CN116167254A - Multidimensional city simulation deduction method and system based on city big data - Google Patents
Multidimensional city simulation deduction method and system based on city big data Download PDFInfo
- Publication number
- CN116167254A CN116167254A CN202310457224.4A CN202310457224A CN116167254A CN 116167254 A CN116167254 A CN 116167254A CN 202310457224 A CN202310457224 A CN 202310457224A CN 116167254 A CN116167254 A CN 116167254A
- Authority
- CN
- China
- Prior art keywords
- data
- population
- module
- city
- scale
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
- Y02A30/60—Planning or developing urban green infrastructure
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The embodiment of the invention discloses a multidimensional city simulation deduction method and system based on city big data. The method comprises the following steps: the urban power module adopts a neural network regression prediction method to deduce the future urban general population and employment rate; population module based on population classification topology algorithm and equal proportion iteration fitting method, from macroscopic population data of current year, microscopic population data of current year of sample expanding person, family, building, land block and regional scale; the traffic module calculates traffic travel data of each scale target year by using a traffic activity chain algorithm; the city deduction module deducts population data change and land data change of each scale target year according to microscopic population data and traffic travel data of each scale based on a city deduction algorithm; the city deduction module and the traffic module form annual alternate feedback and perform iterative calculation to realize annual deduction of the target city. The embodiment realizes urban multi-scale microscopic simulation deduction.
Description
Technical Field
The embodiment of the invention relates to the field of city simulation deduction, in particular to a multidimensional city simulation deduction method and system based on city big data.
Background
City simulation deduction refers to deduction of future states from the existing states of the city in a simulation manner. The city simulation deduction can play important prediction and guidance roles in the aspects of urban traffic, disasters, population flow, land change, urban boundary growth and the like.
The current city simulation deduction system, such as MultiGen Creator series products of MultiGen-Paradigm company, urbansim, magicity and the like, performs city deduction based on macroscopic statistics and probability, can only meet the large-scale requirements of city overall planning and the like, and cannot integrate macroscopic data and microscopic data for towns, buildings or smaller scales, and cannot accurately predict the changes in aspects of land, traffic and the like.
Disclosure of Invention
The embodiment of the invention provides a multidimensional city simulation deduction method and a multidimensional city simulation deduction system based on city big data, which realize city multiscale microscopic simulation deduction.
In a first aspect, an embodiment of the present invention provides a multidimensional urban simulation deduction method based on urban big data, which is applied to a multidimensional urban simulation deduction system based on urban big data, where the system includes: a macroscopic model for reflecting urban macroscopic information and a microscopic model for reflecting urban microscopic information; the macroscopic model comprises an urban power module, and the microscopic model comprises a population module, a traffic module and an urban deduction module;
the method comprises the following steps:
the urban power module adopts a neural network regression prediction method, deduces future urban general population and employment rate according to coupling relation and historical data of macro elements influencing the development of a target city, and forms future macro population data together by the future urban general population and employment rate;
the population module is based on a population classification topological algorithm and an equal proportion iterative fitting method, and is formed by sampling macroscopic population data of the current year, microscopic population data of individuals, families, buildings, plots and region scales of the current year, wherein the microscopic population data comprises general population of each scale and specific characteristic data of each person;
the traffic module calculates traffic travel data of each scale of target years according to land data and microscopic population data of each scale of target years by using a traffic activity chain algorithm;
the city deduction module deducts population data change and land data change of each scale target year according to microscopic population data and traffic travel data of each scale based on a city deduction algorithm;
the city deduction module and the traffic module form annual alternate feedback and perform iterative calculation to realize annual deduction of the target city.
In a second aspect, an embodiment of the present invention provides a multidimensional urban simulation deduction system based on urban big data, including: a macroscopic model for reflecting urban macroscopic information and a microscopic model for reflecting urban microscopic information; the macroscopic model comprises an urban power module, and the microscopic model comprises a population module, a traffic module and an urban deduction module;
the urban power module is used for deducing future urban general population and employment rate according to coupling relation and historical data of macro elements influencing the development of a target city by adopting a neural network regression prediction method, and the future urban general population and employment rate jointly form future macro population data;
the population module is used for expanding microscopic population data of individuals, families, buildings, plots and regional scale current years from macroscopic population data of current years based on a population classification topological algorithm and an equal proportion iterative fitting method, wherein the microscopic population data comprises a general population of each scale and specific characteristic data of each person;
the traffic module is used for calculating traffic travel data of each scale of target years according to land data and microscopic population data of each scale of target years by using a traffic activity chain algorithm;
the city deduction module is used for deducting population data change and land data change of each scale target year according to microscopic population data and traffic travel data of each scale based on a city deduction algorithm;
the city deduction module and the traffic module form annual alternate feedback and perform iterative calculation to realize annual deduction of the target city.
According to the multidimensional urban simulation deduction method provided by the embodiment of the invention, population data is used as a tie of urban macro features and micro features, the urban macro population data is decomposed into multi-scale micro population data through a population classification topological algorithm, and the data relationship between a macro sample and a micro sample is learned by utilizing an artificial intelligence technology, so that the micro feature prediction of any scale and any year is realized; and then, utilizing the traffic activity demands of population, realizing the simulation deduction of urban land and traffic through a traffic activity chain algorithm, and realizing the loop iteration of land and traffic information through a city deduction algorithm to finish the year-by-year deduction of time dimension. Particularly, the urban simulation deduction is further subdivided into personnel, families, buildings, plots and regional multistage small-scale simulation deduction, and the urban simulation deduction method is particularly suitable for urban traffic information and land information planning, and meanwhile, the artificial intelligence technology is adopted to provide refined prediction data, so that the construction and updating of small-scale cities are strongly guided.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are needed in the description of the embodiments or the prior art will be briefly described, and it is obvious that the drawings in the description below are some embodiments of the present invention, and other drawings can be obtained according to the drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic structural diagram of a multidimensional city simulation deduction system based on city big data according to an embodiment of the present invention.
Fig. 2 is a flowchart of a multidimensional city simulation deduction method based on city big data according to an embodiment of the present invention.
Fig. 3 is a logic diagram of a population module according to an embodiment of the present invention.
Fig. 4 is a logic schematic diagram of a traffic module according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below. It will be apparent that the described embodiments are only some, but not all, embodiments of the invention. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the invention, are within the scope of the invention.
In the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. are based on the directions or positional relationships shown in the drawings, are merely for convenience of describing the present invention and simplifying the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and thus should not be construed as limiting the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
In the description of the present invention, it should also be noted that, unless explicitly specified and limited otherwise, the terms "mounted," "connected," and "connected" are to be construed broadly, and may be either fixedly connected, detachably connected, or integrally connected, for example; can be mechanically or electrically connected; can be directly connected or indirectly connected through an intermediate medium, and can be communication between two elements. The specific meaning of the above terms in the present invention will be understood in specific cases by those of ordinary skill in the art.
The embodiment of the invention provides a multidimensional city simulation deduction method based on city big data. To illustrate the method, a multidimensional city simulation deduction system for executing the method is preferentially introduced. Fig. 1 is a schematic structural diagram of a multidimensional urban simulation deduction system based on urban big data according to an embodiment of the present invention, as shown in the figure, the system includes: a macroscopic model for reflecting urban macroscopic information and a microscopic model for reflecting urban microscopic information. The macroscopic model comprises an urban power module, and the microscopic model comprises a population module, a traffic module and an urban deduction module.
And the urban power module deduces future macroscopic data according to the historical macroscopic data of the city. The population module expands microscopic population data of the current year according to the macroscopic data of the current year. The traffic module calculates traffic travel data of the target year according to the urban land data and the micro population data of the target year. The city deduction module deducts population data change and land data change of the target year according to microscopic population data and traffic travel data of each scale; the city deduction module and the traffic module form annual alternate feedback and perform iterative calculation to realize annual deduction of the target city.
It can be seen that the four modules have progressive feedback relation, and the urban power module is used as an input condition to drive the three microscopic models to carry out deduction simulation; the annual evolution results of the population module and the traffic module in the microscopic model are used as input parameters to drive the urban deduction module to deduct land and population microscopic changes of each scale, and then the urban deduction module results are used as input parameters to drive traffic deduction, so that the annual simulation deduction closed loop is realized.
In order to ensure the prediction effect, each module can test the accuracy, stability and reliability of the calculation result after finishing the simulation calculation; under the condition that the test result meets the requirement, each module transmits the calculation result to other modules for the other modules to finish calculation; under the condition that the test result does not meet the requirement, each module executes self-feedback training to improve the calculation accuracy until the test result meets the requirement.
Further, the multidimensional city simulation deduction system can call the SDK (Software Development Kit ) and the API (Application Programming Interface, application programming interface) of each mainstream simulation software to complete the simulation calculation of each module; meanwhile, a main stream simulation deduction algorithm can be called, time deduction is completed, and the specific simulation deduction algorithm comprises the following steps: cellular automata, finite element, data fitting, parameter estimation, traffic activity chain estimation, etc., the present embodiment is not limited.
Based on the above system, fig. 2 is a flowchart of a multidimensional city simulation deduction method based on city big data according to an embodiment of the present invention. The method is suitable for the situation of carrying out simulation deduction on land information and traffic information of various scales of cities. As shown in fig. 2, the method specifically includes:
and S110, the urban power module adopts a neural network regression prediction method, deduces future urban general population and employment rate according to the coupling relation and the historical data of each macroscopic element influencing the development of the target city, and jointly forms future macroscopic population data by the future urban general population and the employment rate.
Macroscopic elements that affect urban development include: urban general population, land, house, energy, double carbon, electricity, water, employment rate and the like, and form the power factor for simulating the operation of the deduction system. The existence of a certain coupling relation (i.e. mutual influence and mutual association relation) among the macro elements will have an influence on the deduction of the macro data. In this embodiment, the coupling relationship is stored in the urban power module relationship table. Illustratively, table 1 shows key fields of the urban power module relationship table, including names, categories, logical relationships, etc. of variables (i.e., macro elements). The historical data and future data of each macro element may be stored in an urban power module data sheet, and exemplary, table 2 shows key fields of the urban power module data sheet.
TABLE 1 urban Power Module relationship Table
Table 2 urban power module data sheet
After the urban power module acquires the coupling relation and the historical data of each macro element, firstly cleaning the data to remove weak influence data and low-efficiency data; then establishing a year-by-year sample of each macro element according to the historical data, inputting the sample and the coupling relation into a neural network, and learning the year-by-year change rule of the urban general population and employment rate; after training, the historical data is input into a trained neural network, future urban general population and employment rate are predicted, and future macroscopic population data is formed by the future urban general population and the employment rate together. Optionally, the neural network uses a mode of combining GNN (Graph Neural Network, graph convolution neural network) and LSTM (Long Short Term Memory, long and short term memory network), uses the coupling relation of each macro factor as a relation graph to execute LSTM convolution operation, and predicts future data of each macro element, including urban general population and employment rate.
In a specific embodiment, the urban power module divides macroscopic factors influencing urban development into six dimensions of population, economy, environment, life, management and fluidity according to the smart city evaluation index, and gradually refines and decomposes the factors into more than 1000 specific elements through logic analysis, wherein the elements are mutually coupled in the dimensions and between the circumferences. The urban power module can display the logical relationship of variables (i.e. elements), the equation of the relationship of the variables, the modification of the variables, the display of historical data and deduction data, and the like through a graphical interface, wherein the display forms comprise a network tree diagram, a change curve, and the like, and the embodiment is not particularly limited.
S120, the population module expands microscopic population data of individuals, families, buildings, plots and regional scale current years from macroscopic population data of current years based on a population classification topological algorithm and an equal proportion iterative fitting method, wherein the microscopic population data comprises general population data of all scales and specific characteristic data of all people.
The method comprises the steps of expanding macro population data to obtain micro population data with all attributes in all areas. Specifically, the method comprises the following steps:
firstly, a population module firstly establishes a space mapping relation among plots, streets and cities, buildings and communities; according to the spatial mapping relation, refining the research scale of the microscopic data from the whole city into a plurality of microscopic levels, wherein the method comprises the following steps: individuals, households, buildings, plots, and areas.
And secondly, the population module utilizes a population classification topology algorithm to automatically clean, classify and reorganize urban resident sampling survey data to obtain resident information of each scale, wherein the resident information comprises general population and personnel behavior data of each scale and the like. Illustratively, the demographic topology algorithm may be implemented using a multi-neuron SOM network.
And thirdly, constructing microscopic population data samples of personal, family, building, land block and area scale according to resident information of each scale, and constructing macroscopic population data samples according to census statistical information, wherein the specific content of each data sample is shown in fig. 3.
And fourthly, the population module takes the macro population data sample as input, takes the micro population data sample as output, puts the micro population data sample into an equal proportion iterative fitting (IPF) model for training, and learns population structural features between the macro population data and micro population data of each scale.
And fifthly, inputting the macroscopic population data of the current year into a trained equal-proportion iterative fitting model by the population module, and outputting microscopic population data of individuals, families, buildings, plots and regional scales of the current year. According to the method, on the basis of keeping the consistency of structural features such as population number, gender, academic, family scale, family income, personnel behavior features and the like, macroscopic population data are expanded into population microscopic data with all attributes in all areas, and connection between macroscopic data and microscopic data is realized.
In one embodiment, the population micro-sampling survey data is used as default input data, and local homonymous file uploading can be selected for coverage. The variable setting page of the population module can set the row value of each variable value, and different value setting modes are provided; the scene setting can be performed, and the scene setting specifically comprises areas, geographical control variables, such as families, personnel and the like; the tolerance, the iteration number, the zero margin correction coefficient, the rounding mode, the filing execution frequency, the weighting method, the tolerance and the iteration parameter of the IPF algorithm can be set, and the population checking parameter, the random seed number, the iteration number and the like can be generated.
And S130, calculating the traffic trip data of each scale of target years according to the land data and the micro population data of each scale of target years by using a traffic activity chain algorithm by the traffic module.
The land data of the city scale comprises administrative boundaries, land block boundaries and attributes, building bases and layer heights and other attributes, traffic roads and attributes, land planning vectors, city multi-period remote sensing images, unmanned aerial vehicle inclination measurement 3D city building models and the like. The ground data for other scales are similar, except that the scales are different.
The traffic module predicts the type, time and place of a resident movable chain by using a traffic movable chain algorithm and taking the characteristic value of the current resident behavior of each scale as input and combining land data and microscopic population data of each scale target year, calculates the travel mode and route of each scale resident target year, and jointly forms traffic travel data of each scale target year. Meanwhile, the traffic module evaluates the running condition of the urban traffic system according to the traffic travel data of each scale target year, predicts the supply and demand balance relation between each scale traffic facility and travel demands, and is used as the basis of traffic regulation and planning. The overall logic is shown in fig. 4.
Specifically, the traffic module input data is divided into map files, trip investigation data and check line investigation data. The map file is divided into an analysis area file and a road network file, and the format is geojson. The analysis area file is the data of the research area and the peripheral administrative area, and the road network file comprises a thinning road network and a road network file, wherein the thinning road network is an original road network which is screened according to rules, and the year represents the road network condition of different years. Trip survey data characteristics include family data, personnel data, activity chain data, trip data, joint travel data, and the like. The check line investigation input data comprise non-motor vehicle check point flow data, non-motor vehicle check point early peak data, bus check point passenger flow data, bus check point early peak data and the like.
The traffic module calculates a traffic activity chain based on the data, calculates travel modes and routes of all scales, and can perform visual display aiming at specific scenes (namely all scales), wherein the visual display comprises checking a line point position distribution diagram, a travel distribution diagram, a traffic distribution diagram and the like; different result evaluation indexes such as average travel distance, average travel time, traffic mode proportion, road average speed and the like of each street can be set.
S140, the city deduction module deducts population data change and land data change of each scale target year according to microscopic population data and traffic travel data of each scale based on a city deduction algorithm; the city deduction module and the traffic module form annual alternate feedback and perform iterative calculation to realize annual deduction of the target city.
In addition to microscopic population data and traffic travel data for each scale, the input of the city deduction module also comprises land control data for each scale, including vectors of each level, building attributes, family attributes, resident attribute tables, and the like. Taking the building scale as an example, part of the control data is shown in table 3:
table 3 building control data sheet
The output data of the city deduction module includes: demographic data changes and land data changes for each scale target year. Wherein the population data changes include family migration data, personnel migration data, etc., and exemplary, partial contents of the family migration data are shown in table 4. The land data transformation includes construction change data and facility point change data, and exemplary facility points include airports, railway stations, subway stations, and the like.
Table 4 family migration data table
Specifically, the city deduction module is used for calculating land data change of each scale of target years from the land data of each scale according to the supply and demand balance relation between each scale of traffic facilities and travel demands based on a city deduction algorithm; deducing population data changes of the target years of each scale according to land data changes and traffic travel data of the target years of each scale; and feeding back the data changes to the communication module, and starting calculation of the next time period.
In a specific embodiment, the city deduction module obtains population data change and land data change of each scale in the target year and feeds the population data change and the land data change back to the traffic module; the traffic module substitutes traffic activity algorithm to calculate traffic trip data of the target year according to land data and microscopic population data of the target year; the city deduction module deducts population data change and land data change of the next step target year of each scale according to microscopic population data and traffic trip data of the target year of each scale based on a city deduction algorithm, feeds back the population data change and the land data change to the traffic module, and starts simulation calculation of the next step target year; and the method is circularly reciprocated, and year-by-year deduction of the target city is realized through closed loop data transmission.
Furthermore, the method can select different scale dimensions (personnel, families, buildings, plots and areas) in each step, so that traffic information, land information and population information under different dimensions can be deduced. The user can select different concerned objects according to the needs to develop simulation deductions of traffic topics, building topics, facility topics and population topics; the graphic display interface can flexibly display simulation deduction information of each topic and each stage.
The other technical details which are not fully described can be realized by referencing classical and leading edge algorithm models, and are not repeated in the application.
According to the multidimensional urban simulation deduction method provided by the embodiment, population data is used as a tie of urban macro features and micro features, urban macro population data are decomposed into multi-scale micro population data through urban space mapping and a neural network-based population classification topological algorithm, a data relationship between a macro sample and a micro sample is learned by utilizing an artificial intelligence technology, and micro feature prediction of any scale and any year is realized by utilizing the data relationship; and then, utilizing the traffic activity demands of population, realizing the simulation deduction of urban land and traffic through a traffic activity chain algorithm, and realizing the loop iteration of land and traffic information through a city deduction algorithm to finish the year-by-year deduction of time dimension. In summary, in the embodiment, urban simulation deduction is subdivided into personnel, families, buildings, plots and areas with multiple small scales, annual deduction is realized, and the space granularity and the time granularity are finer, so that the urban simulation deduction method is particularly suitable for annual planning of urban traffic information and land information; meanwhile, the artificial intelligence technology is adopted to provide refined prediction data, so that construction and update of small-scale cities are guided strongly.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present invention, and not for limiting the same; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some or all of the technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the essence of the corresponding technical solutions from the technical solutions of the embodiments of the present invention.
Claims (10)
1. The multidimensional city simulation deduction method based on the city big data is characterized by being applied to a multidimensional city simulation deduction system based on the city big data, and the system comprises the following steps: a macroscopic model for reflecting urban macroscopic information and a microscopic model for reflecting urban microscopic information; the macroscopic model comprises an urban power module, and the microscopic model comprises a population module, a traffic module and an urban deduction module;
the method comprises the following steps:
the urban power module adopts a neural network regression prediction method, deduces future urban general population and employment rate according to coupling relation and historical data of macro elements influencing the development of a target city, and forms future macro population data together by the future urban general population and employment rate;
the population module is based on a population classification topological algorithm and an equal proportion iterative fitting method, and is formed by sampling macroscopic population data of the current year, microscopic population data of individuals, families, buildings, plots and region scales of the current year, wherein the microscopic population data comprises general population of each scale and specific characteristic data of each person;
the traffic module calculates traffic travel data of each scale of target years according to land data and microscopic population data of each scale of target years by using a traffic activity chain algorithm;
the city deduction module deducts population data change and land data change of each scale target year according to microscopic population data and traffic travel data of each scale based on a city deduction algorithm;
the city deduction module and the traffic module form annual alternate feedback and perform iterative calculation to realize annual deduction of the target city.
2. The method of claim 1, wherein the urban power module employs a neural network regression prediction method to derive future urban general population and employment rates from coupling relationships and historical data of macro elements affecting the development of the target city, and the future urban general population and employment rates together form future macro population data, comprising:
the urban power module acquires coupling relation and historical data of all macro elements affecting the development of a target city, and performs data cleaning, wherein the macro elements comprise: urban general population, employment rate, land and energy;
the urban power module establishes year-by-year samples of all macroscopic elements according to the historical data, inputs the samples and the coupling relation into a neural network, and learns the year-by-year change rule of urban general population and employment rate;
the urban power module inputs the historical data into a trained neural network, predicts future urban general population and employment rate, and forms future macroscopic population data together by the future urban general population and employment rate.
3. The method of claim 1, wherein the demographic topology algorithm is implemented using a multi-neuron SOM network;
the population module is based on a population classification topology algorithm and an equal proportion iterative fitting method, and expands microscopic population data of individuals, families, buildings, plots and regional scale current years from macroscopic population data of current years, and comprises the following steps:
the population module utilizes a SOM network of multiple neurons to automatically clean, classify and reorganize urban resident sampling survey data to obtain resident information of each scale;
the population module constructs microscopic population data samples of personal, family, building, land block and area scale according to resident information of each scale, and constructs macroscopic population data samples according to census statistical information;
the population module takes the macro population data sample as input, takes the micro population data sample as output, inputs the micro population data sample into an equal proportion iteration fitting model for training, and learns population structural features between the macro population data and micro population data of each scale;
the population module inputs macroscopic population data of the current year into a trained equal-proportion iterative fitting model, and outputs microscopic population data of individuals, families, buildings, plots and regional scale current year.
4. The method of claim 1, wherein the traffic module calculates traffic travel data for each scale of target years from land data and micro population data for each scale of target years using a traffic activity chain algorithm, comprising:
the traffic module predicts a travel mode and a route of the scale resident target years by using a traffic activity chain algorithm and taking the characteristic value of the current resident behaviors of each scale as input and combining land data and microscopic population data of each scale target years, and the travel mode and the route jointly form traffic travel data of each scale target years;
and the traffic module predicts the supply and demand balance relation between traffic facilities and travel demands of each scale of target years according to the traffic travel data of each scale of target years.
5. The method of claim 1, wherein the city deduction module derives population data changes and land data changes for each scale of the target year from microscopic population data and traffic travel data for each scale based on a city deduction algorithm, comprising:
the city deduction module is used for calculating land data change of each scale of target years from the land data of each scale according to the supply-demand balance relation between each scale of traffic facilities and travel demands based on a city deduction algorithm;
the city deduction module deducts population data changes of the target years of each scale according to land data changes of the target years of each scale and traffic travel data based on a city deduction algorithm.
6. The method of claim 1, wherein the city deduction module and the traffic module form year-by-year alternate feedback and perform iterative computation to achieve year-by-year deduction of the target city, comprising:
the city deduction module feeds back population data changes and land data changes of each scale target year to the traffic module;
the traffic module substitutes the traffic activity chain algorithm to calculate the traffic trip data of the target year according to the fed-back land data and micro population data of the target year of each scale;
the city deduction module deducts population data change and land data change of the next step target year of each scale according to microscopic population data and traffic trip data of the target year of each scale based on a city deduction algorithm, feeds back the population data change and the land data change to the traffic module, and starts simulation calculation of the next step target year;
the cycle is repeated, and the annual deduction of the target city is realized.
7. The method as recited in claim 1, further comprising:
after each module completes simulation calculation, the accuracy, stability and reliability of the calculation result are checked;
under the condition that the test result meets the requirement, each module transmits the calculation result to other modules for the other modules to finish calculation;
under the condition that the test result does not meet the requirement, each module executes self-feedback training to improve the calculation accuracy until the test result meets the requirement.
8. The method of claim 1, wherein each module invokes an SDK and an API of each mainstream simulation software to perform simulation calculations, invokes a simulation deduction algorithm of a mainstream to perform simulation deduction, the simulation deduction algorithm comprising: at least one of cellular automata, finite element, data fitting, and parameter estimation.
9. The method of claim 1, wherein the system further comprises a graphical display interface, the method further comprising:
and responding to different topics selected by the user, and displaying simulation deduction information of traffic topics, building topics, facility topics or population topics by the graphical display interface.
10. A multidimensional city simulation deduction system based on city big data is characterized by comprising: a macroscopic model for reflecting urban macroscopic information and a microscopic model for reflecting urban microscopic information; the macroscopic model comprises an urban power module, and the microscopic model comprises a population module, a traffic module and an urban deduction module;
the urban power module is used for deducing future urban general population and employment rate according to coupling relation and historical data of macro elements influencing the development of a target city by adopting a neural network regression prediction method, and the future urban general population and employment rate jointly form future macro population data;
the population module is used for expanding microscopic population data of individuals, families, buildings, plots and regional scale current years from macroscopic population data of current years based on a population classification topological algorithm and an equal proportion iterative fitting method, wherein the microscopic population data comprises a general population of each scale and specific characteristic data of each person;
the traffic module is used for calculating traffic travel data of each scale of target years according to land data and microscopic population data of each scale of target years by using a traffic activity chain algorithm;
the city deduction module is used for deducting population data change and land data change of each scale target year according to microscopic population data and traffic travel data of each scale based on a city deduction algorithm;
the city deduction module and the traffic module form annual alternate feedback and perform iterative calculation to realize annual deduction of the target city.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310457224.4A CN116167254A (en) | 2023-04-26 | 2023-04-26 | Multidimensional city simulation deduction method and system based on city big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310457224.4A CN116167254A (en) | 2023-04-26 | 2023-04-26 | Multidimensional city simulation deduction method and system based on city big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116167254A true CN116167254A (en) | 2023-05-26 |
Family
ID=86416775
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310457224.4A Pending CN116167254A (en) | 2023-04-26 | 2023-04-26 | Multidimensional city simulation deduction method and system based on city big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116167254A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117709811A (en) * | 2024-02-05 | 2024-03-15 | 河北省交通规划设计研究院有限公司 | Urban planning system and method based on urban simulation |
-
2023
- 2023-04-26 CN CN202310457224.4A patent/CN116167254A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117709811A (en) * | 2024-02-05 | 2024-03-15 | 河北省交通规划设计研究院有限公司 | Urban planning system and method based on urban simulation |
| CN117709811B (en) * | 2024-02-05 | 2024-04-19 | 河北省交通规划设计研究院有限公司 | Urban planning system and method based on urban simulation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112216108B (en) | Traffic prediction method based on attribute-enhanced space-time graph convolution model | |
| Ke et al. | A partitioned and asynchronous cellular automata model for urban growth simulation | |
| Long et al. | Mapping block-level urban areas for all Chinese cities | |
| Carreno et al. | A cellular automaton approach to spatial electric load forecasting | |
| CN106780089B (en) | Permanent basic farmland planning method based on neural network cellular automaton model | |
| CN112163367B (en) | Firefly algorithm and cellular automaton fused city expansion simulation prediction method | |
| CN112541302A (en) | Air quality prediction model training method, air quality prediction method and device | |
| CN110164129B (en) | Single-intersection multi-lane traffic flow prediction method based on GERNN | |
| CN110826244B (en) | Conjugated gradient cellular automaton method for simulating influence of rail transit on urban growth | |
| Zhao et al. | Incorporating spatio-temporal smoothness for air quality inference | |
| Mantelas et al. | Using fuzzy cellular automata to access and simulate urban growth | |
| Zhang et al. | CGAIL: Conditional generative adversarial imitation learning—An application in taxi Drivers’ strategy learning | |
| Yu et al. | Passenger flow prediction for new line using region dividing and fuzzy boundary processing | |
| CN116167254A (en) | Multidimensional city simulation deduction method and system based on city big data | |
| CN116756828A (en) | Urban space planning method, medium and system | |
| Dadashpour Moghaddam et al. | A GIS-based assessment of urban tourism potential with a branding approach utilizing hybrid modeling | |
| Guan et al. | HGAT-VCA: Integrating high-order graph attention network with vector cellular automata for urban growth simulation | |
| Leprêtre et al. | Fitness landscapes analysis and adaptive algorithms design for traffic lights optimization on SIALAC benchmark | |
| Cao et al. | A grey wolf optimizer–cellular automata integrated model for urban growth simulation and optimization | |
| CN113240219A (en) | Land utilization simulation and prediction method | |
| CN117079148A (en) | Urban functional area identification method, device, equipment and medium | |
| Quan et al. | An optimized task assignment framework based on crowdsourcing knowledge graph and prediction | |
| Ma et al. | Research and application of second-hand housing price prediction model based on LSTM | |
| CN116612633A (en) | Self-adaptive dynamic path planning method based on vehicle-road cooperative sensing | |
| CN108199895A (en) | A kind of intelligent bayonet optimization placement method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |