Urban governance scheduling method and system based on dynamic evaluation

Abstract

The invention discloses an urban governance scheduling method and system based on dynamic evaluation, and relates to the technical field of urban management and governance, and the method comprises the steps: obtaining a first space region divided by a target city, and marking the functional characteristics of the first space region; and analyzing the feature information of the region, and determining the governance fitness of the region. And if the governance fitness meets a predetermined threshold, calling an intensity database for prediction to obtain a first prediction intensity. Calibrating the prediction according to the dynamic feature information of the region to obtain a first actual density; and if the actual density is not within the preset threshold, performing governance scheduling adjustment. The technical problem that in the prior art, dynamic changes of the environment and the personnel flow cannot be responded in time is solved, and the technical effect of dynamically analyzing the environment and the personnel flow in real time is achieved.

Description

Technical Field

[0001] The present application relates to the field of urban management and governance technology, and in particular to a method and system for urban governance scheduling based on dynamic evaluation. Background Art

[0002] With the development of information technology and big data analysis, the role of dynamic evaluation and real-time analysis in regional planning has gradually increased. In this context, a regional planning scheduling method based on dynamic evaluation has emerged. It comprehensively considers multiple factors such as topography and human activities, realizes dynamic evaluation and rapid adjustment of governance adaptability, and can collect and analyze multi-dimensional characteristic information of urban space in real time, providing scientific support for decision-making.

[0003] At the current stage, relevant technologies have the technical problem of being unable to respond to dynamic changes in the environment and personnel flow in a timely manner. Summary of the invention

[0004] This application provides a method and system for urban governance scheduling based on dynamic evaluation, which obtains the first spatial area divided by the target city and identifies its functional characteristics; analyzes the characteristic information of the area to determine its governance fitness. If the governance fitness meets the predetermined threshold, the density database is retrieved for prediction to obtain a first predicted density. The prediction is calibrated according to the dynamic characteristic information of the area to obtain a first actual density; if the actual density is not within the predetermined threshold, the governance scheduling is adjusted, thereby achieving the technical effect of real-time dynamic analysis of the environment and personnel flow.

[0005] This application provides an urban governance scheduling method based on dynamic evaluation, including: A first spatial area is obtained, where the first spatial area refers to any one area in a set of spatial areas obtained by dividing the target city, and the first spatial area has an identification of a first functional characteristic; the first area characteristic information collected of the first spatial area is analyzed to obtain a first governance fitness of the first spatial area determined as the first functional characteristic; when the first governance fitness meets a predetermined fitness threshold, the density database is retrieved to perform density prediction analysis on the first spatial area to obtain a first predicted density; the first predicted density is calibrated and analyzed according to the first dynamic characteristic information of the first spatial area to obtain a first actual density; when the first actual density is not within the predetermined density threshold, a governance scheduling adjustment is performed on the first spatial area.

[0006] This application also provides an urban governance scheduling system based on dynamic evaluation, including: A first spatial area acquisition module, the first spatial area acquisition module is used to acquire a first spatial area, the first spatial area refers to any one of the spatial area set obtained by dividing the target city, and the first spatial area has an identification of a first functional characteristic; a first governance fitness acquisition module, the first governance fitness acquisition module is used to analyze the collected first area characteristic information of the first spatial area, and obtain the first governance fitness of the first spatial area determined as the first functional characteristic; a first predicted density acquisition module, the first predicted density acquisition module is used to retrieve the density database to perform density prediction analysis on the first spatial area when the first governance fitness meets a predetermined fitness threshold, and obtain a first predicted density; a first actual density acquisition module, the first actual density acquisition module is used to calibrate and analyze the first predicted density according to the first dynamic characteristic information of the first spatial area, and obtain a first actual density; a governance scheduling adjustment module, the governance scheduling adjustment module is used to perform governance scheduling adjustment on the first spatial area when the first actual density is not within the predetermined density threshold.

[0007] The urban governance scheduling method and system based on dynamic evaluation proposed in this application first obtains the first spatial area divided by the target city and identifies its functional characteristics; analyzes the characteristic information of the area to determine its governance fitness. If the governance fitness meets the predetermined threshold, the density database is retrieved for prediction to obtain the first predicted density. The prediction is calibrated according to the dynamic characteristic information of the area to obtain the first actual density; if the actual density is not within the predetermined threshold, the governance scheduling is adjusted, achieving the technical effect of real-time dynamic analysis of the environment and personnel flow. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0009] Figure 1 A flow chart of a method for urban governance scheduling based on dynamic evaluation provided in an embodiment of the present application.

[0010] Figure 2 A structural diagram of a city governance scheduling system based on dynamic evaluation provided in an embodiment of the present application.

[0011] Explanation of the accompanying drawings: first spatial area acquisition module 10, first governance fitness acquisition module 20, first predicted density acquisition module 30, first actual density acquisition module 40, governance scheduling adjustment module 50. DETAILED DESCRIPTION

[0012] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0013] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0014] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0015] The present application embodiment provides a method for urban governance scheduling based on dynamic evaluation, such as Figure 1 As shown, the method includes: Step S100, obtaining the first spatial area, the first spatial area refers to any area in the set of spatial areas obtained by dividing the target city, and the first spatial area has the identification of the first functional characteristics. Specifically, first, determine the basis for dividing the target city, and comprehensively consider factors such as geographical features, administrative regions, and functional requirements. Use tools such as geographic information system technology and urban planning software to implement the division operation, such as demarcating different areas based on natural boundaries, administrative boundaries or functional requirements. After the division is completed, a set of spatial areas is obtained, and an area is selected as the first spatial area, and the first functional characteristic identification is assigned according to the specific functions and characteristics of the area, such as a commercial area can be identified as frequent commercial activities and a large flow of people, a residential area can be identified as a concentrated residential area, complete living service facilities, etc., and an industrial area can be identified as a concentrated factory enterprise and a large volume of cargo transportation.

[0016] Step S200, analyzing the collected first area characteristic information of the first spatial area, and obtaining the first governance fitness of the first spatial area determined as the first functional characteristic. Specifically, first determine the characteristic information type of the first spatial area, including topography, traffic conditions, population distribution, building facilities, and public service facilities. Collect information through methods such as geographic information systems, traffic monitoring equipment, and census data. Then, establish an evaluation index system according to the requirements of the first functional characteristic, for example: the commercial area considers traffic convenience, population density, consumption capacity, and supporting degree of commercial facilities; the residential area considers environmental quality, richness of educational and medical resources, and supporting leisure and entertainment facilities. According to the characteristic indicators, a combination of quantitative analysis and qualitative analysis is used to weight and sum the scores of each indicator to obtain the final governance fitness score. This fitness score can be presented in a numerical score (for example, 1-100 points) or in a grade classification (such as low, medium, and high). Through analysis, the first governance fitness is obtained, and the fitness level is determined.

[0017] In a possible implementation, the collected first area characteristic information of the first spatial area is analyzed to obtain the first governance fitness of the first spatial area determined as the first functional characteristic, and step S200 further includes step S210, reading predetermined terrain indicators. Specifically, the content of the predetermined terrain indicators is determined, and it is clarified that the predetermined terrain indicators include specific elements such as altitude, basins, and peaks. The indicators can reflect the natural geographical characteristics of the first spatial area. For example, altitude can affect climate, environment, and architectural design; basin terrain may affect air circulation and drainage systems; and peaks may impose restrictions on transportation routes and landscape planning. Satellite images, topographic maps, and field surveys are combined. Satellite images can provide macroscopic terrain features, topographic maps can display detailed information such as contour lines, and field surveys can verify and supplement information from other data sources.

[0018] Step S220: collecting multi-dimensional features of the first spatial area based on the predetermined terrain and topography indicators to obtain first terrain and topography feature information. Specifically, analyze the impact of altitude on the first spatial area, consider the climate differences in different altitude areas, the higher the altitude, the lower the temperature and the lower the air pressure. For example, more heating and insulation measures are needed in high altitude areas, evaluate the requirements of altitude on building design, analyze the impact of altitude on the environment, the vegetation types and animal distribution at different altitudes will be different, analyze the impact of basin terrain on the first spatial area, consider the impact of basin terrain on air circulation, analyze the restrictions of basin terrain on transportation planning, the mountains around the basin will affect the layout and construction cost of transportation routes, evaluate the impact of peaks on transportation routes, mountains will become obstacles to transportation, and tunnels, bridges and other engineering facilities need to be built to overcome, through tools such as geographic information systems (GIS) and remote sensing technology, summarize and organize the analysis results of terrain indicators such as altitude, basins, and peaks to form the first terrain feature information, including the description of different terrain features, impact assessment and identification of potential problems, and can take the combination of historical data, satellite images and ground field surveys to help quantify and accurately analyze terrain features.

[0019] Step S230, read the predetermined flow index. Specifically, determine the content of the predetermined flow index, clarify that the predetermined flow index includes factors such as the flow of people and vehicles, distance, road conditions, and traffic convenience. The index can reflect the flow of people and vehicles in the first spatial area. For example, the flow of people reflects the population density and activity intensity of the area; the flow of vehicles can reflect traffic congestion and road carrying capacity; the distance can measure the accessibility between different locations; the road condition includes factors such as road width and road surface quality; the traffic convenience takes into account factors such as public transportation coverage and traffic signal light settings, and the vehicle flow data is obtained through traffic monitoring equipment.

[0020] Step S240, based on the predetermined flow index, multi-dimensional features of the first spatial area are collected to obtain first flow feature information. Specifically, first, by analyzing the time distribution, spatial distribution and flow volume of personnel flow and vehicle flow, the impact of personnel and vehicle flow in different areas on the area is evaluated; then, considering the road conditions, traffic convenience and public transportation coverage, the impact on mobility and traffic efficiency is evaluated. By weighting and normalizing these analysis results, the influence of each flow feature is comprehensively evaluated to obtain the final first flow feature information. This information can be presented in the form of numerical, graded or weighted scores. For example, indicators such as personnel flow, vehicle flow, road conditions and traffic convenience will be given different weights, and combined with preset scoring standards (such as 1-10 scores, or low, medium and high levels) for weighted summary, and finally the flow feature score of the area is obtained. This comprehensive analysis will provide a comprehensive evaluation of personnel flow, vehicle flow, road conditions and other aspects.

[0021] Step S250, analyze the first topographic and topographic feature information and the first flow feature information to obtain the first governance fitness. Specifically, analyze the influence of topography and flow characteristics, compare and analyze the first topographic and topographic feature information and the first flow feature information, and find out the relationship and influence between the two. In order to achieve quantitative evaluation of governance fitness, a governance fitness evaluation model can be established based on the analyzed first topographic and topographic feature information and the first flow feature information. The model can be constructed by the analytic hierarchy process (AHP) or the fuzzy comprehensive evaluation method, and the weight and evaluation criteria of each factor are determined by combining multi-dimensional analysis factors, such as traffic convenience, environmental quality, resource utilization efficiency, etc. First, construct respective evaluation dimensions according to the first topographic and topographic feature information and the first flow feature information, and assign different weights. Then, the analytic hierarchy process is used to compare the degree of influence of different indicators, calculate the relative importance of each factor, and determine the weight coefficient. For the fuzzy comprehensive evaluation method, the evaluation dimensions can be fuzzy processed by constructing fuzzy sets and membership functions, and the governance adaptability of the first spatial area can be comprehensively evaluated by combining expert judgment and actual data. The comprehensive evaluation of the first spatial area is to input the evaluation results of topography, flow characteristics and other economic factors (such as transportation convenience, environmental resource endowment, etc.) into the governance fitness evaluation model, and use the weight coefficients of each dimension to perform weighted summation to calculate an overall fitness score.

[0022] In one possible implementation, the first topographic feature information and the first flow feature information are analyzed to obtain the first governance fitness. Step S250 further includes step S251, calling the city governance database, and extracting the first historical governance record in the city governance database. The first historical governance record refers to the urban planning scheduling record that schedules the governance of the first historical spatial area to the first functional characteristic. Specifically, the role of the urban governance database is clarified, which contains the governance records of different spatial areas in different periods. For example, the database records the planning and scheduling process of a certain area from an industrial area to a commercial area in the past, including information such as measures taken, problems encountered, and the final effect. The first historical governance record is extracted, and the urban governance record that schedules the governance of the first historical spatial area to the same first functional characteristic as the current first spatial area, that is, the first historical governance record, is screened out from the urban governance database.

[0023] Step S252, based on the predetermined terrain indicators, the first historical spatial area is formed with the first historical terrain feature information. Specifically, the first historical spatial area is analyzed using the previously determined predetermined terrain indicators, such as altitude, basin, peak, etc. For example, the terrain features of the first historical spatial area are determined by consulting historical maps, geographical data, and field investigations, including whether there are mountains, rivers, ups and downs, etc. The first historical terrain feature information specifically includes: 1) numerical information, such as the specific altitude in the area, the slope of the ground, the direction and basin range of the river, etc.; 2) level information, such as whether the area belongs to a mountainous area, a plain or a hilly area, and is divided into "simple" or "complex" according to the complexity of the terrain; 3) descriptive information, such as whether there are special geographical phenomena (for example, areas with abundant water resources or areas susceptible to floods). Finally, the terrain feature information obtained by the analysis is sorted and summarized to form the first historical terrain feature information.

[0024] Step S253, performing similarity analysis on the first topographic and terrain feature information and the first historical topographic and terrain feature information to obtain a first situation similarity. Specifically, feature information comparison is performed, and the first topographic and terrain feature information of the current first spatial region is compared with the first historical topographic and terrain feature information of the first historical spatial region one by one, for example, the altitude range of the two, whether there are basins or peaks, etc., are compared, and similarity calculation is performed, and appropriate similarity calculation methods, such as cosine similarity, Euclidean distance, etc., are used to quantify the two topographic and terrain feature information. The first historical topographic and terrain feature information is obtained by quantifying the topographic features of the current first spatial region and the first historical spatial region, including altitude, terrain type, slope, etc. Altitude can be represented by the difference between the maximum altitude and the minimum altitude. The terrain type can be encoded as different numerical values. The slope is quantified by calculating the average slope of the area. The quantified terrain feature data is converted into a feature vector. The first situation similarity uses a similarity calculation method such as cosine similarity or Euclidean distance to compare the terrain features of the current area and the historical area. The first situation similarity is obtained by calculating the angle or distance between the feature vectors of the two. The first situation similarity reflects the similarity between the current area and the historical area in terrain features. The larger the value or the smaller the distance, the higher the similarity between the two.

[0025] Step S254, when the first situation similarity meets the predetermined similarity threshold, the first historical governance difficulty in the first historical governance record is extracted. Specifically, the first historical governance difficulty refers to a comprehensive assessment of the various difficulties and challenges encountered when implementing governance measures for a specific spatial area in the past governance process. The difficulty includes but is not limited to the following categories: 1) Geographical and environmental factors, such as complex terrain, extreme weather, environmental protection requirements, etc. in the region, which may lead to an increase in project costs or delays in implementation progress; 2) Social factors, such as population changes, population structure, and industrial development; 3) Economic and technical difficulties, such as excessive construction costs, technical difficulties, infrastructure construction bottlenecks, etc. Each difficulty can be represented by a numerical scoring standard, usually using a scale from 1 to 5 or a specific quantitative indicator (such as the percentage of increased construction costs, the length of delay, etc.) to indicate the severity of the difficulty, and finally a weighted sum is obtained to obtain a comprehensive value as the first historical governance difficulty.

[0026] Step S255, take the inverse of the first historical governance difficulty as the first governance situation coupling degree. Specifically, determine the relationship between the difficulty and the coupling degree, the difficulty and the coupling degree are inversely proportional, that is, the higher the governance difficulty, the lower the governance situation coupling degree; conversely, the lower the governance difficulty, the higher the governance situation coupling degree. For example, if the first historical governance difficulty is 0.6, then the first governance situation coupling degree is 1 / 0.6≈1.67. Determine the first governance situation coupling degree, calculate the inverse of the first historical governance difficulty, and obtain the first governance situation coupling degree. The coupling degree reflects the governance similarity and reference of the current first spatial area and the first historical spatial area in terms of topography. For example, if the first governance situation coupling degree is high, it means that the current area is similar to the historical area in terms of topography.

[0027] Step S256, performing variation weighting processing on the multiple flow characteristic parameters in the first flow characteristic information to obtain the first governance flow coupling degree. Specifically, multiple key flow characteristic parameters are selected from the first flow characteristic information, such as personnel flow, vehicle flow, traffic distance, traffic convenience, etc. For example, the flow of people is represented by the number of people passing through the area every day, and the flow of vehicles is represented by the number of vehicles passing through per hour. Different weights are assigned to each parameter according to the importance of the flow characteristic parameters and the influence of the degree of change. The basis for determining the weight includes the relative importance of the flow characteristic to the current regional governance objectives and the difference in changes compared with the historical area. For example, if the degree of traffic convenience has a greater impact on the area and there is a significant difference from the historical area, a higher weight can be assigned to the parameter. Through weighted calculation, the values ​​of the flow characteristic parameters are combined to obtain the first governance flow coupling degree, that is, the comprehensive coupling degree between the flow characteristics and the governance effect.

[0028] Step S257, taking the average of the first governance situation coupling degree and the first governance flow coupling degree as the first governance fitness. Specifically, taking into account the topography and flow characteristics, the first governance situation coupling degree reflects the governance similarity in topography, and the first governance flow coupling degree reflects the governance similarity in flow characteristics. Taking the average of the two can comprehensively consider these two factors to obtain the first governance fitness. For example, if the first governance situation coupling degree is 1.67 and the first governance flow coupling degree is 1.2, then the first governance fitness is (1.67+1.2) / 2=1.435, and the first governance fitness is determined. The first governance fitness can be used to measure the governance feasibility and adaptability of the current first spatial area as the first functional characteristic. The higher the fitness, the more similar the area is to the historical successful governance area in terms of topography and flow characteristics, and the difficulty of governance is relatively low.

[0029] Step S300, when the first governance fitness meets the predetermined fitness threshold, the density database is retrieved to perform density prediction analysis on the first spatial area to obtain the first predicted density. Specifically, first, the predetermined fitness threshold is determined according to the target and various factors, and the calculated first governance fitness is compared with it. If it is greater than or equal to the threshold, the relevant data is retrieved from the density database according to the identification and functional characteristics of the first spatial area. The database contains historical density records and related influencing factor records of multiple historical spatial areas consistent with the first functional characteristics, and the data structure is organized by time, regional identification, etc. Next, a suitable prediction method is selected, such as time series analysis, regression analysis or machine learning algorithm, and the data is preprocessed, including cleaning missing values ​​and outliers, standardization and feature engineering. Then, the selected method and preprocessed data are used for prediction, such as predicting future density by inputting time and historical data through a time series model. Finally, the first predicted density including personnel predicted density and vehicle predicted density is obtained, which can be expressed as a numerical value or level.

[0030] In a possible implementation, when the first governance fitness meets the predetermined fitness threshold, the density database is retrieved to perform density prediction analysis on the first spatial area to obtain a first predicted density, and step S300 further includes step S310, extracting the first density time series in the density database, wherein the density database includes historical density record data of multiple historical spatial areas consistent with the first functional characteristics, and the first density time series includes a first vehicle density time series and a first personnel density time series. Specifically, the density database is a collection of historical density records of spatial areas related to different functional characteristics, covering personnel and vehicle density data of multiple historical spatial areas at different time points. Data is essential for predicting the density of the first spatial area with the same functional characteristics. For example, for the functional characteristics of a city's commercial district, the database contains personnel and vehicle density data of multiple mature commercial areas in different time periods, including changes on weekdays, holidays, and different seasons. By extracting the first density time series corresponding to the historical density record data, the changes in the number of vehicles and the number of people in the relevant areas over time in history are recorded respectively. The first vehicle density time series is collected through traffic monitoring equipment, parking lot records, etc., and the first personnel density time series is obtained through census data, human flow monitoring equipment, mobile device positioning data, etc. Based on the time series data, using a prediction algorithm (such as time series analysis or regression model), the first predicted density refers to the prediction of the flow density of people and vehicles in the area in the future based on historical density data.

[0031] Step S320, activating the intelligent prediction model, wherein the intelligent prediction model includes a vehicle prediction layer and a personnel prediction layer.Specifically, an intelligent prediction model is constructed to collect data related to vehicle and personnel density. The collected data include but are not limited to: traffic flow data in different time periods, geometric characteristics of roads, land use types in surrounding areas, weather conditions. For personnel density prediction, the collected data include: demographic information in the area, building function information, time characteristics, public transportation routes and station information, and event arrangements. The collected data are sorted and cleaned to remove outliers and missing values ​​to ensure data quality and integrity. Feature engineering is performed on the sorted data to extract useful features to improve the prediction ability of the model. In terms of vehicle density, time features are constructed, such as dividing a day into different time periods and a week into work hours. For weekdays and weekends, the time information is quantified and encoded so that the model can learn the impact of different time periods on vehicle density, extract spatial features, such as calculating the road congestion index, road connectivity, etc., classify and encode weather conditions, such as sunny days, cloudy days, rainy days, snowy days, etc., and use different numerical values ​​to represent them. In terms of population density, construct a population feature vector, including statistics such as the mean and standard deviation of the age distribution, the proportion of occupational structure, etc., calculate the commercial activity index and educational resource concentration based on the building function information, quantify activity events, such as setting different levels according to the scale of the activity and the expected number of participants, and select the appropriate model algorithm based on the data characteristics and the needs of the prediction task. For vehicle density prediction, use time series Analytical algorithms such as ARIMA (autoregressive integrated moving average model) can capture the trend, seasonality and cyclical characteristics in time series data. For the prediction of personnel density, classification and regression algorithms based on machine learning are used. For example, the decision tree algorithm branches according to different feature conditions to build a prediction model for personnel density with good interpretability. The sorted data set is divided into training set, validation set and test set. The training set is used for model learning and parameter adjustment. The validation set is used to evaluate the performance of the model and select the best hyperparameters during the training process. The test set is used to finally evaluate the generalization ability of the model. Taking the prediction of vehicle density as an example, the LSTM model is used to initialize the parameters of the model first, and the first vehicle in the training set is initialized. The multi-domain feature information is input into the LSTM model in time sequence. The model continuously adjusts parameters through the back-propagation algorithm to minimize the error between the predicted vehicle density and the actual vehicle density. For the prediction of personnel density, similarly, the multi-domain feature information of the first person in the training set is input into the selected model for training. For example, in the decision tree training, the model continuously splits according to the different values ​​of the features to construct a tree structure so that each leaf node corresponds to the same personnel density level or a similar range of personnel numbers as much as possible. By continuously adjusting the conditions and parameters of the split, the prediction error of the model on the training set is minimized, and it is verified and optimized on the validation set, and the trained model is finally evaluated using the test set.

[0032] Step S330, the vehicle prediction layer analyzes the first vehicle multi-domain feature information of the first vehicle density time series to obtain the first predicted vehicle density. Specifically, the first vehicle multi-domain feature information is comprehensive data used to describe vehicle density-related features, obtained through the previous feature engineering processing, including time features, spatial features, traffic-related features, and weather features. The vehicle prediction layer uses the trained vehicle density prediction model to analyze the first vehicle multi-domain feature information. For example, if the LSTM model is used, the first vehicle multi-domain feature information at the current moment is input into the model. The model will calculate the vehicle density prediction value for the future time period based on the previously learned time series pattern and feature relationship, that is, the first predicted vehicle density. The LSTM model can effectively process the long-term dependencies in the time series data through its internal memory unit and gating mechanism, accurately capture the changing trend of vehicle density over time and the influence of various factors on it. During the prediction process, the model will gradually update its internal state based on the input feature information, and finally output the prediction result.

[0033] Step S340, the first personnel multi-domain feature information of the first personnel density time series is analyzed by the personnel prediction layer to obtain the first predicted personnel density. Specifically, the first personnel multi-domain feature information is also data related to personnel density after feature engineering processing, including time features, spatial features, demographic features, public transportation features, and activity event features. The personnel prediction layer processes the first personnel multi-domain feature information according to the trained personnel density prediction model. Taking the random forest model as an example, the first personnel multi-domain feature information is input into multiple decision trees for parallel prediction. Each decision tree will branch and judge according to different combinations of features, and finally obtain a prediction result of personnel density. Then, by synthesizing the prediction results of multiple decision trees, the final first predicted personnel density is obtained. The random forest model can reduce the overfitting risk of a single decision tree and improve the accuracy and stability of the prediction by integrating the prediction capabilities of multiple decision trees.

[0034] Step S350, the first predicted vehicle density and the first predicted personnel density together constitute the first predicted density. Specifically, the first predicted vehicle density obtained through the vehicle prediction layer and the first predicted personnel density obtained through the personnel prediction layer are merged, and the two prediction results reflect the density of the first spatial area from the two aspects of vehicles and personnel, respectively, and together constitute the first predicted density. They can be simply combined into a vector form, such as [first predicted vehicle density, first predicted personnel density], or a comprehensive density index can be calculated according to actual needs, such as weighted summing the number of vehicles and personnel to obtain a single value to represent the first predicted density. The first predicted density can be represented and applied in a variety of ways, depending on actual needs. In terms of traffic management, if it is predicted that the first predicted density of the first spatial area in a certain time period is high, the traffic management department can formulate a traffic diversion plan in advance, such as adjusting the time configuration of traffic lights, increasing the number of traffic police on duty, guiding vehicle diversion, etc., to alleviate traffic congestion. At the same time, according to the first predicted vehicle density, the use of parking lots can be reasonably planned, sufficient parking spaces can be reserved in advance, or vehicles can be guided to surrounding vacant parking lots.

[0035] In a possible implementation, the intelligent prediction model is activated, and the intelligent prediction model includes a vehicle prediction layer and a personnel prediction layer. Step S320 further includes step S321, reading a predetermined unit time zone. Specifically, the predetermined unit time zone is determined. The selection of the predetermined unit time zone needs to be determined according to the specific research object and prediction target. Different unit time zones are suitable for different scenarios and analysis needs. If the weekly periodic changes in the area are studied, such as the difference between weekends and weekdays, then the weekly unit time zone is more appropriate. The density characteristics of different days in a week are observed. For some long-term trend analysis, the monthly or quarterly unit time zone is more helpful to discover seasonal or periodic laws.

[0036] Step S322, slicing the first density time series with the predetermined unit time zone as a constraint to obtain a first time series slice set. Specifically, the first density time series is a sequence of records about the changes in the density of people and vehicles in the first spatial area over time, which contains density data arranged in chronological order and is recorded in smaller time intervals such as hours and minutes. For example, if it is the first density time series data of a month, there is a corresponding record of the density of people and vehicles every hour, forming a long sequence of time data. With the predetermined unit time zone as a constraint, the first density time series is divided into multiple fragments. If the predetermined unit time zone is a day, then the continuous 24 hours are taken as a slice, and the entire first density time series is divided into multiple day fragments. If it is a week, the continuous 7 days are taken as a slice. For the unit time zone of a month, the data within a month is taken as a slice, and a set consisting of multiple time series slices is obtained, that is, the first time series slice set, each slice represents the density time series data within a specific unit time zone.

[0037] Step S323, extract the first slice in the first time series slice set, the first slice refers to the first density time series segment. Specifically, a slice is extracted from the first time series slice set as an example for further analysis and processing, the slice is called the first slice, it is a part of the first density time series segment, the selection of the first slice can be used for subsequent model building and data analysis demonstration, the processing method of the first slice can be extended to the entire first time series slice set to achieve unified processing and analysis of data in all time periods, the first slice is extracted from the first time series slice set by indexing or random selection, if it is processed in sequence, the first slice can be used as the first slice; or a slice can be randomly selected for analysis to verify the versatility and stability of the processing method.

[0038] Step S324, construct a first data group based on the multi-domain feature information of the first segment of the first density time series segment and the first density mode group of the first density time series segment. Specifically, the multi-domain feature information of the first segment is a feature description of the first density time series segment, which contains multiple aspects of information, and is used to reflect the relevant factors of density changes in the time period. In terms of time characteristics, it includes the specific time range to which the segment belongs and the classification of time periods. In terms of spatial characteristics, it involves the geographical location characteristics of the area, the distribution and function of buildings in the area, and in terms of historical trend characteristics, it analyzes the density change trend of the segment in similar time periods in historical data. In terms of external factor characteristics, it includes weather conditions. The multi-domain feature information is sorted and quantified to form a feature vector or data set for subsequent data group formation. The mode of the personnel density and vehicle density data in the data set is calculated respectively. The mode is the data value that appears most frequently in a set of data, reflecting the most common density level in the time period. A similar calculation is performed for the vehicle density. The first fragment of multi-domain feature information and the first density mode are combined together to form a first data group. The multi-domain feature information is used as an input variable and the density mode is used as an output variable to construct a data pair form similar to (x, y), where x is the multi-domain feature information vector and y is the corresponding density mode. For example, x includes time features, spatial features, and external factor features, and y is the personnel density mode or the vehicle density mode of the time period.

[0039] Step S325, supervised learning is performed on the first data group to obtain the intelligent prediction model. Specifically, according to the characteristics of the data and the requirements of the prediction task, a suitable supervised learning algorithm is selected. For density prediction problems, if the data has a linear relationship and the features are relatively simple, a linear regression algorithm can be selected. If the data has a complex nonlinear relationship and multiple feature variables, a neural network is selected. Before supervised learning, some preprocessing operations need to be performed on the first data group, for example, standardizing or normalizing the feature data so that the numerical ranges of different features are on a similar scale to improve the training efficiency and accuracy of the model. For classification problems, if the features are text or category data, encoding processing is required to convert them into numerical form, and the selected supervised learning algorithm is used to perform the first data group. Training, taking the feature information (x) in the first data group as input and the density mode (y) as the target output, allowing the model to learn the relationship between them, initializing the structure and parameters of the neural network, inputting the data in the first data group into the neural network in batches, calculating the predicted value through forward propagation, performing back propagation based on the error between the predicted value and the actual value, adjusting the parameters of the neural network, and after multiple iterative training, until the model error reaches a smaller level or meets the predetermined training stop condition, evaluating the performance of the model, and obtaining a model with better performance, namely, the intelligent prediction model, which can predict the density mode of people or vehicles in the area within a specific time period based on the relevant feature information of the input first spatial area.

[0040] In a possible implementation, a first data group is constructed based on the multi-domain feature information of the first segment of the first density time series segment and the first density mode group of the first density time series segment, and step S324 further includes step S3241, extracting the first vehicle density time series segment in the first density time series segment. Specifically, the first density time series segment is a data subset of a time period divided from the first density time series according to a predetermined unit time zone, and contains the density information of people and vehicles in the time period. The segment is the basis for further analyzing the density characteristics of vehicles and people. For example, if the predetermined unit time zone is one day, then the first density time series segment is the data of the change of the density of people and vehicles over time within this day. The data part specifically about the vehicle density is separated from the first density time series segment, that is, the first vehicle density time series segment. Because vehicle density has its own unique characteristics and rules, it needs to be analyzed separately and extracted through data identification or index. Assuming that the first density time series segment is stored in the form of a two-dimensional array or data table, one column represents the personnel density and the other column represents the vehicle density, then the first vehicle density time series segment can be extracted by selecting the data corresponding to the vehicle density column.

[0041] Step S3242, collect time domain features of the first vehicle density time series segment to obtain time domain feature information of the first vehicle segment. Specifically, the time domain feature directly reflects the change of vehicle density in the time dimension. The feature can help us understand the aggregation and dispersion patterns of vehicles in different time periods. Calculate the average value of vehicle density data in the first vehicle density time series segment. The average value reflects the overall level of vehicle density in the time period. For example, if the average value of vehicle density data in a day is high, it means that the vehicles are relatively dense on the whole day. Find the maximum value in the first vehicle density time series segment, that is, the peak value of vehicle density. The time point when the peak value occurs may coincide with the traffic rush hour. Calculate the standard deviation of vehicle density data. The standard deviation can measure the degree of data dispersion. A large standard deviation indicates that the vehicle density changes greatly in the time period. There may be a large fluctuation in traffic flow. Observe the change trend of vehicle density over time, whether it is gradually increasing, gradually decreasing, or remaining relatively stable. Approximately describe this trend by fitting a trend line. For example, use linear regression to fit a straight line to represent the long-term trend of vehicle density. Integrate the time domain feature information to form the time domain feature information of the first vehicle segment.

[0042] Step S3243, collect frequency domain features of the first vehicle density spectrum obtained by fast Fourier transforming the first vehicle density time series segment to obtain frequency domain feature information of the first vehicle segment. Specifically, the fast Fourier transform (FFT) converts the first vehicle density time series segment in the time domain to the frequency domain to obtain the first vehicle density spectrum. In the frequency domain, the frequency components of the vehicle density data can be analyzed to find some regularities and features that are not obvious in the time domain. For example, some periodic traffic patterns may appear as peaks of specific frequencies in the frequency domain. The periodicity is related to daily commuting patterns, weekly workday and weekend cycles, etc. In the first vehicle density spectrum, find the frequency component with the highest energy, that is, the main frequency. The main frequency reflects the most important periodic changes in the vehicle density data.

[0043] Step S3244: The time domain feature information of the first vehicle segment and the frequency domain feature information of the first vehicle segment form the multi-domain feature information of the first vehicle segment. Specifically, the time domain feature information and the frequency domain feature information are combined to more comprehensively describe the features of the first vehicle density time series segment. The time domain feature reflects the direct change of vehicle density over time, while the frequency domain feature reveals the periodicity and frequency components therein. The two complement each other and can provide richer information for subsequent analysis and model building. The time domain feature information of the first vehicle segment and the frequency domain feature information of the first vehicle segment obtained previously are combined to form a comprehensive feature set, namely, the multi-domain feature information of the first vehicle segment. The multi-domain feature information can be represented by a data structure, such as a vector or structure containing time domain and frequency domain feature values.

[0044] Step S3245, obtaining the multi-domain feature information of the first personnel segment of the first personnel density time series segment in the first density time series segment. Specifically, for the personnel density part in the first density time series segment, a similar analysis method to the vehicle density is adopted, firstly extracting the first personnel density time series segment, and then collecting time domain features and frequency domain features respectively, the time domain features include the mean, peak value, valley value, standard deviation and trend of the personnel density, etc., the frequency domain features are obtained by fast Fourier transforming the personnel density time series segment and analyzing it, such as the main frequency, bandwidth and harmonic components, etc., integrating the time domain and frequency domain features to obtain the multi-domain feature information of the first personnel segment, the representation of which is also similar to the multi-domain feature information of the first vehicle segment, which can be a vector or structure containing various feature values.

[0045] Step S3246: The first vehicle segment multi-domain feature information and the first personnel segment multi-domain feature information form the first segment multi-domain feature information. Specifically, the first segment multi-domain feature information is intended to comprehensively describe the overall situation of the first density time series segment, including density characteristics of both vehicles and personnel. The flow of vehicles and personnel is interrelated and needs to be considered simultaneously to more accurately analyze and predict the density of the area. The first vehicle segment multi-domain feature information and the first personnel segment multi-domain feature information are combined to form a more comprehensive feature set, namely, the first segment multi-domain feature information.

[0046] Step S400, calibrate and analyze the first predicted density according to the first dynamic feature information of the first spatial area to obtain the first actual density. Specifically, first, obtain the first dynamic feature information of the first spatial area through multiple channels, including sensor data, mobile device data, social media data, and real-time event data, and integrate the data from different sources to form a data set. Then, analyze the impact of the dynamic feature information on the first predicted density, such as the impact of changes in traffic flow and personnel flow. Next, establish a calibration model or method. Input the first dynamic feature information into the calibration model or process it according to the rules, adjust the first predicted density, obtain the calibrated vehicle density and personnel density, and then integrate them into the first actual density according to actual needs. Finally, verify and evaluate the accuracy and rationality of the first actual density by comparing with the actual observation data and analyzing the time series. If the error is large or does not conform to the trend of change, the entire process needs to be adjusted and optimized.

[0047] In a possible implementation, the first predicted density is calibrated and analyzed according to the first dynamic feature information of the first spatial area to obtain a first actual density, and step S400 further includes step S410, analyzing the first dynamic feature information to obtain a first dynamic density time series. Specifically, the first dynamic feature information includes various data about the real-time changes of the first spatial area, covering multiple aspects of information, such as the real-time flow of people and vehicles, the real-time changes in traffic conditions, etc., which are continuously updated over time and can reflect the current dynamic state of the first spatial area; the real-time flow of vehicles can be obtained through traffic monitoring equipment, such as the number of vehicles, vehicle speed, road occupancy, etc.; changes in traffic conditions include whether the road is congested, the increase or decrease in traffic flow, etc.; information related to the density of people and vehicles is extracted from the first dynamic feature information. For people, the density of people at different time points and in different areas is calculated based on the data of the pedestrian flow sensor. For vehicles, the density of vehicles in different sections and time periods on the road is calculated based on the data of the traffic monitoring equipment. The density information of people and vehicles that changes over time is integrated to form a first dynamic density time series. The time series records the dynamic changes in the density of people and vehicles in the first spatial area over time, and is a density data sequence arranged in chronological order.

[0048] Step S420, based on the principle of spectral density function, trend line analysis is performed on the first dynamic density time series to obtain the first future density at the first future time. Specifically, the spectral density function is used to analyze the frequency characteristics of time series data and identify the periodicity and trend components in the data. For the personnel density time series, the periodic law can reflect changes such as peak periods; for the vehicle density time series, there is a similar peak law. By fitting the results of the spectral density function, a linear regression model is selected as the trend line analysis method. Linear regression fits the historical density data to obtain the best fitting straight line, and uses this straight line to make predictions to obtain the first future density. The specific prediction time point is determined according to actual needs and data resolution. By substituting the future time point into the fitted linear regression equation, the corresponding personnel and vehicle density values ​​are calculated to obtain the first future density.

[0049] Step S430, adjusting the first predicted density according to the first corresponding relationship between the first future time and the first future density to obtain the first actual density. Specifically, since the first predicted density is obtained based on historical data and model prediction, and the first future density obtained by trend line analysis is a future value predicted based on the current dynamic change trend of the first spatial area, in order to obtain a more accurate first actual density, it is necessary to perform a weighted average of the two to determine a weight coefficient. ( 1), used to balance the contribution of the first predicted density and the first future density, for example, if =0.7, it means that it is more inclined to believe the first prediction density, while =0.3 means that more emphasis is placed on the first future density obtained based on trend line analysis. Assuming that the first predicted density is (including predicted population density and vehicle density), the first future density is (also including the future density of people and vehicles), the adjustment for the actual density of people is calculated as follows: Actual density of people = .in is the first prediction of population density, is the first future population density. For the adjustment of the actual vehicle density, the calculation formula is: Actual vehicle density = .in is the first prediction of population density, It is the first future population density. Through the above calculation, the first predicted density and the first future density obtained based on trend line analysis are integrated to obtain the first actual density that is more in line with the actual situation of the first spatial area. The first actual density not only takes into account the prediction results of historical data and models, but also combines the current dynamic change trend for future predictions.

[0050] Step S500, when the first actual density is not within the predetermined density threshold, the first spatial area is adjusted for governance and scheduling. Specifically, first, the predetermined density threshold is determined, which should be set by comprehensively considering the functional characteristics, resource carrying capacity and urban planning goals of the first spatial area, and by analyzing historical data, expert evaluation and urban development planning. Different functional areas have different standards. Then the first actual density is evaluated, which is obtained by analyzing the dynamic characteristic information of the area, reflecting the actual congestion and flow situation, and measuring the actual density of people and vehicles in a variety of ways and comparing it with the predetermined threshold. When the first actual density is not within the threshold, scheduling adjustments are made. In terms of traffic management, it includes traffic flow control, such as dynamic adjustment of traffic light time and other public transportation optimization. In terms of public facility configuration, there are parking space planning; public service facilities adjustment. In terms of personnel evacuation guidance, guidance signs and information release are set; emergency drills and training are also conducted to enhance personnel response capabilities and safety awareness.

[0051] In the above, refer to Figure 1 A method for urban governance scheduling based on dynamic evaluation according to an embodiment of the present invention is described in detail. Figure 2 A city governance scheduling system based on dynamic evaluation according to an embodiment of the present invention is described.

[0052] According to an embodiment of the present invention, a city governance scheduling system based on dynamic evaluation is used to solve the technical problem that the existing technology cannot respond to the dynamic changes of the environment and personnel flow in a timely manner, and achieves the technical effect of real-time dynamic analysis of the environment and personnel flow. A city governance scheduling system based on dynamic evaluation includes: a first spatial area acquisition module 10, a first governance fitness acquisition module 20, a first predicted density acquisition module 30, a first actual density acquisition module 40, and a governance scheduling adjustment module 50.

[0053] The first spatial region acquisition module 10 is used to acquire a first spatial region, where the first spatial region refers to any region in a set of spatial regions obtained by dividing the target city, and the first spatial region has an identifier of a first functional characteristic.

[0054] The first governance fitness acquisition module 20 is used to analyze the collected first area characteristic information of the first spatial area to obtain the first governance fitness of the first spatial area determined as the first functional characteristic.

[0055] The first predicted density acquisition module 30 is used to retrieve the density database to perform density prediction analysis on the first spatial area to obtain the first predicted density when the first governance fitness meets a predetermined fitness threshold.

[0056] The first actual density acquisition module 40 is used to perform calibration analysis on the first predicted density according to the first dynamic feature information of the first spatial area to obtain a first actual density.

[0057] The governance scheduling adjustment module 50 is used to perform governance scheduling adjustment on the first spatial area when the first actual density is not within a predetermined density threshold.

[0058] The specific configuration of the first governance fitness acquisition module 20 will be described in detail below. As described above, the first regional feature information of the first spatial region collected is analyzed to obtain the first governance fitness of the first spatial region determined as the first functional characteristic. The first governance fitness acquisition module 20 further includes: a predetermined terrain index reading unit, the predetermined terrain index reading unit is used to read the predetermined terrain index; a first terrain index feature information acquisition unit, the first terrain index feature information acquisition unit is used to collect multi-dimensional features of the first spatial region based on the predetermined terrain index to obtain the first terrain index feature information; a predetermined flow index reading unit, the predetermined flow index reading unit is used to read the predetermined flow index; a multi-dimensional feature collection unit, the multi-dimensional feature collection unit is used to collect multi-dimensional features of the first spatial region based on the predetermined flow index to obtain the first flow feature information; a first governance fitness acquisition unit, the first governance fitness acquisition unit is used to analyze the first terrain index feature information and the first flow feature information to obtain the first governance fitness.

[0059] Among them, the first terrain and topography feature information and the first flow feature information are analyzed to obtain the first governance fitness, and the first governance fitness acquisition unit further includes: an urban governance database retrieval subunit, the urban governance database retrieval subunit is used to retrieve the urban governance database and extract the first historical governance record in the urban governance database, the first historical governance record refers to the urban governance record that schedules the governance of the first historical spatial area as the first functional characteristic; a first historical terrain and topography feature information assembling subunit, the first historical terrain and topography feature information assembling subunit is used to assemble the first historical terrain and topography feature information of the first historical spatial area based on the predetermined terrain and topography indicators; a first situation similarity acquisition subunit, the first situation similarity acquisition subunit is used to compare the first terrain and topography feature information with the first historical terrain and topography feature information. The information is analyzed for similarity to obtain a first situation similarity; a first historical governance difficulty extraction subunit, the first historical governance difficulty extraction subunit is used to extract the first historical governance difficulty in the first historical governance record when the first situation similarity meets the predetermined similarity threshold; a first governance situation coupling degree acquisition subunit, the first governance situation coupling degree acquisition subunit is used to take the inverse of the first historical governance difficulty as the first governance situation coupling degree; a variation weighted processing subunit, the variation weighted processing subunit is used to perform variation weighted processing on multiple flow feature parameters in the first flow feature information to obtain a first governance flow coupling degree; a first governance fitness acquisition subunit, the first governance fitness acquisition subunit is used to take the average of the first governance situation coupling degree and the first governance flow coupling degree as the first governance fitness degree.

[0060] The specific configuration of the first predicted density acquisition module 30 will be described in detail below. As described above, when the first governance fitness meets the predetermined fitness threshold, the density database is retrieved to perform density prediction analysis on the first spatial area to obtain a first predicted density. The first predicted density acquisition module 30 further includes: a first density time series extraction unit, the first density time series extraction unit is used to extract a first density time series in the density database, wherein the density database includes historical density record data of multiple historical spatial areas consistent with the first functional characteristics, the first density time series includes a first vehicle density time series and a first personnel density time series; an intelligent prediction model activation unit, the intelligent prediction model activation unit is used to activate the intelligent prediction model, the intelligent The prediction model includes a vehicle prediction layer and a personnel prediction layer; a first predicted vehicle density acquisition unit, the first predicted vehicle density acquisition unit is used to analyze the first vehicle multi-domain feature information of the first vehicle density time series through the vehicle prediction layer to obtain a first predicted vehicle density; a first personnel multi-domain feature information analysis unit, the first personnel multi-domain feature information analysis unit is used to analyze the first personnel multi-domain feature information of the first personnel density time series through the personnel prediction layer to obtain a first predicted personnel density; a first predicted density composition unit, the first predicted density composition unit is used to combine the first predicted vehicle density and the first predicted personnel density to form the first predicted density.

[0061] Among them, the intelligent prediction model is activated, and the intelligent prediction model includes a vehicle prediction layer and a personnel prediction layer. The intelligent prediction model activation unit further includes: a predetermined unit time zone reading subunit, and the predetermined unit time zone reading subunit is used to read the predetermined unit time zone; a first time series slice set acquisition subunit, and the first time series slice set acquisition subunit is used to slice the first density time series with the predetermined unit time zone as a constraint to obtain a first time series slice set; a first slice extraction subunit, and the first slice extraction subunit is used to extract the first slice in the first time series slice set, and the first slice refers to the first density time series segment; a first data group assembly subunit, and the first data group assembly subunit is used to construct a first data group based on the first segment multi-domain feature information of the first density time series segment and the first density mode group of the first density time series segment; a data supervised learning subunit, and the data supervised learning subunit is used to perform supervised learning on the first data group to obtain the intelligent prediction model.

[0062] Among them, based on the first segment multi-domain feature information of the first density time series segment and the first density mode group of the first density time series segment, a first data group is constructed, and the first data group construction sub-unit further includes: a density time series segment extraction micro-unit, the density time series segment extraction micro-unit is used to extract the first vehicle density time series segment in the first density time series segment; a time domain feature collection micro-unit, the time domain feature collection micro-unit is used to collect time domain features of the first vehicle density time series segment to obtain the time domain feature information of the first vehicle segment; a frequency domain feature collection micro-unit, the frequency domain feature collection micro-unit is used to collect frequency domain features of the first vehicle density spectrum obtained by fast Fourier transforming the first vehicle density time series segment to obtain The first vehicle segment frequency domain characteristic information; the first vehicle segment multi-domain characteristic information composition micro-unit, the first vehicle segment multi-domain characteristic information composition micro-unit is used for the first vehicle segment time domain characteristic information and the first vehicle segment frequency domain characteristic information to form the first vehicle segment multi-domain characteristic information; the first personnel segment multi-domain characteristic information acquisition micro-unit, the first personnel segment multi-domain characteristic information acquisition micro-unit is used to obtain the first personnel segment multi-domain characteristic information of the first personnel density time series segment in the first density time series segment; the first segment multi-domain characteristic information composition micro-unit, the first segment multi-domain characteristic information composition micro-unit is used for the first vehicle segment multi-domain characteristic information and the first personnel segment multi-domain characteristic information to form the first segment multi-domain characteristic information.

[0063] The specific configuration of the first actual density acquisition module 40 will be described in detail below. As described above, the first predicted density is calibrated and analyzed according to the first dynamic feature information of the first spatial area to obtain the first actual density. The first actual density acquisition module 40 further includes: a first dynamic density time series analysis unit, the first dynamic density time series analysis unit is used to analyze the first dynamic feature information to obtain the first dynamic density time series; a first future density acquisition unit, the first future density acquisition unit is used to perform a trend line analysis on the first dynamic density time series based on the principle of spectral density function to obtain the first future density at the first future time; a first actual density acquisition unit, the first actual density acquisition unit is used to adjust the first predicted density according to the first corresponding relationship between the first future time and the first future density to obtain the first actual density.

[0064] An urban governance scheduling system based on dynamic evaluation provided by an embodiment of the present invention can execute an urban governance scheduling method based on dynamic evaluation provided by any embodiment of the present invention, and has functional modules and beneficial effects corresponding to the execution method.

[0065] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0066] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. A method for urban governance scheduling based on dynamic evaluation, characterized in that: include: Acquire a first spatial region, where the first spatial region refers to any region in a set of spatial regions obtained by dividing the target city, and the first spatial region has an identifier of a first functional characteristic; Analyze the collected first area characteristic information of the first spatial area to obtain a first governance fitness of the first spatial area determined as the first functional characteristic; When the first governance fitness meets a predetermined fitness threshold, calling a density database to perform density prediction analysis on the first spatial area to obtain a first predicted density; Performing calibration analysis on the first predicted density according to first dynamic feature information of the first spatial region to obtain a first actual density; When the first actual density is not within a predetermined density threshold, a governance scheduling adjustment is performed on the first spatial area.

2. According to claim 1, a method for urban governance scheduling based on dynamic evaluation is characterized in that: include: Reading predetermined terrain indicators; Based on the predetermined terrain and topography index, multi-dimensional feature collection is performed on the first spatial area to obtain first terrain and topography feature information; Reading predetermined flow indicators; Based on the predetermined flow index, multi-dimensional feature collection is performed on the first spatial area to obtain first flow feature information; The first terrain feature information and the first flow feature information are analyzed to obtain the first governance fitness.

3. According to the method of urban governance scheduling based on dynamic evaluation according to claim 2, it is characterized in that: include: Retrieving a city governance database, and extracting a first historical governance record in the city governance database, where the first historical governance record refers to a city governance record that schedules the first historical spatial area governance as the first functional characteristic; Based on the predetermined topographic index, first historical topographic feature information of the first historical space area is formed; Performing a similarity analysis on the first topographic and terrain feature information and the first historical topographic and terrain feature information to obtain a first situation similarity; When the first situation similarity meets a predetermined similarity threshold, extracting the first historical governance difficulty in the first historical governance record; The inverse of the first historical governance difficulty is taken as the first governance situation coupling degree; Performing variation and weighted processing on a plurality of flow characteristic parameters in the first flow characteristic information to obtain a first governance flow coupling degree; The average of the first governance situation coupling degree and the first governance flow coupling degree is taken as the first governance adaptability.

4. According to the method of urban governance scheduling based on dynamic evaluation according to claim 1, it is characterized in that: include: Extracting a first density time series from the density database, wherein the density database includes historical density record data of multiple historical spatial areas consistent with the first functional characteristic, and the first density time series includes a first vehicle density time series and a first personnel density time series; activating an intelligent prediction model, wherein the intelligent prediction model includes a vehicle prediction layer and a personnel prediction layer; Analyzing the first vehicle multi-domain feature information of the first vehicle density time series through the vehicle prediction layer to obtain a first predicted vehicle density; Analyzing the first personnel multi-domain feature information of the first personnel density time series through the personnel prediction layer to obtain a first predicted personnel density; The first predicted vehicle density and the first predicted personnel density together constitute the first predicted density.

5. According to claim 4, a method for urban governance scheduling based on dynamic evaluation is characterized in that: include: Read the preset unit time zone; Slicing the first density time series with the predetermined unit time zone as a constraint to obtain a first time series slice set; Extracting a first slice in the first time-series slice set, wherein the first slice refers to a first density time-series segment; Constructing a first data group based on the first segment multi-domain feature information of the first density time series segment and the first density mode group of the first density time series segment; The intelligent prediction model is obtained by performing supervised learning on the first data group.

6. According to claim 5, a method for urban governance scheduling based on dynamic evaluation is characterized in that: include: Extracting a first vehicle density time series segment from the first density time series segment; Collecting time domain features of the first vehicle density time series segment to obtain time domain feature information of the first vehicle segment; Performing frequency domain feature collection on a first vehicle density spectrum obtained by fast Fourier transforming the first vehicle density time series segment to obtain frequency domain feature information of the first vehicle segment; The time domain feature information of the first vehicle segment and the frequency domain feature information of the first vehicle segment constitute the multi-domain feature information of the first vehicle segment; Acquire multi-domain feature information of a first personnel segment of a first personnel density time series segment in the first density time series segment; The first vehicle segment multi-domain feature information and the first person segment multi-domain feature information constitute the first segment multi-domain feature information.

7. According to claim 1, a method for urban governance scheduling based on dynamic evaluation is characterized in that: include: Analyzing the first dynamic feature information to obtain a first dynamic density time series; Performing a trend line analysis on the first dynamic density time series based on the spectral density function principle to obtain a first future density at a first future time; The first predicted density is adjusted according to a first corresponding relationship between the first future time and the first future density to obtain the first actual density.

8. An urban governance dispatching system based on dynamic evaluation, characterized in that: The system is used to implement the urban governance scheduling method based on dynamic evaluation according to any one of claims 1 to 7, and the system includes: A first spatial region acquisition module, the first spatial region acquisition module is used to acquire a first spatial region, the first spatial region refers to any region in a set of spatial regions obtained by dividing the target city, and the first spatial region has an identification of a first functional characteristic; A first governance fitness acquisition module, the first governance fitness acquisition module is used to analyze the collected first area characteristic information of the first spatial area to obtain a first governance fitness of the first spatial area determined as the first functional characteristic; A first predicted density acquisition module, wherein the first predicted density acquisition module is used to retrieve a density database to perform density prediction analysis on the first spatial area to obtain a first predicted density when the first governance fitness meets a predetermined fitness threshold; A first actual density acquisition module, the first actual density acquisition module is used to calibrate and analyze the first predicted density according to first dynamic feature information of the first spatial area to obtain a first actual density; A governance scheduling adjustment module is used to perform governance scheduling adjustment on the first spatial area when the first actual density is not within a predetermined density threshold.

Images