Urban system evolution risk prediction method, electronic equipment and storage medium

Abstract

The invention provides a risk prediction method based on city system evolution, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence and city planning, and the method comprises the steps: obtaining city composition basic data matched with each city composition dimension; the city composition dimension comprises at least one of city land, city economy, population, house price and traffic dimension; and on the basis of the target city constraint rule, inputting the city composition basic data into a city evolution prediction model for city evolution prediction to obtain target city evolution data, and carrying out risk identification on the target city evolution data based on a city planning demand to obtain target city evolution risk data. According to the method, the evolution data of each dimension is predicted through the city evolution prediction model, and the risk identification of city system evolution is carried out based on the evolution data of each dimension and the city planning demand, so that the potential risk in the city system evolution process can be accurately positioned, and the risk prediction accuracy of city system evolution is improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the technical fields of artificial intelligence and urban planning, and particularly to a risk prediction method, an electronic device, and a storage medium for urban system evolution. Background Art

[0002] With the acceleration of the global urbanization process, the development of urban systems has become increasingly complex. Urban development planning and risk prediction accompanying urban development are closely related technical fields. How to effectively predict the risks that a city may face during the process of urban system planning and development has become a technical problem that needs to be solved urgently.

[0003] In related technologies, in urban planning, traditional urban planning and management methods are difficult to cope with the complexity and uncertainty of urban systems. For example, although the urban planning simulation tool of UrbanSim (urban simulation system) can effectively simulate the interactions of entities such as families and enterprises in a city and realize the prediction of urban development changes, UrbanSim has problems such as incomplete coverage of urban system elements, high requirements for input data, and great processing difficulty, and still cannot accurately reflect the actual association between components of a city, resulting in low accuracy of risk prediction for urban system evolution. Therefore, how to improve the accuracy of risk prediction for urban system evolution has become an urgent problem to be solved. Summary of the Invention

[0004] The present application aims to solve at least one of the technical problems existing in the prior art. For this purpose, the present application provides a risk prediction method, an electronic device, and a storage medium based on urban system evolution, which improve the accuracy of risk prediction for urban system evolution.

[0005] To achieve the above object, a first aspect of the embodiments of the present application provides a risk prediction method for urban system evolution, and the method includes: Obtain the target urban system data, target urban constraint rules, and urban planning requirements of the target urban system; Based on a plurality of preset urban composition dimensions, perform data screening on the target urban system data to obtain urban composition basic data matching each of the urban composition dimensions; wherein, the urban composition dimensions include at least one of an urban land dimension, an urban economy dimension, an urban population dimension, an urban housing price dimension, and an urban traffic dimension; On the basis of the target urban constraint rules, input the urban composition basic data into a pre-trained urban evolution prediction model for urban evolution prediction to obtain the target urban evolution data of the target urban system; Based on the urban planning requirements, perform risk identification on the target urban evolution data to obtain target urban evolution risk data.

[0006] In some embodiments, the target city constraint rules include target land constraint rules, target economic constraint rules, target population constraint rules, target housing price constraint rules, and target traffic constraint rules; the urban evolution prediction model includes a land evolution sub-model, an economic evolution sub-model, a population employment evolution sub-model, a housing price evolution sub-model, and a traffic evolution sub-model; the basic urban composition data includes urban land data, urban economic data, urban population data, urban housing price data, and urban traffic data; Based on the target city constraint rules, input the basic urban composition data into the pre-trained urban evolution prediction model for urban evolution prediction to obtain the target urban evolution data of the target city system, including: Based on the target land constraint rules, input the urban land data into the land evolution sub-model for land use evolution prediction to obtain target land evolution data; Based on the target economic constraint rules, input the target land evolution data and the urban economic data into the economic evolution sub-model for economic evolution prediction to obtain target economic evolution data; Based on the target population constraint rules, input the target economic evolution data and the urban population data into the population employment evolution sub-model for population employment evolution prediction to obtain target population employment evolution data; Based on the target housing price constraint rules, input the target population employment evolution data, the target land evolution data, and the urban housing price data into the housing price evolution sub-model for housing price evolution prediction to obtain target housing price evolution data; Based on the target traffic constraint rules, input the target housing price evolution data, the target land evolution data, the target population employment evolution data, and the urban traffic data into the traffic evolution sub-model for traffic evolution prediction to obtain target traffic evolution data; Determine the target urban evolution data of the target city system according to the target land evolution data, the target economic evolution data, the target population employment evolution data, the target housing price evolution data, and the target traffic evolution data.

[0007] In some embodiments, based on the target land constraint rules, input the urban land data into the land evolution sub-model for land use evolution prediction to obtain target land evolution data, including: Based on the target land constraint rules, use the land evolution sub-model to predict the land area planning of the urban land data to obtain the target land use area; Predict the land planning distribution of the urban land data based on the target land use area to obtain land use categories; Predict the proportion of land use categories of the urban land data based on the land use categories to obtain the proportion of land use categories; Identify the mixing degree of land use categories in the target urban area of the urban land data based on the proportion of land use categories to obtain the urban land use mixing degree; Identify the location accessibility of the target urban area based on the urban land use mixing degree to obtain the urban location accessibility; Determine the target land evolution data based on the target land use area, the land use categories, the proportion of land use categories, the urban land use mixing degree, and the urban location accessibility.

[0008] In some embodiments, on the basis of the target economic constraint rule, input the target land evolution data and the urban economic data into the economic evolution sub-model for economic evolution prediction to obtain target economic evolution data, including: On the basis of the target economic constraint rule, perform production economic planning prediction on the urban economic data through the economic evolution sub-model to obtain production economic data; Perform population economic planning prediction on the urban economic data to obtain population economic data; Perform employment economic planning prediction on the urban economic data based on the production economic data, the population economic data, and the target land evolution data to obtain employment economic data; Determine the target economic evolution data based on the production economic data, the population economic data, and the employment economic data.

[0009] In some embodiments, on the basis of the target population constraint rule, input the target economic evolution data and the urban population data into the population employment evolution sub-model for population employment evolution prediction to obtain target population employment evolution data, including: On the basis of the target population constraint rule, input the target land evolution data and the urban population data into the population employment evolution sub-model for population residential distribution evolution prediction to obtain population residential distribution data; Perform population employment distribution evolution prediction on the urban population data based on the employment economic data to obtain population employment distribution data; Determine the target population employment evolution data based on the population residential distribution data and the population employment distribution data.

[0010] In some embodiments, based on the target housing price constraint rule, inputting the target population employment evolution data, the target land evolution data, and the urban housing price data into the housing price evolution sub-model for housing price evolution prediction to obtain target housing price evolution data, including: Based on the target housing price constraint rule, extracting features from the target population employment evolution data through the housing price evolution sub-model to obtain population employment evolution features, extracting features from the target land evolution data to obtain land evolution features, extracting features from urban land data to obtain urban land features, extracting features from urban population data to obtain urban population employment features, and extracting features from the urban housing price data to obtain urban housing price features; Performing housing price regression prediction based on the population employment evolution features, the land evolution features, the urban land features, the urban population employment features, and the urban housing price features to obtain the target housing price evolution data.

[0011] In some embodiments, the traffic evolution sub-model includes a traffic travel volume prediction network and a traffic travel path flow prediction network; Based on the target traffic constraint rule, inputting the target housing price evolution data, the target land evolution data, the target population employment evolution data, and the urban traffic data into the traffic evolution sub-model for traffic evolution prediction to obtain target traffic evolution data, including: Based on the target traffic constraint rule, inputting the target housing price evolution data, the target land evolution data, the target population employment evolution data, and the urban traffic data into the traffic travel volume prediction network for traffic travel demand prediction to obtain the traffic travel volume; Inputting the traffic travel volume into the traffic travel path flow prediction network for traffic travel path prediction to obtain the traffic travel path; Obtaining multiple traffic travel segments corresponding to the traffic travel path and calculating the traffic travel cost of each traffic travel segment; Obtaining the traffic travel population flow of the traffic travel volume and allocating the traffic travel population flow to each traffic travel segment according to the traffic travel cost to obtain the segment travel flow corresponding to each traffic travel segment; Determining the target traffic evolution data according to the traffic travel volume and the segment travel flow.

[0012] In some embodiments, identifying risks for the target urban evolution data based on the urban planning requirements to obtain target urban evolution risk data, including: Identify the risk types of the target urban evolution data based on the urban planning requirements to obtain the target risk categories; Identify the risk category levels of the target urban evolution data based on the target risk categories to obtain the target urban evolution risk data.

[0013] In a second aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the risk prediction method for urban system evolution according to any one of the embodiments in the first aspect of the present application.

[0014] In a third aspect, an embodiment of the present application provides a computer-readable storage medium. The storage medium stores a program, and when the program is executed by a processor, it implements the risk prediction method for urban system evolution according to any one of the embodiments in the first aspect of the present application.

[0015] The risk prediction method for urban system evolution proposed in the present application first screens the target urban system data based on a preset plurality of urban composition dimensions, and can accurately extract the basic data related to urban elements such as urban land, economy, population, housing prices, and transportation, avoiding subsequent prediction deviations in urban development caused by incomplete coverage of urban system elements. Secondly, inputting the screened basic data of urban composition into a pre-trained urban evolution prediction model can more accurately predict the urban evolution trend within the framework of the target urban constraint rules. Finally, risk identification of the target urban evolution data based on urban planning requirements can accurately locate potential risks in the process of urban system evolution, providing more forward-looking and targeted decision-making support for urban planning and management, and improving the accuracy of risk prediction for urban system evolution.

[0016] Other features and advantages of the present application will be described in the following specification, and some will become obvious from the specification, or be understood by implementing the present application. The objectives and other advantages of the present application can be achieved and obtained through the structures specifically pointed out in the specification, claims, and drawings. Description of the Drawings

[0017] Figure 1 is a schematic flowchart of the risk prediction method for urban system evolution provided by an embodiment of the present application; Figure 2 is a schematic flowchart of the risk prediction method for urban system evolution provided by another embodiment of the present application; Figure 3 is a schematic flowchart of the risk prediction method for urban system evolution provided by another embodiment of the present application; Figure 4It is a schematic flowchart of a risk prediction method for urban system evolution provided by another embodiment of the present application; Figure 5 It is a schematic flowchart of a risk prediction method for urban system evolution provided by another embodiment of the present application; Figure 6 It is a schematic flowchart of a risk prediction method for urban system evolution provided by another embodiment of the present application; Figure 7 It is a schematic flowchart of a risk prediction method for urban system evolution provided by another embodiment of the present application; Figure 8 It is a schematic flowchart of a risk prediction method for urban system evolution provided by another embodiment of the present application; Figure 9 It is a schematic hardware structure diagram of an electronic device provided by an embodiment of the present application. Detailed implementation manners

[0018] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application, but not to limit the present application.

[0019] It should be noted that although the functional modules are divided in the device schematic diagram and the logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different module division in the device or a different order in the flowchart. Terms such as "first" and "second" in the specification, claims and the above drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence.

[0020] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the technical field to which this application belongs. The terms used herein are only for the purpose of describing the embodiments of this application and are not intended to limit this application.

[0021] First, several nouns involved in the present application are analyzed: Artificial Intelligence (AI): It is a new technical science that studies and develops theories, methods, technologies, and application systems for simulating, extending, and expanding human intelligence. Artificial intelligence is a branch of computer science. It attempts to understand the essence of intelligence and produce a new intelligent machine that can react in a way similar to human intelligence. The research in this field includes robots, speech recognition, image recognition, natural language processing, and expert systems, etc. Artificial intelligence can simulate the information process of human consciousness and thinking. It also uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain the best results in terms of theories, methods, technologies, and application systems.

[0022] The embodiments of the present application provide a risk prediction method, an electronic device, and a storage medium based on urban system evolution, which improve the accuracy of risk prediction for urban system evolution.

[0023] The embodiments of the present application can acquire and process relevant data based on artificial intelligence technology. Among them, Artificial Intelligence (AI) is a theory, method, technology, and application system that uses digital computers or machines controlled by digital computers to simulate, extend, and expand human intelligence, sense the environment, acquire knowledge, and use knowledge to obtain the best results.

[0024] Artificial intelligence basic technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, big data processing technologies, operation / interaction systems, mechatronics, etc. Artificial intelligence software technologies mainly include several major directions such as computer vision technology, robotics, biometric technology, speech processing technology, natural language processing technology, and machine learning / deep learning.

[0025] The present application can be used in many general or special computer system environments or configurations. For example: personal computers, server computers, handheld devices or portable devices, tablet devices, multi-processor systems, microprocessor-based systems, set-top boxes, programmable consumer electronic devices, network PCs, minicomputers, mainframe computers, distributed computing environments including any of the above systems or devices, and so on. The present application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. The present application can also be practiced in a distributed computing environment where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules can be located in local and remote computer storage media including storage devices.

[0026] Based on this, the embodiments of the present application provide a risk prediction method, an electronic device, and a storage medium based on urban system evolution, which improve the effect of the risk prediction method for urban system evolution by considering the influence of real-time traffic flow on traffic travel paths.

[0027] The risk prediction method, electronic device, and storage medium based on urban system evolution provided by the embodiments of the present application are specifically described through the following embodiments. First, the risk prediction method for urban system evolution in the embodiments of the present application is described.

[0028] Figure 1 is an optional flowchart of the risk prediction method for urban system evolution provided by the embodiments of the present application. Figure 1 The method in may include but is not limited to steps S101 to S104.

[0029] Step S101, obtain the target urban system data, target urban constraint rules, and urban planning requirements of the target urban system.

[0030] Step S102, based on a preset plurality of urban composition dimensions, perform data screening on the target urban system data to obtain urban composition basic data matching each urban composition dimension; wherein, the urban composition dimensions include at least one of the urban land dimension, urban economy dimension, urban population dimension, urban housing price dimension, and urban traffic dimension.

[0031] Step S103, on the basis of the target urban constraint rules, input the urban composition basic data into a pre-trained urban evolution prediction model for urban evolution prediction to obtain the target urban evolution data of the target urban system.

[0032] Step S104, perform risk identification on the target urban evolution data based on the urban planning requirements to obtain the target urban evolution risk data.

[0033] Steps S101 to S104 illustrated in the embodiments of the present application first perform screening on the target urban system data based on a preset plurality of urban composition dimensions, which can accurately extract the basic data related to urban elements such as urban land, economy, population, housing price, and traffic, avoiding subsequent urban development prediction deviations caused by incomplete coverage of urban system elements. Secondly, inputting the screened urban composition basic data into a pre-trained urban evolution prediction model can more accurately predict the urban evolution trend within the framework of the target urban constraint rules. Finally, performing risk identification on the target urban evolution data based on the urban planning requirements can accurately locate the potential risks in the urban system evolution process, providing more forward-looking and targeted decision-making support for urban planning and management, and improving the accuracy of the risk prediction of urban system evolution.

[0034] In step S101 of some embodiments, specifically, the target city system data refers to various types of basic information related to the target city, including but not limited to urban geographical data (such as urban streets, county and district administrative unit base maps, grid unit base maps, highway networks at all levels, bus line data, rail transit data, etc.), urban statistical data (such as census data, economic census data, traffic travel survey data, etc.), and so on.

[0035] Urban planning data mainly involves urban land space planning texts, red lines for cultivated land protection, urban development boundaries, ecological protection red lines, etc. Then, all tabular data is cleaned and standardized, and all files and variables are named in a standardized manner. For image data and text data, technologies such as image recognition are used to extract key information and convert it into digital form or map vectors.

[0036] Specifically, the target city constraint rules refer to the policy regulations, resource limitations, and other conditions that must be followed during the urban planning and evolution process. The target city constraint rules include but are not limited to urban land space planning texts, red lines for cultivated land protection, urban development boundaries, ecological protection red lines, etc.

[0037] Specifically, the urban planning requirements refer to the specific urban planning goals proposed based on the target city constraint rules. The goals include but are not limited to population scale regulation, improvement degree of public transportation coverage, etc.

[0038] Specifically, the target city system data, target city constraint rules, and urban planning requirements of the target city system can be obtained from data such as POI (Point of Interest, that is, specific locations on the map) data, AOI (Area of Interest, that is, specific geographical areas on the map) data, mobile phone signaling data, statistical yearbooks, census data, and urban planning over the years.

[0039] Before step S102 of some embodiments, since the change in the urban land dimension is relatively slow, with a certain lag and stability, it is usually measured in units of years or longer time scales. However, the changes in the dimensions of urban population and urban traffic are relatively rapid, usually reflected in monthly or quarterly changes. This results in differences in the interactions between different elements within the urban system. When training the urban evolution prediction model, a monthly iteration calculation mechanism is added based on multi-year iterations.

[0040] Specifically, the evolution prediction based on urban land data and urban housing price data shows annual prediction results, while the evolution prediction based on urban economic data, urban population data, and urban traffic data shows monthly prediction results.

[0041] Further, taking the prediction of the population distribution and traffic distribution in the target city in April of the prediction year (2030) with a five-year iteration calculation as an example (the base year is 2020): First, conduct a full-process and complete simulation prediction for 2025 and 2030 in the order of the land evolution sub-model, economic evolution sub-model, population employment evolution sub-model, housing price evolution sub-model, and traffic evolution sub-model; Second, re-train the relevant model parameters of the economic evolution sub-model, population employment evolution sub-model, and traffic evolution sub-model according to the data in April of the base year (2020); Third, based on the predicted land evolution data in 2025 and the population distribution data in April 2024, calculate the monthly economic data and monthly population distribution data in April 2025, and further calculate the traffic evolution data in April 2025 based on the monthly employment data in 2025, the housing price calculation results in 2025, and the urban traffic data in April 2024; Fourth, based on the predicted target land evolution data in 2030 and the population distribution data in April 2025, calculate the monthly economic data and monthly population distribution data in April 2030, and further calculate the target traffic evolution data in April 2030 based on the monthly calculation results of population employment in April 2030, the housing price calculation results in 2030, and the urban traffic data in April 2025.

[0042] In this embodiment, by combining the monthly iteration calculation mechanism, different evolution sub-models can be iterated with different prediction periods. On the basis of maintaining the annual iteration of the land evolution sub-model, the population, economic, and traffic evolution sub-models can perform monthly iteration calculations, which can better reflect the spatio-temporal heterogeneity of different elements in the urban system and help improve the prediction accuracy of the urban system evolution model.

[0043] In step S102 of some embodiments, specifically, the urban composition dimension includes at least one of the urban land dimension, urban economic dimension, urban population dimension, urban housing price dimension, and urban traffic dimension, and is used to analyze and evaluate the key elements of the urban system development.

[0044] Specifically, the information related to each urban composition dimension can be extracted from the target urban system data through a preset screening rule.

[0045] For example, in the dimension of urban land, the distribution and area of different types of land can be screened out from land use data; in the dimension of urban economy, the employment distribution of different industries and the economic contribution of the total population can be screened out from economic census data; in the dimension of urban population, the population density and age structure of different regions can be screened out from population census data; in the dimension of urban housing prices, the correlation between housing prices and geographical locations (such as the distance from the city center, surrounding supporting facilities, etc.) can be extracted by combining geographical information data; in the dimension of urban transportation, traffic flow information for different time periods and different road sections can be screened out from mobile signaling data, POI, and AOI data.

[0046] In this embodiment, based on a preset plurality of urban composition dimensions, data screening is performed on the target urban system data to obtain urban composition basic data matching each urban composition dimension, which can accurately extract basic data related to urban elements such as urban land, economy, population, housing prices, and transportation, avoiding subsequent urban development prediction deviations caused by incomplete coverage of urban system elements.

[0047] Please refer to Figure 2 , in some embodiments, the target urban constraint rules include target land constraint rules, target economic constraint rules, target population constraint rules, target housing price constraint rules, and target transportation constraint rules; the urban evolution prediction model includes a land evolution sub-model, an economic evolution sub-model, a population employment evolution sub-model, a housing price evolution sub-model, and a transportation evolution sub-model; the urban composition basic data includes urban land data, urban economic data, urban population data, urban housing price data, and urban transportation data, and step S103 may include, but is not limited to, steps S201 to S206.

[0048] Step S201, based on the target land constraint rule, input the urban land data into the land evolution sub-model for land use evolution prediction to obtain target land evolution data.

[0049] Step S202, based on the target economic constraint rule, input the target land evolution data and urban economic data into the economic evolution sub-model for economic evolution prediction to obtain target economic evolution data.

[0050] Step S203, based on the target population constraint rule, input the target economic evolution data and urban population data into the population employment evolution sub-model for population employment evolution prediction to obtain target population employment evolution data.

[0051] Step S204, based on the target housing price constraint rule, input the target population employment evolution data, target land evolution data, and urban housing price data into the housing price evolution sub-model for housing price evolution prediction to obtain target housing price evolution data.

[0052] Step S205, based on the target traffic constraint rules, input the target housing price evolution data, target land evolution data, target population employment evolution data, and urban traffic data into the traffic evolution sub-model for traffic evolution prediction to obtain the target traffic evolution data.

[0053] Step S206, determine the target urban evolution data of the target urban system according to the target land evolution data, target economic evolution data, target population employment evolution data, target housing price evolution data, and target traffic evolution data.

[0054] Please refer to Figure 3 , in some embodiments, step S201 may include, but is not limited to, steps S301 to S306.

[0055] Step S301, based on the target land constraint rules, use the land evolution sub-model to predict the land area planning of urban land data to obtain the target land use area.

[0056] Step S302, based on the target land use area, predict the land planning distribution of urban land data to obtain the land use categories.

[0057] Step S303, based on the land use categories, predict the proportion of land use categories of urban land data to obtain the proportion of land use categories.

[0058] Step S304, based on the proportion of land use categories, identify the degree of land use category mixing in the target urban area of urban land data to obtain the urban land use mixing degree.

[0059] Step S305, identify the location accessibility of the target urban area to obtain the urban area location accessibility.

[0060] Step S306, determine the target land evolution data according to the target land use area, land use categories, proportion of land use categories, urban land use mixing degree, and urban area location accessibility.

[0061] In step S301 of some embodiments, specifically, the target land constraint rules refer to the policy and regulatory requirements, ecological protection requirements, and land resource limitation requirements that need to be followed in urban development planning.

[0062] Specifically, urban land data refers to the basic information related to urban land use in the past period, including but not limited to historical land use data, employment distribution data on historical land, traffic road network data, cultivated land protection red line, ecological protection red line, and slope data, etc.

[0063] Specifically, the target land use area refers to the predicted land use area of each region in the future city on the premise of meeting the target land constraint rules.

[0064] Specifically, the land evolution sub-model is an integral part of the urban evolution prediction model and is used to predict the changing trend of urban land use.

[0065] Specifically, the land evolution sub-model includes a Markov model. Through the Markov model, the transition probability matrix between various types of land (describing the probability of changing from one land use to another) can be determined, and the land use area can be predicted based on the transition probability matrix to output the target land use area.

[0066] For example, if the target land constraint rules stipulate that a certain proportion of green space area must be reserved in the central area of the target city, and industrial land must be concentrated in the designated industrial park. If the past residential land area of the target city is 100 square kilometers, the commercial land area is 50 square kilometers, the industrial land area is 80 square kilometers, etc., according to the transition probability matrix, it can be calculated that in the predicted year (such as ten years later), the residential land area of the target city may increase to 120 square kilometers, 20 square kilometers of green space area is reserved in the central area of the urban area, the commercial land area may increase to 60 square kilometers, and the industrial land area may decrease to 70 square kilometers.

[0067] In this embodiment, based on the target land constraint rules, the land area planning and prediction of urban land data are carried out through the land evolution sub-model to obtain the target land use area, which can scientifically predict the area distribution of future urban land use according to the current situation and constraint conditions of land use, and provide an accurate land use planning basis for the evolution of the urban system.

[0068] In step S302 of some embodiments, specifically, the land use category refers to different use types of urban land, such as residential land, commercial land, industrial land, green space, etc.

[0069] Specifically, the land evolution sub-model includes a random forest model and a cellular automaton model. The suitability probability of the development and change of each cell region in the city can be calculated through the random forest algorithm based on multiple indicators closely related to urban land use change, such as the number of employment positions, the average housing price of districts and counties, the density of roads at all levels, and the generalized travel cost. Then, the suitability probability is multiplied by the neighborhood effect and constraint conditions output by the cellular automaton model to obtain the development probability of each cell. Based on the roulette algorithm, the land use category to which each cell belongs is determined according to the development probability of each cell. Among them, a cell is the basic spatial unit in the urban land grid area; the neighborhood effect refers to the proportion of the total number of cells with the same land use type as the central cell in the Moore neighborhood of the central cell to the number of neighborhood cells; the constraint conditions include two categories: topographic constraints and planning constraints. Specifically, the slope of residential land is less than 25%, the slope of industrial land is less than 10%, and the slope of road land is less than 5%. Cells that meet the constraint conditions are assigned a value of 1, otherwise 0. Cells outside the urban development boundary, within the cultivated land red line and the ecological protection red line are not allowed to be converted into construction land, that is, cells within the constraint range are assigned a value of 0, and cells outside the range are assigned a value of 1.

[0070] For example, a 5×5 Moore neighborhood can be used to analyze the proportion of the same type of land use around the central cell, combined with slope constraints (such as the slope of residential land <25%) and planning red line restrictions (such as no development in ecological protection areas), to calculate the development probability of cell A. That is, if cell A meets the constraint conditions and the proportion of commercial land in the neighborhood exceeds 30%, the probability of converting to commercial land is 0.7. Iterative simulation is realized through the roulette algorithm. When the simulation result is consistent with the land use area predicted by Markov, the final land use category distribution map is output.

[0071] In this embodiment, based on the target land use area, land planning distribution prediction is performed on urban land data to obtain land use categories, which can further refine the specific distribution of urban land according to the land use area, realize the optimization of the spatial distribution of land use, improve land use efficiency, and meet the needs of different functional areas in the city at the same time.

[0072] In step S303 of some embodiments, specifically, the land use category ratio refers to the proportion of different land use types in urban land use.

[0073] For example, the proportion of residential land in the total land area, the proportion of commercial land, etc.

[0074] In step S304 of some embodiments, specifically, the urban land use mix refers to the degree of mixed use of different land use types in the urban area.

[0075] Specifically, the Shannon entropy index of urban land data is calculated based on the proportion of land use categories, and the quotient of the Shannon entropy index and the natural logarithm of the total number of land use types is calculated according to the formula of land use mixing degree = Shannon entropy index / ln(total number of land use types), so as to obtain the urban land use mixing degree. Among them, the Shannon entropy index is an indicator used to quantify the degree of land use mixing; the total number of land use types refers to the total number of different land use types within the urban area.

[0076] For example, a street in a city has 4 land use types, and its logarithm is ln4. Based on the calculation formula of land use mixing degree, the land use mixing degree of this street can be obtained, and its value ranges from 0 to 1. The closer the value is to 1, the higher the degree of land use type mixing, that is, the more diverse and evenly distributed the land use types are.

[0077] In this embodiment, the degree of land use category mixing in the target urban area of urban land data is identified based on the proportion of land use categories, and the urban land use mixing degree is obtained, which can identify the degree of mixed use of different land use types within the urban area, and further optimize the urban land use layout.

[0078] In step S305 of some embodiments, specifically, the urban location accessibility comprehensively measures the difficulty for people to reach other activity area destinations from one area to obtain facility services.

[0079] Specifically, the urban location accessibility can be determined by the following formula:

[0080] Among them, represents the location accessibility of the v-th land use area in the target urban area i in the predicted time period t; represents the travel attraction potential of various land uses included in the target urban area j, which is calculated by multiplying the v-th land use area in the target urban area j by the travel attraction weight of the v-th land use type; represents the cost sensitivity parameter reflecting the impedance degree, and the default value is 1; represents the travel cost between the target urban area i and the target urban area j in the predicted time period t, which is measured by the minimum Euclidean distance searched between two points; represents the travel attraction potential of various land uses included in the target urban area i; represents the travel cost between the target urban area i and the target urban area i in the predicted time period t.

[0081] In this embodiment, by identifying the location accessibility of the target urban area, the urban location accessibility is obtained, which can identify the distribution and accessibility of transportation facilities within the urban area, and provide information on traffic convenience for urban land planning.

[0082] In step S306 of some embodiments, specifically, by integrating information such as the target land use area, land use categories, proportion of land use categories, urban land use mixing degree, and urban location accessibility, complete evolution data of future land use in the urban area can be obtained.

[0083] Through steps S301 to S306, by comprehensively considering the target land constraint rules and urban land data, and using the land evolution sub-model to conduct a comprehensive prediction of land use evolution, not only can the future target land use area be obtained, but also the planned distribution of land, the proportion of various types of land use, the mixing degree of urban land use, and the urban location accessibility can be predicted, effectively predicting the final data of urban land evolution and ensuring the rationality of urban land planning and utilization.

[0084] Please refer to Figure 4 , in some embodiments, step S202 may include, but is not limited to, steps S401 to S404.

[0085] Step S401, based on the target economic constraint rules, use the economic evolution sub-model to conduct a production economic planning prediction on urban economic data to obtain production economic data.

[0086] Step S402, conduct a population economic planning prediction on urban economic data to obtain population economic data.

[0087] Step S403, based on the production economic data, population economic data, and target land evolution data, conduct an employment economic planning prediction on urban economic data to obtain employment economic data.

[0088] Step S404, determine the target economic evolution data according to the production economic data, population economic data, and employment economic data.

[0089] In step S401 of some embodiments, specifically, the target economic constraint rules refer to the policies, regulations, industrial layout requirements, and economic resource limitation rules that need to be followed in urban planning.

[0090] Specifically, the economic evolution sub-model is a model used to simulate and predict the urban economic development trend.

[0091] Specifically, urban economic data includes economic-related statistical information such as the past gross domestic product, industrial structure, total employment, and total population of the city.

[0092] Specifically, production economic data refers to the statistical data and economic indicators related to production activities in the urban area, used to reflect the economic situation and development trend in the production field of the urban area. The production economic data includes, but is not limited to, the gross domestic product of the urban area and the age data of urban residents, etc.

[0093] Specifically, the economic evolution sub-model includes the AutoRegressive Integrated Moving Average (ARIMA) model. ARIMA combines three methods: autoregression (AR), differencing (I), and moving average (MA). Through differencing operations, non-stationary time series data is transformed into stationary series. Autoregression represents the linear relationship between the current value and the values at previous time points. The moving average part represents the linear relationship between the current value of the time series and the error terms at previous time points. The autoregression, differencing, and moving average are specifically implemented through the auto_arima function in the pmdarima library to automatically select the best ARIMA model parameters.

[0094] For example, if the target economic constraint rule is that the aging ratio in the target city in the next ten years does not exceed 14%, first arrange the population data in the region over the past few decades by year as time series data and directly input it into the auto_arima function in the pmdarima library. This function will automatically try various different combinations of ARIMA model parameters to find the combination of model parameters that best describes the aging change law of the city (such as ARIMA(2,1,3), which means the ARIMA model uses 2 autoregressive terms, 1 differencing, and 3 moving average terms). Finally, use the fitted model to predict the future aging rate.

[0095] In this embodiment, based on the target economic constraint rule, the economic evolution sub-model is used to predict the production economy plan for the urban economic data to obtain the production economy data, which can provide economic-level prediction and guidance for urban planning, enabling the urban evolution to formulate reasonable economic policies based on the prediction results.

[0096] In step S402 of some embodiments, specifically, the population economic data can be the total number of resident population in the city.

[0097] Specifically, the economic evolution sub-model also includes the Long Short-Term Memory (LSTM) network. The total number of resident population in the city and the historical number of job positions are input into the LSTM for feature extraction to obtain the features of the historical total resident population and the historical number of job positions. The features of the historical total resident population and the historical number of job positions are input into the hidden layer (including 128 LSTM units). Each unit captures the long-term dependence relationship between features through a gating mechanism (forget gate, input gate, output gate), and the output of the hidden layer is converted into the predicted population economic data through a fully connected layer.

[0098] In this embodiment, by performing population and economic planning and forecasting on urban economic data to obtain population and economic data, the potential impact of population changes on the urban economy can be revealed, helping urban planners better understand the interaction between population dynamics and economic development, which is conducive to formulating more comprehensive and coordinated urban population and economic policies.

[0099] In step S403 of some embodiments, specifically, the employment economic data includes, but is not limited to, the total number of employment positions in urban evolution and the total number of employment positions in each industry.

[0100] Specifically, the economic evolution sub-model further includes a multiple linear regression algorithm, and the multiple linear regression algorithm can be represented by the following formula:

[0101] where y represents the total number of employment positions, , …, represent independent variables, including but not limited to historical total employment, historical number of employment positions in each industry, target land use area, total resident population, etc., is the intercept term, , …, represent regression coefficients, respectively representing the influence of each independent variable on the dependent variable, represents the error term.

[0102] In this embodiment, based on production economic data, population economic data, and target land evolution data, employment economic planning and forecasting are performed on urban economic data to obtain employment economic data, which can predict the changing trend of the urban employment market, so as to promote the creation of employment opportunities and the optimization of the employment structure, thereby improving the urban employment rate and the quality of life of residents.

[0103] In step S404 of some embodiments, specifically, by integrating production economic data, population economic data, and employment economic data, complete evolution data of the future economic development of the urban area can be obtained.

[0104] Through steps S401 to S404, under the guidance of the target economic constraint rules, economic data in multiple dimensions such as production, population, and employment of the city are integrated. For the planning and forecasting of production economy, the sustainable development of urban industries and the improvement of energy efficiency are ensured. For the economic forecasting of population and employment, the impact of population and employment changes on economic activities is effectively understood, and the accuracy of urban economic evolution forecasting is improved.

[0105] Please refer to Figure 5 , in some embodiments, step S203 may include, but is not limited to, steps S501 to S503.

[0106] Step S501: Based on the target population constraint rules, input the target land evolution data and urban population data into the population employment evolution sub-model for predicting the evolution of population residential distribution, and obtain the population residential distribution data.

[0107] Step S502: Based on the employment economic data, conduct an evolution prediction of the urban population employment distribution for the urban population data to obtain the population employment distribution data.

[0108] Step S503: Determine the target population employment evolution data according to the population residential distribution data and the population employment distribution data.

[0109] In step S501 of some embodiments, specifically, the target population constraint rules refer to the policies and regulations that the population growth and distribution need to follow in urban planning and development, such as controlling the population density and optimizing the population structure.

[0110] Specifically, the urban population data includes the population quantity, age structure, population distribution, living environment, employment distribution, etc. of each urban area in the past period.

[0111] Specifically, the population distribution data refers to the number of people relocating in urban areas in the future period after urban planning.

[0112] Specifically, the population employment evolution sub-model includes a deep neural network and an XGBoost regression model, which are used to predict the distribution of residential population and employment positions at different spatial scales such as grids, streets, and districts and counties.

[0113] Specifically, first use a deep neural network to construct a binary classification model (relocate / not relocate). The input features include indicators such as the population quantity, age structure, population distribution, and living environment of each urban area in the past. The output is the relocate or not relocate result corresponding to the population of each urban area. Predict the relocation scale of the population in each urban area through the XGBoost regression model. Specifically, take the grid as a unit and input the regional attraction indicators (such as the number of newly built schools and the improvement degree of subway accessibility) and economic affordability (such as the change in the housing price-to-income ratio). Multiply the regional attraction indicators as the population relocation weights by the population relocation quantity in each urban area to obtain the population migration data, and combine the population economic data and production economic data to conduct a population residential distribution prediction on the population migration data to obtain the population residential distribution data.

[0114] In this embodiment, by inputting the target land evolution data and urban population data into the population employment evolution sub-model based on the target population constraint rules for predicting the evolution of population residential distribution and obtaining the population residential distribution data, it helps to understand the dynamic changes of urban population and employment based on the population constraint rules, facilitates optimizing the urban industry layout, and reasonably planning residential and commercial areas, improving the accuracy of predicting urban population employment evolution data.

[0115] In step S502 of some embodiments, specifically, the population employment distribution data refers to the employment distribution of the urban resident population in different regions and industries of the city.

[0116] Specifically, the population employment distribution data for a future time period can be predicted based on the total number of employment positions in the employment economic data, the total number of employment positions in each industry, and the historical employment position distribution data.

[0117] In step S503 of some embodiments, specifically, by integrating the population residence distribution data and the population employment distribution data, the complete evolution data of the future population employment development in the urban area can be obtained.

[0118] Through steps S501 to S503, within the framework of the target population constraint rules, data from multiple dimensions such as population migration, residence distribution, and employment distribution can be integrated, which helps to ensure that the planning of urban housing and community facilities can meet the housing needs of future residents. By combining the population employment distribution data, the layout of the future urban employment market can be understood, the accuracy of the prediction of population employment evolution data is improved, and it helps to improve the accuracy of the risk prediction of urban system evolution subsequently.

[0119] Please refer to Figure 6 , in some embodiments, step S204 may include, but is not limited to, steps S601 to S602: Step S601, based on the target housing price constraint rules, feature extraction is performed on the target population employment evolution data through a housing price evolution sub-model to obtain population employment evolution features, feature extraction is performed on the target land evolution data to obtain land evolution features, feature extraction is performed on the urban land data to obtain urban land features, feature extraction is performed on the urban population data to obtain urban population employment features, and feature extraction is performed on the urban housing price data to obtain urban housing price features.

[0120] Step S602, based on the population employment evolution features, land evolution features, urban land features, urban population employment features, and urban housing price features, housing price regression prediction is performed to obtain the target housing price evolution data.

[0121] In step S601 of some embodiments, specifically, the target housing price constraint rules refer to the policies and regulations that housing prices need to follow in urban planning and development, such as controlling the housing price increase rate and ensuring housing supply.

[0122] Specifically, the basic information of urban housing prices refers to the data that have affected housing price fluctuations in the past, including but not limited to the total population, traffic flow, location accessibility, generalized travel cost, and urban land use mix.

[0123] Specifically, the housing price evolution sub-model is used to predict urban housing price information in a future time period.

[0124] Specifically, the housing price evolution sub-model can be an XGBoost (eXtreme Gradient Boosting) regression model.

[0125] Specifically, regarding the characteristics of population employment evolution, it may involve analyzing the impact of population employment changes on housing prices. If the number of job positions increases, it may lead to an increase in housing demand and cause housing prices to rise; regarding the characteristics of land evolution, housing prices may be affected by changes in land supply and the transformation of land use; regarding the characteristics of urban land and urban population employment, if the urban expansion rate, land use efficiency, population growth rate, and average income level change, it will also affect housing prices; regarding the characteristics of urban housing prices, the future housing price fluctuations can be deduced from the historical fluctuations of urban housing prices and regional housing price differences.

[0126] In step S602 of some embodiments, specifically, the target housing price evolution data synthesizes multiple feature dimensions of the characteristics of population employment evolution, land evolution, urban land characteristics, urban population employment characteristics, and urban housing price characteristics.

[0127] Specifically, housing price prediction can be achieved through the following formula:

[0128] Among them, represents the XGBoost regression model, represents the predicted target housing price evolution data, represents the housing price information corresponding to the urban housing price characteristics in the historical period, represents the difference between the predicted characteristics of population employment evolution, land evolution and the urban land characteristics, urban population employment characteristics in the historical period.

[0129] Through steps S601 to S602, under the guidance of the target housing price constraint rule, comprehensively considering population employment evolution, land evolution, and existing urban land and housing price data, the housing price evolution sub-model can be used for multi-dimensional feature extraction and housing price regression prediction. This process can not only identify and quantify the key factors affecting housing prices, but also construct an accurate housing price prediction model through machine learning algorithms such as XGBoost to improve the accuracy of urban housing price prediction.

[0130] Please refer to Figure 7 In some embodiments, the traffic evolution sub-model includes a total traffic volume prediction network and a traffic path flow prediction network. Step S205 can include, but is not limited to, steps S701 to S705: Step S701, based on the target traffic constraint rules, input the target housing price evolution data, target land evolution data, and urban traffic data into the traffic travel volume prediction network to predict the distribution of traffic travel locations and obtain the traffic travel volume.

[0131] Step S702, input the traffic travel volume into the traffic travel path flow prediction network to predict the traffic travel path and obtain the traffic travel path.

[0132] Step S703, obtain multiple traffic travel segments corresponding to the traffic travel path and calculate the traffic travel cost of each traffic travel segment.

[0133] Step S704, allocate the traffic travel volume to each traffic travel segment according to the traffic travel cost to obtain the segment travel flow corresponding to each traffic travel segment.

[0134] Step S705, determine the target traffic evolution data according to the traffic travel volume and the segment travel flow.

[0135] In step S701 of some embodiments, specifically, the target traffic constraint rules refer to the policies and regulations that traffic development needs to follow in urban planning and development, including but not limited to the policy of giving priority to the development of public transportation (such as the coverage rate of 500 meters around subway stations ≥ 80%), the requirement for the proportion of low-carbon travel (such as the proportion of non-motorized travel ≥ 30%), etc.

[0136] Specifically, the urban traffic data refers to the traffic situation information of past cities, including but not limited to information such as urban traffic flow, road network, and public transportation usage.

[0137] Specifically, the traffic travel volume prediction network can be a deep gravity model for predicting the traffic travel volume of urban traffic data.

[0138] Specifically, the traffic travel volume refers to the total number of urban residents who need to travel in the target city.

[0139] Specifically, by taking the population employment distribution data, urban land use mixing degree, urban location accessibility, and target housing price evolution data as input variables and inputting them into the feedforward neural network of the deep gravity model (including 15 hidden layers), in each hidden layer, the parameter matrix (including the weights and biases of the network) interacts with the input variables, extracts the features of the input variables through non-linear transformation, and uses the fully connected layer to output the travel probability matrix with i as the starting point and ij as the flow direction. Finally, the travel probability matrix is activated through an activation function (such as the Softmax function) to obtain the total urban resident travel volume between each traffic grid.

[0140] In this embodiment, on the basis of the target traffic constraint rules, the target housing price evolution data, the target land evolution data, the target population employment evolution data and the urban traffic data are input into the traffic travel total volume prediction network to predict the traffic travel demand, and the total traffic travel volume is obtained, which effectively reflects the impact of urban land use on the travel behavior of urban residents and realizes the effective transformation from urban spatial function to travel volume demand.

[0141] In step S702 of some embodiments, specifically, the transportation travel path refers to an optional path from the travel starting point to the travel end point.

[0142] Specifically, the traffic travel path flow prediction network includes a hybrid path finding allocation algorithm, a discrete choice model (MNL, Multinomial Logit Model) and a user balance method.

[0143] Specifically, a hybrid path finding and allocation algorithm is first used to find a shortest path from each travel start point to the travel end point, and the travel mode of the next node is randomly selected from the travel start point. The travel mode takes into account seven modes of transportation: walking, bicycle, motorcycle, private car, taxi, bus and subway, as well as three travel modes: private car transfer to public transportation, motorcycle transfer to public transportation, and other means of transportation except private cars and motorcycles as the main body of travel, until the travel end point is reached, so as to generate multiple travel paths that can be selected for the total amount of transportation, and select the transportation path according to preset standards (such as minimizing the total travel time, maximizing the capacity of the transportation path, etc.).

[0144] In step S703 of some embodiments, specifically, the transportation cost includes but is not limited to travel time cost, monetary cost, transfer cost, etc.

[0145] Specifically, the transportation cost can be determined by the following formula:

[0146] in, Indicates the travel path The cost of transportation, By traffic route Various modes of transportation The road section travel cost is composed of time cost, monetary cost and transfer cost. The travel costs of all road sections corresponding to each path are the travel costs of the path.

[0147] In step S704 of some embodiments, specifically, the road segment travel flow refers to the number of urban residents traveling on each traffic travel segment.

[0148] Specifically, the traffic travel path with the minimum traffic travel cost is initially selected through a discrete choice model, and the total traffic travel volume is allocated to the traffic travel path with the minimum cost. The traffic travel cost of each traffic travel path is updated by the user equilibrium method. It is identified whether the traffic travel cost corresponding to the updated traffic travel path is greater than the minimum traffic travel cost. If it is greater, it means that the traffic travel cost of this traffic travel path is not the minimum cost, and then the traffic travel flow of this traffic travel path needs to be allocated to the traffic travel path corresponding to the minimum cost until the convergence condition of the user equilibrium method is met (for example, the sum of the absolute values of the changes in the vehicle equivalents of each section of the traffic travel path is less than 1% of the sum of the vehicle equivalents of all sections of the path).

[0149] For example, the traffic travel path includes m1 - m5. Initially, the traffic travel cost corresponding to the m1 path is the lowest. First, the total traffic travel volume is allocated to m1. Then, due to high traffic volume, m1 becomes congested and the cost rises. Since the m2 and m5 paths have some overlapping sections with the m1 path and the costs of these sections increase, the traffic travel costs of the m2 and m5 paths also increase accordingly. The traffic travel costs of m3 and m4 remain unchanged. Then, it is necessary to determine the path with the minimum cost at this time as m2 through the user equilibrium method and transfer the traffic flow of m1 and m5 to the m2 path until the path flow allocation reaches the convergence condition.

[0150] In this embodiment, the total traffic travel volume is allocated to each traffic travel section according to the traffic travel cost, and the section travel flow corresponding to each traffic travel section is obtained, which can realize the selection of the optimal traffic travel path based on real - time traffic flow data, avoid excessive traffic flow concentrating on a few roads, causing traffic congestion, and improve the accuracy of traffic flow allocation.

[0151] In step S705 of some embodiments, specifically, by integrating the total traffic travel volume and the section travel flow, the complete evolution data of the future traffic development in the urban area can be obtained.

[0152] Through steps S701 to S705, on the basis of the target traffic constraint rules, by integrating the total traffic travel volume and the section travel flow, it helps to enhance the reasonable planning of urban traffic, realize the optimization of the urban traffic network design, and improve the accuracy of urban traffic evolution.

[0153] In step S206 of some embodiments, specifically, by integrating the target land evolution data, the target economic evolution data, the target population employment evolution data, the target housing price evolution data, and the target traffic evolution data, the complete evolution data of the future development of the urban area comprehensively described from the dimensions of land, economy, population, housing price, and traffic can be obtained.

[0154] Through steps S201 to S206, by inputting the basic data of the city composition into the pre-trained urban evolution prediction model, it is possible to achieve the coordinated development of urban planning in multiple dimensions such as land, economy, population, housing price, and transportation within the framework of the target city constraint rules, improve the accuracy of the predicted trend of urban system evolution, and help improve the accuracy of risk prediction in the process of urban system evolution in the future.

[0155] Please refer to Figure 8 , in some embodiments, step 104 may include, but is not limited to, steps S801 to S802: Step S801, identify the risk type of the target urban evolution data based on the urban planning requirements to obtain the target risk category.

[0156] Step S802, identify the risk category level of the target urban evolution data based on the target risk category to obtain the target urban evolution risk data.

[0157] In step S801 of some embodiments, in this embodiment, the target urban evolution data can be represented by Table 1: Table 1

[0158] Specifically, through the above table, based on the criteria (i.e., the target city constraint rules), the compliance of the urban system evolution process in achieving the three aspects of land development, basic services, and economic development of the urban system can be evaluated from the situation of each specific urban evolution indicator.

[0159] Specifically, the target risk category refers to the risk category of the land development, basic services, and economic development goals to which the risk of each specific urban evolution indicator belongs.

[0160] In step S802 of some embodiments, specifically, the target urban evolution risk data refers to the specific urban evolution indicators for which there are risks in the urban system evolution, their corresponding risk categories and risk levels. Among them, the risk levels include, but are not limited to, risk-free, low-risk, medium-risk, and high-risk levels, which are specifically determined based on the actual situation. For example, risk-free means that the evolution indicator meets the target requirements, low-risk means that the evolution indicator has a small deviation from the target requirements (such as a deviation from the target value within 5%), medium-risk means that the evolution indicator has a large deviation from the target requirements (such as a deviation from the target value within 10%), and high-risk means that the evolution indicator has a very large deviation from the target requirements (such as a deviation from the target value within 20%).

[0161] For example, for the prediction of the evolution index of the construction land area in the central urban area and the whole city area, it is learned that the proportion of urban construction in the whole city exceeds the target value (40% > 30%), and the proportion of ecological land is lower than the target value (28% < 40%), identifying the risk of unreasonable land use structure with a high - risk level.

[0162] Through steps S801 to S802, the potential risks in the urban system evolution process can be accurately located, providing more forward - looking and targeted decision - making support for urban planning and management, and improving the accuracy of risk prediction for urban system evolution.

[0163] The risk prediction method for urban system evolution proposed in this application first screens the target urban system data based on a preset number of urban composition dimensions, and can accurately extract the basic data related to urban elements such as urban land, economy, population, housing price, and transportation, avoiding the problems of high requirements for urban input data and large processing difficulty, and also avoiding the subsequent prediction deviation of urban development caused by incomplete coverage of urban system elements. Secondly, inputting the screened basic data of urban composition into a pre - trained urban evolution prediction model, within the framework of the target urban constraint rules in multiple dimensions of urban land, economy, population, housing price, and transportation, there is a strong correlation between each sub - model. The prediction result of the previous sub - model will affect the prediction of all subsequent sub - models, and the prediction result of the subsequent sub - model will affect the previous sub - model in the next iteration, which can accurately reflect the actual correlation between the components of each dimension of the city, improving the prediction accuracy of the urban evolution trend and solving the problem of being unable to accurately reflect the actual correlation between the components of the city. Finally, based on the urban planning requirements, risk identification is carried out on the target urban evolution data, which can accurately locate the potential risks in the urban system evolution process, provide more forward - looking and targeted decision - making support for urban planning and management, and improve the accuracy of risk prediction for urban system evolution.

[0164] In a second aspect, an embodiment of the present application provides an electronic device, including: a memory and a processor. The memory stores a computer program, and when the processor executes the computer program, it implements the risk prediction method for urban system evolution according to any one of the embodiments in the first aspect of the present application.

[0165] In a third aspect, an embodiment of the present application provides a computer - readable storage medium, and the storage medium stores a program, and when the program is executed by the processor, it implements the risk prediction method for urban system evolution according to any one of the embodiments in the first aspect of the present application.

[0166] Please refer to Figure 9 , Figure 9 which shows the hardware structure of an electronic device in another embodiment. The electronic device includes: The processor 901 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present application; The memory 902 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM), etc. The memory 902 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 902 and are called by the processor 901 to execute the risk prediction method for urban system evolution in the embodiments of the present application; The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to implement communication interaction between this device and other devices, and can implement communication through wired means (such as USB, network cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.); The bus 905 transmits information between the various components of the device (such as the processor 901, the memory 902, the input / output interface 903, and the communication interface 904); Among them, the processor 901, the memory 902, the input / output interface 903, and the communication interface 904 achieve communication connections with each other inside the device through the bus 905.

[0167] The embodiments of the present application also provide a computer-readable storage medium. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the above-mentioned risk prediction method for urban system evolution is implemented.

[0168] As a non-transitory computer-readable storage medium, the memory can be used to store non-transitory software programs and non-transitory computer-executable programs. In addition, the memory can include high-speed random access memory, and can also include non-transitory memory, such as at least one disk storage device, a flash memory device, or other non-transitory solid-state storage devices. In some embodiments, the memory optionally includes a memory remotely provided relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above-mentioned network include but are not limited to the Internet, an enterprise intranet, a local area network, a mobile communication network, and combinations thereof.

[0169] The embodiments described in the embodiments of the present application are for more clearly explaining the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of the present application are equally applicable to similar technical problems.

[0170] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and may include more or fewer steps than those shown in the figures, or combine some steps, or different steps.

[0171] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separated, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the modules can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0172] Those of ordinary skill in the art can understand that all or some of the steps in the methods disclosed above, and the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, and their appropriate combinations.

[0173] The terms "first", "second", "third", "fourth", etc. (if any) in the specification of the present application and the above-mentioned drawings are used to distinguish similar objects, and do not have to be used to describe a specific order or sequence. It should be understood that such used data can be interchanged under appropriate circumstances so that the embodiments of the present application described here can be implemented in an order other than those illustrated or described here. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products, or devices.

[0174] It should be understood that in this application, "at least one (item)" means one or more, and "a plurality" means two or more. "And / or" is used to describe the association relationship of associated objects, indicating that there can be three relationships. For example, "A and / or B" can mean: only A exists, only B exists, and both A and B exist at the same time. Among them, A and B can be singular or plural. The character " / " generally indicates that the associated objects before and after are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single items (items) or plural items (items). For example, at least one (item) of a, b, or c can mean: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0175] In several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the above division of units is only a logical function division. In actual implementation, there can be other division methods. For example, multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the displayed or discussed coupling or direct coupling or communication connection to each other can be through some interfaces. The indirect coupling or communication connection of devices or units can be in electrical, mechanical or other forms.

[0176] The units described above as separate components may or may not be physically separated. The components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0177] In addition, each functional unit in various embodiments of this application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0178] When the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on such an understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods of various embodiments of this application. The aforementioned storage medium includes: various media that can store programs, such as USB flash drives, mobile hard disks, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical discs.

[0179] The preferred embodiments of the embodiments of this application have been described above with reference to the accompanying drawings, and thus do not limit the scope of the rights of the embodiments of this application. Any modifications, equivalent replacements, and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of this application shall be within the scope of the rights of the embodiments of this application.

Claims

1. A risk prediction method for urban system evolution, characterized in that, The method includes: Obtaining target city system data, target city constraint rules, and urban planning requirements of the target city system; Based on a plurality of preset urban composition dimensions, performing data screening on the target city system data to obtain urban composition basic data matching each of the urban composition dimensions; wherein, the urban composition dimensions include at least one of an urban land dimension, an urban economy dimension, an urban population dimension, an urban housing price dimension, and an urban traffic dimension; Based on the target city constraint rules, inputting the urban composition basic data into a pre-trained urban evolution prediction model for urban evolution prediction to obtain target urban evolution data of the target city system; Based on the urban planning requirements, performing risk identification on the target urban evolution data to obtain target urban evolution risk data.

2. The method according to claim 1, characterized in that The target city constraint rules include target land constraint rules, target economic constraint rules, target population constraint rules, target housing price constraint rules, and target traffic constraint rules; the urban evolution prediction model includes a land evolution sub-model, an economic evolution sub-model, a population employment evolution sub-model, a housing price evolution sub-model, and a traffic evolution sub-model; the urban composition basic data includes urban land data, urban economic data, urban population data, urban housing price data, and urban traffic data; The step of, based on the target city constraint rules, inputting the urban composition basic data into the pre-trained urban evolution prediction model for urban evolution prediction to obtain target urban evolution data of the target city system, includes: Based on the target land constraint rules, inputting the urban land data into the land evolution sub-model for land use evolution prediction to obtain target land evolution data; Based on the target economic constraint rules, inputting the target land evolution data and the urban economic data into the economic evolution sub-model for economic evolution prediction to obtain target economic evolution data; Based on the target population constraint rules, inputting the target economic evolution data and the urban population data into the population employment evolution sub-model for population employment evolution prediction to obtain target population employment evolution data; Based on the target housing price constraint rules, inputting the target population employment evolution data, the target land evolution data, and the urban housing price data into the housing price evolution sub-model for housing price evolution prediction to obtain target housing price evolution data; Based on the target traffic constraint rules, inputting the target housing price evolution data, the target land evolution data, the target population employment evolution data, and the urban traffic data into the traffic evolution sub-model for traffic evolution prediction to obtain target traffic evolution data; Based on the target land evolution data, the target economic evolution data, the target population employment evolution data, the target housing price evolution data, and the target traffic evolution data, determining the target urban evolution data of the target city system.

3. The method according to claim 2, characterized in that, Based on the above-mentioned target land constraint rules, input the urban land data into the land evolution sub-model for land use evolution prediction to obtain target land evolution data, including: Based on the above-mentioned target land constraint rules, use the land evolution sub-model to predict the land area planning of the urban land data to obtain the target land use area; Based on the target land use area, predict the land planning distribution of the urban land data to obtain the land use categories; Based on the land use categories, predict the proportion of land use categories of the urban land data to obtain the proportion of land use categories; Based on the proportion of land use categories, identify the degree of land use category mixing in the target urban area of the urban land data to obtain the urban land use mixing degree; Identify the location accessibility of the target urban area to obtain the urban location accessibility; Determine the target land evolution data based on the target land use area, the land use categories, the proportion of land use categories, the urban land use mixing degree, and the urban location accessibility.

4. The method according to claim 2, wherein Based on the above-mentioned target economic constraint rules, input the target land evolution data and the urban economic data into the economic evolution sub-model for economic evolution prediction to obtain target economic evolution data, including: Based on the above-mentioned target economic constraint rules, use the economic evolution sub-model to predict the production economic planning of the urban economic data to obtain production economic data; Predict the population economic planning of the urban economic data to obtain population economic data; Based on the production economic data, the population economic data, and the target land evolution data, predict the employment economic planning of the urban economic data to obtain employment economic data; Determine the target economic evolution data based on the production economic data, the population economic data, and the employment economic data.

5. The method according to claim 4, characterized in that Based on the above-mentioned target population constraint rules, input the target economic evolution data and the urban population data into the population employment evolution sub-model for population employment evolution prediction to obtain target population employment evolution data, including: Based on the above-mentioned target population constraint rules, input the target land evolution data and the urban population data into the population employment evolution sub-model for population residential distribution evolution prediction to obtain population residential distribution data; Based on the employment economic data, predict the population employment distribution evolution of the urban population data to obtain population employment distribution data; Determine the target population employment evolution data based on the population residential distribution data and the population employment distribution data.

6. The method according to claim 5, characterized in that Based on the above-mentioned target housing price constraint rules, input the target population employment evolution data, the target land evolution data, and the urban housing price data into the housing price evolution sub-model for housing price evolution prediction to obtain target housing price evolution data, including: Based on the target housing price constraint rule, feature extraction is performed on the target population employment evolution data through the housing price evolution sub-model to obtain population employment evolution features, feature extraction is performed on the target land evolution data to obtain land evolution features, feature extraction is performed on the urban land data to obtain urban land features, feature extraction is performed on the urban population data to obtain urban population employment features, and feature extraction is performed on the urban housing price data to obtain urban housing price features; Based on the population employment evolution features, the land evolution features, the urban land features, the urban population employment features and the urban housing price features, housing price regression prediction is performed to obtain the target housing price evolution data.

7. The method according to claim 2, wherein The traffic evolution sub-model includes a total traffic demand prediction network and a traffic path flow prediction network; Based on the target traffic constraint rule, inputting the target housing price evolution data, the target land evolution data, the target population employment evolution data and the urban traffic data into the traffic evolution sub-model for traffic evolution prediction to obtain target traffic evolution data, including: Based on the target traffic constraint rule, inputting the target housing price evolution data, the target land evolution data, the target population employment evolution data and the urban traffic data into the total traffic demand prediction network for traffic demand prediction to obtain the total traffic volume; Inputting the total traffic volume into the traffic path flow prediction network for traffic path prediction to obtain traffic paths; Obtaining multiple traffic segments corresponding to the traffic paths and calculating the traffic cost of each traffic segment; Allocating the total traffic volume to each traffic segment according to the traffic cost to obtain the segment travel flow corresponding to each traffic segment; Determining the target traffic evolution data according to the total traffic volume and the segment travel flow.

8. The method according to any one of claims 1 to 7, characterized in that, The risk identification of the target urban evolution data based on the urban planning requirements to obtain the target urban evolution risk data includes: Performing risk type identification on the target urban evolution data based on the urban planning requirements to obtain the target risk categories; Performing risk category level identification on the target urban evolution data based on the target risk categories to obtain the target urban evolution risk data.

9. An electronic device, characterized in that, Including: A memory and a processor, the memory stores a computer program, and when the processor executes the computer program, the risk prediction method for urban system evolution as described in any one of claims 1 to 8 is implemented.

10. A computer-readable storage medium, characterized in that, The storage medium stores a program, and when the program is executed by the processor, the risk prediction method for urban system evolution as described in any one of claims 1 to 8 is implemented.

Images