Road line selection optimization method and system based on AI and quantitative parameter constraint

Abstract

The invention provides a road line selection optimization method, system and device based on AI and quantitative parameter constraint, and a storage medium. The method comprises the following steps: establishing a road line selection initial preset parameter library; a high-precision remote sensing technology, an unmanned aerial vehicle, a GIS database and a traffic monitoring system are utilized to collect quantitative data, and data preprocessing is automatically carried out; a deep learning model is developed and trained, parameter values in historical cases are automatically identified and calculated, the identified and calculated parameters are trained and learned, and a deep learning result is fed back to a quantitative parameter set; a multi-factor target evaluation index system is constructed, and evaluation index values of all candidate schemes are obtained; and providing a decision support tool to help a user to understand the advantages and disadvantages of each scheme and recommend an optimal line scheme meeting all quantitative parameter constraints. According to the invention, the line selection efficiency and accuracy can be improved, the compliance of the line selection scheme in the aspects of technology, safety, environment and the like is ensured, and an efficient, economic and environment-friendly line selection scheme is provided for a road construction project.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent traffic planning, and more specifically, to a highway route selection optimization method and system based on AI and quantitative parameter constraints. Background Art

[0002] Existing highway route selection technology mainly relies on manual experience and qualitative analysis. This process is not only time-consuming and labor-intensive, but also easily affected by personal subjective judgment, which limits the scientificity and rationality of the route selection results. In terms of technical principles, traditional route selection methods usually involve manual collection and analysis of geographic information such as topography, land use, and ecologically sensitive areas, as well as consideration of socioeconomic factors such as population, economic activities, and traffic flow. However, these methods have problems of low efficiency and insufficient precision in data processing and analysis, and are difficult to meet the needs of modern highway construction projects for route selection accuracy and comprehensive evaluation.

[0003] In the process of implementing the embodiments of the present invention, the inventors found that there are at least the following problems or defects in the prior art: First, the traditional route selection method lacks the ability to efficiently process large amounts of complex data, resulting in the inability to quickly and accurately analyze and make decisions when faced with large-scale data; second, due to excessive reliance on manual experience, the route selection results may have subjective biases and cannot fully consider all influencing factors; finally, the prior art is not perfect in terms of environmental impact assessment and cost-benefit analysis, making it difficult to achieve a comprehensive assessment of the entire life cycle of a highway construction project. Summary of the invention

[0004] The present invention provides a highway route selection optimization method, system, medium and computing device based on AI and quantitative parameter constraints.

[0005] In a first aspect of the present invention, a highway route selection optimization method based on AI and quantitative parameter constraints is provided, comprising:

[0006] S1. Quantitative parameter definition: Establish an initial preset parameter library for highway route selection, automatically search the latest standards and specifications by computer, and automatically update the parameter constraint sets in the three aspects of route overall, traffic safety, and ecological environment through natural language; the latest standards and specifications include: highway engineering technical standards, highway route design specifications, highway bridge and culvert design general specifications, highway project construction land indicators, urban expressway design regulations, highway construction project environmental impact assessment specifications, and urban road traffic engineering project specifications;

[0007] S2. Data collection and processing: Using high-precision remote sensing technology, drones, GIS databases and traffic monitoring systems, computers collect quantitative data on the project area's topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow, and automatically perform data cleaning, mining and analysis preprocessing;

[0008] S3. Deep learning model training and application: Develop and train deep learning models to automatically identify and calculate route overall, traffic safety, and ecological environment parameter values ​​in historical cases, train and learn the identified and calculated parameters, and use the deep learning results as reasonable parameter intervals to feed back to the quantitative parameter set;

[0009] S4, automatic line selection and scheme evaluation: construct a multi-factor target evaluation index system, including population and economic impact evaluation index, cost-effectiveness evaluation index, and environmental impact evaluation index, and use principal component analysis to obtain the evaluation index value of each candidate scheme;

[0010] S5. Intelligent decision support: Provide decision support tools to help users understand the advantages and disadvantages of each solution and recommend the most optimal solution that meets all quantitative parameter constraints.

[0011] Furthermore, the specific steps of S1 are:

[0012] S11. Preset quantitative parameters: 30-50 senior experts in the highway route selection industry are randomly selected by computer, and their opinions are solicited through correspondence. Based on the experts' opinions, an initial parameter constraint set for highway route selection is established, and initial interval values ​​of preset parameters are determined. The initial interval values ​​of preset parameters include a route technical index set, an avoidance index set, and an ecological index set; among which, the route technical parameters include technical grade, number of lanes, design speed, and maximum longitudinal slope; the avoidance parameters include natural gas pipeline safety distance, oil pipeline safety distance, and vertical distance of high-voltage lines; and the ecological parameters include crossing basic farmland, ecological red line, and urban development boundary;

[0013] S12. Natural Language Processing: Computers use natural language processing technology to automatically search policy documents and highway design specification documents, read and automatically identify preset quantitative parameters, and update the above preset constraint parameters to meet the latest standard specification requirements.

[0014] Furthermore, the specific steps of S2 are:

[0015] S21. Internet crawler big data collection: Utilize Internet crawler big data to automatically collect original data related to the project area’s topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow.

[0016] S22. Data cleaning and mining analysis: The computer pre-processes the collected raw data and uses image recognition technology to automatically convert the raw data into parameters that can be automatically identified in AI line selection. The original data includes rivers, lakes, roads, railways, villages, towns, parks, mountains and contour lines that can be automatically identified by the computer based on the three indicators of topography, land use and ecological sensitive areas; the three indicators of population, economic activities and traffic flow are converted into GIS files with coordinates and specific attribute values.

[0017] Furthermore, the S3 specifically includes the following steps:

[0018] S31. The computer automatically searches for completed and under-construction highway projects in the project area and uses them as historical case analysis objects;

[0019] S32, the computer automatically identifies and calculates the preset quantitative parameter values ​​in S12, including a route technical index set, an avoidance index set, and an ecological index set;

[0020] S33, the computer automatically analyzes the calculated quantitative parameter sets one by one, and automatically determines and selects a suitable regression analysis method based on the data rules to obtain the recommended interval value of the quantitative parameter set; the regression analysis method includes but is not limited to linear regression, logistic regression and polynomial regression, stepwise regression, ridge regression and lasso regression;

[0021] S34. Compare the obtained recommended interval value A with the quantitative parameter set interval value B. If A is included in B, the computer stops the regression analysis; if A is not included in B, the computer continues the regression analysis until A is included in B.

[0022] Furthermore, the specific steps of S5 are:

[0023] S51. Automatic line selection by computer: Input a GIS file with specific attribute values ​​and use it as the basis for automatic line selection. The computer uses the input basic data as the independent variable of regression analysis, recommends interval value A according to the regression analysis method, automatically selects lines and forms several candidate line selection schemes.

[0024] Furthermore, the S5 further includes:

[0025] S52. Taking population and economic impact evaluation indicators, cost-benefit evaluation indicators, and environmental impact evaluation indicators as specific evaluation indicators, and taking candidate plans as units to form an evaluation object set, construct an original initial matrix of indicators;

[0026] S53, performing standard normalization processing on the indicator data, constructing a normalized matrix, and calculating the eigenvalues ​​and eigenvectors of the normalized matrix;

[0027] S54. Select several principal components based on the cumulative contribution rate of 90%;

[0028] S55. Using the variance contribution rate of each principal component as a weight, construct a scheme evaluation function, calculate the evaluation index of each candidate scheme, and sort them from large to small.

[0029] Furthermore, the method further comprises the following calculation steps:

[0030] The formula for calculating the population economic impact evaluation index is:

[0031]

[0032] Where E is the population and economic evaluation index; L is the length of the candidate route; P is the total population of the county-level cities through which the candidate passes; and G is the total GDP of the county-level cities through which the candidate passes.

[0033] Calculate the cost-effectiveness evaluation index, the formula is:

[0034]

[0035] Where C is the cost-effectiveness evaluation index; L is the route length of the candidate solution; Q is the bridge-tunnel ratio of the candidate solution; W is the excavation volume of the candidate solution; and T is the filling volume of the candidate solution.

[0036] Calculate the environmental impact assessment index, the formula is:

[0037]

[0038] Where H is the environmental impact assessment index; S is the ecological red line area occupied by the candidate scheme; N is the basic farmland area occupied by the candidate scheme; and K is the urban development boundary area occupied by the candidate scheme.

[0039] In a second aspect of the present invention, a highway route selection optimization system based on AI and quantitative parameter constraints is provided, comprising:

[0040] The quantitative parameter definition module is used to establish an initial preset parameter library for highway route selection. The computer automatically searches for the latest standards and specifications, and automatically updates the parameter constraint sets in the three aspects of route overall, traffic safety, and ecological environment through natural language; the latest standards and specifications include: highway engineering technical standards, highway route design specifications, highway bridge and culvert design general specifications, highway project construction land indicators, urban expressway design regulations, highway construction project environmental impact assessment specifications, and urban road traffic engineering project specifications;

[0041] The data acquisition and processing module is used to collect quantitative data on the topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow in the project area by computer using high-precision remote sensing technology, drones, GIS databases and traffic monitoring systems, and automatically perform data cleaning, mining and analysis preprocessing;

[0042] The deep learning model training and application module is used to develop and train deep learning models, automatically identify and calculate the route overall, traffic safety, and ecological environment parameter values ​​in historical cases, train and learn the identified and calculated parameters, and feed back the deep learning results to the quantitative parameter set as a reasonable parameter range;

[0043] The automatic route selection and scheme evaluation module is used to construct a multi-factor target evaluation index system, including population and economic impact evaluation index, cost-effectiveness evaluation index, and environmental impact evaluation index. The principal component analysis method is used to obtain the evaluation index value of each candidate scheme.

[0044] The intelligent decision support module is used to provide decision support tools to help users understand the advantages and disadvantages of each option and recommend the most optimal line option that meets all quantitative parameter constraints.

[0045] In a third aspect of the present invention, an electronic device is provided, comprising: at least one processor, a memory and an input-output unit; wherein the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute any one of the methods described in the first aspect.

[0046] In a fourth aspect of the present invention, a computer-readable storage medium is provided, which includes instructions, and when the instructions are executed on a computer, the computer executes any one of the methods in the first aspect.

[0047] According to the above-mentioned embodiments of the present invention, at least the following beneficial effects are achieved: the present invention establishes an initial preset parameter library for highway route selection, and uses natural language processing technology to automatically update these parameters to meet the latest standards and specifications. The system can ensure that the parameter constraints in the route selection process are the latest and most accurate. In addition, the system can automatically perform data cleaning, mining, and analysis preprocessing through quantitative data collected by high-precision remote sensing technology, drones, GIS databases, and traffic monitoring systems, thereby improving the accuracy and availability of data. The application of deep learning models can further enhance the ability to analyze historical cases and provide a more scientific parameter recommendation interval for route selection. In addition, the system of the present invention constructs a multi-factor target evaluation index system and uses the principal component analysis method to conduct a comprehensive evaluation of candidate solutions, so as to more objectively evaluate the pros and cons of each solution. The introduction of the intelligent decision support module can provide users with a powerful decision-making tool to help them understand the specific impact of each solution and recommend the optimal route selection solution. This method can not only improve the scientificity and rationality of route selection, but also effectively reduce the cost of highway construction projects, improve economic benefits, and reduce the impact on the ecological environment while meeting technical, safety, and environmental requirements, so as to achieve sustainable development. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, in which:

[0049] Figure 1 A schematic diagram of a process flow of a highway route selection optimization method based on AI and quantitative parameter constraints provided by an embodiment of the present invention;

[0050] Figure 2 A schematic diagram of the structure of a highway route selection optimization system based on AI and quantitative parameter constraints provided by an embodiment of the present invention;

[0051] Figure 3 The schematic diagram schematically shows the structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0052] The principles and spirit of the present invention will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present invention, and are not intended to limit the scope of the present invention in any way. On the contrary, these embodiments are provided to make the present invention more thorough and complete, and to fully convey the scope of the present invention to those skilled in the art.

[0053] Those skilled in the art know that the embodiments of the present invention can be implemented as a system, device, apparatus, method or computer program product. Therefore, the present invention can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software.

[0054] It should be noted that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction and does not have any limiting meaning.

[0055] Reference below Figure 1 , Figure 1 The following is a flow chart of a highway route selection optimization method based on AI and quantitative parameter constraints provided by an embodiment of the present invention. Figure 1 As shown, a highway route selection optimization method 100 based on AI and quantitative parameter constraints includes:

[0056] S1. Quantitative parameter definition: Establish an initial preset parameter library for highway route selection, automatically search the latest standards and specifications by computer, and automatically update the parameter constraint sets in the three aspects of route overall, traffic safety, and ecological environment through natural language; the latest standards and specifications include: highway engineering technical standards, highway route design specifications, highway bridge and culvert design general specifications, highway project construction land indicators, urban expressway design regulations, highway construction project environmental impact assessment specifications, and urban road traffic engineering project specifications;

[0057] S2. Data collection and processing: Using high-precision remote sensing technology, drones, GIS databases and traffic monitoring systems, computers collect quantitative data on the project area's topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow, and automatically perform data cleaning, mining and analysis preprocessing;

[0058] S3. Deep learning model training and application: Develop and train deep learning models to automatically identify and calculate route overall, traffic safety, and ecological environment parameter values ​​in historical cases, train and learn the identified and calculated parameters, and use the deep learning results as reasonable parameter intervals to feed back to the quantitative parameter set;

[0059] S4, automatic line selection and scheme evaluation: construct a multi-factor target evaluation index system, including population and economic impact evaluation index, cost-effectiveness evaluation index, and environmental impact evaluation index, and use principal component analysis to obtain the evaluation index value of each candidate scheme;

[0060] S5. Intelligent decision support: Provide decision support tools to help users understand the advantages and disadvantages of each solution and recommend the most optimal solution that meets all quantitative parameter constraints.

[0061] It should be noted that the highway route selection optimization method is a comprehensive process, covering multiple steps from parameter definition, data collection to deep learning model training, automatic route selection and decision support. These steps together constitute an intelligent highway route selection system, ensuring that the route selection process can be automated and optimized under the premise of complying with various technical, safety and environmental standards.

[0062] Specifically, the quantitative parameter definition involved refers to the set of various parameters that need to be pre-set and considered in the process of highway route selection. These parameters may include technical indicators of the route (such as road width and slope), traffic safety parameters (such as curve radius and sight distance), and ecological environment parameters (such as the distance to ecologically sensitive areas). "Data collection and processing" involves the use of various technical means, such as remote sensing technology, drones, GIS databases, etc., to collect and analyze key information such as topography, land use, and ecologically sensitive areas.

[0063] Preferably, in step S1, the following detailed scheme can be adopted: First, collect opinions and suggestions from senior experts in the highway route selection industry through questionnaires and interviews to form a preliminary parameter library. Then, use natural language processing technology to automatically search and learn the latest highway engineering technical standards and design specifications to achieve automatic updating and optimization of parameters. For the "data acquisition and processing" step, high-precision remote sensing satellite images and high-resolution photos taken by drones can be used in combination with GIS technology to automatically analyze and identify terrain and landforms. At the same time, real-time traffic flow data can be collected through the traffic monitoring system, and data cleaning and preprocessing are performed to provide accurate and reliable data input for subsequent deep learning model training.

[0064] In some embodiments, the specific steps of S1 are:

[0065] S11. Preset quantitative parameters: 30-50 senior experts in the highway route selection industry are randomly selected by computer, and their opinions are solicited through correspondence. Based on the experts' opinions, an initial parameter constraint set for highway route selection is established, and initial interval values ​​of preset parameters are determined. The initial interval values ​​of preset parameters include a route technical index set, an avoidance index set, and an ecological index set; among which, the route technical parameters include technical grade, number of lanes, design speed, and maximum longitudinal slope; the avoidance parameters include natural gas pipeline safety distance, oil pipeline safety distance, and vertical distance of high-voltage lines; and the ecological parameters include crossing basic farmland, ecological red line, and urban development boundary;

[0066] S12. Natural Language Processing: Computers use natural language processing technology to automatically search policy documents and highway design specification documents, read and automatically identify preset quantitative parameters, and update the above preset constraint parameters to meet the latest standard specification requirements.

[0067] It should be noted that the specific step S1 of the highway route selection optimization method emphasizes the use of expert opinions and natural language processing technology to establish and update the parameter library of highway route selection to ensure that the route selection process complies with the latest industry standards.

[0068] Specifically, the preset quantitative parameters need to collect opinions from multiple senior experts in the highway route selection industry to establish an initial parameter library. These parameters include route technical indicators, avoidance indicators, and ecological indicators, and each indicator needs to be set with an initial interval value. For example, the technical level may be set at different levels according to the function and capacity of the highway; the number of lanes can be determined according to the expected traffic flow; and the design speed is set according to the topography and road safety standards.

[0069] Preferably, in step S11, a questionnaire survey can be used to collect expert opinions, and these opinions can be input into a decision support system, which can automatically establish a parameter library based on the collected data. In addition, in step S12, the application of natural language processing technology can be further refined, such as using specific algorithms to parse policy documents and design specifications, and automatically extracting and updating quantitative parameters to ensure the real-time and accuracy of line selection parameters. In addition, a feedback mechanism can be set up to allow the system to accept external review and adjustment during the parameter update process to ensure the rationality and applicability of parameter settings.

[0070] In some embodiments, the specific steps of S2 are:

[0071] S21. Internet crawler big data collection: Utilize Internet crawler big data to automatically collect original data related to the project area’s topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow.

[0072] S22. Data cleaning and mining analysis: The computer pre-processes the collected raw data and uses image recognition technology to automatically convert the raw data into parameters that can be automatically identified in AI line selection. The original data includes rivers, lakes, roads, railways, villages, towns, parks, mountains and contour lines that can be automatically identified by the computer based on the three indicators of topography, land use and ecological sensitive areas; the three indicators of population, economic activities and traffic flow are converted into GIS files with coordinates and specific attribute values.

[0073] It should be noted that the Internet crawler big data collection in step S2 refers to the use of automated tools to crawl various data related to the project area from the Internet, such as topography, land use, etc. Data cleaning and mining analysis involves processing these raw data for subsequent analysis and use. For example, image recognition technology can be used to convert raw data on topography into parameters that can be recognized by computers, such as the location and characteristics of rivers and lakes.

[0074] Preferably, in step S21, multiple data sources can be used to enhance the comprehensiveness and accuracy of the data. In addition to Internet crawlers, geographic information systems (GIS) and satellite remote sensing technology can also be combined to obtain more accurate topographic data. In step S22, data cleaning and mining analysis can be further refined into the following steps: first, the collected raw data is denoised and formatted; second, image recognition and machine learning algorithms are applied to extract key geographic features; then, socioeconomic data such as population, economic activities, and traffic flow are converted into GIS format and assigned corresponding coordinates and attribute values ​​to facilitate spatial analysis. In addition, it is possible to consider introducing data fusion technology to integrate data from different sources and types to obtain a more comprehensive view of the project area.

[0075] In some embodiments, S3 specifically includes the following steps:

[0076] S31. The computer automatically searches for completed and under-construction highway projects in the project area and uses them as historical case analysis objects;

[0077] S32, the computer automatically identifies and calculates the preset quantitative parameter values ​​in S12, including a route technical index set, an avoidance index set, and an ecological index set;

[0078] S33, the computer automatically analyzes the calculated quantitative parameter sets one by one, and automatically determines and selects a suitable regression analysis method based on the data rules to obtain the recommended interval value of the quantitative parameter set; the regression analysis method includes but is not limited to linear regression, logistic regression and polynomial regression, stepwise regression, ridge regression and lasso regression;

[0079] S34. Compare the obtained recommended interval value A with the quantitative parameter set interval value B. If A is included in B, the computer stops the regression analysis; if A is not included in B, the computer continues the regression analysis until A is included in B.

[0080] It should be noted that the specific step S3 of deep learning model training and application is a key link in the highway route selection optimization method, which is used to train the model through historical data to provide recommended interval values ​​of quantitative parameters for highway route selection.

[0081] Specifically, the computer automatically searches for completed and under-construction highway projects in the project area in step S3, which means that the system will automatically identify and collect existing highway data in the project area, including completed and under-construction highway projects, which will be analyzed as historical cases. The computer automatically identifies and calculates the preset quantitative parameter values ​​in S12, which means that the system will use image recognition and data analysis technology to extract key parameters from the collected data, such as route technical index set, avoidance index set and ecological index set.

[0082] Preferably, in step S31, a more advanced search algorithm can be used to improve the efficiency and accuracy of collecting historical case data. In step S32, the process of automatically identifying and calculating preset quantitative parameter values ​​can be optimized by introducing more advanced image recognition and data mining techniques to improve the accuracy of parameter identification. In step S33, for the selection of regression analysis methods, the most suitable regression model, such as linear regression, logistic regression or polynomial regression, can be selected based on the characteristics and distribution of the data. In addition, an automated model selection and optimization process can be set up, and the system will automatically compare the performance of different regression models and select the best model to predict the recommended interval value of the parameter. In step S34, an iterative verification process can be introduced to ensure the consistency of the recommended interval value with the preset parameter set. If it is inconsistent, the system will automatically adjust the model parameters or select a new regression method until the conditions are met.

[0083] In some embodiments, the specific steps of S5 are:

[0084] S51. Automatic line selection by computer: Input a GIS file with specific attribute values ​​and use it as the basis for automatic line selection. The computer uses the input basic data as the independent variable of regression analysis, recommends interval value A according to the regression analysis method, automatically selects lines and forms several candidate line selection schemes.

[0085] It should be noted that a key step in automatic line selection and scheme evaluation is the process of automatic line selection by computer. This step is to apply the recommended interval values ​​of the quantitative parameter set to the actual line selection process to generate multiple candidate schemes, providing a basis for subsequent evaluation and decision-making.

[0086] Specifically, the computer automatic line selection in step S51 involves taking GIS files as input, which contain the geographic information and specific attribute values ​​of the project. The computer uses these data as independent variables, performs line selection calculations based on the interval value A recommended by the regression analysis method, and generates multiple candidate solutions. In this process, the independent variables of the regression analysis refer to the geographic and attribute data that affect the line selection, and the recommended interval value A is the parameter recommendation value obtained based on the training results of the deep learning model.

[0087] Preferably, in step S51, the process of automatic line selection can be further refined. For example, the following scheme can be adopted: First, the initial conditions and constraints of line selection are determined based on geographical information such as topography, land use, and socio-economic factors such as population distribution and economic activities. Then, multi-objective optimization is performed using an optimization algorithm, such as a genetic algorithm or a simulated annealing algorithm, to find the optimal route solution. In addition, a feedback mechanism can be set up to allow parameters and conditions to be adjusted according to actual conditions during the automatic line selection process to improve the adaptability and flexibility of line selection. Alternatives may include using different optimization algorithms, or combining expert systems to provide more professional line selection suggestions.

[0088] In some embodiments, the S5 further includes:

[0089] S52. Taking population and economic impact evaluation indicators, cost-benefit evaluation indicators, and environmental impact evaluation indicators as specific evaluation indicators, and taking candidate plans as units to form an evaluation object set, construct an original initial matrix of indicators;

[0090] S53, performing standard normalization processing on the indicator data, constructing a normalized matrix, and calculating the eigenvalues ​​and eigenvectors of the normalized matrix;

[0091] S54. Select several principal components based on the cumulative contribution rate of 90%;

[0092] S55. Using the variance contribution rate of each principal component as a weight, construct a scheme evaluation function, calculate the evaluation index of each candidate scheme, and sort them from large to small.

[0093] It should be noted that the population and economic impact evaluation index, cost-benefit evaluation index and environmental impact evaluation index are the three main dimensions used to evaluate candidate options. These indicators consider the potential impact of highway route selection on local population and economy, construction costs and environmental impact respectively. For example, the population and economic impact evaluation index can be evaluated by calculating the product of the route length of the candidate option and the population and GDP of the area it passes through; the cost-benefit evaluation index considers factors such as route length, bridge-tunnel ratio, excavation volume and filling volume.

[0094] Preferably, in step S52, a comprehensive evaluation index system can be constructed, taking into account the above three evaluation indexes and other factors that may affect the line selection (such as geological conditions, construction difficulty, etc.). In step S53, data standardization methods, such as Z-score standardization or Min-Max standardization, can be used to process data of different indicators to ensure that they are compared at the same magnitude. In step S54, principal component analysis (PCA) can be selected as a dimensionality reduction technique to extract the principal component that has the greatest impact on the scheme evaluation. More specifically, the number of principal components can be determined by calculating eigenvalues ​​and eigenvectors and combining the cumulative contribution rate. In step S55, a scheme evaluation function can be constructed based on the variance contribution rate of each principal component, and the evaluation indexes of each candidate scheme can be calculated and sorted to determine the most preferred line scheme. In addition, it is also possible to consider introducing a multi-objective optimization algorithm, such as a genetic algorithm or a particle swarm optimization algorithm, to further optimize the scheme selection process.

[0095] In some embodiments, the method further comprises the following calculation steps:

[0096] The formula for calculating the population economic impact evaluation index is:

[0097]

[0098] In the formula, E is the population and economic evaluation index; L is the length of the candidate route; P is the total population of the county-level cities through which the candidate passes; and G is the total GDP of the county-level cities through which the candidate passes.

[0099] Calculate the cost-effectiveness evaluation index, the formula is:

[0100]

[0101] Where C is the cost-effectiveness evaluation index; L is the route length of the candidate solution; Q is the bridge-tunnel ratio of the candidate solution; W is the excavation volume of the candidate solution; and T is the filling volume of the candidate solution.

[0102] Calculate the environmental impact assessment index, the formula is:

[0103]

[0104] In the formula, H is the environmental impact assessment index; S is the ecological red line area occupied by the candidate scheme; N is the basic farmland area occupied by the candidate scheme; K is the urban development boundary area occupied by the candidate scheme.

[0105] It should be noted that the environmental impact assessment index in the highway route optimization method is an important parameter to measure the environmental impact of the highway route selection scheme. It includes the assessment of the occupation of ecological red lines, basic farmland and urban development boundaries, and is the key to ensuring the coordination of highway construction and environmental protection.

[0106] Specifically, the environmental impact assessment index H is calculated by considering the ecological red line area S, basic farmland area N and urban development boundary area K occupied by the candidate scheme. The setting of these parameters needs to be based on national and local environmental protection laws and regulations and land use planning to ensure that the highway route selection scheme can meet traffic needs while minimizing the negative impact on the ecological environment.

[0107] Preferably, when calculating the environmental impact assessment indicators, the following detailed scheme can be adopted: first, accurately measure the land areas occupied by candidate options through GIS technology and remote sensing data; second, set weight coefficients according to environmental protection laws and regulations, and weight different types of land occupation to reflect the severity of their impact on the environment; then, the opinions of environmental impact assessment experts can be introduced to adjust the calculation model to improve the accuracy and rationality of the assessment. In addition, it is also possible to consider introducing a dynamic assessment mechanism to monitor the impact of highway construction on the environment in real time and adjust the route selection plan in a timely manner to reduce negative impacts.

[0108] The above-mentioned embodiments of the present invention have the following beneficial effects: the present invention can significantly improve the efficiency and accuracy of highway line selection through automated parameter updating and data collection and processing. By using artificial intelligence technology, a large amount of data can be quickly analyzed, so as to make more accurate decisions in the line selection process. Secondly, the application of deep learning models can further improve the accuracy of parameter identification and calculation, making the line selection scheme more scientific and reasonable. In addition, the construction of a multi-factor target evaluation index system and the provision of intelligent decision support tools can help decision makers comprehensively evaluate the advantages and disadvantages of each candidate scheme, so as to select the optimal line selection scheme. Furthermore, the implementation of this optimization method can promote the sustainable development of highway construction projects. By comprehensively considering the demographic and economic impact, cost-effectiveness and environmental impact, this method can ensure that highway construction meets the needs of economic and social development while minimizing the damage to the ecological environment. The implementation of this method can also reduce the overall cost of highway construction projects, improve investment benefits, and ensure the environmental friendliness and safety of highway construction projects. In this way, innovation and progress can be brought to the field of highway construction and the technological development of the industry can be promoted.

[0109] like Figure 2 As shown, in some embodiments, a highway route selection optimization system 200 based on AI and quantitative parameter constraints includes:

[0110] The quantitative parameter definition module 201 is used to establish an initial preset parameter library for highway route selection, and the computer automatically searches for the latest standards and specifications, and automatically updates the parameter constraint sets in the three aspects of route overall, traffic safety, and ecological environment through natural language; the latest standards and specifications include: highway engineering technical standards, highway route design specifications, highway bridge and culvert design general specifications, highway project construction land indicators, urban expressway design regulations, highway construction project environmental impact assessment specifications, and urban road traffic engineering project specifications;

[0111] The data collection and processing module 202 is used to collect quantitative data on the topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow in the project area by computer using high-precision remote sensing technology, unmanned aerial vehicles, GIS database and traffic monitoring system, and automatically perform data cleaning, mining and analysis preprocessing;

[0112] The deep learning model training and application module 203 is used to develop and train the deep learning model, automatically identify and calculate the route overall, traffic safety, and ecological environment parameter values ​​in historical cases, train and learn the identified and calculated parameters, and feed back the deep learning results to the quantitative parameter set as a reasonable parameter interval;

[0113] The automatic route selection and scheme evaluation module 204 is used to construct a multi-factor target evaluation index system, including population and economic impact evaluation index, cost-benefit evaluation index, and environmental impact evaluation index, and use the principal component analysis method to obtain the evaluation index value of each candidate scheme;

[0114] The intelligent decision support module 205 is used to provide decision support tools to help users understand the advantages and disadvantages of each solution and recommend the most optimal solution that meets all quantitative parameter constraints.

[0115] It can be understood that the modules and references in the highway route selection optimization system 200 based on AI and quantitative parameter constraints are Figure 1 The steps in the highway route selection optimization method based on AI and quantitative parameter constraints described above correspond to each other. Therefore, the operations, features and beneficial effects described above for the highway route selection optimization method based on AI and quantitative parameter constraints are also applicable to the highway route selection optimization system 200 based on AI and quantitative parameter constraints and the modules contained therein, and will not be repeated here.

[0116] Reference below Figure 3, which shows a schematic diagram of a structure 300 of an electronic device suitable for implementing some embodiments of the present invention. The electronic devices in some embodiments of the present invention may include, but are not limited to, mobile terminals such as mobile phones, notebook computers, digital broadcast receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The terminal device shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0117] like Figure 3 As shown, the electronic device 300 may include a processing device (e.g., a central processing unit, a graphics processing unit, etc.) 301, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 302 or a program loaded from a storage device 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the electronic device 300 are also stored. The processing device 301, the ROM 302, and the RAM 303 are connected to each other via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0118] Typically, the following devices may be connected to the I / O interface 305: input devices 306 including, for example, a touch screen, a touch pad, a keyboard, a mouse, a camera, a microphone, an accelerometer, a gyroscope, etc.; output devices 307 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 308 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 309. The communication devices 309 may allow the electronic device 300 to communicate with other devices wirelessly or by wire to exchange data. Although Figure 3 The electronic device 300 is shown with various devices, but it should be understood that it is not required to implement or possess all the devices shown. More or fewer devices may be implemented or possessed instead. Figure 3 Each block shown in the figure may represent one device, or may represent multiple devices as required.

[0119] Furthermore, the storage medium of the embodiment of the present application stores program instructions that can implement all the above methods, wherein the program instructions can be stored in the above storage medium in the form of a software product, including several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) or a processor to execute all or part of the steps of the methods described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, or terminal devices such as a computer, a server, a mobile phone, and a tablet.

[0120] The above descriptions are only some preferred embodiments of the present invention and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the embodiments of the present invention is not limited to the technical solutions formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above inventive concept. For example, the above features are replaced with (but not limited to) technical features with similar functions disclosed in the embodiments of the present invention to form a technical solution.

Claims

1. A highway route selection optimization method based on AI and quantitative parameter constraints, characterized in that: Highway AI route selection includes the following steps: S1. Quantitative parameter definition: Establish an initial preset parameter library for highway route selection, automatically search the latest standards and specifications by computer, and automatically update the parameter constraint sets in the three aspects of route overall, traffic safety, and ecological environment through natural language; the latest standards and specifications include: highway engineering technical standards, highway route design specifications, highway bridge and culvert design general specifications, highway project construction land indicators, urban expressway design regulations, highway construction project environmental impact assessment specifications, and urban road traffic engineering project specifications; S2. Data collection and processing: Using high-precision remote sensing technology, drones, GIS databases and traffic monitoring systems, computers collect quantitative data on the project area's topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow, and automatically perform data cleaning, mining and analysis preprocessing; S3. Deep learning model training and application: Develop and train deep learning models to automatically identify and calculate route overall, traffic safety, and ecological environment parameter values ​​in historical cases, train and learn the identified and calculated parameters, and use the deep learning results as reasonable parameter intervals to feed back to the quantitative parameter set; S4, automatic line selection and scheme evaluation: construct a multi-factor target evaluation index system, including population and economic impact evaluation index, cost-effectiveness evaluation index, and environmental impact evaluation index, and use principal component analysis to obtain the evaluation index value of each candidate scheme; S5. Intelligent decision support: Provide decision support tools to help users understand the advantages and disadvantages of each solution and recommend the most optimal solution that meets all quantitative parameter constraints.

2. A highway route selection optimization system and method based on AI and quantitative parameter constraints according to claim 1, characterized in that: The specific steps of S1 are: S11. Preset quantitative parameters: 30-50 senior experts in the highway route selection industry are randomly selected by computer, and their opinions are solicited through correspondence. Based on the experts' opinions, an initial parameter constraint set for highway route selection is established, and initial interval values ​​of preset parameters are determined. The initial interval values ​​of preset parameters include a route technical index set, an avoidance index set, and an ecological index set; among which, the route technical parameters include technical grade, number of lanes, design speed, and maximum longitudinal slope; the avoidance parameters include natural gas pipeline safety distance, oil pipeline safety distance, and vertical distance of high-voltage lines; and the ecological parameters include crossing basic farmland, ecological red line, and urban development boundary; S12. Natural Language Processing: Computers use natural language processing technology to automatically search policy documents and highway design specification documents, read and automatically identify preset quantitative parameters, and update the above preset constraint parameters to meet the latest standard specification requirements.

3. A highway route selection optimization system and method based on AI and quantitative parameter constraints according to claim 2, characterized in that: The specific steps of S2 are: S21. Internet crawler big data collection: Utilize Internet crawler big data to automatically collect original data related to the project area’s topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow. S22. Data cleaning and mining analysis: The computer pre-processes the collected raw data and uses image recognition technology to automatically convert the raw data into parameters that can be automatically identified in AI line selection. The original data includes rivers, lakes, roads, railways, villages, towns, parks, mountains and contour lines that can be automatically identified by the computer based on the three indicators of topography, land use and ecological sensitive areas; the three indicators of population, economic activities and traffic flow are converted into GIS files with coordinates and specific attribute values.

4. A highway route selection optimization system and method based on AI and quantitative parameter constraints according to claim 3, characterized in that: The S3 specifically includes the following steps: S31. The computer automatically searches for completed and under-construction highway projects in the project area and uses them as historical case analysis objects; S32, the computer automatically identifies and calculates the preset quantitative parameter values ​​in S12, including a route technical index set, an avoidance index set, and an ecological index set; S33, the computer automatically analyzes the calculated quantitative parameter sets one by one, and automatically determines and selects a suitable regression analysis method based on the data rules to obtain the recommended interval value of the quantitative parameter set; the regression analysis method includes but is not limited to linear regression, logistic regression and polynomial regression, stepwise regression, ridge regression and lasso regression; S34. Compare the obtained recommended interval value A with the quantitative parameter set interval value B. If A is included in B, the computer stops the regression analysis; if A is not included in B, the computer continues the regression analysis until A is included in B.

5. The highway route selection optimization system and method based on AI and quantitative parameter constraints according to claim 1 is characterized in that: The specific steps of S5 are: S51. Automatic line selection by computer: Input a GIS file with specific attribute values ​​and use it as the basis for automatic line selection. The computer uses the input basic data as the independent variable of regression analysis, recommends interval value A according to the regression analysis method, automatically selects lines and forms several candidate line selection schemes.

6. A highway route selection optimization system and method based on AI and quantitative parameter constraints according to claim 1, characterized in that: The S5 further includes: S52. Taking population and economic impact evaluation indicators, cost-benefit evaluation indicators, and environmental impact evaluation indicators as specific evaluation indicators, and taking candidate plans as units to form an evaluation object set, construct an original initial matrix of indicators; S53, performing standard normalization processing on the indicator data, constructing a normalized matrix, and calculating the eigenvalues ​​and eigenvectors of the normalized matrix; S54. Select several principal components based on the cumulative contribution rate of 90%; S55. Using the variance contribution rate of each principal component as a weight, construct a scheme evaluation function, calculate the evaluation index of each candidate scheme, and sort them from large to small.

7. A highway route selection optimization system and method based on AI and quantitative parameter constraints according to claim 6, characterized in that: The method further comprises the following calculation steps: The formula for calculating the population economic impact evaluation index is: In the formula, E is the population and economic evaluation index; L is the length of the candidate route; P is the total population of the county-level cities through which the candidate passes; and G is the total GDP of the county-level cities through which the candidate passes. Calculate the cost-effectiveness evaluation index, the formula is: Where C is the cost-effectiveness evaluation index; L is the route length of the candidate solution; Q is the bridge-tunnel ratio of the candidate solution; W is the excavation volume of the candidate solution; and T is the filling volume of the candidate solution. Calculate the environmental impact assessment index, the formula is: In the formula, H is the environmental impact assessment index; S is the ecological red line area occupied by the candidate scheme; N is the basic farmland area occupied by the candidate scheme; K is the urban development boundary area occupied by the candidate scheme.

8. A highway route selection optimization system based on AI and quantitative parameter constraints, characterized in that: include: The quantitative parameter definition module is used to establish an initial preset parameter library for highway route selection. The computer automatically searches for the latest standards and specifications, and automatically updates the parameter constraint sets in the three aspects of route overall, traffic safety, and ecological environment through natural language; the latest standards and specifications include: highway engineering technical standards, highway route design specifications, highway bridge and culvert design general specifications, highway project construction land indicators, urban expressway design regulations, highway construction project environmental impact assessment specifications, and urban road traffic engineering project specifications; The data acquisition and processing module is used to collect quantitative data on the topography, land use, ecologically sensitive areas, population distribution, economic activities and traffic flow in the project area by computer using high-precision remote sensing technology, drones, GIS databases and traffic monitoring systems, and automatically perform data cleaning, mining and analysis preprocessing; The deep learning model training and application module is used to develop and train deep learning models, automatically identify and calculate the route overall, traffic safety, and ecological environment parameter values ​​in historical cases, train and learn the identified and calculated parameters, and feed back the deep learning results to the quantitative parameter set as a reasonable parameter range; The automatic route selection and scheme evaluation module is used to construct a multi-factor target evaluation index system, including population and economic impact evaluation index, cost-effectiveness evaluation index, and environmental impact evaluation index. The principal component analysis method is used to obtain the evaluation index value of each candidate scheme. The intelligent decision support module is used to provide decision support tools to help users understand the advantages and disadvantages of each option and recommend the most optimal line option that meets all quantitative parameter constraints.

9. An electronic device, comprising: one or more processors; a storage device having one or more programs stored thereon; When the one or more programs are executed by the one or more processors, the one or more processors implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium having executable instructions stored thereon, which, when executed by a processor, enables the processor to implement the method according to any one of claims 1 to 7.

Images