CN115049158A

CN115049158A - Method, system, storage medium and terminal for predicting running state of urban system

Info

Publication number: CN115049158A
Application number: CN202210965717.4A
Authority: CN
Inventors: 赵鹏军
Original assignee: Peking University
Current assignee: Peking University
Priority date: 2022-08-12
Filing date: 2022-08-12
Publication date: 2022-09-13
Anticipated expiration: 2042-08-12
Also published as: CN115049158B

Abstract

The invention discloses a method, a system, a storage medium and a terminal for predicting the running state of an urban system, wherein the method comprises the following steps: determining historical benchmark annual data of a city to be predicted and predicted target future years according to data provided by a data management platform in advance; determining the number of model iterations according to historical benchmark year data and a target future year; if the iteration times are single iterations, inputting historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction, outputting a prediction result of a target future year, and feeding back the prediction result to a customer service platform; the pre-constructed urban system simulation prediction model comprises a plurality of modules, associated variables and mathematical relations exist between the interiors of the modules and the modules, and the associated variables and the mathematical relations are used for simulating the mutual influence and feedback between the interiors of the modules and the modules. The method and the device can improve the quantitative simulation and accurate judgment capability of the city.

Description

Method, system, storage medium and terminal for predicting running state of urban system

Technical Field

The invention relates to the technical field of computer software, in particular to a method, a system, a storage medium and a terminal for predicting an operation state of an urban system.

Background

The city is a complex and huge system, the components of the system are diversified, the interaction relationship is complicated, and the operation and development state of the city relates to aspects of social economy, population employment, land evolution, transportation travel and the like. The advanced dynamic simulation and prediction technology of the urban system can realize real-time simulation perception of the urban comprehensive system, is favorable for identifying and diagnosing urban problems in time and improves urban management efficiency; meanwhile, the influence and consequence of the current important decisions such as city planning, construction and operation in a future period can be accurately predicted and evaluated, the city decisions are optimized according to the conclusion of prediction and evaluation, adverse consequences are avoided, decision risk is reduced, and resources such as city capital and land are saved.

The urban system operation state prediction technology commonly used at present comes from foreign countries, such as the UrbanSim model technology in the United states, but China is still blank in the aspect of the urban simulation technology of systematization integration, and the urban system simulation technology becomes the technology of 'neck card'.

In the prior art, the urban system running state prediction comprises two technical schemes, wherein the first technical scheme is that of UrbanSim, and the second technical scheme is that of simulation of a cellular automaton based on dynamic constraint and a complex urban system.

The UrbanSim technology is a model of an urban system developed by its research team, professor Paul Waddell, California university Berkeley, California. The model comprises sub models such as a family and employment location selection and flow model, a reachability model, a real estate development model, a land price model and the like, and each sub model is constructed based on a random utility theory, a discrete selection model, a microscopic location selection model and characteristic price regression. The required data mainly comprises resident microscopic individual data, employment microscopic individual data, land utilization data, planning data, demographic data, employment statistical data, traffic data and the like, wherein the decision input variables mainly comprise traffic networks, control of total amount or growth rate of families and employment, development constraint, vacancy rate, specific development projects and the like; the decision result output variables cover the policy fields of families, employment, energy consumption, environmental protection and the like. The initial operating computer language of UrbanSim is Java, and the software architecture is updated to Python language later; the initial result can be visualized into a two-dimensional plane display, and then an UrbanSim cloud platform and a user interface based on a browser are gradually built, so that the functions of input, output and 3D Web map display are added.

Cellular Automata (CA) is a dynamic evolution system composed of a large number of cells through simple interaction, and the method is widely applied to urban system simulation and can predict the future evolution process of an city based on the historical development trend. The transformation rule is the core of the CA model, the probability of land transformation needs to be determined according to a plurality of factors such as bidding renting theory and the like in simulation, the probability can be expressed through a multivariate Logistic regression model, and variable parameter values of the model can be corrected through historical data. The main input data is urban historical data, including land utilization types of cells and selected Logistic regression variable data, such as gradient, distance from a city center, distance from a traffic facility and the like; the decision input variables comprise a land planning policy and the like; and outputting variables of the decision result into urban land utilization distribution. The urban system simulation technology mainly relies on GIS software to carry out calculation and two-dimensional visualization, and is not integrated into a mature software product.

In the prior art, the defects of the following layers exist at present, (1) in a theoretical layer, urban elements covered by a model constructed by the existing urban system operation state prediction technology are incomplete, and the operation state of all the urban elements is difficult to simulate and predict. For example, a system model represented by UrbanSim mainly depicts the spatial distribution of population and employment activities in a land module, and classification and land evolution of urban land cannot be predicted, while an urban complex system model represented by CA lacks consideration on the social and economic aspects of cities, and both the models have insufficient response to urban traffic systems, such as microscopic traffic flow distribution and urban congestion problems. The urban system simulation and prediction technology needs to integrate the interaction of regional population, economy, land utilization, traffic and other subsystems and add consideration to elements such as natural resource conditions, policy influence and the like. (2) In terms of model architecture, the urban system simulation model constructed in the prior art is relatively rough in consideration of time difference of change of each element in the subsystem and mutual influence thereof. The urban system model lacks analysis of time-lag effect and interaction relation between sub-modules, and a complete dynamic feedback cycle mechanism is not established. (3) In the aspect of data, the current urban system operation state prediction technology mainly uses statistical data and is insufficient in urban microscopic level simulation. At present, the existing urban model for depicting microscopic individual behaviors based on a discrete selection model is limited by the availability of data, and the difficulty in acquiring data with small granularity is high, so that real-time fine simulation of a city is difficult to realize. (4) In the aspect of policy response, a model constructed by the existing mature city system operation state prediction technology is mostly applied to city practice in Europe and America, and the problem of connection with homeland space planning and government decision making under a Chinese city management system is not considered. The existing system model cannot simulate the development state of the urban system under the condition of the territorial space planning and the government decision intervention, and has insufficient response to the government planning target and the expected policy effect. (5) In the aspect of model usability, the urban system model constructed by the current technology is mainly oriented to scientific researchers and planning practitioners, and needs to be programmed by a computer or be processed geographically in GIS software to calculate the model prediction result.

Disclosure of Invention

The embodiment of the application provides a method, a system, a storage medium and a terminal for predicting an operation state of an urban system. The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview and is intended to neither identify key/critical elements nor delineate the scope of such embodiments. Its sole purpose is to present some concepts in a simplified form as a prelude to the more detailed description that is presented later.

In a first aspect, an embodiment of the present application provides a method for predicting an operating state of an urban system, which is applied to a scientific computing platform, and the method includes:

determining historical benchmark annual data of a city to be predicted and predicted target future years according to data provided by a data management platform in advance;

determining the number of model iterations according to historical benchmark year data and a target future year;

if the iteration times are single iterations, inputting historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction, outputting a prediction result of a target future year, and feeding the prediction result back to a customer service platform;

the pre-constructed urban system simulation prediction model comprises a plurality of modules, associated variables and mathematical relations exist between the interiors of the modules and the modules, and the associated variables and the mathematical relations are used for simulating the interaction and feedback between the interiors of the modules and the modules.

Optionally, determining historical baseline year data of the city to be predicted includes:

connecting a city system simulation measurement model database stored by data provided by a data management platform in advance;

determining the partition of index data in an urban system simulation measurement model database;

extracting basic geographic information data, multivariate space-time big data and statistical data of a historical benchmark year from the partition to which the index data belongs;

and determining basic geographic information data, multivariate space-time big data and statistical data of the historical benchmark year as historical benchmark year data.

Optionally, the pre-constructed urban system simulation and prediction model comprises an urban land simulation and evolution module, a population and employment distribution module, a real estate price module, a traffic demand distribution module and a traffic mode sharing and path distribution module;

inputting historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction, and outputting a prediction result of a target future year, wherein the method comprises the following steps:

integrating an interest point land identification algorithm and a Logistic-CA-Markov model by an urban land simulation and evolution module, and carrying out urban land evolution simulation by combining the historical benchmark year data to obtain a land utilization simulation result;

the population and employment distribution module predicts urban population distribution and employment position distribution by using a location selection model and a space gravity model and combining the historical benchmark annual data and the land utilization simulation result to obtain population and employment total amount and distribution results;

the real estate price module establishes a linear regression model incorporating the population and employment prediction results and the traffic cost, and simulates the development trend of the real estate prices by combining the historical benchmark annual data, the population and employment total amount and the distribution result to obtain a real estate price result;

the traffic demand distribution module is based on a trip chain model and combines the historical reference year data dynamic prediction source point-destination point matrix, a land utilization simulation result, a population employment total amount and distribution result and a room price result to obtain a traffic OD distribution result;

the traffic mode sharing and path distributing module predicts traffic mode selection and path flow distribution through an MNL model and a user balance distributing model and by combining the historical benchmark annual data and the traffic OD distribution result to obtain resident trip traffic mode division and traffic flow road section distribution results;

and determining the land utilization simulation result, the population employment total amount and distribution result, the room price result, the traffic OD distribution result, the resident travel traffic mode division and the traffic flow road section distribution result as the prediction result of the target future year.

Optionally, the method further includes:

according to the pre-constructed urban system simulation prediction model, calculating a decision induction output index by combining the prediction result of the target in the next year;

and judging whether each decision induction output index is in a safe state or not according to a preset early warning threshold value, and carrying out intelligent early warning evaluation on the index in a dangerous state to obtain an evaluation result.

Optionally, the method further includes:

when a decision variable updating request is received, obtaining decision variable data;

updating the corresponding decision variables of the pre-constructed urban system simulation prediction model according to the decision variable data to obtain an updated prediction model;

inputting the historical reference year data into an updated prediction model for simulation prediction, and outputting the prediction result of the city system operation in the next year after decision regulation;

and comparing and analyzing the predicted result of the target coming year with the predicted result of the target coming year after decision regulation and control, and outputting an analysis report.

Optionally, integrating the interest point land identification algorithm and the Logistic-CA-Markov model, and performing urban land evolution simulation by combining historical benchmark year data, includes:

determining interest point data and mobile phone signaling data in the multivariate space-time big data and the statistical data by using an interest point land identification algorithm;

and inputting the point of interest data, the mobile phone signaling data and the basic geographic information data into a Logistic-CA-Markov model to carry out urban land evolution simulation.

Optionally, determining the number of model iterations according to the historical reference year data and the target future year includes:

determining a model operation period;

calculating the total period between the historical benchmark year and the target future year;

and determining the ratio of the total period to the model operation period as the number of model iterations.

In a second aspect, an embodiment of the present application provides a system for predicting an operation state of an urban system, where the system includes:

the system comprises a data management platform, a scientific computing platform and a customer service platform; wherein the content of the first and second substances,

the data management platform, the scientific computing platform and the customer service platform are sequentially in communication connection;

the basic information determining module is used for determining historical benchmark annual data of a city to be predicted and predicted target future years through data provided by the data management platform in advance;

the model iteration frequency determining module is used for determining the model iteration frequency according to the historical reference year data and the target future year;

the prediction result output feedback module is used for inputting the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction if the iteration times are single iteration, outputting the prediction result of the target future year and feeding the prediction result back to the customer service platform;

In a third aspect, embodiments of the present application provide a computer storage medium having stored thereon a plurality of instructions adapted to be loaded by a processor and to perform the above-mentioned method steps.

In a fourth aspect, an embodiment of the present application provides a terminal, which may include: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the above-mentioned method steps.

The technical scheme provided by the embodiment of the application can have the following beneficial effects:

in the embodiment of the application, the urban system running state prediction system firstly determines historical reference year data of a city to be predicted and a predicted target coming year according to data provided by a data management platform in advance, then determines the iteration times of a model according to the historical reference year data and the predicted target coming year, and finally inputs the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction if the iteration times are single iteration, outputs the prediction result of the target coming year and feeds the prediction result back to a client service platform; the pre-constructed simulation prediction model of the urban system comprises a plurality of modules, wherein correlation variables exist among the modules, and the correlation variables are used for simulating the interaction and feedback among the modules. According to the urban system operation state prediction method, the urban system simulation prediction model is constructed in advance and comprises the modules, the associated variables and the mathematical relations exist between the interiors of the modules and among the modules, and the associated variables and the mathematical relations are used for simulating the mutual influence and feedback between the interiors of the modules and among the modules, so that the urban system operation state prediction and early warning with high precision and high spatial resolution can be realized under the mutual cooperation of the modules, the urban system operation state prediction and early warning can be used as an integrated simulation tool to support urban planning, construction and treatment policy making, and the urban quantitative simulation and judgment capability is improved.

It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the invention, as claimed.

Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the invention and together with the description, serve to explain the principles of the invention.

Fig. 1 is a schematic flowchart of a method for predicting an operating state of an urban system according to an embodiment of the present disclosure;

fig. 2 is a structural design diagram of a simulation prediction model of an urban system according to an embodiment of the present disclosure;

fig. 3 is a variable relation diagram of a simulation prediction model of an urban system according to an embodiment of the present disclosure;

fig. 4 is a technical route diagram of a simulation prediction model of an urban system according to an embodiment of the present application;

fig. 5 is a schematic flowchart of another urban system operation state prediction method according to an embodiment of the present application;

fig. 6 is a city simulation and prediction (city sps) application platform architecture provided in an embodiment of the present application;

fig. 7 is a schematic structural diagram of an urban system operation state prediction system according to an embodiment of the present application;

fig. 8 is a schematic structural diagram of a terminal according to an embodiment of the present application.

Detailed Description

The following description and the drawings sufficiently illustrate specific embodiments of the invention to enable those skilled in the art to practice them.

It should be understood that the described embodiments are only some embodiments of the invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

When the following description refers to the accompanying drawings, like numbers in different drawings represent the same or similar elements unless otherwise indicated. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the present invention. Rather, they are merely examples of systems and methods consistent with certain aspects of the invention, as detailed in the appended claims.

In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. The specific meanings of the above terms in the present invention can be understood in specific cases to those skilled in the art. In addition, in the description of the present invention, "a plurality" means two or more unless otherwise specified. "and/or" describes the association relationship of the associated objects, meaning that there may be three relationships, e.g., a and/or B, which may mean: a exists alone, A and B exist simultaneously, and B exists alone. The character "/" generally indicates that the former and latter associated objects are in an "or" relationship.

The application provides a method, a system, a storage medium and a terminal for predicting an operation state of an urban system, so as to solve the problems in the related technical problems. In the technical scheme provided by the application, because the urban system simulation prediction model is constructed in advance, the model comprises a plurality of modules, associated variables and mathematical relations exist between the interiors of the modules and the modules, and the associated variables and the mathematical relations are used for simulating the mutual influence and feedback between the interiors of the modules and the modules, so that the urban system running state monitoring and early warning with high precision and high spatial resolution can be realized under the mutual cooperation of the modules, the urban system simulation prediction model can be used as an integrated simulation tool for supporting urban planning and policy making of construction and treatment, the urban quantitative simulation and accurate judgment capabilities are improved, and the following exemplary embodiment is adopted for detailed description.

The method for predicting the operating state of the urban system according to the embodiment of the present application will be described in detail below with reference to fig. 1 to 6. The method may be implemented by means of a computer program, which may be run on a city system operating state prediction system based on the von neumann system. The computer program may be integrated into the application or may run as a separate tool-like application.

Referring to fig. 1, a schematic flow chart of a method for predicting an operating state of an urban system is provided in an embodiment of the present application, and is applied to a scientific computing platform. As shown in fig. 1, the method of the embodiment of the present application may include the following steps:

s101, determining historical reference year data of a city to be predicted and a predicted target future year according to data provided by a data management platform in advance;

the system of the application is composed of three parts, namely a data management platform, a scientific computing platform and a customer service platform. The data management platform is a flow tool for entering data from a local storage into a server (database) for storage, provides data for a scientific computing platform, is generally maintained and used by a platform operator, and provides two main functions of data standardization check and parameter automatic computation. A scientific computing platform integrates a core algorithm of a city whole-system quantitative simulation model, realizes core functions of city element deduction, decision simulation, intelligent early warning and the like through the support of software and hardware environments of a high-performance server, and provides result data which are analyzed and processed well for a customer service platform. The customer service platform provides services to users through a browser in a SaaS (software as a service) or DaaS (data as a service) manner. Has five functional modules: the method comprises the following steps of city element deduction (city reference prediction), city decision simulation (policy simulation through core policy regulation and control indexes), city dynamic monitoring (visual large-screen display of all calculation results), city intelligent early warning (early warning of element items deviating from city development targets), and city data service (providing functions such as data space statistical analysis).

Specifically, in terms of the runtime platform and development language: the system platform integrally adopts a B/S architecture. In the aspect of server hardware, an ARM chip architecture and an X86 chip architecture are simultaneously supported; in the aspect of a server operating system, the operation is based on a Linux operating system; the database adopts a Vasebase database (developed based on open Gauss open source enterprise-level database); the core business code is developed mainly based on python language; the user side interface is operated based on a browser and is mainly developed by adopting an HTML (hypertext markup language) and a javaScript language.

In terms of computing performance and duration: taking a typical scenario and a low-carbon city policy scenario as an example, a complete policy simulation deduction operation needs to sequentially run calculation links such as a city land simulation and evolution module, a population and employment distribution module, a real estate price module, a traffic demand distribution module, a traffic mode sharing and path distribution module, a format conversion module, a policy induction index output module, a policy scoring module and the like, and the calculation takes about 15-20 hours in a typical calculation environment (mainly configured as a kunpeng 920-32 core chip, the chip frequency is 2.6GHz, and the memory is 256 GB).

The platform has flexible redevelopment performance and is embodied in the following aspects: the core algorithm adopts a modular organization scheme, so that a new functional module is conveniently added; according to decision requirements, a new policy simulation scene can be developed, or the existing core regulation and control indexes are flexibly organized to form a new decision path scheme; the method supports the introduction of a new implementation algorithm aiming at the same city calculation scene to form mutual verification, or selects a technical method with higher matching for different cities or regions.

In the embodiment of the application, when historical benchmark year data of a city to be predicted is determined, firstly, a city system simulation measurement model database stored by data provided by a data management platform in advance is connected, then, the affiliated subarea of index data in the city system simulation measurement model database is determined, secondly, basic geographic information data, multivariate spatiotemporal big data and statistical data of the historical benchmark year are extracted from the affiliated subarea of the index data, and finally, the basic geographic information data, the multivariate spatiotemporal big data and the statistical data of the historical benchmark year are determined as the historical benchmark year data.

Specifically, the urban system simulation measurement model database is built, and good support is provided for spatial data types, spatial indexes and spatial functions. The database carries out partition management on system support data and index data, the system support data comprises relevant data such as platform users and project management, and the index data comprises input data, process data and result data relevant to city model calculation. The index data is a core part of the database of the application and is composed of index metadata (attribute related data) and index content data. The input data in the index data comprises basic geographic information data (urban base map, road network, public traffic line, track network and the like), multivariate space-time big data (mobile phone signaling data, POI data and the like), statistical data (statistical yearbook, economic census, traffic trip survey data and the like), process data is an intermediate result of model operation, and result data comprises a submodule prediction result and a decision induction index output result.

Specifically, the invention applies the space-time big data on the basis of basic geographic information data and statistical data, and can realize the microscopic simulation prediction of kilometer grid scales.

The first category of spatiotemporal big data is POI (point of interest) data. In the invention, POI data is mainly used for identifying the functions of the urban current land. And carrying out significance weight assignment on various POI facilities, calculating the POI frequency density of the land grid, and identifying the land function corresponding to the POI with the highest frequency density as the dominant land function of the grid. POI data is large in quantity, fine in classification and easy to obtain, and urban land function simulation of a grid scale of 250 meters can be achieved.

The second type is mobile phone signaling big data. In the invention, the big data of the mobile phone signaling is extracted, cleaned and processed to provide the reference annual data of the kilometer grid scale population, employment and traffic generation distribution for the prediction model. The method comprises the following steps that firstly, city classification is carried out on distribution and migration data of frequent population and employment, wherein the data comprises age, gender, residence information, residential area grid number, grid residential population number and grid employment population number; OD data among urban grids comprises a starting point grid, a finishing point grid, a gender grouping, an age grouping and a population number of sample expansion; and thirdly, urban traffic trip chain data comprise a starting point grid, a residence point track, a terminal point grid and population flow.

Meanwhile, the mobile phone signaling data is used for correcting the land function identification. And training the mapping relation between the resident travel activities based on the mobile phone signaling big data and the urban land functions through a machine learning model, and further correcting the land function distribution identified through the POI data.

S102, determining the iteration times of the model according to historical reference year data and a target future year;

in the embodiment of the application, when the number of model iterations is determined according to the historical reference year data and the target future year, the model operation period is determined firstly, then the total period between the historical reference year and the target future year is calculated, and finally the ratio of the total period to the model operation period is determined as the number of model iterations.

S103, if the iteration frequency is single iteration, inputting historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction, outputting a prediction result of a target future year, and feeding the prediction result back to a customer service platform;

Generally, the urban system simulation and prediction model constructed by the method comprises five modules of urban land simulation and evolution, population and employment distribution, real estate price, traffic demand distribution, traffic mode sharing and path distribution, and covers the key elements of population, industry, land, traffic and the like in the urban system.

For example, as shown in fig. 2, since the urban land utilization pattern affects the real estate price, thereby affecting population migration decisions, population distribution and job-hold relationship directly affect the generation of travel demands, and the operation level of the urban transportation system generates feedback on the land utilization pattern by changing the traffic accessibility. Therefore, the model takes the real estate price, the land mixture degree, the position relation coefficient, the traffic travel cost and the location accessibility as important association variables among the submodules, and simulates the interaction among the submodules. On one hand, a sub-module quantitative model is constructed to simulate the evolution process inside each sub-system, and on the other hand, the correlation variables among the sub-modules are set to simulate the mutual influence and feedback among the sub-systems.

In the embodiment of the application, a POI land identification and Logistic-CA-Markov model is integrated by an urban land simulation and evolution module to simulate urban land evolution; the population employment distribution module predicts urban population distribution and employment post distribution by utilizing a zone bit selection model and a space gravity model; the real estate price module establishes a linear regression model incorporating the population and employment prediction results and the traffic cost, and simulates the development trend of the real estate price; the traffic demand distribution module dynamically predicts an OD matrix based on a trip chain model; the traffic mode sharing and path distribution module realizes traffic mode selection and path flow distribution prediction through an MNL model and a user balance distribution model.

In a possible implementation mode, firstly, an urban land simulation and evolution module integrates an interest point land recognition algorithm and a Logistic-CA-Markov model, and carries out urban land evolution simulation by combining historical benchmark annual data to obtain a land utilization simulation result, then a population and employment distribution module utilizes a position selection model and a space gravity model, and predicts urban population distribution and employment position distribution by combining the historical benchmark annual data and the land utilization simulation result to obtain population employment total amount and distribution results, secondly, a real estate price module establishes a linear regression model for incorporating the population and employment prediction results and traffic costs, and simulates the room price development trend by combining the historical benchmark annual data, the population employment total amount and the distribution results to obtain a room price result, and a traffic demand distribution module is based on a travel chain model, and combining the historical benchmark annual data dynamic prediction source point-destination point matrix, a land utilization simulation result, a population employment total amount and distribution result and a room price result to obtain a traffic OD distribution result, then predicting traffic manner selection and path flow distribution by a traffic manner sharing and path distribution module through an MNL (network management language) model and a user balance distribution model by combining the historical benchmark annual data and the traffic OD distribution result to obtain resident trip traffic manner division and traffic flow road section distribution results, and finally determining the land utilization simulation result, the population employment total amount and distribution result, the room price result, the traffic OD distribution result, the resident trip traffic manner division and the traffic flow road section distribution result as the prediction result of the target future year.

Specifically, when an interest point land recognition algorithm and a Logistic-CA-Markov model are integrated and urban land evolution simulation is carried out by combining historical benchmark year data, the interest point land recognition algorithm is firstly adopted to determine interest point data and mobile phone signaling data in multivariate space-time big data and statistical data, and then the interest point data, the mobile phone signaling data and basic geographic information data are input into the Logistic-CA-Markov model to carry out urban land evolution simulation.

Further, when the number of model iterations is not a single iteration, the prediction result generated after the current iteration can be used as the input of the next iteration to continue the iteration, for example, the selected future year is predicted by using the known reference year data as the initial input, the time period of the model operation is 1 year or 5 years, and a multi-round iterative operation mode is adopted. That is, if the model predicts the urban development state in 2035 years at time intervals of 5 years by using 2020 as a reference year, the model will undergo three iterations of 2020-.

Further, after a prediction result of a target in the next year is output, firstly, a prediction model is simulated according to a pre-constructed urban system, decision-making induction output indexes are calculated according to the prediction result of the target in the next year, whether each decision-making induction output index is in a safe state or not is judged according to a preset early warning threshold value, and intelligent early warning evaluation is carried out on the indexes in a dangerous state to obtain an evaluation result. On the basis of a land utilization simulation result, a population employment total amount and distribution result, a room price result, a traffic OD distribution result, a traffic flow road section and other prediction results, a decision-making sensing output index is established by a model, a decision-making sensing output index result is calculated, and the social livability, economic efficiency and ecological civilization level of a city are comprehensively evaluated. Furthermore, the intelligent early warning evaluation is carried out on the index exceeding the threshold value by setting the threshold value for the output index.

Further, after a prediction result of a target coming year is obtained, when a decision variable updating request is received, firstly, decision variable data are obtained, then, corresponding decision variables of a pre-constructed urban system simulation prediction model are updated according to the decision variable data to obtain an updated prediction model, secondly, historical benchmark year data are input into the updated prediction model for simulation prediction, a decision-regulated urban system operation prediction result of the target coming year is output, and finally, the prediction result of the target coming year and the decision-regulated prediction result of the target coming year are compared and analyzed. In the recursive prediction process of the system model, in each prediction period, part of decision variables of the urban system can be updated by depending on a decision implementation scheme, so that the policy effect is simulated in real time. Without decision variable updating, the system model will conform to the existing trend recursive change, i.e. benchmark prediction, while at decision variable updating, the model will operate according to the situation set by the decision variable. The updatable decision variables cover three fields of macroscopic social economy, space management and control and traffic planning management, and are used as core decision regulation variables of a system model to reflect expected values of urban development or specific decisions.

Specifically, when the prediction result is fed back to the customer service platform for display, the user operation interface is a main way for the user to obtain the service of the city simulation and prediction (city sps) application platform. An authorized user can access and use two services of SaaS and DaaS through a browser end. The SaaS service mainly comprises the functions of city factor deduction, city decision simulation, city dynamic monitoring, city intelligent early warning and the like. The DaaS service can obtain the results of various gate data sets of urban subsystems including urban population, land, housing, traffic, public service facilities and the like, and meets the data application requirements of different industries.

The city simulation and prediction (city SPS) application platform developed by the application provides a visualization function, and is realized in the following three ways: firstly, visualizing a console data chart, and performing data visualization expression by comprehensively using various chart modes such as a bar chart, a scatter diagram, a line chart, a box chart and the like for descriptive statistical results; visualization of data space of the console, providing a space visualization method for data carrying space information, and supporting two-dimensional and three-dimensional map visualization; and thirdly, the data visualization large screen is mainly divided into a full system comprehensive large screen and a subsystem subentry large screen from the aspect of function positioning. The whole system comprehensive large screen is used for providing the most important running state data and monitoring and early warning information of the city to the city comprehensive management department. The whole system comprehensive large screen has a plate customization function, and a user can select the content and the position of the comprehensive large screen display by himself. The subsystem large screen comprises city land simulation and evolution, population and employment distribution, real estate price, traffic demand distribution, traffic mode sharing and path distribution plates.

For example, as shown in fig. 3, fig. 3 is a variable relation diagram of an urban system simulation prediction model provided by the present application, where fig. 3 includes an input variable system, a model calculation system, an output variable system, and a decision regulation and control system, data in the input variable system includes basic geographic information data (e.g., an urban base map, a road network, a public traffic line, a track network, etc.), multiple spatial-temporal big data (e.g., cell phone signaling data, POI data, etc.), statistical data (e.g., statistical yearbook, economic census, transportation survey data, etc.), and data fed back by the output variable system, and the above data are input into each model of the model calculation system for prediction, so as to obtain a prediction result of a prediction year, and the prediction result may be influenced according to a decision variable in the decision regulation and control system, so as to obtain a prediction result under decision regulation and control.

The elements in the urban system which are connected with each other are in a dynamic and unbalanced state, so that the system model has high complexity and nonlinear characteristics. How to describe and characterize the urban system structure and mechanism in a quantitative way is the key point of the invention.

For example, as shown in fig. 4, fig. 4 is a technical route diagram of a simulation prediction model of an urban system provided by the present application, and fig. 4 illustrates in detail a model design of each submodule of a quantitative simulation model of an urban system constructed by the present invention, and an action relationship of a kernel endogenous variable and an exogenous input variable in the model. The model traverses each sub-module according to the sequence of urban land simulation and evolution, population and employment distribution, real estate price, traffic demand distribution, traffic mode sharing and path distribution. The urban land simulation and evolution as a starting module only depends on external input data of the base year for calculation. The four module calculation variables comprise external input data of the basic year and prediction results of the preamble module. The prediction result of the preamble module is used as an inter-submodule correlation prediction variable to reflect the mutual influence among urban subsystems. The real estate price, the land mixing degree, the position relation coefficient, the traffic travel cost and the zone bit accessibility are used as important correlation variables among the submodules and are simultaneously used as core input variables of the next iteration to reflect the time delay effect of mutual influence among the subsystems.

In the embodiment of the application, the urban system running state prediction system firstly determines historical reference year data of a city to be predicted and a predicted target coming year according to data provided by a data management platform in advance, then determines the iteration times of a model according to the historical reference year data and the predicted target coming year, and finally inputs the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction if the iteration times are single iteration, outputs the prediction result of the target coming year and feeds the prediction result back to a client service platform; the pre-constructed simulation prediction model of the urban system comprises a plurality of modules, wherein correlation variables exist among the modules, and the correlation variables are used for simulating the interaction and feedback among the modules. Because the urban system simulation prediction model is constructed in advance and comprises the modules, the associated variables and the mathematical relations exist between the interiors of the modules and among the modules, and the associated variables and the mathematical relations are used for simulating the mutual influence and feedback between the interiors of the modules and among the modules, the urban system operation state prediction and early warning with high precision and high spatial resolution can be realized under the mutual cooperation of the modules, the urban system simulation prediction and early warning device can be used as an integrated simulation tool to support urban planning, construction and treatment policy making, and the urban quantitative simulation and accurate judgment capability is improved.

Referring to fig. 5, a schematic flow chart of another method for predicting an operating state of an urban system is provided in the present application, and is applied to a scientific computing platform. As shown in fig. 5, the method of the embodiment of the present application may include the following steps:

s201, determining historical reference year data of a city to be predicted and a predicted target future year according to data provided by a data management platform in advance;

s202, determining the iteration times of the model according to historical benchmark year data and target future years;

s203, if the iteration times are single iteration, inputting historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction, outputting a prediction result of a target future year, and feeding the prediction result back to a customer service platform; the pre-constructed urban system simulation prediction model comprises a plurality of modules, associated variables and mathematical relations exist between the interiors of the modules and the modules, and the associated variables and the mathematical relations are used for simulating the interaction and feedback between the interiors of the modules and the modules.

S204, calculating a decision induction output index according to the pre-constructed urban system simulation prediction model and by combining the prediction result of the target in the next year; for example, as shown in tables 1, 2, and 3; the contents shown in table 1, table 2 and table 3 can be unified and pieced together to be the final decision induction output index;

TABLE 1 decision-making sense output index

TABLE 2 decision-making sense output index

TABLE 3 decision-making sense output index

S205, judging whether each decision induction output index is in a safe state according to a preset early warning threshold value, and carrying out intelligent early warning evaluation on the index in a dangerous state to obtain an evaluation result;

s206, when a decision variable updating request is received, obtaining decision variable data;

according to the method and the system, the core decision regulation variables can be updated according to the decision or planning target through the reserved decision input interface, and the rest conditions are kept unchanged from the reference conditions, so that the simulation of the decision situation is realized. The renewable core decision-making regulation and control variable covers three fields of macroscopic social economy, space management and control and traffic planning management, and the list is shown in a table 4 according to the arrangement of the sub-modules. Core decision control variables are combined to form a control combination aiming at a specific urban strategy, and eight policy control variable combinations of the urban strategy are set in the model by default (table 5 and table 6); table 5 and table 6 can be pieced together to form a final eight-major city strategy policy control variable combination, and the user can also make a user-defined decision on the control variable combination to meet personalized requirements.

TABLE 4 core decision regulatory variable List

TABLE 5 eight major urban strategic policy control variable combinations

TABLE 6 combination of variables for regulating strategic policies of eight cities

S207, updating corresponding decision variables of a pre-constructed urban system simulation prediction model according to the decision variable data to obtain an updated prediction model;

s208, inputting the historical reference year data into the updated prediction model for simulation prediction, and outputting a decision regulation prediction result of the target future year;

s209, comparing and analyzing the prediction result of the target year before with the decision regulation and control prediction result of the target year before, and outputting an analysis report.

The platform of the application consists of three platforms of 'data management', 'scientific computing' and 'customer service'. The data management platform is used for processing standardized data and parameters and inputting the standardized data and the parameters into the scientific computing platform. A scientific computing platform integrates a core algorithm of a city whole-system dynamic simulation and prediction model, and provides core space analysis and computing service through a high-performance server. The customer service platform operates based on a browser, and provides services to users in a SaaS (software as a service) or DaaS (data as a service) manner.

For example, as shown in fig. 6, the SaaS service platform is composed of four service boards: deducing urban elements: a reference prediction platform. And evaluating the development and evolution situation of various core elements of the city in a prediction period, and providing scientific support for city planning.

Secondly, urban decision simulation: and (5) a regulation and control platform of a policy scenario. Aiming at city future policy adjustment, major project planning and the like, a new policy and planning implementation are responded in time by modifying externally input regulation and control indexes and dynamically updating a planning scheme. Monitoring urban state: and carrying out large-screen visual display on the urban state evaluation index results output by the reference prediction and policy scenes. Fourthly, urban data service: and services such as data browsing, data analysis and reporting, data interface (for interfacing with a CIM platform and the like) and the like are provided. The DaaS service platform can obtain data set results of various departments of urban subsystems including urban population, land, housing, transportation, public service facilities and the like, and meets data application requirements of different industries.

The application has the following specific effects:

the technology has good simulation and prediction effects.

The technology of the invention is applied to predict 2020 Beijing City with 2015 as a base year, and the prediction result is compared with actual values such as general population survey, traffic development annual newspaper of Beijing City and the like: in the aspect of urban land simulation and evolution, the total prediction precision of Beijing city reaches 88.16%; in the aspect of the residential population, the prediction precision of the distribution quantity of the residential population of the global grid in Beijing is 71.3 percent; in the aspect of employment position distribution, the prediction precision of the global employment position distribution quantity in Beijing is 83.03%; in terms of real estate price prediction, the overall accuracy is 84%; in the aspect of resident travel mode division, the private travel mode accuracy of a private car reaches 81.4%, and the public transport travel mode prediction accuracy reaches 94.5%. The model has high prediction precision and good simulation effect.

TABLE 7 prediction accuracy of dynamic simulation prediction model of urban system

(II) the technology of the invention builds a user service platform

The technology of the invention builds a user service platform and provides services in two modes of SaaS (software as a service) and DaaS (data and service). Authorized users can access and use the above two services through a local browser. The SaaS service comprises the related functions of city element deduction, city decision simulation, city intelligent early warning, city dynamic monitoring, city data service and the like. The DaaS service can provide various types of foundations and analysis data sets of urban subsystems such as urban population, land, houses, transportation and public service facilities and the like for authorized users, and meets the data application requirements of different industries.

(III) the invention realizes real-time response of decision regulation simulation

The technology realizes real-time response to policy simulation by regulating and controlling exogenous input variables. Taking a low-carbon city policy scenario set by a model as an example, the scenario supports a user to simulate and set a land utilization structure target and a green building coverage rate target of a prediction year, implement a policy of regulating and controlling the holding capacity of a motor vehicle, reduce plans such as a bus fare policy and the like, and a prediction result of city carbon emission under a policy route, and perform intelligent early warning and judgment. Thereby helping the decision maker judge the response condition of the formulated policy to the expected target in real time.

(2) Advantages of the invention

Advantages compared with the background art (urban system simulation technology):

firstly, the invention innovates the dynamic simulation and prediction technology of the urban system. Compared with the background technology, the technology of the invention establishes the dynamic quantitative simulation model of the urban system, truly simulates the city overall view, and improves the accuracy and the scientificity of the model for quantitatively predicting the future development trend of the city. The technology brings more elements on the basis of the existing urban system model, and reflects the urban overall system: expanding the factors such as regional population, economic and natural resource conditions and the like in the dimension of the former factor of two core submodules of land and traffic; in the dimension of the post effect, energy consumption, carbon emission influence and the like are included, and a policy sensing module is added. The technology embodies the mutual influence among the urban subsystems by designing the operation flow of the sub-modules and taking the prediction result of the preorder module as the inter-sub-module association prediction variable; time lag effects of mutual influence among subsystems are reflected by setting core endogenous variables; through model iteration, a longer-term prediction function is realized, and a set of complete and scientific urban system running state simulation and prediction technology is formed.

Secondly, based on multi-source space-time big data, the grid-level refined city simulation and prediction are realized, the urban land simulation reaches 250-meter grid scale, the population distribution simulation reaches 1-kilometer grid scale, and the traffic travel mode division and flow distribution simulation can be accurate to the road segment scale. In addition, the space-time big data has wide data resource coverage, low cost and easy collection, and improves the economic practicability and the popularization of the technology.

Third, the present invention supports multiple decision simulation and optimization scheme selections. The model design of the invention provides a plurality of decision regulation and control interfaces for decision makers, and can simulate future development targets, policy vision and the like in the aspects of urban economy, population, land, traffic and the like, and make early warning judgment, thereby evaluating the rationality and overall benefit of decisions.

Fourthly, the invention constructs an urban simulation and prediction (City SPS) application platform and realizes innovation on the integration of urban system simulation technology. The dynamic simulation and prediction model of the urban system researched and developed by the technology is based on input and processing data of a city SPS data management platform, high-performance calculation is carried out based on the calculation platform, and result visualization inquiry and real-time interactive decision simulation are carried out based on a customer service platform. The development of the application platform realizes the full-flow operation from data processing to model calculation to visual display of the urban system simulation, and the urban system simulation technology with complete functions, real-time interaction and technology integration is constructed.

Fifthly, the city simulation and prediction (city SPS) application platform constructed by the technology has the characteristics of easy landing, easy use, expandability and the like. The easy landing is embodied in that: the method adopts standardized data and algorithm design, is suitable for different types of cities in different regions, and has strong data availability and high algorithm adaptability. The easy use is embodied as follows: the platform adopts the technical means of data selection automation, continuous iteration automation, strategy selection optimization, parameter adjusting range rationalization, analysis report one-key and the like, so that the platform use threshold is effectively reduced; the learning cost is low, professional knowledge background is not needed, the operation is flexible and simple, and non-professional technicians such as government workers can operate on the client service platform. The expandability is enhanced as follows: the platform function adopts a modular organization mode, and new function modules can be flexibly added according to application requirements; meanwhile, the service scene can flexibly organize the available parameters to form a new decision scheme; different technical path methods can be flexibly added in the same calculation scene; in the aspect of function providing, the operation party can optimize and adjust the back-end code of the server and the front-end code of the browser, and the use party can realize the 'non-inductive' upgrading of the platform function.

In one possible embodiment, for example, the example application is developed for Beijing, as follows:

(1) data preparation

TABLE 8 data Source and Profile information

(2) Operation platform

The urban whole-system dynamic quantitative simulation model operates on a data management and scientific computing platform of a City SPS application system constructed by the technology. First, the city in which the model operates is selected: beijing, deducing time granularity: five years, baseline year: in 2015, basic conditions for model operation are set later, and finally all input data required by the model operation are input.

The input data is firstly processed into formats required by each submodule through a data importing and cleaning module, the formats comprise topological statistics of a road network, conversion of grid-level data, street-level data and the like, and then automatic calibration operation of regional parameters is carried out according to historical data input by a prediction city to obtain calibration parameters of each model in the operation of the model.

Importing the input data processed by the preposed module into a computing platform, traversing each sub-module by the computing platform according to the sequence of 'urban land simulation and evolution-population and employment distribution-real estate price-traffic demand distribution-traffic mode sharing and path distribution' to calculate to obtain a prediction result under the reference situation of 2020, and visually displaying the result in an urban element deduction module.

Meanwhile, in a city decision simulation module of a client service end, prediction results under different combination policy situations can be obtained by changing expected planning policy conditions given and input by a user external generation (the rest conditions are kept unchanged from the reference situation), and visual display and comparative analysis of the prediction results are performed on a SaaS service platform of an application system. Taking a low-carbon city as an example, the adjustable policy regulation variables are above, and the proportion of the green buildings of public buildings, commercial buildings and residential buildings can be adjusted by clicking the project for improving the coverage rate of the green buildings.

(3) Simulation prediction

Firstly, in the aspect of displaying results, all simulation prediction results can be visually displayed on a CitySPS platform at a webpage end, including index display, online map display and the like.

In the aspect of prediction accuracy, the prediction result is compared with the actual values of general population survey, Beijing city traffic development annual newspaper and the like: in the aspect of urban land simulation and evolution, the total prediction precision of Beijing city reaches 88.16%; in the aspect of the residential population, the prediction precision of the distribution quantity of the residential population of the global grid in Beijing is 71.3 percent; in the aspect of employment position distribution, the prediction precision of the global employment position distribution quantity in Beijing is 83.03%; in terms of real estate price prediction, the overall accuracy is 84%; in the aspect of resident travel mode division, the private travel mode accuracy of a private car reaches 81.4%, and the public transport travel mode prediction accuracy reaches 94.5%. The model has high prediction precision and good simulation effect.

In the aspect of policy simulation, decision support simulation is realized for predicting and judging whether a target is realized or not according to an expected target of a user-set policy. The low-carbon scene simulates the urban carbon emission result under the expected policies of adjusting a land utilization structure target, a green building coverage rate target, a bus subway fare and the like, and the model predicts that when the urban industrial land and the residential land are reduced by 10% on the basis of the natural evolution result, the urban land carbon emission can be reduced by 5.39%, and the urban total carbon emission can be reduced by 2.74%; when the green building coverage rate of public buildings and residential buildings is improved to 50%, the carbon emission of urban buildings can be reduced by 6.2%, and the total carbon emission of cities can be reduced by 4.36%. Therefore, this policy route fails to achieve the expected effect according to the carbon emission reduction target set by the user by 10%. The user can further inquire and browse the carbon emission change condition of each street unit before and after regulation and control on the result visualization page. The policy simulation result provides powerful data support for the establishment of the urban emission reduction policy.

In the embodiment of the application, the urban system running state prediction system firstly determines historical reference year data of a city to be predicted and a predicted target coming year according to data provided by a data management platform in advance, then determines the iteration times of a model according to the historical reference year data and the predicted target coming year, and finally inputs the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction if the iteration times are single iteration, outputs the prediction result of the target coming year and feeds the prediction result back to a client service platform; the pre-constructed simulation prediction model of the urban system comprises a plurality of modules, wherein correlation variables exist among the modules, and the correlation variables are used for simulating the interaction and feedback among the modules. According to the urban system operation state prediction method, the urban system simulation prediction model is constructed in advance and comprises the modules, the associated variables and the mathematical relations exist between the interiors of the modules and among the modules, and the associated variables and the mathematical relations are used for simulating the mutual influence and feedback between the interiors of the modules and among the modules, so that the urban system operation state prediction with high precision and high spatial resolution can be realized under the mutual cooperation of the modules, the urban system operation state prediction method can be used as an integrated simulation tool to support the planning, construction and management policy making of the city, and the quantitative simulation and judgment capability of the city is improved.

The following are embodiments of systems of the present invention that may be used to perform embodiments of methods of the present invention. For details which are not disclosed in the embodiments of the system of the present invention, reference is made to the embodiments of the method of the present invention.

Referring to fig. 7, a schematic structural diagram of a city system operation state prediction system according to an exemplary embodiment of the present invention is shown. The urban system operation state prediction system can be realized by software, hardware or a combination of the software and the hardware to form all or part of the terminal. The system comprises a data management platform, a scientific computing platform and a customer service platform; wherein the content of the first and second substances,

the scientific computing platform 1 comprises a basic information determining module 10, a model iteration number determining module 20 and a prediction result output feedback module 30.

The basic information determining module 10 is used for determining historical benchmark year data of a city to be predicted and predicted target future years through data provided by the data management platform in advance;

a model iteration frequency determining module 20, configured to determine a model iteration frequency according to historical reference year data and a target future year;

the prediction result output feedback module 30 is used for inputting the historical reference year data into a pre-constructed city system simulation prediction model for simulation prediction if the iteration times are single iteration, outputting the prediction result of the target future year, and feeding the prediction result back to the customer service platform;

It should be noted that, when the urban system operation state prediction system provided in the foregoing embodiment executes the urban system operation state prediction method, only the division of the above functional modules is taken as an example, and in practical application, the above function distribution may be completed by different functional modules according to needs, that is, the internal structure of the device is divided into different functional modules, so as to complete all or part of the above described functions. In addition, the embodiment of the urban system operation state prediction system and the embodiment of the urban system operation state prediction method provided by the above embodiments belong to the same concept, and the detailed implementation process is shown in the method embodiments and is not described herein again.

The above-mentioned serial numbers of the embodiments of the present application are merely for description and do not represent the merits of the embodiments.

The invention also provides a computer readable medium, on which program instructions are stored, and when the program instructions are executed by a processor, the method for predicting the running state of the urban system provided by the above method embodiments is realized.

The present invention also provides a computer program product containing instructions which, when run on a computer, cause the computer to perform the method for predicting an operating state of a city system according to the above-described method embodiments.

Please refer to fig. 8, which provides a schematic structural diagram of a terminal according to an embodiment of the present application. As shown in fig. 8, terminal 1000 can include: at least one processor 1001, at least one network interface 1004, a user interface 1003, memory 1005, at least one communication bus 1002.

Wherein a communication bus 1002 is used to enable connective communication between these components.

The user interface 1003 may include a Display screen (Display) and a Camera (Camera), and the optional user interface 1003 may also include a standard wired interface and a wireless interface.

The network interface 1004 may optionally include a standard wired interface, a wireless interface (e.g., WI-FI interface), among others.

Processor 1001 may include one or more processing cores, among other things. The processor 1001, which is connected to various parts throughout the electronic device 1000 using various interfaces and lines, performs various functions of the electronic device 1000 and processes data by executing or executing instructions, programs, code sets, or instruction sets stored in the memory 1005 and calling data stored in the memory 1005. Alternatively, the processor 1001 may be implemented in at least one hardware form of Digital Signal Processing (DSP), Field-Programmable Gate Array (FPGA), and Programmable Logic Array (PLA). The processor 1001 may integrate one or more of a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), a modem, and the like. Wherein, the CPU mainly processes an operating system, a user interface, an application program and the like; the GPU is used for rendering and drawing the content required to be displayed by the display screen; the modem is used to handle wireless communications. It is understood that the modem may not be integrated into the processor 1001, but may be implemented by a single chip.

The Memory 1005 may include a Random Access Memory (RAM) or a Read-Only Memory (Read-Only Memory). Optionally, the memory 1005 includes a non-transitory computer-readable medium. The memory 1005 may be used to store an instruction, a program, code, a set of codes, or a set of instructions. The memory 1005 may include a stored program area and a stored data area, wherein the stored program area may store instructions for implementing an operating system, instructions for at least one function (such as a touch function, a sound playing function, an image playing function, etc.), instructions for implementing the various method embodiments described above, and the like; the storage data area may store data and the like referred to in the above respective method embodiments. The memory 1005 may optionally be at least one memory system located remotely from the processor 1001. As shown in fig. 8, a memory 1005, which is a kind of computer storage medium, may include therein an operating system, a network communication module, a user interface module, and a city system operation state prediction application program.

In the terminal 1000 shown in fig. 8, the user interface 1003 is mainly used as an interface for providing input for a user, and acquiring data input by the user; the processor 1001 may be configured to call the city system operation state prediction application stored in the memory 1005, and specifically perform the following operations:

In one embodiment, the processor 1001 specifically performs the following operations when determining the historical reference year data of the city to be predicted:

extracting basic geographic information data, multivariate space-time big data and statistical data of a historical benchmark year from the subarea of the index data;

In one embodiment, when the processor 1001 performs simulation prediction by inputting historical reference year data into a pre-constructed city system simulation prediction model and outputs a prediction result of a target future year, the following operations are specifically performed:

integrating an interest point land recognition algorithm and a Logistic-CA-Markov model by using an urban land simulation and evolution module, and combining the historical benchmark annual data to carry out urban land evolution simulation to obtain a land utilization simulation result;

In one embodiment, the processor 1001 further performs the following operations:

In one embodiment, the processor 1001 also performs the following operations:

In one embodiment, the processor 1001, when executing the integrated interest point land recognition algorithm and the Logistic-CA-Markov model, and performing the urban land evolution simulation in combination with the historical reference year data, specifically performs the following operations:

In one embodiment, the processor 1001, when performing the determination of the number of model iterations according to the historical reference year data and the target future year, specifically performs the following operations:

determining a model operation period;

In the embodiment of the application, the urban system running state prediction system firstly determines historical reference year data of a city to be predicted and a predicted target coming year according to data provided by a data management platform in advance, then determines the iteration times of a model according to the historical reference year data and the predicted target coming year, and finally inputs the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction if the iteration times are single iteration, outputs the prediction result of the target coming year and feeds the prediction result back to a client service platform; the pre-constructed simulation prediction model of the urban system comprises a plurality of modules, wherein correlation variables exist among the modules, and the correlation variables are used for simulating the interaction and feedback among the modules. According to the urban system operation state prediction method, the urban system simulation prediction model is constructed in advance and comprises the modules, the associated variables and the mathematical relations exist between the interiors of the modules and among the modules, and the associated variables and the mathematical relations are used for simulating the mutual influence and feedback between the interiors of the modules and among the modules, so that the urban system operation state prediction and early warning with high precision and high spatial resolution can be realized under the mutual cooperation of the modules, the urban system operation state prediction and early warning can be supported as an integrated simulation tool to make urban planning, construction and treatment policies, and the urban quantitative simulation and judgment capabilities are improved.

It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above may be implemented by a computer program to instruct related hardware, and the program for predicting the operating state of the urban system may be stored in a computer-readable storage medium, and when executed, may include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory or a random access memory.

The above disclosure is only for the purpose of illustrating the preferred embodiments of the present application and is not to be construed as limiting the scope of the present application, so that the present application is not limited thereto, and all equivalent variations and modifications can be made to the present application.

Claims

1. A simulation prediction method for an urban system running state is applied to a scientific computing platform, and comprises the following steps:

determining the number of model iterations according to the historical reference year data and the target future year;

if the iteration times are single iterations, inputting the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction, outputting the prediction result of the target previous year, and feeding back the prediction result to a customer service platform;

2. The method of claim 1, wherein the determining historical baseline year data for the city to be predicted comprises:

determining the partition of index data in the urban system simulation measurement model database;

and determining basic geographic information data, multivariate space-time big data and statistical data of the historical reference year as historical reference year data.

3. The method of claim 1 or 2, wherein the pre-constructed urban system simulation prediction model comprises an urban land simulation and evolution module, a population and employment distribution module, a real estate price module, a traffic demand distribution module, a traffic mode sharing and path distribution module;

inputting the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction, and outputting the prediction result of the target future year, wherein the method comprises the following steps:

the traffic demand distribution module is based on a trip chain model and combines the historical benchmark annual data dynamic prediction source point-destination point matrix, a land utilization simulation result, a population employment total amount and distribution result and a room price result to obtain a traffic OD distribution result;

4. The method of claim 1, further comprising:

5. The method of claim 3, further comprising:

6. The method of claim 3, wherein integrating the point of interest land recognition algorithm and the Logistic-CA-Markov model and combining the historical benchmark year data for urban land evolution simulation comprises:

7. The method of claim 1, wherein said determining a number of model iterations from said historical baseline year data and said target future year comprises:

determining a model operation period;

calculating a total period between the historical baseline year and the target future year;

8. A prediction system for urban system operating conditions, the system comprising:

the basic data determining module is used for determining historical benchmark annual data of a city to be predicted and predicted target future years through data provided by the data management platform in advance;

the model iteration frequency determining module is used for determining the model iteration frequency according to the historical reference year data and the target previous year;

the prediction result output feedback module is used for inputting the historical reference year data into a pre-constructed urban system simulation prediction model for simulation prediction if the iteration times are single iteration, outputting the prediction result of the target previous year and feeding the prediction result back to a customer service platform;

9. A computer storage medium, characterized in that it stores a plurality of instructions adapted to be loaded by a processor and to perform the method steps according to any of claims 1-7.

10. A terminal, comprising: a processor and a memory; wherein the memory stores a computer program adapted to be loaded by the processor and to perform the method steps of any of claims 1-7.