Method for analyzing influence of expressway transportation on development indexes based on deep learning

Abstract

The invention discloses a deep learning-based method for analyzing the influence of expressway transportation on development indexes, and relates to the technical field of traffic transportation engineering management, and the method comprises the steps: collecting the historical traffic information of passing trucks in an expressway toll station of a to-be-analyzed region and the historical regional traffic transportation industry output value data; dividing time periods of each year according to periodic characteristics of regional freight and economy, numbering the time periods to obtain period serial numbers, and obtaining related indexes for judging development conditions of the regional transportation industry by constructing a transfer time model of a truck and a related model of regional freight and transportation industry output values; and judging the development trend of the regional transportation industry according to the related indexes. According to the method, the period serial number is obtained by dividing the time period according to the periodical rule of freight and economy, and the period serial number is used as a parameter of the training set data for training, so that the prediction result can reflect the periodical rule of regional freight and economy.

Description

[0005] The present invention relates to the technical field of transportation engineering management, and specifically to an analysis method of the impact of highway transportation on development indicators based on deep learning. Background Art

[0006] The cargo flow capacity can reflect the economic activity and infrastructure development level of a region. An efficient logistics system indicates that production, supply chain management and market transactions are frequent within the region, which not only reduces the operating costs of enterprises, but also promotes economic growth.

[0007] In addition, the ability of goods to flow directly affects the region's foreign trade and economic integration. A region with smooth logistics is more likely to integrate into the global market, form good economic cooperation relations with surrounding regions, and enhance its position and influence in the global supply chain.

[0008] Finally, the ability to move goods is closely related to social welfare and quality of life. An efficient logistics system ensures that residents have access to daily necessities and enriches their consumption choices. It also demonstrates the region's efforts in promoting sustainable development and has a positive impact on long-term economic and social development.

[0009] Predicting the local flow of goods and taking timely measures to stabilize local economic development has become an important direction of current urban economic management.

[0010] In the prior art, the application number is CN201911157047.8, which discloses a method for analyzing the coupling relationship between highway freight transportation volume and regional GDP: including the following steps: S1. Collect highway toll data in a set statistical period to build a historical database for highway network freight transportation statistics; S2. Data preprocessing, calculate the two major freight transportation volume indicators of freight volume and freight turnover in the highway network; S3. Establish a correlation analysis model between highway freight transportation volume indicators and economic indicators; S4. Construct a correlation analysis model between highway freight transportation volume indicators and economic indicators. The present invention relies on the existing highway toll data to automatically count the freight transportation indicators of the highway network, realizes the automatic monitoring of the transportation indicators of the entire highway network, makes full use of the existing data resources, and constructs a complete highway freight transportation volume indicator and economic indicator correlation analysis method, revealing the inherent coupling relationship and coordinated development mechanism between highway freight transportation volume and regional economy.

[0011] However, although the existing technology references time data during the training process, it does not perform periodic analysis and processing on the time data. The final prediction results of the model cannot reflect the cyclical laws of regional freight and economic conditions, resulting in inaccurate prediction results. Summary of the invention

[0012] The purpose of the present invention is to provide a method for analyzing the impact of highway transportation on development indicators based on deep learning, so as to solve the problems raised in the above background technology.

[0013] To achieve the above object, the present invention provides the following technical solutions:

[0014] A method for analyzing the impact of highway transportation on development indicators based on deep learning, comprising the following steps:

[0015] Step 1: Collect the historical traffic information of trucks passing through the highway toll stations in the area to be analyzed and the historical regional transportation output value data of the area to be analyzed, and divide the annual time period according to the cyclical characteristics of regional freight and economy, sort and number the time periods to obtain the period serial number, and finally pre-process the collected data;

[0016] Step 2: Construct a transit time model for trucks. Take the load, exit time, and type of trucks in historical traffic information when they leave the toll station as the training set, and the time of re-entry as the label. Train the transit time model for trucks to obtain the trained transit time model.

[0017] Step 3: Obtain the actual load and actual exit time of all trucks leaving the toll station in the current cycle of the area to be analyzed, input the actual load and actual exit time into the trained transit time model, obtain the predicted entry time of each truck, and collect the actual entry time of the truck in real time to calculate the regional freight capacity change index;

[0018] Step 4: Construct a correlation model between regional freight and transportation industry output value. In the corresponding time period, calculate the total calculated incoming load and total calculated outgoing load in the corresponding period through the historical traffic information of the regional trucks. Take the total calculated incoming load, total calculated outgoing load, and period number as the data set, and the regional transportation industry output value data of the corresponding period as the label. Train the correlation model between regional freight and transportation industry output value to obtain the trained freight and economic correlation model.

[0019] Step 5: Obtain the actual load of all trucks leaving the toll station in the current cycle of the area to be analyzed, the corresponding truck type and the actual regional transportation industry output value data, calculate the total actual incoming load and the total actual outgoing load in the cycle, input the total actual incoming load, the total actual outgoing load and the cycle number into the trained freight and economic related models, and obtain the predicted regional transportation industry output value of the current cycle, and calculate the expected output value of the regional transportation industry based on the predicted regional transportation industry output value and the regional freight capacity change index, and calculate the regional transportation industry development index and the regional transportation industry development speed index based on the expected output value of the regional transportation industry and the actual regional transportation industry output value data.

[0020] Preferably, the historical traffic information of the truck collected in step 1 includes the load a, exit time c, and re-entry time d of the truck when it leaves the toll station, and the truck is classified according to the type of cargo it carries to determine the type g of each truck. The historical regional transportation output value data of the area to be analyzed is recorded as p, and the cycle number is recorded as t;

[0021] Furthermore, the collected data is preprocessed, including data cleaning and normalization. The data cleaning includes removing the data of the years affected by social environmental problems, as well as obvious noise and outliers in the data; the normalization uses the Z-score standardization method to standardize the data. The specific formula is:

[0022]

[0023] Among them, z i is the standardized data, x i is the original data, μ is the mean of the data, and σ is the standard deviation of the data.

[0024] Preferably, the step 2 is trained using an LSTM model, the input layer accepts the truck's load a, exit time c and truck type g, the output layer is the truck's re-entry time d, the mean square error MSE is used as the loss function, and the Adam optimizer is used for model training, and finally a trained transit time model is obtained.

[0025] Preferably, step 3 includes obtaining the actual load a0 and actual exit time c0 of all trucks leaving the toll station in the current cycle t0 in the area to be analyzed and inputting them into the trained transit time model, obtaining the predicted entry time d1 of each truck, and collecting the actual entry time d0 of the truck in real time, dividing the difference between the actual entry time d0 and the predicted entry time d1 of the truck by the predicted entry time d1 to obtain the change index of the actual freight capacity of a single truck relative to the predicted situation, and then summing and averaging the freight capacity change indexes of all trucks in the current cycle to obtain the calculation formula of the regional freight capacity change index A:

[0026]

[0027] Where j is the number of samples of trucks traveling in the current cycle t0.

[0028] Preferably, step 4 includes, in a corresponding time period t, calculating the total calculated load h in the corresponding period through the historical traffic information of the trucks passing through the region, taking the total calculated load h and the period serial number t as data sets, and the regional transportation industry output value data p of the corresponding period as labels, training the correlation model between regional freight and transportation industry output value, obtaining the trained freight and economic correlation model, and performing weighted processing on the load a of all trucks leaving the toll station in the corresponding time period t according to the truck type and summing them up, and obtaining the calculation formula of the total calculated entry load h:

[0029]

[0030] Where l is the number of truck samples coming and going in the time period, and β is a weight parameter related to the truck type;

[0031] Furthermore, the freight and economy related model is trained using the MLP model. The input layer accepts the total calculated incoming load h, the total calculated outgoing load k and the cycle number t. The output layer is the predicted regional transportation industry output value data p. The mean square error MSE is used as the loss function, and the Adam optimizer is used for model training, and finally the trained freight and economy related model is obtained.

[0032] Preferably, the specific process of step 5 is:

[0033] Obtain the actual load a0 of all trucks leaving the toll station in the current cycle t0 of the area to be analyzed, the corresponding truck type g, and the actual regional transportation industry output value data p0. By weighting the actual load a0 of all trucks leaving the toll station in the current cycle t0 according to the truck type and summing them up, the total calculated load h0 in the cycle is calculated as follows:

[0034]

[0035] Where l0 is the number of truck samples coming and going in the current cycle;

[0036] The total calculated load h0 and cycle number t0 in the cycle are input into the trained freight and economic correlation model to obtain the output value p1 of the predicted regional transportation industry in the current cycle. The predicted output value p1 of the regional transportation industry is added to the product of the predicted output value p1 of the regional transportation industry and the regional freight capacity change index A. Different correction parameters are used to correct the result according to the correlation between the expected output value p2 of the local area and the regional freight capacity change index A. The calculation formula for the expected output value p2 of the regional transportation industry is obtained as follows:

[0037] p2=λp1(1+A)

[0038] Where λ is a correction parameter, which can be adjusted according to actual conditions;

[0039] The difference between the actual regional transportation industry output value p0 and the predicted regional transportation industry output value p1 is divided by the predicted regional transportation industry output value p1 to obtain the difference between the actual regional transportation industry output value p0 and the predicted regional transportation industry output value p1 as the regional transportation industry development index. The calculation formula of the regional transportation industry development index B is:

[0040]

[0041] The difference between the actual regional transportation industry output value p0 and the expected regional transportation industry output value p2 is divided by the expected regional transportation industry output value p2 to obtain the difference between the actual regional transportation industry output value p0 and the expected regional transportation industry output value p2 as the regional transportation industry development speed index. The calculation formula of the regional transportation industry development speed index C is:

[0042]

[0043] Finally, the development status of the regional transportation industry is comprehensively judged based on the regional transportation industry development index B and the regional transportation industry development speed index C, and different measures are taken to promote the healthy development of the local transportation industry.

[0044] Compared with the prior art, the beneficial effect of the present invention is: by dividing the time period according to the cyclical laws of freight and economy to obtain the cycle number, and using the cycle number as a parameter of the training set data for training, the prediction result of the final model can reflect the cyclical laws of regional freight and economy, making the prediction result more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1A schematic diagram of the steps of the method for analyzing the impact of highway transportation on development indicators based on deep learning of the present invention;

[0046] Figure 2 It is a flow chart of the method for analyzing the impact of highway transportation on development indicators based on deep learning of the present invention; DETAILED DESCRIPTION

[0047] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with specific embodiments.

[0048] It should be noted that, unless otherwise defined, the technical terms or scientific terms used in the present invention should be understood by people with ordinary skills in the field to which the present invention belongs. The words "first", "second" and similar words used in the present invention do not indicate any order, quantity or importance, but are only used to distinguish different components. "Include" or "comprise" and similar words mean that the elements or objects appearing before the word include the elements or objects listed after the word and their equivalents, without excluding other elements or objects. "Connect" or "connected" and similar words are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. "Up", "down", "left", "right" and the like are only used to indicate relative positional relationships. When the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0049] Example:

[0050] See also Figure 1 to Figure 2 , the present invention provides a technical solution:

[0051] A method for analyzing the impact of highway transportation on development indicators based on deep learning, comprising the following steps:

[0052] Step 1: Collect the historical traffic information of trucks passing through the highway toll stations in the area to be analyzed and the historical regional transportation output value data of the area to be analyzed, and divide the annual time period according to the cyclical characteristics of regional freight and economy, sort and number the time periods to obtain the period serial number, and finally pre-process the collected data;

[0053] Step 2: Construct a transit time model for trucks. Take the load, exit time, and type of trucks in historical traffic information when they leave the toll station as the training set, and the time of re-entry as the label. Train the transit time model for trucks to obtain the trained transit time model.

[0054] Step 3: Obtain the actual load and actual exit time of all trucks leaving the toll station in the current cycle of the area to be analyzed, input the actual load and actual exit time into the trained transit time model, obtain the predicted entry time of each truck, and collect the actual entry time of the truck in real time to calculate the regional freight capacity change index;

[0055] Step 4: Construct a correlation model between regional freight and transportation industry output value. In the corresponding time period, calculate the total calculated incoming load and total calculated outgoing load in the corresponding period through the historical traffic information of the regional trucks. Take the total calculated incoming load, total calculated outgoing load, and period number as the data set, and the regional transportation industry output value data of the corresponding period as the label. Train the correlation model between regional freight and transportation industry output value to obtain the trained freight and economic correlation model.

[0056] Step 5: Obtain the actual load of all trucks leaving the toll station in the current cycle of the area to be analyzed, the corresponding truck type and the actual regional transportation industry output value data, calculate the total actual incoming load and the total actual outgoing load in the cycle, input the total actual incoming load, the total actual outgoing load and the cycle number into the trained freight and economic related models, and obtain the predicted regional transportation industry output value of the current cycle, and calculate the expected output value of the regional transportation industry based on the predicted regional transportation industry output value and the regional freight capacity change index, and calculate the regional transportation industry development index and the regional transportation industry development speed index based on the expected output value of the regional transportation industry and the actual regional transportation industry output value data.

[0057] As a preferred embodiment, the historical traffic information of trucks collected in step 1 includes the load a, exit time c, and re-entry time d of the trucks leaving the toll station, and the trucks are classified according to the type of cargo they carry to determine the type g of each truck. The historical regional transportation output value data of the area to be analyzed is recorded as p, and the cycle number is recorded as t;

[0058] Furthermore, the collected data is preprocessed, including data cleaning and normalization. Data cleaning includes removing data from years affected by social environmental issues, as well as obvious noise and outliers in the data; normalization uses the Z-score standardization method to standardize the data. The specific formula is:

[0059]

[0060] Among them, z i is the standardized data, x i is the original data, μ is the mean of the data, and σ is the standard deviation of the data.

[0061] As a preferred embodiment, step 2 adopts LSTM model for training, the input layer accepts the truck load a, departure time c and truck type g, the output layer is the truck re-entry time d, the mean square error MSE is used as the loss function, and the Adam optimizer is used for model training, and finally the trained transit time model is obtained.

[0062] As a preferred embodiment, step 3 includes obtaining the actual load a0 and actual exit time c0 of all trucks leaving the toll station in the current cycle t0 in the area to be analyzed and inputting them into the trained transit time model, obtaining the predicted entry time d1 of each truck, and collecting the actual entry time d0 of the truck in real time, dividing the difference between the actual entry time d0 and the predicted entry time d1 of the truck by the predicted entry time d1 to obtain the change index of the actual freight capacity of a single truck relative to the predicted situation, and then summing and averaging the freight capacity change indexes of all trucks in the current cycle to obtain the calculation formula of the regional freight capacity change index A:

[0063]

[0064] Where j is the number of samples of trucks traveling in the current cycle t0, the actual load a0 and the actual exit time c0 describe the basic information and travel time of the trucks, which determine the time when the trucks re-enter the toll station. The heavier the truck load, the longer the estimated entry time may be; the later the exit time, the later the re-entry time will be. The regional freight capacity change index A reflects the changes in regional transportation efficiency.

[0065] As a preferred embodiment, step 4 includes, in the corresponding time period t, calculating the total calculated load h in the corresponding period through the historical traffic information of the trucks passing through the region, taking the total calculated load h and the period serial number t as the data set, and the regional transportation industry output value data p of the corresponding period as the label, training the correlation model of regional freight and transportation industry output value, obtaining the trained freight and economic correlation model, and weighting the load a of all trucks leaving the toll station in the corresponding time period t according to the truck type and summing them up, and obtaining the calculation formula of the total calculated entry load h:

[0066]

[0067] Where l is the number of truck samples coming and going within the time period t, β is a weight parameter related to the truck type, which is used to measure the value of the unit weight of cargo carried by different truck types; the total calculated incoming load h reflects the total load of trucks passing through the toll station during the time period, which is used to measure the freight flow in the area and indirectly evaluate the output value of the regional transportation industry through the freight flow.

[0068] Furthermore, the freight and economic correlation model is trained using the MLP model. The input layer accepts the total calculated incoming load h, the total calculated outgoing load k and the cycle number t. The output layer is the predicted regional transportation industry output value data p. The mean square error MSE is used as the loss function, and the Adam optimizer is used for model training, finally obtaining the trained freight and economic correlation model.

[0069] As a preferred embodiment, the specific process of step 5 is:

[0070] Obtain the actual load a0 of all trucks leaving the toll station in the current cycle t0 of the area to be analyzed, the corresponding truck type g, and the actual regional transportation industry output value data p0. By weighting the actual load a0 of all trucks leaving the toll station in the current cycle t0 according to the truck type and summing them up, the total calculated load h0 in the cycle is calculated as follows:

[0071]

[0072] Where l0 is the number of truck samples in the current period t0; the total calculated load h0 reflects the total load of trucks passing through the toll station during the time period, which is used to measure the freight flow in the area and indirectly evaluate the output value of the regional transportation industry through the freight flow.

[0073] Furthermore, the total calculated load h0 and the cycle number t0 in the cycle are input into the trained freight and economic correlation model to obtain the predicted regional transportation industry output value p1 of the current cycle, and the predicted regional transportation industry output value p1 is added to the predicted regional transportation industry output value p1 multiplied by the regional freight capacity change index A, and different correction parameters are used to correct the result according to the correlation between the expected output value p2 of the local regional transportation industry and the regional freight capacity change index A, and the calculation formula for the expected output value p2 of the regional transportation industry is obtained as follows:

[0074] p2=λp1(1+A)

[0075] Among them, λ is a correction parameter, which can be adjusted according to the actual situation. The larger the λ is, the greater the change in the expected output value of the regional transportation industry p2 regional freight capacity change index A will be;

[0076] When the regional transportation industry develops healthily, the expected output value p2 of the regional transportation industry should change with the regional freight capacity. The expected output value p2 of the transportation industry reflects the ideal output value of the regional transportation industry when it develops healthily in the current cycle based on the changes in regional freight capacity. When the regional freight capacity change index A is positive, it indicates that the change in regional freight capacity is on an upward trend. Ideally, the expected output value p2 of the regional transportation industry should increase accordingly. The larger the absolute value of the regional freight capacity change index A, the greater the change in the expected output value p2 of the regional transportation industry.

[0077] Furthermore, the difference between the actual regional transportation industry output value p0 and the predicted regional transportation industry output value p1 is divided by the predicted regional transportation industry output value p1 to obtain the difference between the actual regional transportation industry output value p0 and the predicted regional transportation industry output value p1 as the development index of the regional transportation industry. The calculation formula of the development index B of the regional transportation industry is:

[0078]

[0079] The development index B of the regional transportation industry reflects the change of the output value p0 of the actual regional transportation industry relative to the predicted output value p1 of the regional transportation industry. Since the predicted output value p1 of the regional transportation industry is obtained through a model trained based on past data, when the value of B is positive, it indicates that the development of the current regional transportation industry is on an upward trend relative to the past. When the value of B is negative, it indicates that the development of the current regional transportation industry is on a downward trend relative to the past. The larger the absolute value of B, the greater the change in the development of the current regional transportation industry relative to the past.

[0080] The difference between the actual regional transportation industry output value p0 and the expected regional transportation industry output value p2 is divided by the expected regional transportation industry output value p2 to obtain the difference between the actual regional transportation industry output value p0 and the expected regional transportation industry output value p2 as the regional transportation industry development speed index. The calculation formula of the regional transportation industry development speed index C is:

[0081]

[0082] The development speed index C of the regional transportation industry reflects the change of the actual regional transportation industry output value p0 relative to the expected output value p2 of the regional transportation industry. At the same time, since the expected output value p2 of the regional transportation industry reflects the change of regional freight capacity, when the value of C is positive, it indicates that the current development speed of the regional transportation industry is higher than the expected speed defined by the change of regional freight capacity. When the value of C is negative, it indicates that the current development of the regional transportation industry is lower than the expected speed defined by the change of regional freight capacity. The larger the absolute value of C, the greater the impact of the development speed of regional freight capacity on the current development speed of the regional transportation industry.

[0083] Finally, the development status of the regional transportation industry is comprehensively judged based on the development index B of the regional transportation industry and the development speed index C of the regional transportation industry, and different measures are taken to promote the healthy development of the local transportation industry. When B is a negative value, it indicates that the current development of the regional transportation industry is on a downward trend compared with the past, and the local government should promptly analyze the problem and take measures to stabilize the current development of the regional transportation industry; when the value of C is a negative value, it indicates that the current development of the regional transportation industry does not match the changes in regional freight capacity, and timely analysis and measures should be taken to enable the changes in regional freight capacity to be fed back to the development of the regional transportation industry in a timely manner, so that the regional transportation industry can develop healthily and rapidly and keep up with the speed of changes in regional freight capacity.

[0084] The above formulas are all dimensionless and numerical calculations. The formula is a formula for the most recent real situation obtained by collecting a large amount of data and performing software simulation. The preset parameters in the formula are set by technicians in this field according to actual conditions.

[0085] The above embodiments may be implemented in whole or in part by software, hardware, firmware or any other combination thereof. When implemented using software, the above embodiments may be implemented in whole or in part in the form of a computer program product. Those skilled in the art may appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein may be implemented by computer software, electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed by hardware or software depends on the specific application and design constraints of the technical solution.

[0086] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, and may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0087] The above description is only a specific implementation manner of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application.

Claims

1. A method for analyzing the impact of highway transportation on development indicators based on deep learning, characterized in that: The following steps are involved: Step 1: Collect the historical traffic information of trucks passing through the highway toll stations in the area to be analyzed and the historical regional transportation output value data of the area to be analyzed, and divide the annual time period according to the cyclical characteristics of regional freight and economy, sort and number the time periods to obtain the period serial number, and finally pre-process the collected data; Step 2: Construct a transit time model for trucks. Take the load, exit time, and type of trucks in historical traffic information when they leave the toll station as the training set, and the time of re-entry as the label. Train the transit time model for trucks to obtain the trained transit time model. Step 3: Obtain the actual load and actual exit time of all trucks leaving the toll station in the current cycle of the area to be analyzed, input the actual load and actual exit time into the trained transit time model, obtain the predicted entry time of each truck, and collect the actual entry time of the truck in real time to calculate the regional freight capacity change index; Step 4: Construct a correlation model between regional freight and transportation industry output value. In the corresponding time period, calculate the total calculated incoming load and total calculated outgoing load in the corresponding period through the historical traffic information of the regional trucks. Take the total calculated incoming load, total calculated outgoing load, and period number as the data set, and the regional transportation industry output value data of the corresponding period as the label. Train the correlation model between regional freight and transportation industry output value to obtain the trained freight and economic correlation model. Step 5: Obtain the actual load of all trucks leaving the toll station in the current cycle of the area to be analyzed, the corresponding truck type and the actual regional transportation industry output value data, calculate the total actual incoming load and the total actual outgoing load in the cycle, input the total actual incoming load, the total actual outgoing load and the cycle number into the trained freight and economic related models, and obtain the predicted regional transportation industry output value of the current cycle, and calculate the expected output value of the regional transportation industry based on the predicted regional transportation industry output value and the regional freight capacity change index, and calculate the regional transportation industry development index and the regional transportation industry development speed index based on the expected output value of the regional transportation industry and the actual regional transportation industry output value data.

2. According to claim 1, a method for analyzing the impact of highway transportation on development indicators based on deep learning is characterized in that: The historical traffic information of the trucks collected in step 1 includes the load a, the exit time c, and the re-entry time d of the trucks when they leave the toll station, and the trucks are classified according to the type of cargo they carry to determine the type g of each truck. The historical regional transportation output value data of the area to be analyzed is recorded as p, and the cycle number is recorded as t; The preprocessing of the collected data includes data cleaning and normalization. The data cleaning includes removing the data of the years affected by social environmental problems, as well as obvious noise and outliers in the data. The normalization uses the Z-score standardization method to standardize the data. The specific formula is: Among them, z i is the standardized data, x i is the original data, μ is the mean of the data, and σ is the standard deviation of the data.

3. The method for analyzing the impact of highway transportation on development indicators based on deep learning according to claim 2 is characterized in that: The step 2 adopts the LSTM model for training, the input layer accepts the truck load a, the departure time c and the truck type g, the output layer is the truck re-entry time d, the mean square error MSE is used as the loss function, and the Adam optimizer is used for model training, and finally the trained transit time model is obtained.

4. The method for analyzing the impact of highway transportation on development indicators based on deep learning according to claim 3 is characterized in that: The step 3 includes obtaining the actual load a0 and actual exit time c0 of all trucks leaving the toll station in the current cycle t0 in the area to be analyzed and inputting them into the trained transit time model, obtaining the predicted entry time d1 of each truck, and collecting the actual entry time d0 of the truck in real time, dividing the difference between the actual entry time d0 and the predicted entry time d1 of the truck by the predicted entry time d1 to obtain the change index of the actual freight capacity of a single truck relative to the predicted situation, and then summing and averaging the freight capacity change indexes of all trucks in the current cycle to obtain the calculation formula of the regional freight capacity change index A: Where j is the number of samples of trucks traveling in the current cycle t0.

5. The method for analyzing the impact of highway transportation on development indicators based on deep learning according to claim 4 is characterized in that: The step 4 includes, in a corresponding time period t, calculating the total calculated load h in the corresponding period through the historical traffic information of the trucks passing through the region, taking the total calculated load h and the period serial number t as data sets, and the regional transportation industry output value data p of the corresponding period as labels, training the correlation model of regional freight and transportation industry output value, obtaining the trained freight and economic correlation model, and performing weighted processing on the load a of all trucks leaving the toll station in the corresponding time period t according to the truck type and summing them up, and obtaining the calculation formula of the total calculated entry load h: Where l is the number of truck samples coming and going in the time period t, and β is the weight parameter related to the truck type; The freight and economy related model is trained using the MLP model. The input layer accepts the total calculated incoming load h, the total calculated outgoing load k and the cycle number t. The output layer is the predicted regional transportation industry output value data p. The mean square error MSE is used as the loss function, and the Adam optimizer is used for model training, and finally the trained freight and economy related model is obtained.

6. The method for analyzing the impact of highway transportation on development indicators based on deep learning according to claim 5 is characterized in that: The specific process of step 5 is as follows: Obtain the actual load a0 of all trucks leaving the toll station in the current cycle t0 of the area to be analyzed, the corresponding truck type g, and the actual regional transportation industry output value data p0. By weighting the actual load a0 of all trucks leaving the toll station in the current cycle t0 according to the truck type and summing them up, the total calculated load h0 in the cycle is calculated as follows: Where l0 is the number of truck samples coming and going in the current cycle t0; The total calculated load h0 and cycle number t0 in the cycle are input into the trained freight and economic correlation model to obtain the output value p1 of the predicted regional transportation industry in the current cycle. The predicted output value p1 of the regional transportation industry is added to the product of the predicted output value p1 of the regional transportation industry and the regional freight capacity change index A. Different correction parameters are used to correct the result according to the correlation between the expected output value p2 of the local area and the regional freight capacity change index A. The calculation formula for the expected output value p2 of the regional transportation industry is obtained as follows: p2=λp1(1+A) Where λ is a correction parameter, which can be adjusted according to actual conditions; The difference between the actual regional transportation industry output value p0 and the predicted regional transportation industry output value p1 is divided by the predicted regional transportation industry output value p1 to obtain the difference between the actual regional transportation industry output value p0 and the predicted regional transportation industry output value p1 as the regional transportation industry development index. The calculation formula of the regional transportation industry development index B is: The difference between the actual regional transportation industry output value p0 and the expected regional transportation industry output value p2 is divided by the expected regional transportation industry output value p2 to obtain the difference between the actual regional transportation industry output value p0 and the expected regional transportation industry output value p2 as the regional transportation industry development speed index. The calculation formula of the regional transportation industry development speed index C is: Finally, the development status of the regional transportation industry is comprehensively judged based on the regional transportation industry development index B and the regional transportation industry development speed index C, and different measures are taken to promote the healthy development of the local transportation industry.

Images