Traffic prediction method based on multi-graph gating convolution and Conv-LSTM

Abstract

The invention belongs to the technical field of traffic transportation, and particularly relates to a traffic prediction method based on multi-graph gating convolution and Conv-LSTM, which comprises the following steps: calculating the similarity between time sequences through a DTWN similarity value filling module, and taking K data average values with higher similarity to fill missing so as to ensure the integrity of traffic data. The method comprises the following steps: decomposing traffic data through DWT, and dividing the traffic data into an approximation coefficient and a detail coefficient; the approximation coefficient reflects the long-term trend of the traffic flow, the detail coefficient comprises short-term fluctuation information, and the data obtained by processing the DWT by combining and using different models. The detail coefficients are processed through multi-graph gating cavity convolution MGDCN to capture short-term fluctuation; the approximation coefficients are processed by Conv-LSTM to capture long term trends. Compared with an existing traffic prediction model, missing data can be fully filled, short-term fluctuation and long-term trend of traffic can be captured, errors in traffic prediction can be effectively reduced, and traffic prediction accuracy is improved.

Description

Technical Field

[0001] The present invention belongs to the technical field of transportation, and in particular relates to a traffic prediction method based on multi-graph gated convolution and Conv-LSTM. Background Art

[0002] Traffic forecasting is an indispensable part of intelligent transportation systems (ITS). Its purpose is to predict the future status of urban transportation systems (such as traffic flow and speed, passenger demand, etc.), optimize the allocation and scheduling of traffic resources, better help travelers arrange their daily travel reasonably, and alleviate traffic congestion and environmental problems.

[0003] Traffic forecasting aims to predict future traffic conditions based on historical traffic data and traffic network structure. Traditional forecasting methods include statistical methods and machine learning methods, which regard forecasting as a regression problem. The most representative algorithms are the historical average algorithm (HA) and the autoregressive integrated moving average algorithm (ARIMA). However, these methods usually only consider time information and ignore the spatial correlation of traffic data. Later, some traditional machine learning methods were proposed to model more complex data, such as the vector regression (VAR) method to solve the traffic forecasting problem. Although more complex data can be modeled, the data quality requirements are high and it still cannot meet the requirements of nonlinear and non-stationary time series data. With the advent of the deep learning craze, such as speech recognition, natural language processing, and image processing, more and more researchers have applied deep learning to spatiotemporal data prediction tasks and developed various deep learning-based traffic forecasting prediction models, which can provide drivers with real-time road flow information, thereby improving road utilization.

[0004] However, this task remains challenging due to the complex correlation between time and space. On the one hand, it is reflected in the limitation of incomplete data. In the real-world traffic data collection, data is missing due to sensor failure, communication interruption and other external factors. If these missing data are not processed, the prediction model will make inferences based on incomplete data, thereby reducing the prediction accuracy. On the other hand, traffic time series data is highly dynamic, mainly reflected in the fact that its change pattern is composed of short-term fluctuations (traffic peaks, emergencies, etc.) and long-term trends (daily commuting patterns, seasonal changes, etc.). If the model only focuses on one of the characteristics, some factors with significant influence may be ignored, such as changes in traffic patterns caused by holidays or special events, and existing models fail to consider these two key characteristics at the same time. In addition, the non-Euclidean structure of the traffic road network further increases the complexity of analysis and prediction, that is, two roads with close relative positions but opposite driving directions may present completely different traffic conditions. Summary of the invention

[0005] In view of the technical problem that in the above-mentioned real-world traffic data collection, data is missing due to sensor failure, communication interruption and other external factors. If these missing data are not processed, the prediction model will make inferences based on incomplete data, thereby reducing the prediction accuracy. The present invention provides a traffic prediction method of multi-graph gated convolution and Conv-LSTM. The module calculates the similarity between time series through DTW, and then takes the average value of K data with higher similarity to fill the missing data to ensure the integrity of the traffic data.

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is:

[0007] A traffic prediction method based on multi-graph gated convolution and Conv-LSTM includes the following steps:

[0008] S1. Obtain historical traffic flow data and preprocess the data, including detecting data integrity, interpolating incomplete data, and normalizing the data to obtain preprocessed data;

[0009] S2, perform multi-scale decomposition on the pre-processed data in S1, use discrete wavelet transform DWT, input the time series into low-pass filter and high-pass filter, and obtain the approximate coefficients of different components and detail coefficients;

[0010] S3, process the detail coefficients through the multi-graph gated convolutional network MGDCN to capture the changes of short-term fluctuations. MGDCN consists of two parts: the multi-graph convolutional network MGCN and the gated dilated convolutional network GDCN;

[0011] S4. Use Conv-LSTM to process approximate coefficients and capture long-term trend feature changes. In the long short-term convolutional memory network Conv-LSTM, all input, forgetting, output gates, and unit state updates are completed by convolution operations;

[0012] S5, divide the data set into training set, validation set and test set in chronological order of 7:2:1, and use the past 10 consecutive time steps to predict the traffic status of the next 15min, 30min and 60min;

[0013] S6. Use the traffic prediction model trained in S5 to perform authenticity check on the test data

[0014] The method for preprocessing the data in S1 is: using the DTW algorithm in the DTWN module to calculate the similarity values ​​between the missing data points and other time series. For each missing value, the DTW algorithm calculates the K time series that are most similar to it, and selects the sequence with the highest similarity to fill the missing data points; using the Min-Max normalization method to standardize the data to ensure that the data is within the same range.

[0015] The method of using discrete wavelet transform DWT in S2 is: input the time series into a low-pass filter and a high-pass filter to obtain the approximate coefficient dA and detail coefficient dD of different components; the process is expressed by the following formula:

[0016]

[0017] Where x is the original data sequence, the low-pass filter L(n) is used to capture the overall trend and major changes in the signal, and the output is the approximate coefficient dA; the high-pass filter H(n) is used to capture the fluctuation details or differences in the signal and obtain the detail coefficient dD.

[0018] The method for processing detail coefficients by the multi-graph gated convolutional network MGDCN in S3 is:

[0019] S3.1, MGCN focuses on capturing the spatial features of different semantics in the traffic network. By fusing the predefined adjacency matrix and the similarity matrix based on different similarity measures, the weighted parameters α and β are used to adjust Aperson and Aspearson to adapt to the dynamically changing spatial relationship in the traffic flow. The activated output is added to the hidden state H of the previous layer through the addition operation. l Combined to generate the hidden state H of the next layer 1+1 ;

[0020] S3.2, GDCN further captures temporal features through gating mechanisms and dilated convolutions. The dilated receptive field of dilated convolutions allows the network to capture a wider range of node neighborhoods. The activation function σ is applied to the output of the dilated convolution, enabling the model to learn more complex feature representations.

[0021] The method for processing the approximate coefficients by Conv-LSTM in S4 is:

[0022] S4.1. The input gate receives the feature map of the input time series and processes the input feature map through convolution operation to capture spatial information and decide which information will be written into the unit state. The forget gate uses convolution operation to process the hidden state of the previous moment and the current input, generates a weight for the unit state of the previous moment, indicating the degree of retention of each state unit and deciding which information will be discarded from the unit state. The forget gate, input gate and hidden state of the current moment are calculated respectively.

[0023] S4.2. Under the control of the input gate and the forget gate, Conv-LSTM updates the cell state; the candidate cell state fuses the hidden state at the current moment and the hidden state at the previous moment. After the output gate determines the information of the output cell state, it is multiplied element by element through the activation function to obtain the final result.

[0024] The DTW algorithm is used to calculate the similarity value between the missing data points and other time series. The DTW algorithm formula is as follows:

[0025] D(i,j)=|x i ―y j |+min(D(i―1,j),D(i,j―1),D(i―1,j―1))

[0026] Where X i =(x 1 ,x 2 ,…,x n ) and Y j =(y 1 ,y 2 ,…,y n ) represent the traffic sequence data of node i and node j respectively, DTW(i, j) represents the similarity value between traffic nodes i and j. The higher the similarity, the closer the two time series are in morphology and mode.

[0027] The DTW algorithm calculates the K most similar time series, and its formula is as follows:

[0028]

[0029] For each missing data point, find the set of K data points that are most similar to it, and then take the average of these K most similar data points as the interpolation value of the missing point.

[0030] The hidden state H of the next layer is generated in S3.1 1+1 The method is as follows: MGCN focuses on capturing the spatial features of different semantics in the traffic network, and uses weighted parameters α and β to adjust Aperson and Aspearson by fusing the predefined adjacency matrix and the similarity matrix based on different similarity measures to adapt to the dynamically changing spatial relationship in the traffic flow; the MGCN module designs two different adjacency matrices: the predefined adjacency matrix A and the dynamic similarity matrix A s , respectively input into GCN to capture different semantic space features of the traffic network. The formula is as follows:

[0031]

[0032] Among them, X i =(x 1 ,x 2 ,…,x n ) and Y j =(y 1 ,y 2 ,…,y n ) represent the traffic sequence data of node i and node j respectively, Person(Xi ,Y j ) and Spearman(X i ,Y i ) represent the sequence X i and Y j The Pearson and Spearman correlation coefficients between them, α and β are the influencing factors controlling these two coefficients, and ε is the standard deviation of the distance; given the adjacency matrix A and the similarity matrix A s After that, we use GCN to capture the spatial features of the traffic network under different semantics. The formula is as follows:

[0033]

[0034] Among them, σ(·) is a nonlinear activation function, W l and W s l Respectively represent the weight matrix of the l-th layer GCN, and The predefined adjacency matrix A and similarity matrix A are s The symmetric normalized matrix of I represents the identity matrix, They are The degree matrix of the word is then fused to obtain the output result H gcn , the formula is as follows:

[0035] H gcn =H l+1 +H s l+1 .

[0036] The method of further capturing temporal features by GDCN through gating mechanism and dilated convolution in S3.2 is as follows: GDCN further captures temporal features through gating mechanism and dilated convolution. The dilated receptive field of dilated convolution allows the network to capture a wider range of node neighborhoods. The activation function σ is applied to the output of dilated convolution, so that the model can learn more complex feature representations. The core of GDCN is the dilated convolutional neural network Dilated CNN. The dilation operation increases the receptive field of the convolution kernel, so that the network can capture a wider range of contextual information without increasing the computational complexity, thereby better simulating the traffic flow characteristics at different time scales. In this structure, GDCN first receives the output H of the multi-graph convolution. gcn , the dilated convolution can better capture the long-term features, and combine them using the gating mechanism to obtain the spatiotemporal features H final , the formula is as follows:

[0037] H final =Z*H gcn+(1―Z)σ(DilationConv(H gcn )).

[0038] The method for calculating the forget gate, input gate and the hidden state at the current moment in S4.1 is: the forget gate f t Determine the feature information to be retained, input gate i t To control the transmission of characteristic information, the formula of each gate is as follows:

[0039] f t =σ(W f *[h t―1 ,x t ]+b f )

[0040] i t =σ(W i *[h t―1 ,x t ]+b i )

[0041]

[0042] Among them, f t 、i t and Respectively represent the forget gate, input gate and the hidden state at the current moment, W f , W i , W C and b f 、b i 、b C are the trainable parameters of each gate, σ(·) represents the Sigmod activation function, and * represents the convolution operation.

[0043] In S4.2, after the information of the output unit state is determined by the output gate, the method of obtaining the final result by element-by-element multiplication of the activation function is as follows:

[0044] After the forget gate and input gate are calculated, the candidate unit state merges the hidden state at the current moment and the hidden state C at the previous moment t―1 , the formula is as follows:

[0045]

[0046] Among them, Wc and b c are trainable weights, and C t Respectively represent the cell state at time t and its updated value, ⊙ represents the Hadamard product; after the cell state is updated, it passes through the output gate o tDetermine which information of the cell state is output, and multiply it element-wise with the cell state through the tanh activation function to obtain the final result h t , the formula is as follows:

[0047] o t =σ(W o *[h t―1 ,x t ]+b o )

[0048] h t =o t ⊙tanh(C t )

[0049] Among them, h t Indicates output status; W o and b o are trainable weights.

[0050] Compared with the prior art, the present invention has the following beneficial effects:

[0051] 1. This paper proposes a DTWN similarity filling module, which ensures the integrity of traffic data through DTW calculation. In real-world traffic data collection, data is missing due to sensor failure, communication interruption and other external factors. If these missing data are not processed, the prediction model will make inferences based on incomplete data, thereby reducing the prediction accuracy. Although some studies have used mean, hot plateau or random interpolation methods to fill missing data, these methods usually fail to take into account time dependencies, such as seasonality and trend changes. Mean interpolation may smooth too many data details, while hot plateau interpolation may introduce bias due to the selection of inappropriate "neighboring" data. K-nearest neighbor (KNN) and multiple interpolation methods are widely used. KNN interpolation interpolates by finding the K neighbor values ​​with the closest Euclidean distance to the missing data point in the data set. Multiple interpolation generates multiple possible complete data sets to estimate the uncertainty of interpolation while filling. These methods can better maintain the essential characteristics and structure of the data and provide more accurate interpolation effects than simple methods. However, existing data interpolation methods often ignore a key factor when dealing with missing data problems: the similarity between data points, which results in the inability to fully utilize the inherent correlation and pattern of the data during the interpolation process and the inability to reflect the essential characteristics of the real data. The present invention calculates the similarity between time series through DTW, and then takes the average value of K data with higher similarity to fill in the missing data, thereby ensuring the integrity of traffic data.

[0052] 2. The present invention uses DWT to decompose traffic flow data, and separately processes the approximate coefficients that reflect the long-term trend of traffic flow and the detailed coefficients that contain short-term fluctuation information. Traffic time series data is highly dynamic, which is mainly reflected in the fact that its changing pattern is composed of short-term fluctuations (traffic peaks, emergencies, etc.) and long-term trends (daily commuting patterns, seasonal changes, etc.). If the model only focuses on one of the characteristics, some factors with significant influence may be ignored, such as changes in traffic patterns that may be caused by holidays or special events, and the existing models fail to consider these two key characteristics at the same time. The present invention decomposes traffic data through DWT and divides it into approximate coefficients and detailed coefficients. The approximate coefficients reflect the long-term trend of traffic flow, while the detailed coefficients contain short-term fluctuation information. The data obtained by processing DWT is obtained by combining different models.

[0053] 3. The present invention designs a multi-graph gated dilated convolution MGDCN to process detail coefficients to capture short-term fluctuations; and uses Conv-LSTM to process approximate coefficients to capture long-term trends. An important parameter of traffic flow data is time series. Multi-graphs cannot meet the needs of increasingly complex time-dependent sequence data and real-time changes. Scholars have begun to use the architecture of codecs to develop prediction models. For example, the multi-scale spatiotemporal perception transformer (MSSTAT) model, by combining the multi-scale transformer architecture and the data-driven graph convolutional network, can not only capture static features in geographical locations, but also dynamically reflect the similarity of traffic patterns, thereby better simulating and predicting traffic flow. However, existing models have ignored the two major characteristics of traffic data: short-term fluctuations and long-term trends, which may result in the inability to adjust the prediction strategy in time when facing emergencies, resulting in insufficient or inaccurate response to traffic conditions. The decomposition model strategy of the present invention not only improves the model's ability to capture short-term and long-term traffic data characteristics, but also can more comprehensively understand and predict the complex change patterns of traffic flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0055] The structures, proportions, sizes, etc. illustrated in this specification are only used to match the contents disclosed in the specification so as to facilitate understanding and reading by persons familiar with the technology. They are not used to limit the conditions under which the present invention can be implemented, and therefore have no substantial technical significance. Any structural modification, change in proportion or adjustment of size shall still fall within the scope of the technical contents disclosed in the present invention without affecting the effects and purposes that can be achieved by the present invention.

[0056] Figure 1 It is a schematic diagram of the principle of the present invention.

[0057] Figure 2 It is a schematic diagram of the MGDCN module of the present invention.

[0058] Figure 3 Schematic diagram of the Dilated CNN module of the present invention.

[0059] Figure 4 Schematic diagram of the Conv-LSTM module of the present invention. DETAILED DESCRIPTION

[0060] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. These descriptions are only to further illustrate the features and advantages of the present invention, rather than to limit the claims of the present invention. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of this application.

[0061] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0062] refer to Figure 1-Figure 4 , the technical solution of the present invention is introduced in detail below.

[0063] Step 1) Obtain historical traffic flow data and preprocess the data, including detecting data integrity, interpolating incomplete data, and normalizing the data to obtain preprocessed data;

[0064] Step 2) Use the DTW algorithm in the DTWN module to calculate the similarity between the missing data points and other time series. For each missing value, the DTW algorithm calculates the K most similar time series and selects the most similar series to fill the missing data points. Use the Min-Max normalization method to standardize the data to ensure that the data is in the same range.

[0065] Step 3) Perform multi-scale decomposition on the pre-processed data in step 1, use discrete wavelet transform DWT, input the time series into low-pass filter and high-pass filter, and obtain approximate coefficients of different components and detail coefficients.

[0066] Step 4) Process the detail coefficients through the Multi-graph Gated Convolutional Network (MGDCN) to capture the changes in short-term fluctuations. MGDCN consists of two parts: Multi-graph Convolutional Network MGCN and Gate-controlled Dilated Convolutional Network GDCN.

[0067] Step 5) MGCN focuses on capturing spatial features with different semantics in traffic networks. By fusing the predefined adjacency matrix and the similarity matrix based on different similarity measures, weighted parameters α and β are used to adjust Aperson and Aspearson to adapt to the dynamically changing spatial relationship in traffic flow. The activated output is added to the hidden state H of the previous layer through an addition operation. l Combined to generate the hidden state H of the next layer 1+1 ;

[0068] Step 6) GDCN further captures temporal features through gating mechanisms and dilated convolutions. The dilated receptive field of dilated convolutions allows the network to capture a wider range of node neighborhoods. The activation function σ is applied to the output of the dilated convolution, enabling the model to learn more complex feature representations.

[0069] Step 7) Process the approximate coefficients through Conv-LSTM to capture the long-term trend feature changes. In the long short-term convolutional memory network Conv-LSTM, all input, forgetting, output gates and unit state updates are completed by convolution operations;

[0070] Step 8) The input gate receives the feature map of the input time series and processes the input feature map through convolution operations to capture spatial information and determine which information will be written into the cell state. The forget gate uses convolution operations to process the hidden state of the previous moment and the current input, and generates a weight for the cell state of the previous moment, indicating the degree of retention of each state unit, and determines which information will be discarded from the cell state. The forget gate, input gate, and hidden state of the current moment are calculated respectively;

[0071] Step 9) Under the control of the input gate and the forget gate, Conv-LSTM updates the cell state. The candidate cell state fuses the hidden state at the current moment and the hidden state at the previous moment. After the output gate determines the information of the output cell state, it is multiplied element by element by the activation function to obtain the final result.

[0072] Step 10) The data set is divided into a training set, a validation set, and a test set in a time order of 7:2:1, and the past 10 consecutive time steps are used to predict the traffic status of the next 15 minutes, 30 minutes, and 60 minutes. The present invention is compared with other algorithms, and the influence of parameters is analyzed. The individual contribution of each module in the traffic prediction task is understood through ablation experiments.

[0073] Step 11) Use the traffic prediction model trained in step 5 to perform authenticity check on the test data.

[0074] A series of experiments were conducted on two datasets, PEMSD7(M) and PEMSD7(L), which are collected in real time every 30 seconds by the California Livonia Transportation Performance System (PEMS). The two datasets cover the traffic information collected on weekdays from May to June 2012, and the raw data are aggregated into timestamps every 5 minutes. The PeMSD7(M) dataset contains data monitored by 228 sensors, and the PeMSD7(L) dataset contains data from 1026 sensors. The accuracy (ACC) on these two datasets reached 0.92 and 0.91 respectively, while the mean absolute error (MAE) was reduced to 2.86 and 3.18 respectively, and the root mean square error (RMSE) was reduced to 4.96 and 5.53 respectively. It is verified that the present invention has high accuracy and low error, and can be applied to traffic flow prediction.

[0075] Only the preferred embodiments of the present invention are described in detail above, but the present invention is not limited to the above embodiments. Various changes can be made within the knowledge scope of ordinary technicians in this field without departing from the purpose of the present invention, and various changes should be included in the protection scope of the present invention.

Claims

1. A traffic prediction method based on multi-graph gated convolution and Conv-LSTM, characterized in that: The following steps are involved: S1. Obtain historical traffic flow data and preprocess the data, including detecting data integrity, interpolating incomplete data, and normalizing the data to obtain preprocessed data; S2, perform multi-scale decomposition on the pre-processed data in S1, use discrete wavelet transform DWT, input the time series into low-pass filter and high-pass filter, and obtain the approximate coefficients of different components and detail coefficients; S3, process the detail coefficients through the multi-graph gated convolutional network MGDCN to capture the changes of short-term fluctuations. MGDCN consists of two parts: the multi-graph convolutional network MGCN and the gated dilated convolutional network GDCN; S4. Use Conv-LSTM to process approximate coefficients and capture long-term trend feature changes. In the long short-term convolutional memory network Conv-LSTM, all input, forgetting, output gates, and unit state updates are completed by convolution operations; S5, divide the data set into training set, validation set and test set in chronological order of 7:2:1, and use the past 10 consecutive time steps to predict the traffic status of the next 15min, 30min and 60min; S6. Use the traffic prediction model trained in S5 to perform authenticity check on the test data.

2. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 1, characterized in that: The method for preprocessing the data in S1 is: using the DTW algorithm in the DTWN module to calculate the similarity value between the missing data points and other time series. For each missing value, the DTW algorithm calculates the K time series that are most similar to it, and selects the series with the highest similarity to fill the missing data points; The data were normalized using the Min-Max normalization method to ensure that the data were within the same range.

3. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 1, characterized in that: The method of using discrete wavelet transform DWT in S2 is: input the time series into a low-pass filter and a high-pass filter to obtain the approximate coefficient dA and detail coefficient dD of different components; the process is expressed by the following formula: Where x is the original data sequence, the low-pass filter L(n) is used to capture the overall trend and major changes in the signal, and the output is the approximate coefficient dA; the high-pass filter H(n) is used to capture the fluctuation details or differences in the signal and obtain the detail coefficient dD.

4. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 1, characterized in that: The method for processing detail coefficients by the multi-graph gated convolutional network MGDCN in S3 is: S3.1, MGCN focuses on capturing the spatial features of different semantics in the traffic network. By fusing the predefined adjacency matrix and the similarity matrix based on different similarity measures, the weighted parameters α and β are used to adjust Aperson and Aspearson to adapt to the dynamically changing spatial relationship in the traffic flow. The activated output is added to the hidden state H of the previous layer through the addition operation. l Combined to generate the hidden state H of the next layer 1+1 ; S3.2, GDCN further captures temporal features through gating mechanisms and dilated convolutions. The dilated receptive field of dilated convolutions allows the network to capture a wider range of node neighborhoods. The activation function σ is applied to the output of the dilated convolution, enabling the model to learn more complex feature representations.

5. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 1, characterized in that: The method for processing the approximate coefficients by Conv-LSTM in S4 is: S4.

1. The input gate receives the feature map of the input time series and processes the input feature map through convolution operation to capture spatial information and decide which information will be written into the unit state. The forget gate uses convolution operation to process the hidden state of the previous moment and the current input, generates a weight for the unit state of the previous moment, indicating the degree of retention of each state unit and deciding which information will be discarded from the unit state. The forget gate, input gate and hidden state of the current moment are calculated respectively. S4.2, under the control of the input gate and the forget gate, Conv-LSTM updates the unit state; The candidate unit state fuses the hidden state at the current moment and the hidden state at the previous moment. After passing through the output gate to determine the information of the output unit state, it is multiplied element by element through the activation function to obtain the final result.

6. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 2, characterized in that: The DTW algorithm is used to calculate the similarity value between the missing data points and other time series. The DTW algorithm formula is as follows: D(i,j)=|x i ―y j |+min(D(i―1,j),D(i,j―1),D(i―1,j―1)) Where X i =(x1,x2,…,x n ) and Y j =(y1,y2,…,y n ) represent the traffic sequence data of node i and node j respectively, DTW(i, j) represents the similarity value between traffic nodes i and j. The higher the similarity, the closer the two time series are in morphology and mode. The DTW algorithm calculates the K most similar time series, and its formula is as follows: For each missing data point, find the set of K data points that are most similar to it, and then take the average of these K most similar data points as the interpolation value of the missing point.

7. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 4, characterized in that: The hidden state H of the next layer is generated in S3.1 1+1 The method is as follows: MGCN focuses on capturing the spatial features of different semantics in the traffic network, and uses weighted parameters α and β to adjust Aperson and Aspearson by fusing the predefined adjacency matrix and the similarity matrix based on different similarity measures to adapt to the dynamically changing spatial relationship in the traffic flow; the MGCN module designs two different adjacency matrices: the predefined adjacency matrix A and the dynamic similarity matrix A s , respectively input into GCN to capture different semantic space features of the traffic network. The formula is as follows: Among them, X i =(x1,x2,…,x n ) and Y j =(y1,y2,…,y n ) represent the traffic sequence data of node i and node j respectively, Person(X i ,Y j ) and Spearman(X i ,Y j ) represent the sequence X i and Y j The Pearson and Spearman correlation coefficients between them, α and β are the influencing factors controlling these two coefficients, and ε is the standard deviation of the distance; given the adjacency matrix A and the similarity matrix A s After that, we use GCN to capture the spatial features of the traffic network under different semantics. The formula is as follows: Among them, σ(·) is a nonlinear activation function, W l and W s l Respectively represent the weight matrix of the l-th layer GCN, and The predefined adjacency matrix A and similarity matrix A are s The symmetric normalized matrix of I represents the identity matrix, They are The degree matrix of the word is then fused to obtain the output result H gcn , the formula is as follows: H gcn =H l+1 +H s l+1 。 8. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 4, characterized in that: The method of further capturing temporal features by GDCN through gating mechanism and dilated convolution in S3.2 is as follows: GDCN further captures temporal features through gating mechanism and dilated convolution. The dilated receptive field of dilated convolution allows the network to capture a wider range of node neighborhoods. The activation function σ is applied to the output of dilated convolution, so that the model can learn more complex feature representations. The core of GDCN is the dilated convolutional neural network Dilated CNN. The dilation operation increases the receptive field of the convolution kernel, so that the network can capture a wider range of contextual information without increasing the computational complexity, thereby better simulating the traffic flow characteristics at different time scales. In this structure, GDCN first receives the output H of the multi-graph convolution. gcn , the dilated convolution can better capture the long-term features, and combine them using the gating mechanism to obtain the spatiotemporal features H final , the formula is as follows: H final =Z*H gcn +(1-Z)σ(DilationConv(H gcn ))。 9. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 5, characterized in that: The method for calculating the forget gate, input gate and the hidden state at the current moment in S4.1 is: t Determine the feature information to be retained and input gate i t To control the transmission of characteristic information, the formula of each gate is as follows: f t =σ(W f *[h t-1 ,x t ]+b f ) i t =σ(W i *[h t-1 ,x t ]+b i ) Among them, f t 、i t and Respectively represent the forget gate, input gate and the hidden state at the current moment, W f , W i , W C and b f 、b i 、b C are the trainable parameters of each gate, σ(·) represents the Sigmod activation function, and * represents the convolution operation.

10. The traffic prediction method based on multi-graph gated convolution and Conv-LSTM according to claim 5, characterized in that: In S4.2, after the information of the output unit state is determined by the output gate, the method of obtaining the final result by element-by-element multiplication of the activation function is as follows: After the forget gate and input gate are calculated, the candidate unit state merges the hidden state at the current moment and the hidden state C at the previous moment t-1 , the formula is as follows: Among them, Wc and b c are trainable weights, and C t Respectively represent the cell state at time t and its updated value, ⊙ represents the Hadamard product; after the cell state is updated, it passes through the output gate o t Determine which information of the cell state is output, and multiply it element-wise with the cell state through the tanh activation function to obtain the final result h t , the formula is as follows: the t =σ(W o *[h t―1 ,x t ]+b o ) h t =o t ⊙tanh(C t ) Among them, h t Indicates output status; W o and b o are trainable weights.

Images