Method and system for urban and rural road planning based on artificial intelligence

Abstract

The present invention discloses a method and system for urban and rural road planning based on artificial intelligence, which specifically relates to the technical field of road planning, and includes the following steps: collecting historical information of urban and rural target roads to obtain a historical information set of urban and rural target roads; collecting urban and rural planning policy information to obtain an urban and rural planning policy information set; classifying road types according to preset classification standards to obtain a road type set; constructing an auxiliary prediction model and performing joint analysis based on the road type set, the historical information set of urban and rural target roads, and the output data of the auxiliary prediction model to obtain a joint analysis value, evaluating the satisfaction of the target area, and making corresponding planning according to the preset planning strategy and the satisfaction of the target area; the present invention provides a powerful tool for urban planners and decision makers to cope with the increasingly complex challenges of transportation and urban development, and is conducive to building a more effective, safer and more sustainable urban and rural road network.

Description

Technical Field

[0001] The present invention relates to the technical field of road planning, and more specifically, to a method and system for urban and rural road planning based on artificial intelligence. Background Art

[0002] With the increasing complexity of urban and rural structures and the continuous growth of traffic demand, traditional road planning methods have been unable to cope with the rapid development of modern society. The urban and rural road planning system is a key component of urban infrastructure planning, which directly affects the city's operating efficiency, residents' quality of life and economic development. However, urban and rural planning involves a lot of information and is scattered in different departments and institutions. The lack of effective integration and utilization leads to incomplete planning decisions. The existing urban and rural planning system often does not respond quickly enough to real-time changes in traffic conditions and policy adjustments, and cannot optimize the road network layout in a timely manner. Due to the lack of refined evaluation methods, the allocation of resources between urban and rural areas often cannot achieve the optimal level, resulting in excessive road construction in some areas and serious shortages in other areas. Therefore, this paper proposes a method and system for urban and rural road planning based on artificial intelligence to solve the above problems. Summary of the invention

[0003] To achieve the above object, the present invention provides the following technical solutions:

[0004] The urban and rural road planning system based on artificial intelligence includes information module one, information module two, classification module, neural network module, analysis module, evaluation module and planning module;

[0005] The information module 1 is used to collect historical information of urban and rural target roads, obtain historical information sets of urban and rural target roads and transmit them to the classification module and the analysis module;

[0006] The information module 2 is used to collect urban and rural planning policy information, obtain the urban and rural planning policy information set and transmit it to the neural network module;

[0007] The classification module is used to classify the road types of the historical information set of urban and rural target roads according to the preset classification standards, obtain the road type set and transmit it to the analysis module;

[0008] The neural network module is trained using the urban and rural planning policy information set to build an auxiliary prediction model. The specific construction steps are as follows:

[0009] S1, the neural network module receives the urban and rural planning policy information set, takes the target road coverage area prediction data, target road planning period data, and target road policy data in the urban and rural planning policy information set as the input data for model training, takes the target road pressure data as the output data for model training, and assigns it to 0 or 1 to train the model, where 0 indicates that the target road pressure data is less than or equal to the set threshold, and 1 indicates that the target road pressure data is greater than the set threshold;

[0010] S2: Using the urban and rural planning policy information set of the most recent time planning window preset by the information module 2 as the input data of the model, when the output data of the model is 0, using the urban and rural planning policy information set of the most recent time planning window of the information module 2 as the training data of the model to perform secondary training on the model; when the output data of the model is 1, using the urban and rural planning policy information set of the most recent time planning window of the information module 2 as the training data of the model to perform secondary training on the model while sending instructions to the analysis module;

[0011] The analysis module is used to perform joint analysis based on the road type set, the urban and rural target road historical information set, and the target road pressure data in the neural network module when receiving the instruction, obtain the joint analysis value and transmit it to the evaluation module;

[0012] The evaluation module is used to evaluate the satisfaction of the target area according to the joint analysis value and transmit the satisfaction to the planning module;

[0013] The planning module is used to make corresponding plans based on the preset planning strategy and the satisfaction of the target area.

[0014] In a preferred embodiment, the urban and rural planning policy information includes target road coverage area prediction data, target road planning period data, and target road policy data.

[0015] In a preferred embodiment, the neural network module receives the urban and rural planning policy information set, uses the target road coverage area prediction data, target road planning life data, and target road policy data in the urban and rural planning policy information set as input data for model training, and uses the target road pressure data as output data for model training:

[0016] The coverage area in the target road coverage area prediction data is marked as Mi, the coverage area population is marked as Ri, the average annual growth rate of the coverage area population in the last n years is Ki, the target road planning period data is marked as Ni, and the policy change amount in the target road policy data is marked as Gi. The pressure value is calculated as X1, where t is the preset planning life stability value. The pressure value X2 is calculated, where gi is the specific coefficient preset for the policy type corresponding to the policy change Gi, and Gi' is the standard value corresponding to the policy change Gi; then the target road pressure data is obtained through the calculation formula, YL is the target road pressure data, f1 and f2 are both preset proportional coefficients and are positive numbers. The pressure value X1 and pressure value X2 are obtained through the target road coverage area prediction data, target road planning life data, and target road policy data in the urban and rural planning policy information set as the input data for model training, and the target road pressure data YL is used as the output data for model training.

[0017] In a preferred embodiment, the classification module is used to classify the road type of the urban and rural target road history information set according to the preset classification standard, which means:

[0018] The classification module sets the highway grade of the urban and rural target roads in the urban and rural target road historical information set according to a preset classification standard, and marks the highway grade of the urban and rural target roads as Di.

[0019] In a preferred embodiment, the analysis module is used to perform a joint analysis based on the road type set, the urban and rural target road historical information set, and the target road pressure data in the neural network module when receiving the instruction, and obtain the joint analysis value and transmit it to the evaluation module, which means:

[0020] Step A1: divide the urban and rural areas into regions, obtain the highway grade Di of all urban and rural target roads in the target area, mark the area of ​​the regional division as Si, and calculate the highway density value of the target area. MDi is the highway density value of the target area, u is the standard value of the area division, and di is the grade coefficient value corresponding to the highway grade Di;

[0021] Step A2, obtain the traffic data of all urban and rural target roads in the target area from the target road historical information set, mark the traffic data as Ji, calculate the road traffic value under the same highway grade, JTi = ∑ (ji Ji), ji is the preset proportional coefficient of the traffic data Ji, JTi is the road traffic value, then calculate the product of the road traffic value JTi and the grade coefficient value di corresponding to the corresponding highway grade Di and record it as the product value CJi, then sum all the product values ​​CJi to obtain the congestion value YDi of the target area;

[0022] Step A3, obtaining target road pressure data of all urban and rural target roads in the target area and summing them up to obtain a total pressure value ZYi of the target area;

[0023] Step A4, the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area are calculated as follows: FXi=p1·(MDi-q1)-p2·(YDi-q3)-p3·(ZYi-q3), p1, p2, p3 are respectively the preset highway quality coefficients of the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area, and all of them are not 0, q1, q2, q3 are respectively the standard values ​​corresponding to the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area, and all of them are not 0, and FXi is the joint analysis value;

[0024] Step A5: Send the joint analysis value FXi to the evaluation module.

[0025] In a preferred embodiment, the evaluation module is used to evaluate the satisfaction of the target area according to the joint analysis value, which means:

[0026] The satisfaction of the target road is evaluated based on the joint analysis value FXi and the satisfaction threshold Z preset in the evaluation module. v is the preset deviation coefficient, and ZDi is the satisfaction degree of the target area.

[0027] In a preferred embodiment, a method for urban and rural road planning based on artificial intelligence includes the following steps:

[0028] Step 1: Collect historical information of urban and rural target roads to obtain a historical information set of urban and rural target roads;

[0029] Step 2: Collect urban and rural planning policy information to obtain an urban and rural planning policy information set;

[0030] Step 3: classify the urban and rural target road history information set into road types according to a preset classification standard to obtain a road type set;

[0031] Step 4: Use the urban and rural planning policy information set for training and build an auxiliary prediction model;

[0032] Step 5: Perform joint analysis based on the road type set, the urban and rural target road historical information set, and the output data of the auxiliary prediction model to obtain a joint analysis value;

[0033] Step 6: Evaluate the satisfaction of the target area based on the joint analysis value, and make corresponding plans based on the preset planning strategy and the satisfaction of the target area.

[0034] Technical effects and advantages of the present invention:

[0035] The present invention realizes the dynamic optimization of the urban and rural road network layout by integrating multiple modules. The system can collect and analyze historical road information and real-time urban and rural planning policy data, and can predict and solve traffic problems that may arise in the future. The system uses a large amount of historical and real-time data to train and optimize the neural network model to ensure that road planning decisions are based on evidence rather than intuition. The neural network module can predict the pressure situation of the target road, making the planning more forward-looking and adaptable. The present invention provides a powerful tool for urban planners and decision makers to cope with the increasingly complex challenges of transportation and urban development, and is conducive to building a more effective, safer and more sustainable urban and rural road network.

[0036] The present invention combines multiple data sources, including road types, historical information and policy impacts, through the analysis module to provide a comprehensive performance evaluation. The evaluation module can quantify the satisfaction of the target area and help decision makers understand the performance of the current road network. The planning module not only makes plans based on existing data, but also adjusts planning strategies according to the changing environment and policies. Through accurate prediction and satisfaction evaluation, the system helps to allocate construction resources more effectively and avoid waste. The system can identify potential congestion points and propose improvement measures to reduce traffic delays and improve traffic efficiency. By optimizing road design, the probability of accidents can be reduced and overall traffic safety can be improved. The setting of information module 2 enables the system to respond quickly to policy changes and adjust plans in a timely manner. The overall design of the system promotes sustainable urban development, taking into account long-term planning and rational use of resources.

[0037] The present invention can solve the problems that urban and rural planning involves a large amount of information scattered in different departments and institutions, lacks effective integration and utilization, resulting in incomplete planning decisions; the existing urban and rural planning system often does not respond quickly enough to real-time changing traffic conditions and policy adjustments, and cannot optimize the road network layout in a timely manner; and due to the lack of refined evaluation methods, the allocation of resources between urban and rural areas is often not optimal, resulting in excessive road construction in some areas and serious shortages in other areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0038] In order to facilitate understanding by those skilled in the art, the present invention is further described below in conjunction with the accompanying drawings;

[0039] Figure 1 This is a schematic diagram of the urban and rural road planning system based on artificial intelligence in the present invention.

[0040] Figure 2 This is a schematic diagram of the method for urban and rural road planning based on artificial intelligence in the present invention. DETAILED DESCRIPTION

[0041] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0042] Example 1

[0043] The urban and rural road planning system based on artificial intelligence aims to use artificial intelligence technology to optimize the layout of urban and rural road networks. The system consists of different modules, each module is responsible for performing specific tasks, and together completes the entire planning process. The urban and rural road planning system based on artificial intelligence includes information module one, information module two, classification module, neural network module, analysis module, evaluation module, and planning module.

[0044] Information module one is used to collect historical information of urban and rural target roads, obtain historical information sets of urban and rural target roads and transmit them to the classification module and analysis module; the main responsibility of information module one is to collect historical information related to target urban and rural roads, which includes existing road structure, traffic data such as traffic flow, traffic accident records, traffic road conditions, etc. The collected information will be organized into historical information sets and then transmitted to the classification module and analysis module for subsequent processing and analysis.

[0045] Information module two is used to collect urban and rural planning policy information, obtain urban and rural planning policy information sets and transmit them to the neural network module; Information module two focuses on collecting urban and rural planning policy information, involving current policy direction changes, budget allocation changes, construction project changes and other information, by integrating the key data in these information into urban and rural planning policy information sets and providing them to the neural network module to adjust and optimize the prediction model.

[0046] The classification module is used to classify the road types of the historical information set of urban and rural target roads according to the preset classification standards, obtain the road type set and transmit it to the analysis module; the task of the classification module is to classify the target roads according to the preset standards, for example, according to the function, design speed, carrying capacity of the road, the roads are divided into expressways, main roads, secondary roads or national roads, provincial roads, county roads, township roads and other types. Such classification helps the subsequent analysis module to analyze the regional road network more accurately.

[0047] The neural network module is trained using the urban and rural planning policy information set to build an auxiliary prediction model. The specific construction steps are as follows:

[0048] S1, the neural network module receives the urban and rural planning policy information set, takes the target road coverage area prediction data, target road planning period data, and target road policy data in the urban and rural planning policy information set as the input data for model training, takes the target road pressure data as the output data for model training, and assigns it to 0 or 1 to train the model, where 0 indicates that the target road pressure data is less than or equal to the set threshold, and 1 indicates that the target road pressure data is greater than the set threshold;

[0049] S2: The urban and rural planning policy information set of the most recent time planning window preset by information module 2 is used as the input data of the model. When the output data of the model is 0, the urban and rural planning policy information set of the most recent time planning window of information module 2 is used as the training data of the model to perform secondary training on the model; when the output data of the model is 1, the urban and rural planning policy information set of the most recent time planning window of information module 2 is used as the training data of the model to perform secondary training on the model while sending instructions to the analysis module; the neural network module uses machine learning algorithms such as deep learning to build and train the model. The purpose of the model is to learn how to predict the pressure situation of the target road based on the input urban and rural planning policy information. The training process of the model includes using historical data for preliminary training, and continuously performing secondary training based on new policy information sets to improve the accuracy of the prediction.

[0050] The analysis module is used to perform a joint analysis based on the road type set, the historical information set of urban and rural target roads, and the target road pressure data in the neural network module when the instruction is received, and obtain the joint analysis value and transmit it to the evaluation module; the analysis module combines the road type set, the historical information set and the target road pressure data provided by the neural network module to perform a comprehensive analysis, with the aim of evaluating the performance of different road types under the influence of specific policies, and generating a joint analysis value to provide a decision-making basis for the evaluation module.

[0051] The evaluation module is used to evaluate the satisfaction of the target area based on the joint analysis value and transmit the satisfaction to the planning module. The evaluation module evaluates the satisfaction of the target area based on the joint analysis value provided by the analysis module. The satisfaction here refers to the performance of the road network in meeting traffic needs, alleviating congestion, and improving traffic safety. The evaluation results will directly affect the decision-making of the planning module.

[0052] The planning module is used to make corresponding plans based on the preset planning strategies and the satisfaction of the target area. If the satisfaction of the target area meets the conditions of a preset planning strategy, the planning strategy will be used as the road planning scheme for the area, which includes but is not limited to building new roads of different levels to increase the overall road density, expanding existing roads, improving road quality or changing traffic flow.

[0053] The neural network module uses a series of calculation steps to process urban and rural planning policy information and converts this information into input and output data that can be used to train the model. The model takes into account the area, population, population growth rate, planning period, and policy change factors of the target road coverage area, and estimates the pressure value of the target road through a specific calculation formula. The design of the entire system allows the modules to collaborate with each other to form a dynamic and adaptive urban and rural road planning environment. With the continuous input of new data, the system can update its models and planning strategies in real time to adapt to the ever-changing urban and rural road needs and policy environment. This artificial intelligence-based method can significantly improve the efficiency and effectiveness of urban and rural road planning.

[0054] The urban and rural planning policy information includes target road coverage area prediction data, target road planning life data, and target road policy data. The neural network module receives the urban and rural planning policy information set, and uses the target road coverage area prediction data, target road planning life data, and target road policy data in the urban and rural planning policy information set as input data for model training, and uses the target road pressure data as output data for model training.

[0055] The coverage area in the target road coverage area prediction data is marked as Mi, the coverage area population is marked as Ri, the average annual growth rate of the coverage area population in the last n years is Ki, the target road planning period data is marked as Ni, and the policy change amount in the target road policy data is marked as Gi. The pressure value is calculated as X1, where t is the preset planning life stability value. The pressure value X2 is calculated, where gi is the specific coefficient preset for the policy type corresponding to the policy change Gi, and Gi' is the standard value corresponding to the policy change Gi; then the target road pressure data is obtained through the calculation formula, YL is the target road pressure data, f1 and f2 are both preset proportional coefficients and are positive numbers. The pressure value X1 and pressure value X2 are obtained through the target road coverage area prediction data, target road planning period data, and target road policy data in the urban and rural planning policy information set as the input data for model training, and the target road pressure data YL is used as the output data for model training. The larger the pressure value X1, the higher the demand for road improvement. The larger the pressure value X2, the higher the degree of road improvement of the target road policy. The larger the target road pressure data, the more urgent the demand for improvement of the target road is overall.

[0056] The classification module is used to classify the road types of the urban and rural target road history information set according to the preset classification standards, which refers to:

[0057] The classification module sets the highway grade of the urban and rural target roads in the urban and rural target road historical information set according to a preset classification standard, and marks the highway grade of the urban and rural target roads as Di.

[0058] The analysis module is used to perform joint analysis based on the road type set, the urban and rural target road historical information set, and the target road pressure data in the neural network module when receiving the instruction, and obtain the joint analysis value and transmit it to the evaluation module.

[0059] Step A1: divide the urban and rural areas into regions, obtain the highway grade Di of all urban and rural target roads in the target area, mark the area of ​​the regional division as Si, and calculate the highway density value of the target area. MDi is the highway density value of the target area, u is the standard value of the regional division area, and di is the grade coefficient value corresponding to the highway grade Di; the larger the highway density value of the target area, the higher the overall carrying capacity of the highway in the area;

[0060] Step A2, obtaining the traffic data of all urban and rural target roads in the target area from the target road historical information set, marking the traffic data as Ji, calculating the road traffic value under the same highway grade, JTi = ∑ (ji Ji), ji is the preset proportional coefficient of the traffic data Ji, JTi is the road traffic value, then calculating the product of the road traffic value JTi and the grade coefficient value di corresponding to the corresponding highway grade Di and recording it as the product value CJi, then summing up all the product values ​​CJi to obtain the congestion value YDi of the target area; the larger the congestion value YDi of the target area, the worse the overall smooth quality of the highway in the area;

[0061] Step A3, obtaining the target road pressure data of all urban and rural target roads in the target area and summing them up to obtain the total pressure value ZYi of the target area; the larger the total pressure value ZYi of the target area is, the greater the need to improve the overall carrying capacity of the roads in the area;

[0062] Step A4, the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area are calculated as follows: FXi=p1·(MDi-q1)-p2·(YDi-q3)-p3·(ZYi-q3), p1, p2, p3 are respectively the preset highway quality coefficients of the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area, and all of them are not 0, q1, q2, q3 are respectively the standard values ​​corresponding to the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area, and all of them are not 0, FXi is the joint analysis value; the larger the joint analysis value FXi is, the higher the overall traffic quality of the highway in the area is;

[0063] Step A5: Send the joint analysis value FXi to the evaluation module.

[0064] The evaluation module is used to evaluate the satisfaction of the target area based on the joint analysis value, which refers to:

[0065] The satisfaction of the target road is evaluated based on the joint analysis value FXi and the satisfaction threshold Z preset in the evaluation module. v is the preset deviation coefficient, ZDi is the satisfaction degree of the target area. The greater the satisfaction degree of the target area, the higher the overall road bearing quality and traffic quality in the area, and the more it meets the traffic needs of people in the area.

[0066] Example 2

[0067] A method for urban and rural road planning based on artificial intelligence, comprising the following steps:

[0068] Step 1: Collect historical information of urban and rural target roads to obtain a historical information set of urban and rural target roads;

[0069] Step 2: Collect urban and rural planning policy information to obtain an urban and rural planning policy information set;

[0070] Step 3: classify the urban and rural target road history information set into road types according to a preset classification standard to obtain a road type set;

[0071] Step 4: Use the urban and rural planning policy information set for training and build an auxiliary prediction model;

[0072] Step 5: Perform joint analysis based on the road type set, the urban and rural target road historical information set, and the output data of the auxiliary prediction model to obtain a joint analysis value;

[0073] Step 6: Evaluate the satisfaction of the target area based on the joint analysis value, and make corresponding plans based on the preset planning strategy and the satisfaction of the target area.

[0074] 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.

[0075] It should be understood that in the various embodiments of the present application, the size of the serial numbers of the above-mentioned processes does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0076] In addition, each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.

[0077] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0078] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0079] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present 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. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

Claims

1. The urban and rural road planning system based on artificial intelligence is characterized by: It includes information module 1, information module 2, classification module, neural network module, analysis module, evaluation module and planning module; The information module 1 is used to collect historical information of urban and rural target roads, obtain historical information sets of urban and rural target roads and transmit them to the classification module and the analysis module; The information module 2 is used to collect urban and rural planning policy information, obtain the urban and rural planning policy information set and transmit it to the neural network module; The classification module is used to classify the road types of the historical information set of urban and rural target roads according to the preset classification standards, obtain the road type set and transmit it to the analysis module; The neural network module is trained using the urban and rural planning policy information set to build an auxiliary prediction model. The specific construction steps are as follows: S1, the neural network module receives the urban and rural planning policy information set, takes the target road coverage area prediction data, target road planning period data, and target road policy data in the urban and rural planning policy information set as the input data for model training, takes the target road pressure data as the output data for model training, and assigns it to 0 or 1 to train the model, where 0 indicates that the target road pressure data is less than or equal to the set threshold, and 1 indicates that the target road pressure data is greater than the set threshold; S2: Using the urban and rural planning policy information set of the most recent time planning window preset by the information module 2 as the input data of the model, when the output data of the model is 0, using the urban and rural planning policy information set of the most recent time planning window of the information module 2 as the training data of the model to perform secondary training on the model; when the output data of the model is 1, using the urban and rural planning policy information set of the most recent time planning window of the information module 2 as the training data of the model to perform secondary training on the model while sending instructions to the analysis module; The analysis module is used to perform joint analysis based on the road type set, the urban and rural target road historical information set, and the target road pressure data in the neural network module when receiving the instruction, obtain the joint analysis value and transmit it to the evaluation module; The evaluation module is used to evaluate the satisfaction of the target area according to the joint analysis value and transmit the satisfaction to the planning module; The planning module is used to make corresponding plans according to the preset planning strategy and the satisfaction of the target area; The urban and rural planning policy information includes the target road coverage area prediction data, target road planning period data, and target road policy data; The neural network module receives the urban and rural planning policy information set, takes the target road coverage area prediction data, target road planning years data, and target road policy data in the urban and rural planning policy information set as input data for model training, and takes the target road pressure data as output data for model training: The coverage area in the target road coverage area prediction data is marked as Mi, the coverage area population is marked as Ri, the average annual growth rate of the coverage area population in the last n years is Ki, the target road planning period data is marked as Ni, and the policy change amount in the target road policy data is marked as Gi. The pressure value X1 is calculated, t is the preset planning period stability value, and the pressure value X2 is calculated by the formula X2=∑[gi·(Gi-Gi')], gi is the specific coefficient preset for the policy type corresponding to the policy change Gi, and Gi' is the standard value corresponding to the policy change Gi; then the target road pressure data is obtained by the calculation formula, YL is the target road pressure data, f1 and f2 are both preset proportional coefficients and are positive numbers. The pressure value X1 and the pressure value X2 obtained through the target road coverage area prediction data, target road planning years data, and target road policy data in the urban and rural planning policy information set are used as the input data for model training, and the target road pressure data YL is used as the output data for model training; The classification module is used to classify the road types of the urban and rural target road history information set according to the preset classification standards, which refers to: The classification module sets the highway grade of the urban and rural target roads in the urban and rural target road historical information set according to a preset classification standard, and marks the highway grade of the urban and rural target roads as Di; The analysis module is used to perform joint analysis based on the road type set, the urban and rural target road historical information set, and the target road pressure data in the neural network module when receiving the instruction, and obtain the joint analysis value and transmit it to the evaluation module. Step A1: divide the urban and rural areas into regions, obtain the highway grade Di of all urban and rural target roads in the target area, mark the area of ​​the regional division as Si, and calculate the highway density value of the target area. MDi is the highway density value of the target area, u is the standard value of the area division, and di is the grade coefficient value corresponding to the highway grade Di; Step A2, obtain the traffic data of all urban and rural target roads in the target area from the target road historical information set, mark the traffic data as Ji, calculate the road traffic value under the same highway grade, JTi = ∑ (ji Ji), ji is the preset proportional coefficient of the traffic data Ji, JTi is the road traffic value, then calculate the product of the road traffic value JTi and the grade coefficient value di corresponding to the corresponding highway grade Di and record it as the product value CJi, then sum all the product values ​​CJi to obtain the congestion value YDi of the target area; Step A3, obtaining target road pressure data of all urban and rural target roads in the target area and summing them up to obtain a total pressure value ZYi of the target area; Step A4, the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area are calculated as follows: FXi=p1·(MDi-q1)-p2·(YDi-q3)-p3·(ZYi-q3), p1, p2, p3 are respectively the preset highway quality coefficients of the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area, and all of them are not 0, q1, q2, q3 are respectively the standard values ​​corresponding to the highway density value MDi of the target area, the congestion value YDi of the target area, and the total pressure value ZYi of the target area, and all of them are not 0, and FXi is the joint analysis value; Step A5, transmitting the joint analysis value FXi to the evaluation module; The evaluation module is used to evaluate the satisfaction of the target area based on the joint analysis value, which refers to: The satisfaction of the target road is evaluated based on the joint analysis value FXi and the satisfaction threshold Z preset in the evaluation module. v is the preset deviation coefficient, and ZDi is the satisfaction degree of the target area.

2. A method for urban and rural road planning based on artificial intelligence, implemented based on the urban and rural road planning system based on artificial intelligence according to claim 1, characterized in that: The following steps are involved: Step 1: Collect historical information of urban and rural target roads to obtain a historical information set of urban and rural target roads; Step 2: Collect urban and rural planning policy information to obtain an urban and rural planning policy information set; Step 3: classify the urban and rural target road history information set into road types according to a preset classification standard to obtain a road type set; Step 4: Use the urban and rural planning policy information set for training and build an auxiliary prediction model; Step 5: Perform joint analysis based on the road type set, the urban and rural target road historical information set, and the output data of the auxiliary prediction model to obtain a joint analysis value; Step 6: Evaluate the satisfaction of the target area based on the joint analysis value, and make corresponding plans based on the preset planning strategy and the satisfaction of the target area.

Images