CN116823578A - Intelligent city planning system and method based on big data analysis - Google Patents

Abstract

The invention relates to an intelligent city planning system and method based on big data analysis. The method comprises the following modules: the planning scheme optimizing module is used for collecting city related big data, storing the collected big data, cleaning and preprocessing the collected big data, analyzing the cleaned and preprocessed data, making targets and indexes of intelligent city planning, constructing a model of intelligent city planning, evaluating a generated planning scheme and optimizing and adjusting the planning scheme. The system and method of the present invention has a number of potential benefits including data driven decision making, prediction and planning optimization, improved efficiency and sustainability, enhanced public participation and transparency, rapid response and sensitivity, and improved city quality and resident satisfaction. These effects help to achieve a more intelligent, sustainable and affordable urban development.

Description

Intelligent city planning system and method based on big data analysis

Technical Field

The invention relates to an intelligent city planning system and method based on big data analysis.

Background

While intelligent city planning systems based on big data analysis currently have many advantages, there are also some drawbacks and shortcomings, including the following: 1. data privacy and security: the use of big data in intelligent city planning systems requires a large amount of data collection and storage, a large amount of sensitive information related to individuals, businesses and institutions. This may raise data privacy and security issues such as data leakage, abuse, and unauthorized access. 2. Data quality and reliability: the quality and reliability of big data is critical for intelligent city planning. However, the quality of data may suffer from loss, errors and inaccuracies, thus requiring data cleaning and preprocessing. In addition, deviations and errors in the source of the data and the method of acquisition may also exist. 3. Data ownership and usage rights: urban data relates to a number of data owners and users, including governments, businesses, and individuals. Determining ownership and usage rights of data is a complex problem involving legal, ethical, and ethical aspects of the application. 4. Lack of interdisciplinary collaboration: intelligent city planning systems require collaboration across multiple discipline areas, including city planning, data science, social science, and the like. However, current collaboration and collaboration mechanisms are not yet complete, and there may be information islands and subject barriers. 5. Artificial deviation and limitation: while big data analysis may provide objective data support, the decision process is still impacted by the subjective judgment, bias, and limitations of the decision maker. The background, knowledge level and preferences of the decision maker may lead to deviations and incomplete accuracy of the decision result. 6. Lack of participation and transparency: intelligent city planning systems require extensive participation in public opinion and participation to ensure transparency and democracy of the planning process. However, in practice, the degree of public engagement varies, and the decision logic and algorithms of smart city planning systems may lack transparency, which makes it difficult to provide opportunities for public understanding and engagement.

In view of the foregoing, smart city planning systems based on big data analysis are also faced with many challenges and shortcomings, requiring further improvements in terms of solving data privacy and security problems, improving data quality and reliability, enhancing interdisciplinary collaboration, promoting public participation, and improving transparency. Meanwhile, related policies and regulations are required to be formulated, the legality and morality of the system are ensured, and factors such as social fairness, rights and interests protection, sustainable development and the like are fully adopted in the decision making process.

Disclosure of Invention

The intelligent city planning system and method based on big data analysis is an innovative method for carrying out city planning and decision support in a data driven mode by utilizing big data technology and analysis method. The method utilizes widely collected data in cities, including sensor data, social media data, traffic data, environmental data and the like, and helps decision makers to better know the current situation of cities, predict future development trends and formulate more scientific and effective planning strategies through integration, cleaning, analysis and modeling.

The invention solves the technical problems as follows: an intelligent city planning system based on big data analysis comprises the following modules: a data collection module for collecting city related big data including, but not limited to, demographics, traffic flow, environmental data: a data storage module for storing the collected big data and providing data retrieval and management functions:

The data cleaning and preprocessing module is used for cleaning and preprocessing collected big data to remove noise and process missing values and abnormal values: a data analysis module for analyzing the cleaned and preprocessed data, including data mining, machine learning, and statistical analysis:

the planning target setting module is used for making targets and indexes of intelligent city planning and optimizing according to data analysis results: a planning model construction module for constructing a model of intelligent city planning, comprising a space model, a network model and an optimization model: a planning scheme generating module for generating an intelligent city planning scheme according to the planning model and the target setting:

and evaluating the generated planning scheme, wherein the planning scheme comprises a feasibility analysis module, a risk assessment module and an effect prediction module: and a planning scheme optimizing module for optimizing and adjusting the planning scheme based on the evaluation result: and the visual display module is used for displaying the planning scheme and the analysis result in a graphical mode and providing an visual intelligent city planning visual interface.

Further, the data collection module further comprises a sensor data collection sub-module, a social media data collection sub-module and a public data platform interface sub-module; the data analysis module further comprises a trend analysis sub-module, a correlation analysis sub-module and a prediction modeling sub-module; the planning model construction module further comprises a space layout model sub-module, a traffic network model sub-module and a resource allocation model sub-module;

The planning scheme evaluation module further comprises an economic evaluation sub-module, an environment evaluation sub-module and a social evaluation sub-module; the planning scheme optimizing module further comprises a multi-objective optimizing sub-module and a genetic algorithm optimizing sub-module; the visual display module further comprises a map display sub-module, a chart display sub-module and a virtual reality display sub-module.

An intelligent city planning method based on big data analysis comprises the following steps:

s1, collecting big data related to cities;

s2, cleaning and preprocessing the collected big data;

s3, analyzing the cleaned and preprocessed data;

s4, formulating targets and indexes of intelligent city planning;

s5, constructing an intelligent city planning model;

s6, generating an intelligent city planning scheme;

s7, evaluating the generated planning scheme;

s8, optimizing and adjusting a planning scheme;

s9, displaying a planning scheme and an analysis result;

further, the sensor data collection sub-module: for collecting data from the sensor device; the sensor data collection sub-module is preferably a physical device and is used for monitoring the environment including but not limited to temperature, humidity and air pressure; the sensor data collection submodule comprises a physical sensor, a collection circuit, a microcontroller and a phase software tool, and is responsible for reading sensor data, processing, storing and transmitting;

The social media data collection sub-module: for collecting data from a social media platform; through interaction with an API interface of the social media platform, data related to cities, including but not limited to position check-in, comments and text, published by a user on the platform are obtained; the social media data collection submodule comprises a data acquisition module, an API integration and an authentication mechanism; the public data platform interface submodule comprises: the method comprises the steps of interacting with a public data platform to obtain public data related to cities;

the trend analysis submodule is used for determining trends and modes in data; further the trend analysis sub-module is used for analyzing the change trend of the data, including but not limited to seasonal change, periodic change or long-term trend in the time series data; the association analysis sub-module is used for identifying association relations and relativity in the data; the association analysis submodule further helps to determine the association degree and potential causal relation between different data under given conditions; the association analysis is in the fields of market basket analysis, user behavior analysis and recommendation systems;

the prediction modeling module is used for constructing a model based on historical data and predicting future trend and behavior by using the model; future development of the data is predicted using different statistical and machine learning algorithms, including but not limited to regression analysis, time series analysis, neural networks.

Further, the space layout model submodule is used for simulating and analyzing space layout and land utilization conditions in cities; the space layout model sub-module is further used for helping planners and decision makers understand the purpose and function distribution of different areas of the city, predicting land requirements and optimizing land utilization; the space layout model submodule analyzes and simulates based on Geographic Information System (GIS) data, demographic data and land use planning input so as to support city planning and land management decision-making;

the traffic network model submodule is used for modeling and simulating an urban traffic system; simulating roads, traffic flow, road congestion and traffic and transportation demands, and further evaluating traffic conditions, optimizing traffic planning and predicting traffic demands; the traffic network model submodule analyzes and simulates traffic survey data, traffic flow data and road network data input to assist traffic planning and traffic management decision-making;

the resource allocation model sub-module is used for evaluating and optimizing allocation and utilization of urban resources; the resource allocation model submodule further helps to understand the requirements and supply conditions of different resources in the city, and deduces an optimal resource allocation scheme through simulation and optimization algorithm, including but not limited to energy use, water resource management and public facility planning; the resource allocation model submodule further performs resource analysis and decision support based on resource investigation data, supply and demand situation data and cost benefit analysis input.

Further, the economic evaluation submodule is used for evaluating economic benefits and cost benefits of projects or policies; the economic evaluation submodule further helps to evaluate potential returns, market influences, employment opportunities and financial benefits of investment projects; the method of the economic evaluation sub-module comprises net present value analysis, internal yield and cost benefit analysis;

the environment evaluation submodule is used for evaluating potential influence and sustainability of the project or policy on the environment; the environment evaluation submodule is further used for helping to identify and evaluate problems in terms of resource utilization, pollution, ecological damage and carbon footprint environment and providing suggestions for environmental protection and sustainable development; the environmental assessment sub-module uses Environmental Impact Assessment (EIA) and Life Cycle Assessment (LCA) methods to perform environmental risk assessment and environmental benefit analysis;

the social evaluation sub-module is used for evaluating potential influence of projects or policies on society and social sustainability; the social evaluation submodule helps to identify and evaluate social problems of social smoothness, fairness, social benefits and community participation, and provides social development and social sense suggestions; the social evaluation sub-module further uses social impact evaluation (SIA) and sustainability evaluation methods to analyze and evaluate social impact and social benefit.

Further, the objective optimization submodule is used for solving the problem of searching an optimal value of an objective function under a given constraint condition; further the objective optimization submodule helps to determine the optimal decision variable settings to maximize or minimize the result of the objective function; the target optimization sub-module searches for an optimal solution by using different optimization algorithms including, but not limited to, linear programming, nonlinear programming and integer programming; target optimization is widely used in various fields including but not limited to engineering design, operations research, financial investment;

the genetic algorithm optimization submodule is an optimization method based on a biological evolution principle; the genetic algorithm optimization submodule simulates the genetic and evolutionary processes of the nature, and searches for an optimal solution by creating and evolving a group of candidate solutions; the genetic algorithm optimization submodule uses an evaluation function to moderately evaluate candidate solutions and generates new-generation solutions through selection, crossover and mutation operations; the genetic algorithm optimization submodule is suitable for complex problems and optimization in a high-dimensional space, and comprises parameter optimization and machine learning model parameter adjustment;

The genetic algorithm optimization submodules are used independently of each other and are also used in combination to solve the complex optimization problem; including without limitation: genetic algorithms are used as a method of target optimization to take advantage of their broad search space and global search capabilities; the specific implementation and technical details will depend on the specific problem and optimization objectives;

the target optimization submodule is realized by utilizing different optimization strategies and technologies based on mathematical optimization theory and algorithm; the genetic algorithm optimization submodule realizes the selection, crossing and mutation operations in the genetic algorithm and performs iterative search by combining with moderate evaluation and evolution processes; the implementation uses programming languages and optimization libraries, including, but not limited to, sciPy library of Python, optimization toolkit of MATLAB.

Further, the map display submodule is used for displaying geographic information and space data on a visual interface; the map display submodule helps a user to intuitively understand geographical position, topography and regional distribution information; the map display submodule further provides map display functions including map marking, region coloring and labeling and map interaction functions including zooming in and zooming out, dragging and inquiring; map presentation is implemented using map library and Geographic Information System (GIS) technology, including but not limited to Google Maps APIs, leaflet, arcGIS;

The chart display submodule is used for displaying data in a chart form on a visual interface; the chart display submodule further helps users understand the trend, association and distribution of data; the chart showing submodule further provides various types of charts, including, but not limited to, a line chart, a bar chart, a pie chart and a scatter chart, and allows users to interact, including, but not limited to, data screening, chart scaling and data labels; the chart shows implementation using a chart library and data visualization tools, including without limitation matplotlib, d3.Js, tableau;

the virtual reality display submodule is used for displaying data or scenes in a virtual reality environment; the virtual reality display submodule helps users to experience and interact immersively in an immersive manner; the virtual reality display submodule is further combined with virtual reality equipment, and comprises a head-mounted display and a handle controller, so that a realistic virtual environment is created, wherein the realistic virtual environment comprises virtual earth, a building model and 3D data visualization; virtual reality presentation is implemented using virtual reality development tools and software platforms, including without limitation Unity, unreal Engine.

Further, the step of the data cleaning and preprocessing module comprises the following steps:

s1, collecting data in various relevant fields, including population data, traffic data and environmental data; data comes from sensors, monitoring devices, public departments, sources of social media diversification;

s2, cleaning the collected data, including removing repeated data, processing missing values and solving abnormal values;

s3, converting the original data into a format for analysis; data format conversion, unit conversion and data standardization operation are needed to ensure the consistency and comparability of data;

s4, merging and integrating data from different sources and different data sources; data matching and data association operations are involved to obtain a more comprehensive and comprehensive data set;

s5, converting the data into a unified format and standard; the method comprises the steps of unifying a time format, a geographic coordinate format and a unit standard so as to facilitate subsequent calculation and analysis;

s6, sampling and sampling the large-scale data to reduce the calculated amount and improve the efficiency; the sampling method selects random sampling and uniform sampling according to the requirements;

s7, dividing the data set into a training set, a verification set and a test set so as to perform model training, verification and evaluation; the dividing ratio is adjusted according to the requirements of specific tasks and algorithms;

S8, marking the data and generating labels so as to facilitate supervision of learning and modeling of classification problems; labeling is performed manually, also with automated tools.

Further, the specific working steps of the planning target setting module include:

s1, selecting and setting a proper planning target from a target library according to the characteristics, the requirements and the planning standard of a city

S2, acquiring related city data through a data collection module, and processing and analyzing the data by using a data analysis tool to know the current city condition and trend;

s3, setting weight of each planning target aiming at the set planning targets so as to reflect importance and priority of the targets;

s4, calculating the achievement condition of each target by using a data analysis tool, and evaluating according to the actual condition; including without limitation, that the goal is not achieved or not reasonable, and adjustments and resets are made.

Based on the technical scheme, the invention can bring the following advantages:

1. data driven decision: the intelligent city planning system is capable of collecting, integrating and analyzing a large amount of city data, helping decision makers make decisions based on the data. This helps reduce the impact of subjective bias and subjective judgment, improving the objectivity and scientificity of the planning decisions.

2. Prediction and planning optimization: by analyzing and modeling big data, the intelligent city planning system can predict future development trends of cities, including population growth, traffic flow, environmental influence and the like. This may help the planner to better optimize city planning and infrastructure construction to suit future needs.

3. Efficiency and sustainability are improved: the intelligent city planning system can help planners to better manage city resources and services, and improve efficiency and sustainability. By analyzing the big data, the resource utilization optimization scheme such as energy management, traffic optimization, garbage disposal and the like can be identified, so that the running efficiency and the environment sustainability of the city are improved.

4. Enhancing public participation and transparency: the intelligent city planning system can promote the participation of the public and the opinion feedback, and the participation of the public is increased in the decision making process. The system can provide visual presentation of data and models, show effects and influences of different planning options to the public, and enhance transparency and fairness of decisions.

5. Rapid response and sensitivity: the intelligent city planning system can monitor and analyze city data in real time and quickly discover problems and changes. This enables the planner to quickly make countermeasures, improving city sensitivity and ringing capabilities, such as traffic control, natural disaster management, etc.

6. Improving city quality and resident satisfaction: through data analysis and planning optimization, the intelligent city planning system is beneficial to improving the quality of cities and satisfaction of residents. For example, optimizing traffic flow may reduce traffic congestion, improving urban living environments; and urban green space and public facilities are reasonably planned, so that the life quality of residents can be improved, and the like.

In summary, the intelligent city planning system and method based on big data analysis has a number of potential benefits including data driven decision making, prediction and planning optimization, efficiency and sustainability improvement, public participation and transparency enhancement, quick response and sensitivity improvement, city quality improvement and resident satisfaction improvement. These effects help to achieve a more intelligent, sustainable and affordable urban development.

Drawings

Fig. 1 is a flowchart of the whole intelligent city planning system based on big data analysis.

Fig. 2 is a flowchart of the whole intelligent city planning method based on big data analysis.

FIG. 3 is a flow chart of the steps of the data cleaning and preprocessing module.

Description of the embodiments

The following describes the embodiments of the present invention in detail with reference to the drawings.

Examples: an intelligent city planning system based on big data analysis comprises the following modules: and a data collection module: for collecting city-related big data including, but not limited to, demographics, traffic flow, environmental data, etc.;

The collection module for implementing city planning requires the following steps and aspects:

first, it is necessary to specify the specific data types and metrics required for city planning and decision making. This may involve demographic data, traffic flow data, environmental data, and the like. The specific data requirements are determined according to the characteristics, scale and development requirements of the city. Next, the source of the data needs to be determined. The data may come from a variety of sources, such as government agencies, municipal services, third party data providers, sensors, and the like. It is important to ensure the reliability and accuracy of the data. Establishing partnership with relevant institutions and formulating data sharing protocols can ensure the acquisition and legal use of data.

And determining a specific data collection mode according to the characteristics and the reliability of the data source. This may include various ways of online data crawling, data questionnaires, periodic data reporting, sensor data, and so forth. The data collection mode is convenient to operate and manage, and timeliness and integrity of the data are ensured.

During the data collection process, measures need to be taken to ensure the quality and privacy protection of the data. This may include data cleansing and preprocessing to remove outliers and erroneous data. Meanwhile, a data security and privacy protection mechanism is established to protect personal privacy and security of sensitive information.

The collected data typically comes from different data sources and formats, requiring data integration and storage. The method can be realized by establishing a data warehouse or a data lake iso-centering storage mode or adopting cloud storage and other technical means. And ensuring the accessibility and the security of the data.

Finally, analysis and modeling is performed using the collected data to extract useful information and knowledge. And mining and modeling data by adopting a data analysis and machine learning algorithm so as to support the requirements of intelligent city planning and decision making.

The data is finally analyzed and modeled by utilizing the data, and effective data support is provided for the intelligent city planning system. There is a need to integrate technical, resource and legal issues and to conduct close collaboration and negotiations with related institutions and stakeholders.

And a data storage module: the system is used for storing the collected big data and providing efficient data retrieval and management functions;

data cleaning and preprocessing module: to clean and preprocess collected big data to remove noise, process missing values and outliers, the following methods and techniques may be employed:

1. Noise removal: a filter is used: filters in digital signal processing, such as mean filtering, median filtering, gaussian filtering, etc., are used to remove noise from the signal. Setting a threshold value: values below or above a certain threshold are regarded as noise data and removed or replaced according to the noise characteristics and the data distribution.

2. Missing value processing: deletion of missing values: for cases where there is less data missing, the samples, features or fields containing the missing values may be deleted directly. Interpolation filling: for numerical data, the missing values may be filled using means, medians, modes, linear interpolation, and the like. For categorical data, the most common category fill may be used. Predictive filling: and (5) utilizing other characteristics or existing data to build a prediction model to predict the missing value and fill in.

3. Outlier processing: based on a statistical method: statistical features of the data, such as mean and standard deviation, are used to identify and reject outliers. The phase processing can be performed by setting a threshold value, and regarding data exceeding the threshold value range as an outlier. Based on a machine learning algorithm: outliers are identified and processed using anomaly detection algorithms, such as clustering, isolated forests, nearest neighbors, and the like. Manual auditing: and (5) checking and judging the data through manual checking and field expertise to determine whether abnormal values exist or not, and performing phase processing.

The above methods may be used alone or in combination, the specific implementation depending on the nature and requirements of the data. In practice, this attention is also paid to keeping records and documents of the data processing for traceability and verification. In addition, the periodic data cleansing and pre-processing scrutiny is performed to ensure that the data remains accurate and reliable throughout.

And a data analysis module: to perform data mining, machine learning, and statistical analysis on the cleaned and preprocessed data, the method may be implemented as follows:

first, exploratory analysis of data is performed, including statistical description, data visualization, correlation analysis, and the like. These operations may help understand the distribution, relationships, and characteristics of data and discover potential patterns and trends.

And selecting proper characteristics according to the analysis target, and performing characteristic engineering operation. This may include feature transformation, feature derivation, feature selection, etc. By extracting and constructing meaningful features, modeling and prediction accuracy can be improved.

A suitable data modeling method, such as a machine learning algorithm, a statistical model, etc., is selected. The data is divided into a training set, a verification set and a test set according to analysis requirements, and a data model is built by using the training set.

And evaluating and optimizing the established model to improve the performance and generalization capability of the model. The model is evaluated and selected using evaluation metrics such as accuracy, precision, recall, etc. For the machine learning model, operations such as super parameter tuning and cross verification can be performed.

Predictions and inferences are made using the built data model. The models may be utilized for classification, regression, clustering, or other tasks according to actual needs. Interpretation and interpretation of the predicted and inferred results are performed to support decision making and use.

The analysis results are interpreted and visualized for ease of understanding and communication. Results are presented in the form of charts, images, reports, etc., and provide explanation and insight. In practice, various data analysis and modeling tools may be utilized, such as pandas, scikit-learn, matplotlib in Python, etc., or tidyverse, caret, ggplot2 in R language, etc. According to the characteristics and analysis requirements of the data, a proper method and a proper tool are selected, and are analyzed and interpreted by combining with the technical knowledge of the field.

Notably, data modeling and analysis is an iterative process requiring constant verification, adjustment, and improvement. Meanwhile, attention is paid to problems in terms of interpretability, robustness, fairness and the like of the model so as to ensure the reliability and reliability of analysis results.

Planning target setting module: to achieve the objective and the index of intelligent city planning and optimize according to the data analysis result, the following steps and methods can be adopted:

firstly, the targets of intelligent city planning are defined, such as improving the life quality of residents, optimizing the resource utilization, improving the city management efficiency and the like. Indicators of phase, such as air quality index, traffic flow, energy consumption, etc., are then determined for measuring the degree of achievement of the objective.

Data related to smart city planning is collected and integrated, including demographic data, traffic data, environmental data, energy data, and the like. Multiple sources of data, such as sensors, social media, government agencies, etc., may be acquired to ensure the integrity and accuracy of the data.

The collected data is processed and analyzed using data analysis and modeling techniques. Methods such as statistical analysis, machine learning, data mining, etc. can be used to explore potential patterns and associations in the data. And establishing a proper model for predicting and optimizing targets and indexes of the intelligent city planning.

And according to the result of the data analysis, evaluating the actual conditions of the targets and the indexes, and finding problems and potential opportunities. Based on the analysis results, optimization strategies and measures for phasing are formulated to improve the intelligent city planning implementation.

Simulation and verification are performed using the built model and optimization strategy. And evaluating the effect and feasibility of the optimization strategy through a simulation experiment. And adjusting and improving according to the simulation result until an optimal scheme or a scheme close to the optimal scheme is found.

In the intelligent city implementation process, the change of data and indexes is continuously monitored and timely fed back to decision makers and related departments. And according to the feedback result, adjustment and improvement are carried out, and the realization and continuous optimization of the intelligent city planning target are ensured. In the implementation process, a proper data platform and analysis environment need to be established, including a data management system, a data analysis tool, a visualization platform and the like. Meanwhile, the intelligent city planning system is cooperated with related departments and stakeholders to jointly promote the establishment and implementation of intelligent city planning.

The planning model construction module: to implement the model for constructing intelligent city planning and the planning scheme generation module, the following methods and techniques may be adopted:

geographic Information System (GIS): and collecting, managing and analyzing the spatial data related to the city by utilizing a GIS technology. Spatial data processing, visualization, and spatial analysis, such as determining landmark locations, land utilization types, traffic networks, etc., may be performed using GIS software.

Through space statistics and mode analysis methods, laws and features of urban space distribution are revealed. And the techniques of point mode analysis, nuclear density analysis, spatial clustering and the like can be used for providing spatial reference and prediction information for intelligent city planning.

Traffic network model: and analyzing urban traffic flow, bottleneck and congestion conditions by using traffic network data and a simulation model, and providing decision support for traffic planning and optimization. Traffic conditions can be predicted and road network layout and traffic management strategies can be optimized by using traffic simulation software and network model algorithms.

And constructing a city communication network model, and analyzing coverage, network performance and data transmission capacity of a city communication infrastructure. By optimizing network planning and layout, more reliable and efficient communication services are provided.

And optimizing the intelligent city planning problem by using a linear programming method and an integer programming method. For example, for land use planning, resource allocation, etc., a linear programming model may be used to optimize decision variables and objective functions to achieve an optimal solution.

For the problem of multiple decision target conflicts, a set of approximate non-inferior solutions can be solved by using a multi-target optimization method, such as a genetic algorithm, an ant colony algorithm and the like, and the balance and the selection can be performed.

Using the framework and method of DSS, planning models and data are integrated together for generating intelligent city planning schemes. Through a user interface and algorithm design, a planning scheme meeting the requirements can be automatically generated according to the input targets, constraints and assumptions.

And generating a scheme for intelligent city planning by using intelligent algorithms such as genetic algorithm, simulated annealing and the like. The algorithm with strong adaptability and high searching efficiency can be designed based on the characteristics and constraint conditions of city planning. In practice, it is necessary to build appropriate datasets and model libraries for storing and managing urban space data, network data, optimization models, etc. At the same time, there is a need to continuously adjust and refine models to accommodate changes in different cities and planning requirements.

Planning scheme evaluation module: to enable evaluation of the generated planning schemes, including feasibility analysis, risk assessment, effect prediction, etc., the following methods and techniques may be employed:

the feasibility of the techniques and solutions employed in the planning scheme is assessed. For example, the availability, cost effectiveness, implementation difficulties, etc. of the analysis-related techniques.

Consider the economic viability of a planning scheme, including budget estimation, revenue analysis, return on investment, and the like. And evaluating the economic benefit and the sustainability of the planning scheme through the financial index. And adopting a planning scheme to influence society and environment. Social impact assessment, environmental assessment, sustainability analysis, and the like are performed to ensure that the planning scheme is consistent with the sustainable development goals of society and environment.

Risk factors that may face the planning scheme are identified, including technical risk, policy risk, economic risk, and the like. And identifying and classifying risk factors through expert opinion, data analysis and potential problem analysis.

The identified risk factors are evaluated, including analysis in terms of risk probability, risk impact, risk controllability, and the like. And (5) evaluating and prioritizing the risks by adopting a qualitative and quantitative method.

For the identified risk factors, phased risk pair policies and measures are formulated. For example, risk avoidance, risk transfer, risk control, etc., to reduce the impact of risk on the implementation of the planning scheme.

And simulating the implementation effect of the planning scheme by using data simulation and emulation technology. The influence of the planning scheme on urban operation, people flow, traffic and the like can be predicted by adopting an urban model, a traffic simulation model, an environment model and the like.

By the social economic influence assessment method, the influence of the planning scheme on economy, employment, social public land level and the like is analyzed. The effect that the planning scheme may produce is predicted by index evaluation, questionnaire, etc.

In practice, implementation of the planning scheme evaluation module may be supported by related tools and techniques, such as risk assessment software, simulation software, cost-effectiveness analysis tools, and the like.

In addition, there is a need to refer to related specifications, standards and guidelines, such as national and regional planning standards, environmental assessment guidelines, sustainable development guidelines, etc., to ensure the scientificity and reliability of the assessment process.

The assessment results are fed back to planning teams and decision makers in time for further improvement and adjustment. Based on the evaluation result, the risk pair strategy of the phase is determined, and scheme optimization and adjustment are considered to achieve a better planning effect. It should be noted that planning scheme evaluation is a complex process involving a number of relevant factors and variables. Therefore, the proposal fully utilizes the expertise and technology in the implementation process, and ensures the comprehensiveness, the accuracy and the credibility of the evaluation result by means of the cross cooperation and the expert opinion of multiple disciplines. Finally, the planning scheme evaluation module is not just a one-time process, but rather a continuous loop iteration process. With the change and development of cities, the planning schemes need to be continuously updated and re-evaluated, so that the sustainability and the adaptability of the intelligent cities are ensured.

The optimization module for realizing the planning scheme optimizes and adjusts the planning scheme based on the evaluation result so as to meet different planning requirements, and the following method and technology are adopted:

According to the evaluation result and the planning requirement, the optimization target of the planning scheme, such as economic benefit, environmental influence, social public average and the like, is clearly defined. Ensuring scalability and operability of the optimization objective.

Planning variables that can be adjusted, such as land use type, road layout, building design, etc., are determined. These variables are used as decision variables in the optimization process.

Based on a multi-objective optimization theory and method, a mathematical model is established, and an evaluation result and an optimization objective are combined. For example, using a multi-objective genetic algorithm, a multi-objective particle swarm algorithm, or the like, an optimal solution that balances between multiple optimization objectives is sought.

And determining constraint conditions to be met by the planning scheme according to the planning requirements and the constraint conditions. Such as building height restrictions, traffic flow restrictions, environmental quality standards, etc.

And incorporating the constraint conditions into the optimization model, and establishing a constraint optimization model. Constraint optimization algorithms and methods, such as linear programming, integer programming, constraint genetic algorithms, etc., may be used to find optimal solutions that meet constraints.

And optimizing a planning scheme by using an intelligent algorithm. The intelligent algorithm has strong searching and optimizing capability and can be used for processing complex planning problems. Such as genetic algorithms, simulated annealing, ant colony algorithms, and the like.

And establishing an adaptability function for evaluating the merits of the planning schemes of different parameter combinations. The fitness function can be designed by combining the evaluation result, the planning target, the constraint condition and other factors.

And (3) carrying out simulation experiments and verification on the planning scheme by using the established optimization model and optimization algorithm. Through simulation and verification, the effect and feasibility of the optimization scheme are evaluated. And adjusting and improving according to the simulation result to find an optimal or near-optimal planning scheme.

Planning is a dynamic process that requires continuous optimization and adjustment. And according to the new requirements and the evaluation result, iterative optimization is continuously carried out, and the quality and effect of the planning scheme are improved. And (5) incorporating actual data and feedback information in the planning implementation process into an optimization model for learning and improvement. And optimizing a planning scheme according to the actual effect and the feedback result, and ensuring the adaptability and the sustainability of the planning scheme.

Furthermore, in the implementation process, the optimization target and the limitation condition of the planning are explicitly planned before the planning scheme is optimized. These goals and conditions may relate to various aspects of economy, environment, society, and technology, and need to be considered in combination.

Data related to the planning scheme is collected and analyzed, including assessment results, geographic data, economic data, and the like. These data will be used to build an optimization model and evaluate the performance of the solution.

And selecting a proper optimization algorithm according to the optimization target and the problem complexity. Common algorithms include genetic algorithms, particle swarm optimization, simulated annealing, and the like. For the multi-objective optimization problem, a multi-objective optimization algorithm can be used for processing.

And establishing a mathematical model to describe the planning scheme and the optimization target thereof according to the evaluation result and the optimization target. This typically involves translating the evaluation index into an optimized objective function and constraining the solution space to meet the planning requirements and constraints.

And optimizing and adjusting the planning scheme by using the selected optimization algorithm and the established optimization model. And searching an optimal or near-optimal solution according to the optimization target and the constraint condition.

And performing simulation experiments and verification on the optimized planning scheme. Through simulation experiments, the effect and feasibility of the optimization scheme are evaluated, and potential problems and improvement space are found.

And feeding back and iterating the optimization scheme according to the actual implementation process and the feedback of the result. According to the actual situation, the planning scheme is adjusted and improved so as to better meet the planning requirements.

And when the planning scheme optimizing module is implemented, the expertise of multiple disciplines and the opinion of domain experts are fully combined. Furthermore, timely communication and collaboration is critical to ensure the feasibility and acceptance of planning schemes. It is also essential to constantly learn and refine optimization models and algorithms to adapt to the changes in different cities and planning requirements.

To realize the visual display module, display the planning scheme and the analysis result in a graphical mode and provide an intuitive intelligent city planning visual interface, the following method and technique can be adopted:

using data visualization tools: the planning scheme and analysis result are converted into the form of interactive charts, graphs, maps and the like for display by means of data visualization tools (such as Tableau, power BI, matplotlib, D3.Js and the like).

And using statistical charts such as bar charts, line charts, box charts, pie charts and the like to reflect key indexes, evaluation results, effect prediction and the like of the planning scheme. The design, layout, effect, etc. of the planning scheme is presented using graphics, images, or animations.

And combining the spatial information of the planning scheme with geographic data by means of GIS software (such as ArcGIS, QGIS and the like), and drawing the geographic spatial distribution of the planning scheme. The area coverage, infrastructure distribution, environmental characteristics, etc. of the planning scheme are shown in the form of a map.

And carrying out space-time analysis by using a GIS technology, and displaying the influence and the change of the planning scheme on the aspects of urban operation, traffic jam, environmental quality and the like.

The planning scheme is displayed in the form of a stereoscopic model through a three-dimensional visualization technology (such as Unity, cityEngine, sketchUp and the like). And restoring the real scene of the planning scheme by using a three-dimensional modeling and rendering technology, and displaying the spatial layout and effects of buildings, roads, communities and the like. By utilizing VR and AR technologies, immersive plan scheme display is provided, so that a user can experience the effect and feel of the plan scheme in person; the user-friendly interactive interface is designed to enable the user to freely browse, explore and manipulate the various layers and details of the planning scheme. Dynamic demonstration and navigation functions are provided, so that a user can observe a planning scheme according to own requirements and with different time scales, distance scales, visual angles and the like.

To assist the user in understanding the effect of changes in the planning scheme on the results, sensitivity analysis and comparison may be performed. For example, the key parameters are adjusted, the variation trend of the analysis result is displayed, and then planning decisions are guided.

Providing a way for users to communicate and feedback to collect user opinion and advice on planning schemes. Through user participation, the visual display module is continuously improved, and user experience and participation are enhanced. And selecting proper visualization methods and technologies according to specific conditions, and flexibly applying various display forms by combining the characteristics and requirements of a planning scheme so as to present an intuitive and easily-understood intelligent city planning visualization interface.

The data collection module further comprises a sensor data collection sub-module, a social media data collection sub-module and a public data platform interface sub-module; the data analysis module further comprises a trend analysis sub-module, a correlation analysis sub-module and a prediction modeling sub-module; the planning model construction module further comprises a space layout model sub-module, a traffic network model sub-module and a resource allocation model sub-module; wherein the planning scheme evaluation module further comprises an economic evaluation sub-module, an environmental evaluation sub-module and a social evaluation sub-module; the planning scheme optimizing module further comprises a multi-objective optimizing sub-module and a genetic algorithm optimizing sub-module; the visual display module further comprises a map display sub-module, a chart display sub-module and a virtual reality display sub-module.

An intelligent city planning method based on big data analysis comprises the following steps:

s1, collecting big data related to cities comprises the following steps:

government agency data: government agencies and organizations typically collect and manage various types of urban data such as demographics, traffic flows, land planning, environmental monitoring, and the like. These data resources may be obtained through government open data platforms or data requests by related departments. Public facility data: public transportation, energy supply, waste disposal, water management, etc. utilities also generate large amounts of data that can be retrieved or collected from the relevant public institutions or service providers. Geographic information data: geographic Information System (GIS) data, including spatial information, topography, land utilization, building information, etc., is typically provided by government authorities and geographic information institutions.

Sensor and thing networking equipment:

a large amount of city related data can be collected in real time by utilizing a sensor network in the city, such as a traffic monitoring sensor, a weather observation station, an environmental pollution monitoring device and the like. These sensor networks may be deployed in various locations in a city for collecting traffic flow, environmental quality, noise level, etc.

The intelligent devices and the internet of things devices in the city, such as intelligent home, intelligent traffic systems, intelligent parking systems and the like, can also generate a large amount of data. These devices are typically connected via the internet and can collect and analyze relevant data.

Social media and online platform:

social media platforms, such as Twitter, facebook, instagram, etc., provide a large amount of user-generated data. Through social media APIs and data mining techniques, data can be collected regarding urban life, travel, traffic, and the like. For example, information on urban population flows, public opinion trends, etc. can be obtained by analyzing the user's location tags, published content, and user behavior.

On-line platforms, such as e-commerce websites, shared economy platforms, travel service platforms, etc., can also generate large amounts of city-related data. These platforms typically record information about the user's behavior, transactions, location, etc., and can provide data on urban businesses, trips, etc.

Private sector and third party data provider:

multiple private departments and businesses collect and maintain a large number of city-related data, such as retail sales data, traffic data, property data, and the like. Such data may be obtained through collaboration, purchase, or collaboration agreements with the data provider.

There are many third party data providers that specifically collect and provide city related data. These providers typically cooperate with industries to provide various types of urban data, such as geography, traffic, media, and the like.

Data sharing and collaboration:

partnerships and partners, academic institutions, non-profit organizations, etc., facilitate sharing of city-related data. This may be accomplished by signing data sharing protocols, formulating shared data standards and specifications, and the like.

S2, data cleaning and processing:

when collecting big data related to cities, problems such as inconsistency, missing, errors and the like of the data can be encountered. And (5) cleaning and preprocessing the data to ensure the quality and accuracy of the data.

The collected multi-source data is integrated and normalized for analysis and use. Ensuring consistency and comparability of data.

Data management and storage:

and formulating a data management strategy, including data classification, marking, storage and other specifications. Ensuring easy management and storage of data for subsequent analysis and use of the data.

Large-scale city related data is effectively managed and stored by utilizing big data technology and a platform, such as distributed storage, cloud computing and the like.

Data analysis and mining:

the collected city related data is analyzed using appropriate data analysis methods and techniques, such as statistical analysis, machine learning, data mining, etc. These methods can reveal associations, trends, and patterns between data, extracting useful information and knowledge.

Measurement and prediction model: and (3) establishing a prediction model to predict future development trend, demand and challenges of the city. This may be accomplished by regression analysis, time series analysis, machine learning, etc. based on historical data.

Ethical and privacy protection:

anonymization and desensitization: during data collection and processing, anonymization and desensitization processing are carried out on personal identity and sensitive information so as to protect personal privacy.

Following applicable privacy regulations and regulations, such as the General Data Protection Regulations (GDPR) in europe, the consumer privacy act (CCPA) in california, etc. Ensuring legal use and processing of the data.

Continuous improvement:

and (3) data quality management: a data quality management mechanism is established to monitor and improve the process of data collection, processing and analysis to ensure accuracy, integrity and reliability of the data.

Feedback and verification: continuously communicating with and feeding back by data users, domain experts and users, verifying the validity and availability of data, and timely adjusting and improving data collection strategies. The collection of city-related big data requires the integration of a variety of channels and methods while following privacy protection and legal regulations. Appropriate methods and techniques are employed in the data processing and analysis, and data quality management and improvement is continued. This will provide powerful support for smart city planning and decision making.

S3, analyzing the cleaned and preprocessed data, wherein specific analysis targets and problems are combined, and the data analysis is performed by the following steps and methods:

data exploration and visualization: statistical descriptions and overviews of data are performed, including statistical indicators (e.g., mean, variance, maximum, minimum, etc.) and data distribution. And drawing a statistical chart, a trend chart, a correlation chart and the like of the data by using visualization tools such as charts, graphs and the like, and exploring the relationship, trend and mode among the data.

Descriptive statistical analysis:

and calculating central trends of the data, such as mean, median, mode and the like, and knowing the concentration degree of the data.

The variability of the data, such as variance, standard deviation, range, etc., is calculated to know the degree of dispersion of the data.

And analyzing the distribution of the data, such as normal distribution, bias distribution and the like, and judging the distribution characteristics of the data.

Correlation analysis: and calculating correlation coefficients between the data, such as a pearson correlation coefficient, a spearman correlation coefficient and the like, and judging the correlation between the variables. And drawing a correlation map or thermodynamic diagram, and visualizing correlation relations among the data to help find a correlation mode.

Predictive modeling: and selecting a proper prediction model, such as linear regression, a decision tree, a random forest, a neural network and the like, according to the characteristics of the data and the analysis target. The data are divided into a training set and a testing set, and the performance indexes of the model, such as mean square error, accuracy, recall rate and the like, are obtained through training the model and evaluating the model. Clustering the data samples finds the inherent structure and similarity therein, helping to identify the population, class, etc. in the city. And classifying and analyzing the data samples by using a machine learning algorithm, and classifying the data samples according to some known labels or features to realize automatic classification and identification. : trend analysis is performed on the time series data, and seasonality, periodicity and trending in the data are found, so that references are provided for planning decisions.

The time series data is used for predicting future trend and change, and is helpful for planning future development.

S4, formulating targets and indexes of intelligent city planning is a key step, which can help to define the planning direction and evaluate the planning effect, and the specific substeps are as follows:

s1.1, determining the willingness and the idea of the intelligent city: the wish and core concepts of the intelligent city are defined, such as improving the life quality of residents, promoting sustainable development, improving the running efficiency of the city and the like.

S1.2, researching the current situation and problems of cities: knowing the challenges, pain points and demands faced by current cities. This may be achieved by investigation, data analysis, communication with related departments and stakeholders, etc.

S1.3, making an intelligent city target: and (3) formulating a specific target according to the landscape and the current situation analysis of the intelligent city. The goal should be scalable, achievable, and tightly coupled with smart technology and urban operations, such as increasing digital service coverage, increasing energy efficiency, increasing traffic fluidity, etc.

S1.4, determining key indexes: to evaluate the success of smart city planning, a set of key indicators needs to be determined. These metrics should correspond to the goals established and reflect the progress and effect of the planning implementation. For example, digitization of service usage, energy consumption reduction rate, traffic congestion index, etc.

S1.5. Reference is made to planning standards and guidelines: reference is made to relevant smart city planning standards, guidelines and best practices, such as the ISO/IEC 30182 smart city reference frame, the national or regional smart city planning guidelines, etc. These references may provide guidance and reference to ensure the rationality and feasibility of the targets and indices.

S1.6, making a time frame and milestones: to achieve intelligent city planning goals, time frames and milestones need to be formulated. This helps track and monitor the progress of the implementation of the plan and adjust and optimize it in time.

S1.7. Integrate stakeholders and public participation: targeting and index formulation for intelligent city planning should take into account the opinion and needs of stakeholders and the public. By participating in planning and multiparty collaboration, acceptability and sustainability of the planning is ensured.

Finally, the goals and metrics formulated should be flexible, capable of being adjusted and optimized according to city development and changes. And periodically evaluating and monitoring the realization condition of the index, and timely feeding back and adjusting the planning strategy to realize the sustainable development of the intelligent city.

S5, constructing an intelligent city planning model is a complex task, and various aspects of city development and requirements of stakeholders need to be comprehensively considered. The following steps and methods are as follows: and the application scene and the target of the intelligent city planning model are defined, such as improving traffic fluidity, improving energy efficiency, improving public service and the like.

Various data related to city development is collected and consolidated, including infrastructure data, demographic data, traffic data, energy data, environmental data, and the like. Such data may come from government agencies, public institutions, enterprises, communities, and the like.

And determining the type of an applicable planning model, such as an optimization model, a simulation model, a risk model and the like, according to the problems and the targets.

Variables and constraints in the model are determined based on the specific problem and data. Variables may include construction projects, resource allocation, policy formulation, etc., constraints may include cost limits, environmental protection requirements, sustainable development requirements, etc.

Based on the questions and data, a mathematical function or algorithm of the model is constructed to describe key factors and influencing factors of city development.

And solving and optimizing the model by using an optimization algorithm or a simulation technology to find an optimal planning scheme.

And (5) evaluating the accuracy and the reliability of the model through the verification of the actual data and the scene. The historical data can be used for backtracking testing and compared with the actual results. Meanwhile, the stability and feasibility of the model under different conditions can be evaluated through sensitivity analysis and robustness analysis.

The construction process of the intelligent city planning model should fully participate in various stakeholders and the public. By developing workshops, joint studies and common decisions, the acceptability and sustainability of the model are ensured.

Smart city planning is a dynamic process that requires continuous iteration and modification of the model. Parameters and assumptions of the model are adjusted in time to accommodate new needs and challenges, based on city development and changes. It should be noted that constructing the intelligent city planning model requires the interdisciplinary collaboration and comprehensive application of various methods and techniques, such as big data analysis, artificial intelligence, optimization algorithms, etc. In addition, the establishment and application of the model need to combine the actual situation and the policy environment, and both scientificity and feasibility are considered.

S6, generating an intelligent city planning scheme needs to comprehensively consider the development requirements, the technical feasibility and the participation of stakeholders of the city. The method comprises the following steps:

s1.1, defining planning targets and principles: the goals of intelligent city planning, such as improving resident life quality, increasing energy efficiency, improving traffic fluidity, etc., are clarified. Meanwhile, the planning principle such as sustainable development, social fairness, data safety and the like is determined.

S1.2, analyzing urban development trend and challenges: understanding the trends in urban development and the challenges faced include population growth, economic development, environmental stress, etc. The existing advantages and disadvantages of the city are analyzed, and a foundation is provided for the formulation of the planning scheme.

S1.3. Data were collected and analyzed: data related to urban development including infrastructure, demographics, traffic flow, energy consumption, etc. is collected and analyzed. Through data analysis, problems and needs are insights and potential improvements and innovation opportunities are found.

S1.4. Utilizing intelligence techniques and solutions: consider the application of intelligent technology in urban development, such as internet of things, artificial intelligence, big data analysis, etc. Exploring the potential of intelligent technologies, such as intelligent traffic management, intelligent energy supply, intelligent environmental monitoring, etc., provides innovation and feasibility for planning schemes.

S1.5, planning simulation and optimization are carried out: the urban development is modeled and analyzed using simulation and optimization techniques. By simulating different planning schemes, the influence and potential effect of the urban target are evaluated. Meanwhile, an optimal planning scheme is found by utilizing an optimization algorithm, and the balance and optimization of a plurality of factors are considered.

S1.6. Participating stakeholders and the public: the generation of intelligent city planning schemes requires extensive participation in opinion and participation by stakeholders and the public. And the communication and cooperation in the forms of workshops, interviews and the like are carried out, so that the acceptability and the co-creativity of the planning scheme are improved.

S1.7, programming a planning scheme and a roadmap: based on the results of the analysis and simulation, an intelligent city planning scheme and an implementation roadmap are compiled. The solution should include specific action plans, schedules, and resource requirements.

S1.8. Continuous monitoring and evaluation: after the planning scheme is implemented, monitoring and evaluation are carried out, and the realization condition of the urban targets is evaluated. And according to the evaluation result, timely adjusting the scheme and strategy to adapt to the change and development of the city.

And S7, evaluating the generated planning scheme to judge the feasibility, the sustainability and the contribution degree to the urban development targets. The following are the evaluation methods and indices:

comprehensive evaluation indexes: economic benefit: the contribution of planning schemes to urban economies is evaluated, including employment growth, industry development, economic growth rate, and the like.

Social benefit: and evaluating the influence of the planning scheme on society, including improvement of life quality of residents, social balance, social security and the like. Environmental benefit: the influence of the planning scheme on the environment is evaluated, and the method comprises the steps of reducing pollution emission, saving resources, improving ecological environment and the like. Sustainability: and evaluating the support degree of the planning scheme on sustainable development of economy, society and environment.

Index evaluation: traffic flow: and evaluating the influence of the planning scheme on the traffic mobility, including the degree of traffic jam, reducing the commute time, improving the traffic travel mode and the like.

Energy efficiency: the impact of the planning scheme on energy consumption is evaluated, such as reducing energy waste, promoting renewable energy utilization, and the like. Digital service: and (3) evaluating improvement of the coverage degree of the digital service by the planning scheme, including intelligent city management, digital public service and the like. Space planning: and (5) evaluating the reasonable utilization of the urban space and the optimization degree of the urban functions by the planning scheme. Community participation: and (5) improving the participation degree of community residents by the evaluation planning scheme, such as community activities, decision participation and the like.

Simulation and optimization based evaluation: the planning scheme is input into the city simulation platform, the implementation process and effect of the planning scheme are simulated, and the influence and expected effect of the planning scheme on the city are evaluated. Based on the data and the index, the planning scheme is evaluated and compared through an optimization algorithm, and an optimal scheme is found.

Collecting stakeholder comments: communicating and exchanging with stakeholders of each party involved in the planning scheme, and collecting opinion and feedback of the stakeholders. The public participating in the activities is carried out, and the public evaluation of the planning scheme is collected through questionnaires, public listening and proving and other modes. When the planning scheme is evaluated, different indexes and methods can be combined with each other to comprehensively evaluate so as to comprehensively and objectively evaluate the effect and feasibility of the planning scheme. The evaluation result can provide basis for further optimizing planning schemes, adjustment strategies and decisions. Importantly, the opinion and participation of stakeholders are fully considered in the evaluation process, so that the fairness and the sharing property of the evaluation are ensured.

And S8, optimizing and adjusting a planning scheme to improve the effect and adapt to the change and the demand of the city. The following are the methods and steps: collecting feedback and evaluation results: and collecting feedback opinions of stakeholders and public of each party, and analyzing the previous evaluation results. The advantages, disadvantages and improvements of planning schemes are known.

Review the goals of the planning scheme and evaluate its feasibility. According to the latest development trend and situation of the city, whether the target needs to be adjusted or redefined is confirmed. At the same time, potential constraints, such as regulations, finance, etc., are of interest to ensure the feasibility of the planning scheme.

And adjusting and improving the modeling and optimizing algorithm of the planning scheme. And optimizing parameters, weights and constraint conditions in the scheme according to the collected data and the evaluation result to obtain a better result.

The whole planning process is decomposed into stages, and specific targets and corresponding measures are formulated for each stage. This allows for better tracking, monitoring and assessment of the progress of the implementation of the planning scheme, and timely adjustment and correction.

Multiparty collaboration and collaborative work is carried out, and deep collaboration is carried out with stakeholders, professional teams and government departments of each party. Through intensive thinking and collaborative innovation, the planning scheme is further perfected and optimized.

The latest technical developments and solutions are evaluated to see if the planning scheme can be improved by introducing new technologies or innovative solutions. Such as intelligent transportation systems, renewable energy technology, digital management platforms, and the like.

And establishing a continuous monitoring and evaluating mechanism, and monitoring the implementation condition of the planning scheme in real time. Through regular data collection and analysis, the effectiveness and success of the planning scheme are evaluated, and problems and opportunities for improvement are discovered in time.

Participation and feedback mechanisms are introduced: participation and feedback mechanisms for stakeholders and the public are continually introduced, including the development of forms of public listening, interviewing, questionnaire, and the like. Listening to their opinion and advice, the planning schemes are adjusted in time to meet the needs and desires of different stakeholders.

A flexible adjustment mechanism is established: urban development is a dynamic process and planning schemes need to have the ability to adjust and adapt to changes. And a flexible adjustment mechanism is established, so that urban changes, new requirements and challenges are responded in time, and the sustainability and long-term effectiveness of a planning scheme are ensured.

Continuous learning and improvement: planning is a progressive process requiring continuous learning and improvement. And periodically reviewing the implementation condition of the planning scheme, summarizing experience training, and combining the latest development trend and technical innovation to continuously perfect and update the planning scheme.

S9, the planning schemes and analysis results are displayed to convey information to stakeholders, government departments and the public, and strive for support and understanding. The following are some methods and gist for showing planning schemes and analysis results:

visual presentation: and visually displaying the planning scheme and the analysis result by using visualization tools such as charts, images, maps, models and the like. For example, urban improvement effects are demonstrated using three-dimensional models, traffic flow changes are demonstrated using flow charts or thermodynamic diagrams, and the like. By means of the visual mode, the audience is better informed and feel the content and influence of the planning scheme.

Making reports and documents: specialized reports and documents are written detailing the context, goals, policies, and analysis results of the planning scheme. The report should be logical and structural, clearly illustrate core concepts and key points, and support analysis results with data and graphs.

In the implementation steps, the following needs to be added:

sensor data collection sub-module: for collecting data from the sensor device; the sensor may be a physical device for monitoring various parameters in the environment, such as temperature, humidity, air pressure, etc.; the submodule possibly comprises a physical sensor, an acquisition circuit, a microcontroller and a related software tool, and is responsible for reading sensor data and processing, storing and transmitting the sensor data;

Social media data collection sub-module: for collecting data from a social media platform; through interaction with the API interface of the social media platform, data related to cities, such as position check-in, comments, text pushing and the like, issued by a user on the platform can be obtained; the sub-module may include a data acquisition module, API integration and authentication mechanisms to ensure that social media data is legally acquired;

public data platform interface submodule: the system comprises a public data platform, a public data storage platform and a public data storage platform, wherein the public data platform is used for interacting with the public data storage platform to acquire public data related to cities; the public data platform provides a series of public data such as traffic data, demographic data, infrastructure data and the like, and can be used as an important basis for urban planning and management; the sub-module may include functions such as API integration and data extraction, conversion and storage.

The trend analysis sub-module is used for determining trends and modes in the data; it can analyze the trend of the data, such as seasonal, periodic, or long-term trends in the time series data; such analysis may help determine the direction of development and possible future trends of the data;

the association analysis sub-module is used for identifying association relations and relativity in the data; it can help determine the degree of association and potential causal relationships between different data under given conditions; correlation analysis is often used in the fields of market basket analysis, user behavior analysis, recommendation systems and the like to help reveal hidden patterns and rules in data;

The prediction modeling module is used for constructing a model based on historical data and predicting future trend and behavior by using the model; it can use different statistical and machine learning algorithms, such as regression analysis, time series analysis, neural networks, etc., to predict future development of data; such models are typically based on analysis of historical data, with predictions made by learning past patterns and trends;

these sub-modules are typically used in big data analysis and decision support systems to extract insight and make predictions from the collected data; they are interrelated, together providing support for data analysis and prediction, helping to discover patterns, trends, and potential laws in the data to guide decisions and planning; specific implementations and technical details will depend on the actual requirements and data characteristics.

The space layout model sub-module, the traffic network model sub-module and the resource allocation model sub-module are all modules or methods used in the urban planning and management field; the following is a specific explanation of each sub-module:

the space layout model submodule is used for simulating and analyzing space layout and land utilization conditions in the city; the method can help planners and decision makers understand the application and function distribution of different areas of the city, forecast land requirements and optimize land utilization; such models may be analyzed and simulated based on Geographic Information System (GIS) data, demographic data, land use planning, etc. inputs to support city planning and land management decisions;

The traffic network model submodule is used for modeling and simulating an urban traffic system; the system can simulate roads, traffic flow, road congestion, traffic and transportation demands and the like to evaluate traffic conditions, optimize traffic planning and forecast traffic demands; the model can be analyzed and simulated based on inputs of traffic investigation data, traffic flow data, road network data and the like to assist in traffic planning and traffic management decisions;

the resource allocation model sub-module is used for evaluating and optimizing allocation and utilization of urban resources; the method can help understand the requirements and supply conditions of different resources in the city, and deduce an optimal resource configuration scheme, such as energy use, water resource management, public facility planning and the like through simulation and optimization algorithms; the model can carry out resource analysis and decision support based on input of resource investigation data, supply and demand situation data, cost benefit analysis and the like;

these sub-modules are typically used in city planning, traffic planning, resource management and decision support systems to provide insight and advice on city development and sustainability; the specific implementation and technical details will depend on the specific requirements and the nature of the available data; you can consult city planners, traffic planners and professionals in the relevant fields to get more specific information and support.

The economic evaluation submodule is used for evaluating economic benefits and cost benefits of projects or policies; it can help evaluate potential returns for investment projects, market impact, employment opportunities, financial returns, etc.; common methods for such modules include net present value analysis, internal profitability, cost-effectiveness analysis, etc., to provide support for economic decisions;

the environment assessment submodule is used for assessing the potential influence and sustainability of the project or policy on the environment; the method can help identify and evaluate the problems of resource utilization conditions, pollution, ecological damage, carbon footprint and other environmental aspects, and provide suggestions for environmental protection and sustainable development; such modules typically use Environmental Impact Assessment (EIA) and lifecycle assessment (LCA) methods to perform environmental risk assessment and environmental benefit analysis;

the social evaluation sub-module is used for evaluating potential influence of projects or policies on society and social sustainability; the method can help identify and evaluate social problems such as social equality, fairness, social benefits, community participation and the like, and provide suggestions of social development and social sense; such modules typically use methods such as Social Impact Assessment (SIA) and sustainability assessment to analyze and evaluate social impact and social benefits;

These assessment submodules are often used in project assessment, policy making and planning decision-making processes to integrate multiple factors of economy, environment and society; specific implementation and technical details will depend on the specific case and available data; economic, environmental and social assessment typically require specialized evaluators and domain experts to participate to ensure accuracy and reliability of the assessment results.

The target optimization submodule is used for solving the problem of searching an optimal value of the target function under a given constraint condition; it can help determine the optimal decision variable settings to maximize or minimize the outcome of the objective function; such sub-modules may use different optimization algorithms, such as linear programming, nonlinear programming, integer programming, etc., to search for optimal solutions; target optimization is widely used in various fields, such as engineering design, operation study, financial investment, etc.;

the genetic algorithm optimization submodule is an optimization method based on the biological evolution principle; the method simulates the genetic and evolutionary processes in nature, and searches for an optimal solution by creating and evolving a group of candidate solutions; the genetic algorithm uses an evaluation function to moderately evaluate candidate solutions and generates a new generation of solutions through operations such as selection, crossover, mutation and the like; the optimization method is suitable for complex problems and optimization in a high-dimensional space, such as parameter optimization, machine learning model parameter adjustment and the like;

The optimization sub-modules can be used independently of each other, and can also be used in combination to solve the complex optimization problem; for example, genetic algorithms may be used as a method of target optimization to take advantage of their broad search space and global search capabilities; the specific implementation and technical details will depend on the specific problem and optimization objectives;

the target optimization submodule is generally based on mathematical optimization theory and algorithm and can be realized by utilizing different optimization strategies and technologies; the genetic algorithm optimization submodule needs to realize the operations of selection, crossing, variation and the like in the genetic algorithm, and performs iterative search by combining with moderate evaluation and evolution processes; the implementation can use programming languages and optimization libraries, such as SciPy library of Python, optimization tool kit of MATLAB, and the like; in addition, other optimization methods and algorithm libraries may be used to select the most appropriate optimization strategy and algorithm based on the needs of a particular problem.

The map display submodule is used for displaying geographic information and space data on the visual interface; the method can help users intuitively understand information such as geographic positions, terrains, regional distribution and the like; such sub-modules typically provide map display functions, such as map marking, region shading, labeling, etc., as well as map interaction functions, such as zoom-in, zoom-out, drag, query, etc.; map presentation may be implemented using map library and Geographic Information System (GIS) technology, such as Google Maps APIs, leaflet, arcGIS, etc.;

The chart display submodule is used for displaying data in a chart form on the visual interface; it can help users better understand trends, associations, and distributions of data; such sub-modules typically provide various types of charts, such as line charts, bar charts, pie charts, scatter charts, etc., and allow user interaction, such as data screening, chart scaling, data labels, etc.; the graph presentation may be implemented using a graph library and data visualization tools, such as matplotlib, d3.Js, tableau, etc.;

the virtual reality display submodule is used for displaying data or scenes in a virtual reality environment; it can help users experience and interact immersively through the manner of being in the scene; such sub-modules typically incorporate virtual reality devices (e.g., head mounted displays, handle controllers, etc.) to create realistic virtual environments, such as virtual earth, building models, 3D data visualizations, etc.; the virtual reality presentation can be realized by using a virtual reality development tool and a software platform, such as Unity, unreal Engine and the like;

these presentation sub-modules may be combined or used separately according to specific needs and scenarios to provide a visual, interactive, and immersive data presentation experience; the specific implementation and technical details will depend on the gallery, chart gallery, virtual reality platform and development tool selected for use; in practical use, the most suitable display sub-module and technology can be selected according to the data type, the user requirement and the display requirement;

Data cleaning and preprocessing is a very important step in intelligent urban planning systems, which involves cleaning, converting, integrating and normalizing raw data for subsequent analysis and modeling; the following are the steps of the data cleaning and preprocessing module:

s1, data collection: collecting data of various relevant fields, such as population data, traffic data, environment data and the like; the data may come from a variety of sources such as sensors, monitoring devices, public departments, social media, etc.;

s2, data cleaning: cleaning the collected data, including removing repeated data, processing missing values, solving abnormal values and the like; repeated data and outliers affect the subsequent analysis results, and therefore need to be screened and repaired;

s3, data conversion: converting the raw data into a format usable for analysis; operations such as data format conversion, unit conversion, data normalization, etc. may be required to ensure consistency and comparability of data;

s4, data integration: merging and integrating data from different sources and different data sources; this may involve data matching, data correlation, etc. operations to obtain a more comprehensive and comprehensive data set;

S5, data normalization: converting the data into a unified format and standard; this may include uniform time formats, geographic coordinate formats, unit standards, etc. to facilitate subsequent calculations and analysis;

s6, data sampling and sampling: sampling and sampling large-scale data to reduce the calculated amount and improve the efficiency; the sampling method can select random sampling, uniform sampling and the like according to the requirements;

s7, data set division: dividing the data set into a training set, a verification set and a test set so as to perform model training, verification and evaluation; the dividing ratio can be adjusted according to the requirements of specific tasks and algorithms;

s8, data labeling and label generation: labeling the data and generating labels so as to facilitate the supervision of learning and modeling of classification problems; labeling can be performed manually or by using an automation tool;

in the data cleaning and preprocessing module, strict data quality control and verification are carried out, so that the data quality after cleaning and preprocessing is ensured to be reliable, and the requirements of subsequent analysis and modeling are met; thus, the accuracy and the reliability of the intelligent city planning system can be improved, and a decision maker is helped to make a more intelligent decision;

The planning target setting module is a key component in the intelligent city planning system and is used for determining the target and the wish of city planning and providing guidance and constraint for the subsequent planning work; the following is a specific working procedure of the planning target setting module:

s1, target setting: selecting and setting a proper planning target from a target library according to the characteristics, the requirements and the planning standards of the city; the target can be a quantitative index or a qualitative description;

s2, data collection and analysis: acquiring related city data through a data collection module, and processing and analyzing the data by using a data analysis tool to know the current city condition and trend;

s3, setting target weight: for each planning target set, setting weight of each planning target to reflect importance and priority of the target; the weight can be set according to subjective judgment of a planner or based on expert opinion;

s4, target evaluation and adjustment: calculating the achievement condition of each target by using a data analysis tool, and evaluating according to the actual condition; if the goal is not achieved or is unreasonable, adjustments and resets can be made.

The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the foregoing embodiments, and that the foregoing embodiments and description are merely illustrative of the principles of this invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims (10)

1. An intelligent city planning system based on big data analysis comprises the following modules:

a data collection module for collecting city related big data including, but not limited to, demographics, traffic flow, environmental data: a data storage module for storing the collected big data and providing data retrieval and management functions:

the data cleaning and preprocessing module is used for cleaning and preprocessing collected big data to remove noise and process missing values and abnormal values: a data analysis module for analyzing the cleaned and preprocessed data, including data mining, machine learning, and statistical analysis:

the planning target setting module is used for making targets and indexes of intelligent city planning and optimizing according to data analysis results: a planning model construction module for constructing a model of intelligent city planning, comprising a space model, a network model and an optimization model: a planning scheme generating module for generating an intelligent city planning scheme according to the planning model and the target setting:

and evaluating the generated planning scheme, wherein the planning scheme comprises a feasibility analysis module, a risk assessment module and an effect prediction module: and a planning scheme optimizing module for optimizing and adjusting the planning scheme based on the evaluation result: and the visual display module is used for displaying the planning scheme and the analysis result in a graphical mode and providing an visual intelligent city planning visual interface.

2. The intelligent city planning system based on big data analysis of claim 1, wherein: the data collection module further comprises a sensor data collection sub-module, a social media data collection sub-module and a public data platform interface sub-module; the data analysis module further comprises a trend analysis sub-module, a correlation analysis sub-module and a prediction modeling sub-module; the planning model construction module further comprises a space layout model sub-module, a traffic network model sub-module and a resource allocation model sub-module;

the planning scheme evaluation module further comprises an economic evaluation sub-module, an environment evaluation sub-module and a social evaluation sub-module; the planning scheme optimizing module further comprises a multi-objective optimizing sub-module and a genetic algorithm optimizing sub-module; the visual display module further comprises a map display sub-module, a chart display sub-module and a virtual reality display sub-module.

3. An intelligent city planning method based on big data analysis comprises the following steps:

s1, collecting big data related to cities;

s2, cleaning and preprocessing the collected big data;

S3, analyzing the cleaned and preprocessed data;

s4, formulating targets and indexes of intelligent city planning;

s5, constructing an intelligent city planning model;

s6, generating an intelligent city planning scheme;

s7, evaluating the generated planning scheme;

s8, optimizing and adjusting a planning scheme;

and S9, displaying a planning scheme and an analysis result.

4. The intelligent city planning system based on big data analysis of claim 2, wherein:

the sensor data collection sub-module: for collecting data from the sensor device; the sensor data collection sub-module is preferably a physical device and is used for monitoring the environment including but not limited to temperature, humidity and air pressure; the sensor data collection submodule comprises a physical sensor, a collection circuit, a microcontroller and corresponding software tools, and is responsible for reading sensor data, processing, storing and transmitting;

the social media data collection sub-module: for collecting data from a social media platform; through interaction with an API interface of the social media platform, data related to cities, including but not limited to position check-in, comments and text, published by a user on the platform are obtained; the social media data collection submodule comprises a data acquisition module, an API integration and an authentication mechanism; the public data platform interface submodule comprises: the method comprises the steps of interacting with a public data platform to obtain public data related to cities;

The trend analysis submodule is used for determining trends and modes in data; further the trend analysis sub-module is used for analyzing the change trend of the data, including but not limited to seasonal change, periodic change or long-term trend in the time series data; the association analysis sub-module is used for identifying association relations and relativity in the data; the association analysis submodule further helps to determine the association degree and potential causal relation between different data under given conditions; the association analysis is in the fields of market basket analysis, user behavior analysis and recommendation systems;

the prediction modeling module is used for constructing a model based on historical data and predicting future trend and behavior by using the model; future development of the data is predicted using different statistical and machine learning algorithms, including but not limited to regression analysis, time series analysis, neural networks.

5. The intelligent city planning system based on big data analysis of claim 2, wherein:

the space layout model submodule is used for simulating and analyzing space layout and land utilization conditions in cities; the space layout model sub-module is further used for helping planners and decision makers understand the purpose and function distribution of different areas of the city, predicting land requirements and optimizing land utilization; the space layout model submodule analyzes and simulates based on Geographic Information System (GIS) data, demographic data and land use planning input so as to support city planning and land management decision-making;

The traffic network model submodule is used for modeling and simulating an urban traffic system; simulating roads, traffic flow, road congestion and traffic and transportation demands, and further evaluating traffic conditions, optimizing traffic planning and predicting traffic demands; the traffic network model submodule analyzes and simulates traffic survey data, traffic flow data and road network data input to assist traffic planning and traffic management decision-making;

the resource allocation model sub-module is used for evaluating and optimizing allocation and utilization of urban resources; the resource allocation model submodule further helps to understand the requirements and supply conditions of different resources in the city, and deduces an optimal resource allocation scheme through simulation and optimization algorithms, including but not limited to energy use, water resource management and public facility planning; the resource allocation model submodule further performs resource analysis and decision support based on resource investigation data, supply and demand situation data and cost benefit analysis input.

6. The intelligent city planning system based on big data analysis of claim 2, wherein:

the economic evaluation submodule is used for evaluating economic benefits and cost benefits of projects or policies; the economic evaluation submodule further helps to evaluate potential returns, market influences, employment opportunities and financial benefits of investment projects; the method of the economic evaluation sub-module comprises net present value analysis, internal yield and cost benefit analysis;

The environment evaluation submodule is used for evaluating potential influence and sustainability of the project or policy on the environment; the environment evaluation submodule is further used for helping to identify and evaluate problems in terms of resource utilization, pollution, ecological damage and carbon footprint environment and providing suggestions for environmental protection and sustainable development; the environmental assessment sub-module uses Environmental Impact Assessment (EIA) and Life Cycle Assessment (LCA) methods to perform environmental risk assessment and environmental benefit analysis;

the social evaluation sub-module is used for evaluating potential influence of projects or policies on society and social sustainability; the social evaluation submodule helps to identify and evaluate social problems of social smoothness, fairness, social benefits and community participation, and provides social development and social sense suggestions; the social evaluation sub-module further uses social impact evaluation (SIA) and sustainability evaluation methods to analyze and evaluate social impact and social benefit.

7. The intelligent city planning system based on big data analysis of claim 2, wherein:

the target optimization submodule is used for solving the problem of searching an optimal value of the target function under a given constraint condition; further the objective optimization submodule helps to determine the optimal decision variable settings to maximize or minimize the result of the objective function; the target optimization sub-module searches for an optimal solution by using different optimization algorithms including, but not limited to, linear programming, nonlinear programming and integer programming; target optimization has wide application in various fields including but not limited to engineering design, operations research, financial investment;

The genetic algorithm optimization submodule is an optimization method based on a biological evolution principle; the genetic algorithm optimization submodule simulates the genetic and evolutionary processes of the nature, and searches for an optimal solution by creating and evolving a group of candidate solutions; the genetic algorithm optimization submodule further uses an evaluation function to evaluate the adaptability of the candidate solutions, and generates a new generation of solutions through selection, crossover and mutation operations; the genetic algorithm optimization submodule is suitable for complex problems and optimization in a high-dimensional space, and comprises parameter optimization and machine learning model parameter adjustment;

the genetic algorithm optimization submodules are used independently of each other and are also used in combination to solve the complex optimization problem; including without limitation: genetic algorithms are applied as a method of target optimization to take advantage of their broad search space and global search capabilities; the specific implementation and technical details will depend on the specific problem and optimization objectives;

the target optimization submodule is realized by utilizing different optimization strategies and technologies based on mathematical optimization theory and algorithm; the genetic algorithm optimization submodule realizes the selection, crossing and mutation operations in the genetic algorithm and carries out iterative search by combining with the fitness evaluation and evolution process; the implementation uses programming languages and optimization libraries, including, but not limited to, sciPy library of Python, optimization toolkit of MATLAB.

8. The intelligent city planning system based on big data analysis of claim 2, wherein:

the map display submodule is used for displaying geographic information and space data on the visual interface; the map display submodule helps a user to intuitively understand geographical position, topography and regional distribution information; the map display submodule further provides map display functions including map marking, region coloring and labeling and map interaction functions including zooming in and zooming out, dragging and inquiring; map presentation is implemented using map library and Geographic Information System (GIS) technology, including but not limited to Google Maps APIs, leaflet, arcGIS;

the chart display submodule is used for displaying data in a chart form on a visual interface; the chart display submodule further helps users understand the trend, association and distribution of data; the chart showing submodule further provides various types of charts, including, but not limited to, a line chart, a bar chart, a pie chart and a scatter chart, and allows users to interact, including, but not limited to, data screening, chart scaling and data labels; the chart shows implementation using a chart library and data visualization tools, including without limitation matplotlib, d3.Js, tableau;

The virtual reality display submodule is used for displaying data or scenes in a virtual reality environment; the virtual reality display submodule helps users to experience and interact immersively in an immersive manner; the virtual reality display submodule is further combined with virtual reality equipment, and comprises a head-mounted display and a handle controller, so that a realistic virtual environment is created, wherein the realistic virtual environment comprises virtual earth, a building model and 3D data visualization; virtual reality presentation is implemented using virtual reality development tools and software platforms, including without limitation Unity, unreal Engine.

9. The intelligent city planning system based on big data analysis of claim 1, wherein the step of data cleaning and preprocessing module comprises:

s1, collecting data in various relevant fields, including population data, traffic data and environmental data; data comes from sensors, monitoring devices, public departments, sources of social media diversification;

s2, cleaning the collected data, including removing repeated data, processing missing values and solving abnormal values;

s3, converting the original data into a format for analysis; data format conversion, unit conversion and data standardization operation are needed to ensure the consistency and comparability of data;

S4, merging and integrating data from different sources and different data sources; data matching and data association operations are involved to obtain a more comprehensive and comprehensive data set;

s5, converting the data into a unified format and standard; the method comprises the steps of unifying a time format, a geographic coordinate format and a unit standard so as to facilitate subsequent calculation and analysis;

s6, sampling and sampling the large-scale data to reduce the calculated amount and improve the efficiency; the sampling method selects random sampling and uniform sampling according to the requirements;

s7, dividing the data set into a training set, a verification set and a test set so as to perform model training, verification and evaluation; the dividing ratio is adjusted according to the requirements of specific tasks and algorithms;

s8, marking the data and generating labels so as to facilitate supervision of learning and modeling of classification problems; labeling is performed manually, also with automated tools.

10. The intelligent city planning system based on big data analysis of claim 1, wherein the specific working steps of the planning target setting module include:

s1, selecting and setting a proper planning target from a target library according to the characteristics, the requirements and the planning standard of a city

S2, acquiring related city data through a data collection module, and processing and analyzing the data by using a data analysis tool to know the current city condition and trend;

s3, setting weight of each planning target aiming at the set planning targets so as to reflect importance and priority of the targets;

s4, calculating the achievement condition of each target by using a data analysis tool, and evaluating according to the actual condition; including without limitation, that the goal is not achieved or not reasonable, and adjustments and resets are made.