solved. Summary of the Invention

[0005] This application provides a transportation hub passenger flow prediction method that takes into account multiple collection and distribution modes, which can accurately predict the passenger flow of multiple modes of transportation within the transportation hub.

[0006] In order to achieve the above object, the present invention adopts the following technical solutions:

[0007] In a first aspect, the present invention provides a method for predicting passenger flow at a transportation hub taking into account multiple collection and distribution modes, the method comprising:

[0008] Collect multi-modal passenger flow data and external factor data, pre-process the data and obtain raw data;

[0009] Constructing a prediction model, the prediction model includes a multi-channel timing enhancement module, a spatiotemporal coding and channel fusion module, and an optimization and prediction module;

[0010] The multi-channel timing enhancement module enhances the timing characteristics of the original data through multiple channels;

[0011] In the spatiotemporal coding and channel fusion module, a spatiotemporal dynamic graph convolutional recurrent network is constructed based on a gated recurrent unit and a dynamic graph convolution operation, wherein the matrix product in the gated recurrent unit is replaced by a dynamic graph convolution operation, and then the original data enhanced by the temporal features is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain encoded data, and then the encoded data is fused using an adaptive channel attention mechanism to obtain fused data;

[0012] The optimization and prediction module converts the external factor data into a continuous vector representation, designs external information encoding corresponding to the passenger flow data of each transportation mode, uses position encoding to represent the order of the fused data, obtains auxiliary prediction data, defines each transportation hub in the fused data as a multimodal transportation graph network, abstracts each traffic flow as a node, and combines the auxiliary prediction data to project the feature representation of each node in the time dimension and feature dimension through a self-attention mechanism to obtain passenger flow distribution prediction values ​​for multiple transportation modes;

[0013] Based on the multimodal passenger flow data and the external factor data, training the prediction model based on a preset loss function and training settings;

[0014] The multi-mode passenger flow data and external factor data are input into the trained prediction model to obtain passenger flow distribution prediction values ​​of multiple transportation modes in the transportation hub.

[0015] In a preferred example of the present application, it can be further configured that the multi-channel timing enhancement module enhances the timing characteristics of the original data through multiple channels, including:

[0016] The multi-channel time series enhancement module processes the original data using a sequence decomposition channel, a history enhancement channel, and a peak enhancement channel to obtain original data with enhanced time series features.

[0017] In a preferred example of the present application, it can be further configured to include:

[0018] The sequence decomposition channel decomposes the signal serially into a series of intrinsic mode functions through empirical mode decomposition, each intrinsic mode function represents an oscillation component in a different frequency range, and then integrates each decomposition result through the CEEMDAN algorithm to obtain the decomposition result;

[0019] The history enhancement channel performs history enhancement on the original data based on dilated causal convolution;

[0020] The peak enhancement channel captures peak information on different time scales in the original data by combining different MaxPooling 1D convolution kernels.

[0021] In a preferred example of the present application, it can be further configured that the raw data enhanced by the temporal features is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain the encoded data, including:

[0022] After the original data enhanced by the time series features is input into the spatiotemporal dynamic graph convolutional recurrent network, the spatiotemporal dynamic graph convolutional recurrent network extracts the spatiotemporal correlation of each node from the time series data at each moment, and maps it into a dynamic adjacency matrix;

[0023] Normalizing the generated dynamic adjacency matrix to obtain a dynamic convolution kernel;

[0024] Based on the dynamic convolution kernel, the transmission of interactive information between each node is completed through the graph convolution operation to obtain encoded data.

[0025] In a preferred example of the present application, it can be further configured that the adaptive channel attention mechanism is then used to fuse the encoded data to obtain fused data, including:

[0026] At each moment, the multi-channel spatiotemporal codes of each traffic flow in the coded data are stacked into one code, and then the code is transformed into a shape for matrix operation, and the matrix multiplication result of the SoftMax layer is used to obtain the channel attention map;

[0027] Use the average pooling layer to extract the overall channel weight;

[0028] The channel attention map is used to weight-enhance the multi-channel spatiotemporal coding, and the overall weight is used to fuse the multi-channel coding to obtain fused data.

[0029] In a preferred example of the present application, it can be further configured that the external factor data includes:

[0030] Holidays, weather conditions and time information.

[0031] In a second aspect, the present application provides a transportation hub passenger flow prediction device that considers multiple collection and distribution modes, the device comprising:

[0032] The data acquisition module is used to collect multi-mode passenger flow data and external factor data, pre-process the data, and obtain the original data;

[0033] A model construction module is used to construct a prediction model, which includes a multi-channel time series enhancement module, a spatiotemporal coding and channel fusion module, and an optimization and prediction module; the multi-channel time series enhancement module enhances the time series features of the original data through multiple channels; in the spatiotemporal coding and channel fusion module, a spatiotemporal dynamic graph convolutional recurrent network is constructed based on a gated recurrent unit and a dynamic graph convolution operation, wherein the matrix product in the gated recurrent unit is replaced by a dynamic graph convolution operation, and then the original data after time series feature enhancement is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain encoded data, and then the encoded data is fused using an adaptive channel attention mechanism to obtain fused data; the optimization and prediction module converts the external factor data into a continuous vector representation, designs the external information encoding corresponding to the passenger flow data of each traffic mode, uses position encoding to represent the order of the fused data, obtains auxiliary prediction data, defines each transportation hub in the fused data as a multimodal transportation graph network, and abstracts each traffic flow as a node. Combined with the auxiliary prediction data, the feature representation of each node in the time dimension and feature dimension is projected through the self-attention mechanism to obtain passenger flow distribution prediction values ​​for multiple transportation modes;

[0034] a model training module, configured to train the prediction model based on the multimodal passenger flow data and external factor data, and based on a preset loss function and training settings;

[0035] The prediction module is used to input the multi-mode passenger flow data and external factor data into the trained prediction model to obtain the passenger flow distribution prediction values ​​of multiple transportation modes in the transportation hub.

[0036] In a third aspect, the present application provides a computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the processor implements the steps of the method for predicting passenger flow at a transportation hub considering multiple distribution modes as described in any one of the above items.

[0037] In a fourth aspect, the present application provides a computer-readable storage medium having a program stored thereon, wherein when the program is executed by a processor, a method for predicting passenger flow at a transportation hub taking into account a plurality of distribution modes as described in any one of the above items is implemented.

[0038] In a fifth aspect, the present application provides a computer program product comprising computer instructions, which, when executed by a processor, implement the steps of a method for predicting passenger flow at a transportation hub taking into account a variety of distribution patterns as described in any one of the above items.

[0039] In summary, compared with the prior art, the technical solutions provided by the embodiments of the present application have at least the following beneficial effects:

[0040] The present application provides a method for predicting passenger flow at a transportation hub that takes into account a variety of distribution modes. It not only focuses on the dynamic spatiotemporal dependencies of multiple modes, but also integrates external factors such as holidays, weather conditions, and time information. It can make refined predictions of passenger flow for multiple modes of transportation within the transportation hub, rather than just predicting the overall flow. This unique perspective provides stronger practical value for significantly improving collaborative management under abnormal circumstances. The integrated time enhancement strategy of the present application using signal decomposition and convolution processing technology can effectively deal with the problems of strong volatility and insufficient data spike processing capabilities in time series data. Compared with existing methods, it can obtain better time series feature representation to serve downstream prediction tasks. The spatiotemporal dynamic graph convolutional recurrent network is data-driven, can comprehensively capture global and local spatiotemporal patterns, and simultaneously complete efficient encoding of spatiotemporal features. Compared with existing methods, it can break through the inherent limitations of static feature extraction. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flowchart of a method for predicting passenger flow at a transportation hub taking into account multiple distribution modes is provided as an embodiment of the present application.

[0042] Figure 2 A spatial dynamic correlation diagram of a transportation hub is provided for a transportation hub passenger flow prediction method that takes into account multiple distribution modes, provided in one embodiment of the present application.

[0043] Figure 3 This is a structural diagram of the prediction model for a method for predicting passenger flow at a transportation hub that takes into account multiple distribution modes, provided in one embodiment of the present application.

[0044] Figure 4 A diagram showing the construction of a multi-head self-attention module for a method of predicting passenger flow at a transportation hub that takes into account multiple distribution patterns, provided as an embodiment of the present application.

[0045] Figure 5 A temporal convolutional neural network diagram consisting of dilated causal convolutions is provided for a method of predicting passenger flow at a transportation hub that takes into account multiple distribution patterns, provided as an embodiment of the present application.

[0046] Figure 6A spatiotemporal dynamic graph convolutional recurrent network diagram of a transportation hub passenger flow prediction method considering multiple distribution patterns is provided as an embodiment of the present application.

[0047] Figure 7 A flowchart of a method for predicting passenger flow at a transportation hub taking into account multiple distribution patterns, provided as an embodiment of the present application, which uses an adaptive channel attention mechanism to fuse the encoded data.

[0048] Figure 8 A schematic diagram of a loss function for a method for predicting passenger flow at a transportation hub taking into account multiple distribution patterns, provided as an embodiment of the present application.

[0049] Figure 9 A structural diagram of a transportation hub passenger flow prediction device that takes into account multiple distribution modes, provided in one embodiment of the present application. DETAILED DESCRIPTION

[0050] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0051] In one embodiment of the present application, a method for predicting passenger flow at a transportation hub considering various distribution modes is provided. Figure 1 As shown, the method includes:

[0052] S100: Collect multi-mode passenger flow data and external factor data, pre-process the data, and obtain raw data;

[0053] Specifically, the multi-modal passenger flow data includes passenger flow data of passengers arriving or leaving the transportation hub using multiple modes of transportation, such as Figure 2 As shown, the transportation hub can be a train station, and the means of arrival or departure can be taxi, private car, etc. The data preprocessing includes abnormal data cleaning and data normalization. The external factor data refers to factors that affect the passenger flow of the transportation hub, such as weather, road conditions, and holidays.

[0054] Furthermore, the external factor data includes holidays, weather conditions, temperature and time information.

[0055] S200: Constructing a prediction model, the prediction model includes a multi-channel time series enhancement module, a spatiotemporal coding and channel fusion module, and an optimization and prediction module; the multi-channel time series enhancement module performs time series feature enhancement on the original data through multiple channels; in the spatiotemporal coding and channel fusion module, a spatiotemporal dynamic graph convolutional recurrent network is constructed based on a gated recurrent unit and a dynamic graph convolution, wherein the matrix product in the gated recurrent unit is replaced by a dynamic graph convolution operation, and then the original data after time series feature enhancement is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain encoded data, and then the encoded data is fused using an adaptive channel attention mechanism to obtain fused data; the optimization and prediction module converts the external factor data into a continuous vector representation, designs the external information encoding corresponding to the passenger flow data of each traffic mode, uses position encoding to represent the order of the fused data, obtains auxiliary prediction data, defines each transportation hub in the fused data as a multimodal transportation graph network, and abstracts each traffic flow as a node. Combined with the auxiliary prediction data, the feature representation of each node in the time dimension and feature dimension is projected through the self-attention mechanism to obtain passenger flow distribution prediction values ​​of multiple transportation modes;

[0056] Specifically, the overall network structure is as follows Figure 3 As shown, the processing steps of the original data are:

[0057] The first step attempts to enhance temporal features on multiple channels, including serial decomposition to reveal complex temporal patterns, history enhancement to mitigate data volatility, and peak enhancement to emphasize abnormal data.

[0058] The second step is to synchronously encode the spatiotemporal dependencies of each channel through a data-driven spatiotemporal dynamic graph convolutional recurrent network (STDGCRN). Then, an adaptive channel attention mechanism is used to fuse the multi-channel encodings and obtain optimized feature representations based on different prediction tasks.

[0059] The third step is to use the self-attention mechanism and combine it with external factors to strengthen the guidance of external priors, and finally map it into passenger flow distribution predictions for multiple modes of transportation. Each transportation hub can be defined as a multimodal transportation graph network, namely G = (V, E, A). Where V is a set of N nodes and E is a set of connected edges. Each transportation mode can generate passenger flow data in up to two directions (i.e., arrivals and departures). Each traffic flow is abstracted as a node. Figure 3 The adjacency matrix in represents the correlation between each traffic passenger flow and is an N×N real symmetric matrix.

[0060] Given multivariate traffic flow data X with a fixed history length P =[x t-P+1 ,…,x t-1 ,xt ]∈R P×N×C , by learning a complex prediction function, aiming to predict the future fixed-length multivariate traffic flow data Y Q =[y t+1 ,…,y t+Q ]∈R Q ×N×C , where P represents the size of the history window and Q represents the size of the prediction window.

[0061] S300: Based on the multi-modal passenger flow data and the external factor data, the prediction model is trained based on a preset loss function and training settings;

[0062] S400: Inputting the multi-mode passenger flow data and external factor data into the trained prediction model to obtain passenger flow distribution prediction values ​​of multiple transportation modes in the transportation hub.

[0063] Specifically, the text information of various external factors, including holidays, weather conditions, and time information, is first numerically numbered and converted into numerical types. Then, embedding technology is used to convert the data into a continuous vector representation.

[0064] Under the same external environment, each type of traffic flow data presents different spatiotemporal characteristics, so it is necessary to design a unique external information encoding for each type of traffic flow data. P ∈R P×N×F Through this encoding, the model will learn the unique association between external information and each type of traffic flow data as much as possible, thereby improving the accuracy of prediction as much as possible.

[0065] Furthermore, positional encoding is introduced in the Transformer model to address the problem that the self-attention mechanism itself does not contain position information. When processing sequential data, the self-attention mechanism treats them as equivalent regardless of the order of the sequence, which is clearly inconsistent with reality. Because the self-attention mechanism is used, positional encoding is also required to represent the order. Positional encoding generally consists of sine and cosine functions and is expressed using Equations 24 and 25, where t represents the position at the sequence moment, i represents the specific dimension, and F represents the length of the embedding vector.

[0066]

[0067] In this way, for each position in the input sequence, an embedding vector of length F corresponding to its positional information is obtained. This positional encoding of sine and cosine functions provides the model with positional information of varying frequencies, helping it capture long-range dependencies in the sequence. Furthermore, due to the periodicity of sine and cosine functions, this positional encoding method is also robust, meaning that the model can still handle changes in sequence length.

[0068] It should be noted that the position code does not change during the model training process and only represents a fixed position code.

[0069]

[0070] As shown in Formula 25, all codes are added together to get the final spatiotemporal feature representation Emb P ∈R P×N×F , which is used as the input of the time series attention enhancement layer. The fusion process allows the model to learn the impact of external factors on time series prediction while maintaining the model's sensitivity to the order of time series data.

[0071] Given sequence data, it can be mapped to query vector Q, key vector K and value vector V. The self-attention mechanism is expressed as shown in Formula 26:

[0072]

[0073] For each traffic flow representation, a self-attention layer is used to perform temporal attention enhancement operation. i Input (Q i , K i and V i ) all use the feature encoding that combines external information and position information obtained previously It is represented by, where i=0,1,…,N-1 represents the sequence number of the multivariate traffic flow, d k Emb P Embedding dimension F. After the temporal enhancement processing of the self-attention layer, the output result It can be expressed by formula 27:

[0074]

[0075] like Figure 4As shown in the figure, the multi-head self-attention block consists of layer normalization, node-level multi-head self-attention layer, random dropout layer, and residual connection layer. Layer normalization is applied to stabilize network layer data and accelerate training convergence. The model performs a residual connection (i.e., addition) between the output of the self-attention block and the original input, which helps the model learn the identity mapping and accelerates the training process. The random dropout layer is used to prevent overfitting and enhance the generalization ability of the model. The final representation after attention enhancement is

[0076] Finally, the feature representations of each node in the time dimension and feature dimension are projected to obtain the predicted data

[0077]

[0078] In this embodiment, not only the dynamic spatiotemporal dependencies of multiple modes are emphasized, but also external factors such as holidays, weather conditions and time information are integrated. It is possible to make refined predictions of passenger flows of multiple modes of transportation in transportation hubs, rather than just predicting overall flows. This unique perspective provides stronger practical value for significantly improving collaborative management under abnormal circumstances. The integrated time enhancement strategy of this application using signal decomposition and convolution processing technology can effectively deal with the problems of strong volatility and insufficient data spike processing capabilities in time series data. Compared with existing methods, it can obtain better time series feature representations to serve downstream prediction tasks. The spatiotemporal dynamic graph convolutional recurrent network is data-driven, can comprehensively capture global and local spatiotemporal patterns, and simultaneously complete efficient encoding of spatiotemporal features. Compared with existing methods, it can break through the inherent limitations of static feature extraction.

[0079] In some embodiments, the multi-channel timing enhancement module enhances the timing characteristics of the original data through multiple channels, including:

[0080] The multi-channel time series enhancement module processes the original data using a sequence decomposition channel, a history enhancement channel, and a peak enhancement channel to obtain original data with enhanced time series features.

[0081] The sequence decomposition channel decomposes the signal serially into a series of intrinsic mode functions through empirical mode decomposition, each intrinsic mode function represents an oscillation component in a different frequency range, and then integrates each decomposition result through the CEEMDAN algorithm to obtain the decomposition result;

[0082] The history enhancement channel performs history enhancement on the original data based on dilated causal convolution;

[0083] The peak enhancement channel captures peak information on different time scales in the original data by combining different MaxPooling 1D convolution kernels.

[0084] In specific implementation, the original data X P Through the comprehensive time series enhancement solution (i.e., serial decomposition, history enhancement and peak amplification), it is processed into Dp, Bp and Mp to deal with strong volatility, data sparsity and data peaks respectively.

[0085] The specific steps of processing the original data by the sequence decomposition channel are:

[0086] Empirical Mode Decomposition (EMD) can adaptively decompose a signal serially into a series of Intrinsic Mode Functions (IMFs), each of which represents an oscillatory component in a different frequency range.

[0087] Fully Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) introduces adaptive noise to address the sensitivity of EMD to noise when dealing with non-stationary signals, thereby improving modal decomposition. For each time series, CEEMDAN is applied to capture different temporal patterns and mitigate the volatility of the data.

[0088] In a given one-dimensional sequence s o (t), add I-order Gaussian white noise Then perform EMD decomposition. For the first component Find the average value and get the corresponding first residual component As shown in Formula 1 and Formula 2. Where, Represents the signal-to-noise ratio.

[0089]

[0090] Repeat the above steps for the obtained residual signal until the last is a monotonic function or constant, where u represents the final number of decompositions. For multimodal passenger flows, the maximum number of decomposed IMFs is m. Zero padding is then used to ensure consistency and facilitate subsequent network model processing. The final result can be expressed as Equation 3.

[0091]

[0092] Finally, the N passenger flows decomposed by CEEMDAN and their respective components are recombined into new data, that is, Among them C dRepresents the number of feature channels after decomposition. The CEEMDAN algorithm integrates the results of each EMD decomposition to obtain a more complete and robust decomposition result. This completeness can better capture the characteristics of time series and improve its adaptability to nonlinearity and nonstationarity.

[0093] The specific steps of processing the original data by the history enhancement channel are as follows:

[0094] Dilated causal convolution is a special convolution operation that aims to simultaneously increase the receptive field of the model and ensure temporal causality, so that dependencies over a longer time range can be captured. Dilated convolution introduces a dilation factor into the convolution kernel, enabling the convolution kernel to extract features within a larger receptive field, effectively increasing the range of information that the model can observe. Causal convolution is a strict time-constrained model that ensures that each convolution kernel can only depend on its previous input data, thereby avoiding information leakage and enabling the network to better cope with the processing needs of time series data. The temporal convolutional neural network composed of dilated causal convolution is as follows: Figure 5 As shown. In the given one-dimensional sequence s o (t), the dilated causal convolution is expressed as shown in Formula 4, where d represents the dilation factor, k T Indicates the size of the convolution kernel.

[0095]

[0096] Each dilated causal convolution block can be expressed as Equation 5. The combination of two dilated causal convolution blocks and residual connections forms a TCN block. Combining TCN blocks with different receptive fields, the information transfer capability of long sequences is further improved. Finally, for X P Each traffic flow time series data is processed using multiple TCN Blocks with different parameters. Among them C b It represents the number of feature channels after historical enhancement, achieving the purpose of historical enhancement of long-sequence data to solve the data sparsity problem in the original data.

[0097] DCBlock(s o (t))=Dropout(Relu(WeightNorm(DConv(s) o (t)))));(5)

[0098] The specific steps of processing the raw data by the peak enhancement channel are as follows:

[0099] Combining different MaxPooling 1D convolution kernels can capture peak information at different time scales. Smaller kernels can capture finer temporal patterns, while larger kernels focus more on the overall structure. The entire process is expressed as shown in Formula 6. M Indicates the size of the convolution kernel. P Each traffic flow time series data is processed through peak enhancement operation to obtain Among them C m Indicates the number of feature channels after peak enhancement.

[0100]

[0101] In some embodiments, the step of inputting the raw data enhanced by the temporal features into the spatiotemporal dynamic graph convolutional recurrent network to obtain the encoded data includes:

[0102] After the original data enhanced by the time series features is input into the spatiotemporal dynamic graph convolutional recurrent network, the spatiotemporal dynamic graph convolutional recurrent network extracts the spatiotemporal correlation of each node from the time series data at each moment, and maps it into a dynamic adjacency matrix;

[0103] Normalizing the generated dynamic adjacency matrix to obtain a dynamic convolution kernel;

[0104] Based on the dynamic convolution kernel, the transmission of interactive information between each node is completed through the graph convolution operation to obtain encoded data.

[0105] Furthermore, the adaptive channel attention mechanism is then used to fuse the encoded data to obtain fused data, including:

[0106] At each moment, the multi-channel spatiotemporal codes of each traffic flow in the coded data are stacked into one code, and then the code is transformed into a shape for matrix operation, and the matrix multiplication result of the SoftMax layer is used to obtain the channel attention map;

[0107] Use the average pooling layer to extract the overall channel weight;

[0108] The channel attention map is used to weight-enhance the multi-channel spatiotemporal coding, and the overall weight is used to fuse the multi-channel coding to obtain fused data.

[0109] In practice, to better integrate spatiotemporal features, a Spatial-Temporal Dynamic Graph Convolutional Recurrent Network (STDGCRN) was constructed based on data-driven dynamic graph convolution to encode data from three channels. This network can comprehensively process global and local spatiotemporal correlations. An adaptive channel-wise attention mechanism is then used to better fuse the encodings.

[0110] The STDGCRN node includes the following process when processing data:

[0111] Dynamic graph convolution kernels can be dynamically learned from the node features and structural information of the graph to adapt to changes in the graph structure and thus better process various complex graph data. Figure 6 As shown in Figure 2, STDGCRN extracts the spatiotemporal correlation of each node from the time series data at each moment and maps it into a dynamic adjacency matrix.

[0112] The input of the current time step t is passed through the MLP layer to extract the dynamic signal, as shown in Formula 7. t ∈R N×L represents the dynamic information after filtering, and L represents the channel dimension of the dynamic information.

[0113] F t =MLP(x t );(7)

[0114] Construct a learnable embedding representation E for each node t ∈R N×L , used to represent the spatiotemporal pattern of each node, and then in F t and E t Perform an element-wise multiplication operation on to generate a dynamic graph embedding As shown in Formula 8:

[0115]

[0116] The spatial dependence can be explained by and In order to meet the requirements of Chebyshev polynomials, the generated dynamic matrix is ​​normalized as shown in Formula 9. represents the dynamic adjacency matrix at time t, Represents the dynamic degree matrix at time t.

[0117]

[0118] The calculation expression of the GCN-based dynamic graph convolution kernel is shown in Formula 10, and its simplified form is shown in Formula 11:

[0119]

[0120] It represents the graph embedding representation after dynamic graph convolution processing at each moment, and F represents the embedding dimension size.

[0121] The model dynamically adapts according to the spatiotemporal characteristics of each time step in the traffic flow data, and then obtains the dynamic convolution kernel after normalization, and completes the effective transmission of interactive information between each node through graph convolution operation.

[0122] Traffic prediction involves complex temporal and spatial correlations. Traditional GRU can effectively capture temporal features. Based on this, dynamic graph convolution operations are used to replace the matrix product in GRU.

[0123] First calculate the reset gate. Input x at the current moment t and the output h of the hidden layer at the previous moment t-1 After the dynamic graph convolution transformation, it is connected to Sigmoid (represented by σ), and its output value is Between is used to select how much information to leave, as shown in Formula 12:

[0124]

[0125] The update gate is then calculated. The calculation process is similar to the reset gate, where It is used to select how much information to use for the update, as shown in Formula 13:

[0126]

[0127] Next, the current memory content is calculated. A reset gate is used to store relevant information from the past and combine it with the current input information, as shown in Formula 14:

[0128]

[0129] The final memory of the current time step t is determined by the update gate to determine the distribution of information, as shown in Formula 15. Among them, the embedding dimension of the hidden layer representation at the current time t is determined by the dynamic graph convolution kernel To control, that is

[0130]

[0131] As shown in formula 16-18, the previously obtained multi-channel timing data (D p 、B p and Mp ) are each encoded using a STDGCRN, and the final multi-channel spatiotemporal representation is obtained ( and ). This shows that each STDGCRN channel will learn and update parameters according to the distribution characteristics of its own data.

[0132]

[0133] The adaptive channel attention mechanism is used to fuse the encoded data to obtain a fused data channel attention mechanism, including the following process:

[0134] A channel attention mechanism is designed to perform channel fusion on multi-channel spatiotemporal feature encodings. This allows the model to focus on important information in the channel dimension during feature extraction, thereby improving feature representation. Furthermore, for different downstream prediction tasks, the model pays different attention to different channel encodings, which can better assist the model in making decisions and enhance the model's robustness. For example, for long-term predictions, the channel attention mechanism may focus on historically enhanced encoded data with more specific weights.

[0135] At each time t, the multi-channel spatiotemporal codes of each traffic flow are stacked into one code, emb t ∈R 3×N×F . Then emb t Transform the shape to get To perform matrix operations, apply the SoftMax layer to and The matrix multiplication result is used to obtain the channel attention map A t ∈R 3×3 To express the channel correlation, as shown in Equation 19 and Equation 20:

[0136]

[0137] Here, α represents the scale factor, a constant that scales the input tensor so that its value range is suitable for the input of the SoftMax function. This scaling can better control the output of the SoftMax layer, making the distribution of attention weights more stable and conducive to improving the training stability and performance of the model.

[0138] Use the average pooling layer to extract the overall channel weight W t ∈R 3 , as shown in formula 21:

[0139] W t =SoftMax(MLP(AvgPool(embt )));(twenty one)

[0140] Using channel attention map A t The multi-channel spatiotemporal coding is weighted to obtain As shown in formula 22. Adjust the shape to get Then use the overall weight W t Perform multi-channel coding fusion to obtain the final coding representation As shown in Formula 23:

[0141]

[0142] The schematic diagram of channel attention encoding fusion is as follows Figure 7 As shown in , after the encoding fusion of multi-channel attention, the model can adaptively focus on important features on different channels and perform weighted fusion according to the importance of these features. This mechanism significantly improves the representation ability of features, allowing the model to more effectively capture and utilize key information in the data when processing complex tasks. By increasing the model's sensitivity to key features, the robustness of the model is improved. In addition, the channel attention mechanism can also help the model achieve better sharing and migration between multiple prediction tasks. The final spatiotemporal encoding is

[0143] In some embodiments, training the prediction model based on the multimodal passenger flow data and external factor data and a preset loss function and training settings includes:

[0144] In the specific implementation, in order to improve the accuracy of peak data prediction, a new loss function called Enhanced Peak Exponential Loss (EPEL) is designed, as shown in Formula 28. Among them, p and q are adjustment terms that control the sensitivity of EPEL to different errors. After normalization, the data is scaled to [0,1]. Therefore, the data is mapped to [0,∞] in an exponentially amplified manner. By adjusting p and q, the error is further amplified, and a higher penalty is imposed on the error of the peak data. Figure 8 As shown, the exponential function and different exponential terms make it more sensitive to larger errors, especially for peaks.

[0145]

[0146] During the actual training of the network, 12 2-layer TCN blocks and 6 1-layer MaxPooling blocks are used. The convolution kernel size increases linearly with the number of layers in both blocks. The number of CEEMDAN decompositions is determined by the complexity of the data itself. Each STDGCRN is a single layer and encodes the data into a spatiotemporal representation of size 128. Finally, a 2-layer self-attention block is used to enhance the temporal features. The AdamW optimizer is used with a batch size of 128 and a weight decay set to 0.0001. The duration of early stopping is 6 seconds. The initial learning rate is set to 10 -4 The parameters in the EPEL function are set to p=2 and q=1.

[0147] This application also provides a transportation hub passenger flow prediction device that takes into account multiple distribution modes. Figure 9 As shown, the device includes:

[0148] The data collection module 100 is used to collect multi-mode passenger flow data and external factor data, pre-process the data, and obtain raw data;

[0149] The model construction module 200 is used to construct a prediction model, which includes a multi-channel timing enhancement module, a spatiotemporal coding and channel fusion module, and an optimization and prediction module; the multi-channel timing enhancement module enhances the timing features of the original data through multiple channels; in the spatiotemporal coding and channel fusion module, a spatiotemporal dynamic graph convolutional recurrent network is obtained based on the gated recurrent unit and the dynamic graph convolution operation, wherein the matrix product in the gated recurrent unit is replaced by the dynamic graph convolution operation, and then the original data after the timing feature enhancement is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain the encoded data, and then the adaptive The channel attention mechanism corresponding to the encoding data is used to fuse the encoded data to obtain fused data; the optimization and prediction module converts the external factor data into a continuous vector representation, designs the external information encoding corresponding to the passenger flow data of each transportation mode, uses position encoding to represent the order of the fused data, obtains auxiliary prediction data, defines each transportation hub in the fused data as a multimodal transportation graph network, abstracts each traffic flow as a node, combines the auxiliary prediction data, and projects the feature representation of each node in the time dimension and feature dimension through the self-attention mechanism to obtain passenger flow distribution prediction values ​​for multiple transportation modes;

[0150] A model training module 300 is configured to train the prediction model based on the multimodal passenger flow data and external factor data, based on a preset loss function and training settings;

[0151] The prediction module 400 is used to input the multi-mode passenger flow data and external factor data into the trained prediction model to obtain the passenger flow distribution prediction values ​​of multiple transportation modes in the transportation hub.

[0152] The functional implementation of each module in the above-mentioned transportation hub passenger flow prediction device considering multiple distribution modes corresponds to the steps in the above-mentioned transportation hub passenger flow prediction method embodiment considering multiple distribution modes, and its functions and implementation processes will not be repeated here one by one.

[0153] The present application also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method for predicting passenger flow at a transportation hub considering multiple distribution modes as described in any of the above embodiments are implemented.

[0154] The present application also provides a computer-readable storage medium having a program stored thereon, wherein the computer-readable storage medium refers to a carrier for storing data and may include, but is not limited to, a floppy disk, an optical disk, a hard disk, a flash memory, a USB flash drive, and / or a memory stick, and the computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The working process, working details, and technical effects of the computer-readable storage medium provided in this embodiment can be found in the above embodiment of a method for predicting passenger flow at a transportation hub considering multiple distribution modes, and will not be repeated here.

[0155] The application also provides a computer program product comprising computer instructions, which, when executed by a processor, implement the steps of the method for predicting passenger flow at a transportation hub considering multiple collection and distribution modes as described in any of the above embodiments.

[0156] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0157] The technical features of the above embodiments can be combined arbitrarily. In order to make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. The above-mentioned embodiments only express several implementation methods of the present application. The description is relatively specific and detailed, but it cannot be understood as a limitation on the scope of the invention patent. It should be pointed out that for ordinary technicians in this field, without departing from the concept of the present application, several variations and improvements can be made, which all fall within the scope of protection of the present application. Therefore, the scope of protection of the patent of this application shall be based on the attached claims.

Claims

1. A method for predicting passenger flow at a transportation hub considering multiple collection and distribution modes, characterized in that: include: Collect multi-modal passenger flow data and external factor data, and pre-process the data to obtain raw data, wherein the external factor data includes holidays, weather conditions, and time information; Constructing a prediction model, the prediction model includes a multi-channel timing enhancement module, a spatiotemporal coding and channel fusion module, and an optimization and prediction module; The multi-channel time series enhancement module processes the original data using a sequence decomposition channel, a history enhancement channel, and a peak enhancement channel to obtain original data with enhanced time series features; The sequence decomposition channel decomposes the signal serially into a series of intrinsic mode functions through empirical mode decomposition, each intrinsic mode function represents an oscillation component in a different frequency range, and then integrates each decomposition result through the CEEMDAN algorithm to obtain the decomposition result; The history enhancement channel performs history enhancement on the original data based on dilated causal convolution; The peak enhancement channel captures peak information on different time scales in the original data by combining different MaxPooling1D convolution kernels; In the spatiotemporal coding and channel fusion module, a spatiotemporal dynamic graph convolutional recurrent network is constructed based on a gated recurrent unit and a dynamic graph convolution operation, wherein the matrix product in the gated recurrent unit is replaced by a dynamic graph convolution operation, and then the original data enhanced by the temporal features is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain encoded data, and then the encoded data is fused using an adaptive channel attention mechanism to obtain fused data; The optimization and prediction module converts the external factor data into a continuous vector representation, designs external information encoding corresponding to the passenger flow data of each transportation mode, uses position encoding to represent the order of the fused data, obtains auxiliary prediction data, defines each transportation hub in the fused data as a multimodal transportation graph network, abstracts each traffic flow as a node, and combines the auxiliary prediction data to project the feature representation of each node in the time dimension and feature dimension through a self-attention mechanism to obtain passenger flow distribution prediction values ​​for multiple transportation modes; Based on the multimodal passenger flow data and the external factor data, training the prediction model based on a preset loss function and training settings; The multi-mode passenger flow data and external factor data are input into the trained prediction model to obtain passenger flow distribution prediction values ​​of multiple transportation modes in the transportation hub.

2. The method for predicting passenger flow at a transportation hub considering multiple collection and distribution modes according to claim 1, characterized in that: The raw data enhanced by the temporal features is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain encoded data, including: After the original data enhanced by the time series features is input into the spatiotemporal dynamic graph convolutional recurrent network, the spatiotemporal dynamic graph convolutional recurrent network extracts the spatiotemporal correlation of each node from the time series data at each moment, and maps it into a dynamic adjacency matrix; Normalizing the generated dynamic adjacency matrix to obtain a dynamic convolution kernel; Based on the dynamic convolution kernel, the transmission of interactive information between each node is completed through the graph convolution operation to obtain encoded data.

3. The method for predicting passenger flow at a transportation hub considering multiple collection and distribution modes according to claim 1, characterized in that: The adaptive channel attention mechanism is then used to fuse the encoded data to obtain fused data, including: At each moment, the multi-channel spatiotemporal codes of each traffic flow in the coded data are stacked into one code, and then the code is transformed into a shape for matrix operation, using The channel attention map is obtained by matrix multiplication of the layers; Use the average pooling layer to extract the overall channel weight; The channel attention map is used to weight-enhance the multi-channel spatiotemporal coding, and the overall weight is used to fuse the multi-channel coding to obtain fused data.

4. A passenger flow prediction device for a transportation hub considering multiple distribution modes, characterized in that: include: A data acquisition module is used to collect multi-modal passenger flow data and external factor data, and pre-process the data to obtain raw data. The external factor data includes holidays, weather conditions and time information; A model building module is used to construct a prediction model, wherein the prediction model includes a multi-channel timing enhancement module, a spatiotemporal coding and channel fusion module, and an optimization and prediction module; The multi-channel time series enhancement module processes the original data using a sequence decomposition channel, a history enhancement channel, and a peak enhancement channel to obtain original data with enhanced time series features; The sequence decomposition channel decomposes the signal serially into a series of intrinsic mode functions through empirical mode decomposition, each intrinsic mode function represents an oscillation component within a different frequency range, and then integrates each decomposition result through the CEEMDAN algorithm to obtain a decomposition result; the history enhancement channel performs history enhancement on the original data based on dilated causal convolution; The peak enhancement channel captures peak information on different time scales in the original data by combining different MaxPooling1D convolution kernels; In the spatiotemporal coding and channel fusion module, a spatiotemporal dynamic graph convolutional recurrent network is constructed based on a gated recurrent unit and a dynamic graph convolution, wherein the matrix product in the gated recurrent unit is replaced by a dynamic graph convolution operation, and then the original data enhanced by the time series features is input into the spatiotemporal dynamic graph convolutional recurrent network to obtain encoded data, and then the encoded data is fused using an adaptive channel attention mechanism to obtain fused data; the optimization and prediction module converts the external factor data into a continuous vector representation, designs the external information encoding corresponding to the passenger flow data of each traffic mode, uses position encoding to represent the order of the fused data, obtains auxiliary prediction data, and defines each transportation hub in the fused data as a multimodal transportation graph network, and abstracts each traffic flow as a node. Combined with the auxiliary prediction data, the feature representation of each node in the time dimension and feature dimension is projected through the self-attention mechanism to obtain passenger flow distribution prediction values ​​of multiple transportation modes; a model training module, configured to train the prediction model based on the multimodal passenger flow data and external factor data, and based on a preset loss function and training settings; The prediction module is used to input the multi-mode passenger flow data and external factor data into the trained prediction model to obtain the passenger flow distribution prediction values ​​of multiple transportation modes in the transportation hub.

5. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the method for predicting passenger flow at a transportation hub considering multiple collection and distribution modes are implemented as described in any one of claims 1 to 3.

6. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a program, wherein when the program is executed by the processor, the method for predicting passenger flow at a transportation hub considering multiple collection and distribution modes according to any one of claims 1 to 3 is implemented.

7. A computer program product comprising computer instructions, characterized in that When executed by a processor, the computer instructions implement the steps of the method for predicting passenger flow at a transportation hub considering multiple collection and distribution modes as described in any one of claims 1 to 3.

Images