A method and system for analyzing urban spatial morphology data based on machine learning

Abstract

The present application is applicable to the field of data analysis technology, and in particular to a method and system for analyzing urban spatial morphology data based on machine learning, the method comprising: determining urban data to be analyzed of urban spatial morphology; wherein the urban data to be analyzed is used to indicate the transportation infrastructure area in the urban spatial morphology; performing multi-factor analysis on the data to be analyzed to obtain factor impact data; wherein the factor impact data is used to reflect the impact of multiple factors on traffic in the transportation infrastructure area; generating factor result data of urban spatial morphology based on the factor impact data; wherein the factor result data is used to indicate a solution obtained based on the traffic impact. The urban spatial morphology data analysis method based on machine learning provided in the present application can meet the traffic needs of different situations, reduce traffic congestion, and improve traffic efficiency.

Description

Technical Field

[0001] The present application belongs to the field of data analysis technology, and in particular, relates to a method and system for analyzing urban spatial morphology data based on machine learning. Background Art

[0002] Urban spatial form refers to the organizational structure and layout of urban space within a certain geographical range. Urban spatial form describes the distribution, density and relationship of physical elements such as transportation, buildings, streets, green spaces, etc. within the city, reflecting the diversity of the city in terms of function, economy, culture and society.

[0003] In related technologies, with the acceleration of urbanization and the surge in the number of vehicles, the road systems of many cities are unable to meet the traffic needs in different situations, and serious traffic congestion problems are prone to occur, which not only reduces traffic efficiency, but also increases vehicle fuel consumption and exhaust emissions, easily leading to traffic accidents, and has a certain impact on the future development of the city. Summary of the invention

[0004] The embodiments of the present application provide a method and system for analyzing urban spatial morphology data based on machine learning, which can solve the problems of traffic congestion, low traffic efficiency, and proneness to traffic accidents caused by the inability to meet traffic needs in different situations.

[0005] In a first aspect, an embodiment of the present application provides an urban spatial morphology data analysis method based on machine learning, comprising:

[0006] Determine the urban data to be analyzed of the urban spatial form; wherein the urban data to be analyzed is used to indicate the transportation infrastructure area in the urban spatial form;

[0007] Performing a multi-factor analysis on the data to be analyzed to obtain factor impact data; wherein the factor impact data is used to reflect the impact of multiple factors on traffic in the traffic infrastructure area;

[0008] Based on the factor impact data, factor result data of the urban space form are generated; wherein the factor result data is used to indicate a solution obtained according to the traffic impact situation.

[0009] The urban spatial morphology data analysis method based on machine learning provided in this application determines the urban spatial morphology data to be analyzed. By determining the urban data to be analyzed, urban planners can identify traffic bottleneck areas and design a more reasonable traffic network layout accordingly. In addition, these data can also help optimize the routes and schedules of public transportation, reduce unnecessary waiting time, and increase the attractiveness of public transportation. Multi-factor analysis is performed on the data to be analyzed to obtain factor influence data. Through the factor influence data, the peak hours and key sections of traffic flow and the main influencing factors can be identified. It can also help decision makers optimize traffic signals and formulate more reasonable traffic control measures, which will help improve the overall operation efficiency of the road network, reduce traffic delays, and enhance the public travel experience. According to the factor influence data, the factor result data of the urban spatial morphology is generated, which can provide more accurate traffic flow predictions, urban planners can better understand traffic patterns, and can also help decision makers evaluate the effectiveness of existing traffic management measures, and predict possible future traffic development trends, provide a scientific basis for the formulation of long-term traffic strategies, reduce traffic congestion, and thus improve traffic efficiency.

[0010] In a second aspect, the embodiment of the present application provides an urban space morphology data analysis system based on machine learning, comprising:

[0011] A determination unit, used to determine the urban data to be analyzed of the urban spatial form; wherein the urban data to be analyzed is used to indicate the transportation infrastructure area in the urban spatial form;

[0012] An analysis unit, configured to perform a multi-factor analysis on the data to be analyzed to obtain factor impact data; wherein the factor impact data is used to reflect the impact of multiple factors on traffic in the traffic infrastructure area;

[0013] The result unit is used to generate factor result data of urban space form according to the factor impact data; wherein the factor result data is used to indicate a solution obtained according to the traffic impact situation.

[0014] In a third aspect, an embodiment of the present application provides an urban spatial morphology data analysis device based on machine learning, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program, when executed by the processor, implements a method as described in any one of the first aspects above.

[0015] In a fourth aspect, an embodiment of the present application provides a computer program product. When the computer program product runs on an urban space morphology data analysis device based on machine learning, the urban space morphology data analysis device based on machine learning executes the urban space morphology data analysis method based on machine learning described in any one of the first aspects above.

[0016] It can be understood that the beneficial effects of the second to fourth aspects mentioned above can be found in the relevant description of the first aspect mentioned above, and will not be repeated here. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0018] Figure 1 It is a flowchart of an urban space morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0019] Figure 2 This is a schematic diagram of the implementation process of step S100 in the urban spatial morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0020] Figure 3 It is a schematic diagram of the implementation process of step S200 in the urban space morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0021] Figure 4 This is a schematic diagram of the implementation process of step S210 in the urban spatial morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0022] Figure 5 It is a schematic diagram of the implementation process of step S213 in the urban space morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0023] Figure 6 It is a schematic diagram of the implementation process of step S230 in the urban space morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0024] Figure 7 It is a schematic diagram of the implementation process of step S234 in the urban space morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0025] Figure 8It is a schematic diagram of the implementation process of step S300 in the urban spatial morphology data analysis method based on machine learning provided in one embodiment of the present application;

[0026] Fig. 9 It is a structural diagram of an urban space morphology data analysis system based on machine learning provided in an embodiment of the present application;

[0027] Fig.10 It is a structural diagram of an urban space morphology data analysis device based on machine learning provided in an embodiment of the present application. DETAILED DESCRIPTION

[0028] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0029] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0030] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0031] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0032] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0033] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0034] Urban spatial form refers to the organizational structure and layout of urban space within a certain geographical range. Urban spatial form describes the distribution, density and relationship of physical elements such as transportation, buildings, streets, green spaces, etc. within the city, reflecting the diversity of the city in terms of function, economy, culture and society.

[0035] In related technologies, with the acceleration of urbanization and the surge in the number of vehicles, the road systems of many cities are unable to meet the traffic needs in different situations, and serious traffic congestion problems are prone to occur, which not only leads to reduced traffic efficiency, but also increases vehicle fuel consumption and exhaust emissions, causing certain impacts on the future development of the city.

[0036] To solve the above problems, the embodiment of the present application provides a method and system for analyzing urban spatial morphology data based on machine learning. In the method, the urban data to be analyzed of the urban spatial morphology can be determined. By determining the urban data to be analyzed, urban planners can identify traffic bottleneck areas and design a more reasonable traffic network layout accordingly. In addition, these data can also help optimize the routes and schedules of public transportation, reduce unnecessary waiting time, and increase the attractiveness of public transportation. Multi-factor analysis is performed on the data to be analyzed to obtain factor influence data. Through the factor influence data, the peak hours and key sections of traffic flow and the main influencing factors can be identified. It can also help decision makers optimize traffic signals and formulate more reasonable traffic control measures, which is helpful to improve the overall operation efficiency of the road network, reduce traffic delays, and enhance the public travel experience. According to the factor influence data, the factor result data of the urban spatial morphology is generated, which can provide more accurate traffic flow prediction, urban planners can better understand the traffic mode, and can also help decision makers evaluate the effectiveness of existing traffic management measures, and predict possible future traffic development trends, so as to provide a scientific basis for formulating long-term traffic strategies, thereby reducing traffic congestion and improving traffic efficiency.

[0037] The urban space morphology data analysis method based on machine learning provided in the embodiment of the present application can be applied to an urban space morphology data analysis device based on machine learning. At this time, the urban space morphology data analysis device based on machine learning is the execution entity of the urban space morphology data analysis method based on machine learning provided in the embodiment of the present application. The embodiment of the present application does not impose any restrictions on the specific type of the urban space morphology data analysis device based on machine learning.

[0038] For example, the urban spatial morphology data analysis device based on machine learning can be a mobile phone, a tablet computer, a laptop computer, a super mobile personal computer, a netbook, a desktop computer, a smart large screen, a computing device, a computer, a laptop computer, a handheld communication device, a handheld computing device, etc.

[0039] In order to better understand the urban space morphology data analysis method based on machine learning provided in the embodiment of the present application, the specific implementation process of the urban space morphology data analysis method based on machine learning provided in the embodiment of the present application is exemplarily introduced below.

[0040] Figure 1 A schematic flow chart of an urban space morphology data analysis method based on machine learning provided in an embodiment of the present application is shown. The urban space morphology data analysis method based on machine learning includes:

[0041] S100, determining urban data to be analyzed in the urban spatial form; wherein the urban data to be analyzed is used to indicate the transportation infrastructure area in the urban spatial form.

[0042] It can be understood that the transportation infrastructure area can be an area with transportation facilities; the transportation facilities are traffic roads on which vehicles travel.

[0043] For example, determining the city data to be analyzed can be done by using online map services, visiting the official website of the government or local transportation department, or through professional geographic information system (GIS) software, which can analyze and obtain detailed information on transportation infrastructure. Online map services can be Google Maps or Baidu Maps, which can search for transportation infrastructure in a specific area. Among them, to find or obtain areas with transportation infrastructure, there are usually several different methods. You can use a web search engine, enter relevant keywords for query, and refer to maps and transportation guides, which usually mark the location of transportation infrastructure in detail.

[0044] In one possible implementation, see Figure 2 , S100, determine the urban data to be analyzed of the urban spatial form, including:

[0045] S110, obtaining the territory standard data and all the morphological data in the urban space; wherein the territory standard data is used to indicate the territory height on the ground in the current urban space, and the morphological data is used to indicate all the morphological areas in the urban space.

[0046] It can be understood that the territory height on the ground in the current urban space can be the territory height in the current city, where the territory height is the ground level height or the altitude height (i.e., the altitude of a city on a plain can be in the range of 0 degrees). All morphological areas can be all areas that can be planned and laid out in the current urban space, such as transportation facility areas, green space areas, building areas, etc., but are not limited thereto.

[0047] For example, the standard data of the territory in the urban space can be obtained by searching the geographic information of the city or by searching the geographic information of the urban space on the Internet; all the morphological data can be obtained by dividing the entire space of the city according to various forms (the urban space can be divided into transportation, green space, buildings, etc.), so that all forms can be obtained.

[0048] S120, performing contour processing on the morphological region indicated by the morphological data to obtain first processed data; wherein the first processed data is used to indicate the contour shape of the morphological region indicated by each morphological data.

[0049] It can be understood that the morphological area is mapped to the display screen (computer or mobile phone), and the morphological area mapped to the display screen is contoured. The contour processing can be to outline the morphological area so that the overall shape of the morphological area can be fully displayed. Advanced image processing technology can be used, combined with the edge detection algorithm in machine learning, to effectively identify the boundary of the morphological area. The specific steps can be to improve the image quality through a preprocessing step, and then use methods such as the Canny edge detector or the Sobel operator to identify the contour of the area; the Canny edge detector or the Sobel operator can detect significant edges in the image, thereby forming a contour line. In addition, in order to view the contour line or contour shape in more detail, the contour line can be refined by image segmentation technology to obtain a more accurate morphological area boundary, and then the contour line is converted into vector data to form the first processed data.

[0050] S130, performing connectivity feature processing on the morphological data based on the territory standard data to obtain second processed data; wherein the second processed data is used to reflect the connectivity of objects within the morphological area indicated by each morphological data.

[0051] It can be understood that the connectivity feature processing can be the connectivity between each object in the morphological area; the morphological data is subjected to connectivity analysis and detection based on the territory standard data to obtain the second processed data;

[0052] Exemplarily, the connectivity analysis test of the morphological data may be the connectivity relationship between various traffic facilities within the current morphological area or the relationship between traffic facilities and traffic lights; the connectivity analysis test may also be to convert the morphological data into a graph structure; wherein nodes represent objects within the morphological area (which may be traffic facilities), and edges represent the connection relationship between objects, and by calculating the connectivity components of the graph, independent connected areas and the connectivity between multiple objects can be identified.

[0053] S140, obtaining city data to be analyzed according to the first processed data and the second processed data.

[0054] Exemplarily, the contour shape indicated by the first processed data is compared with the contour shape in the database to obtain the first processed data that meets the preset matching value; the connectivity indicated by the second processed data is compared with the connectivity in the database to obtain the second processed data that meets the preset matching value; and the first processed data that meets the preset matching value and the second processed data that meets the preset matching value are determined as the city data to be analyzed. The database is constructed by contour shape and connectivity, and the contour shape and connectivity in the database are obtained from the drawings used by construction workers when constructing traffic roads. Meeting the preset matching value means that the contour shape indicated by the first processed data is compared with the contour shape in the database to obtain the same value between the two, and the connectivity indicated by the second processed data is compared with the connectivity in the database to obtain the same value between the two, which satisfies the preset matching value.

[0055] S200, performing a multi-factor analysis on the data to be analyzed to obtain factor impact data; wherein the factor impact data is used to reflect the impact of multiple factors on traffic in the traffic infrastructure area.

[0056] Exemplarily, a multi-factor analysis can be conducted on the traffic conditions in the traffic facility area indicated by the analyzed data to obtain factor influence data; the multi-factor analysis can be conducted through a mathematical model, with multiple factors such as traffic flow, road width, traffic light settings, and external influences (weather or road emergencies, etc.) as independent variables, and the degree of traffic congestion as the dependent variable, so as to analyze the specific impact and degree of impact of each factor on the traffic conditions, and quantify the impact weight of different factors on traffic, providing a basis for traffic management and planning.

[0057] In one possible implementation, see Figure 3 , S200, conduct multi-factor analysis on the data to be analyzed to obtain the factor influencing data, including:

[0058] S210, performing a first traffic factor analysis on the data to be analyzed to obtain time factor data; wherein the time factor data is used to reflect the traffic impact within the traffic infrastructure area indicated by the data to be analyzed according to the time condition.

[0059] Exemplarily, the time factor analysis is performed on the data to be analyzed to obtain the time factor data; the time factor analysis of the data to be analyzed can be performed by using the time series analysis method, by collecting traffic flow data in different time periods, analyzing the law of traffic flow changes over time, and identifying the difference in traffic flow during peak hours and off-peak hours. Among them, the traffic flow trend in a certain time period in the future is predicted through time series analysis, which provides a basis for traffic scheduling and resource allocation. In addition, the analysis results of the time factor data can also help the traffic management department to formulate more reasonable time-dependent traffic policies, such as adjusting the timing of traffic lights and optimizing the operation schedule of public transportation.

[0060] In one possible implementation, see Figure 4 S210, performing a first traffic factor analysis on the data to be analyzed to obtain time factor data, including:

[0061] S211, obtaining time period data; wherein the time period data includes early time period data and late time period data, the early time period data is used to indicate the morning time period of the day, and the late time period data is used to indicate the evening time period of the day.

[0062] It is understandable that the morning time period can be from 7:00 to 9:30 in the morning, and the evening time period can be from 5:00 to 7:30 in the evening, etc., but it is not limited thereto. It can be determined according to the specific situation of the current city. For example, compared with third-tier cities, the time period of first-tier cities is longer than that of third-tier cities. Due to the large traffic flow in first-tier cities, the time for companies to open will be extended, so the specific start and end time of the time period can be determined according to different situations.

[0063] For example, the morning time period and the evening time period may be determined by people's daily routines; the morning time period and the evening time period may also be defined by traffic (the morning time period may be the time with the heaviest traffic volume, followed by the evening time period), etc., but not limited to these.

[0064] S212, identifying the traffic flow of the data to be analyzed based on the early data and the late data to obtain first impact data; wherein the first impact data is used to indicate the frequency of traffic congestion in the traffic infrastructure area indicated by the data to be analyzed during the morning time period and the evening time period.

[0065] It can be understood that the traffic congestion frequency may be the number of times the traffic congestion occurs during the morning time period and the evening time period.

[0066] For example, real-time traffic data can be collected by sensors installed at traffic intersections. Sensors at traffic intersections can record information such as the number of vehicles passing through the intersection, speed, and direction of travel. Among them, the time series analysis method can be used to identify and quantify the traffic flow variation patterns in different time periods, and the day can be effectively divided into different traffic flow periods, so as to obtain the traffic congestion frequency and congestion situation in the traffic infrastructure area based on the early and late data. It can also be the use of classification algorithms in machine learning. The classification algorithm can be through historical traffic data, so that it can identify the traffic flow characteristics in different time periods, classify the real-time data, and obtain the traffic congestion situation and congestion frequency in specific time periods such as the morning time period and the evening time period.

[0067] S213, based on the first impact data, a vehicle type analysis is performed on the vehicles in the traffic infrastructure area indicated by the data to be analyzed to obtain second impact data; wherein the second impact data is used to reflect the frequency of traffic congestion in the traffic infrastructure area indicated by the data to be analyzed in the city under different vehicle characteristics.

[0068] For example, based on the first impact data, the clustering algorithm is used to analyze the vehicle types of vehicles in the traffic infrastructure area indicated by the data to be analyzed, and the second impact data is obtained; wherein the clustering algorithm can be through the collected vehicle type data to identify the characteristics and behavior patterns of different vehicles, and then use the model to analyze the real-time traffic data to classify the vehicles into different categories, such as private cars, buses, commercial vehicles, motorcycles, etc., so as to understand the impact of different vehicle types on traffic flow in more detail, thereby providing more detailed data support for traffic planning and management. In addition, the analysis method can also reveal the distribution pattern of specific vehicle types in a specific time period, providing a targeted method for alleviating traffic congestion.

[0069] In one possible implementation, see Figure 5 S213, performing vehicle type analysis on vehicles in the traffic infrastructure area indicated by the data to be analyzed to obtain second impact data, including:

[0070] S2131, obtaining data on vehicle types that are passable within the traffic infrastructure area indicated by the data to be analyzed; wherein the vehicle type data is used to indicate the types of vehicles that are allowed to pass within the traffic infrastructure area indicated by the data to be analyzed, and the types of vehicles that are allowed to pass include at least three types of vehicles from among cars, trucks, buses, transport vehicles and coaches.

[0071] It can be understood that the data on the types of vehicles that can pass can be at least three types of vehicles that are allowed to pass; some traffic infrastructure does not allow vehicles that exceed the weight, transport vehicles or passenger vehicles to pass.

[0072] For example, the data on the types of vehicles that can pass through the traffic infrastructure area indicated by the data to be analyzed can be obtained through a real-time monitoring system, which includes but is not limited to video monitoring, sensor networks and GPS tracking methods. Through video monitoring, sensor networks and GPS tracking technologies, these methods can capture the flow of vehicles in the traffic infrastructure area, and classify vehicles through image recognition and data processing algorithms. For example, a video monitoring system can capture vehicle images and then analyze the appearance characteristics of the vehicle to identify the type of vehicle. The sensor network can collect information such as weight and size when the vehicle passes, further assisting in classification. GPS tracking technology can track the vehicle's travel path and, combined with time series analysis, help determine whether the vehicle is of a type that is allowed to pass. Through these comprehensive analysis methods, the system can effectively obtain and update the data on the types of vehicles that can pass through the traffic infrastructure area.

[0073] S2132, obtaining width data of the traffic infrastructure area indicated by the data to be analyzed and vehicle size data of the vehicle type; wherein the width data is used to indicate the width value of the traffic infrastructure area indicated by the data to be analyzed, and the vehicle size data is used to indicate the vehicle width value and the vehicle length value.

[0074] Exemplarily, the width data of the traffic infrastructure area indicated by the data to be analyzed and the vehicle size data of the vehicle type can be obtained by integrating multiple sensors and data acquisition equipment to achieve accurate measurement of vehicles in the traffic infrastructure area. For example, a laser scanner can be used to measure the width of the road, and a vehicle detector can collect the size information of the vehicle when it passes; the specific size information of the vehicle can also be determined by identifying the vehicle logo and matching the vehicle model corresponding to the vehicle logo, and the width of the road can also be obtained by identifying the location or section of the road and matching the information of the section to obtain the specific width of the road (which can be obtained from the information during construction). The road width of the road to be analyzed can be obtained through the construction information when the road is built, and then the vehicle width and vehicle length of each vehicle can be obtained through the size detector.

[0075] S2133, performing a traffic analysis on the width data and the vehicle size data to obtain second impact data.

[0076] For example, within a unit time, vehicles on the road are detected in real time, the width value indicated by the width data is divided by the width value of the vehicle indicated by the vehicle size data to obtain the number of vehicles that the road can accommodate, the moving distance of each vehicle on the road is obtained within a unit time (within 2 minutes), the moving distance is subtracted from the vehicle length indicated by the vehicle size data to obtain the actual moving distance, and the actual moving distance of the vehicle is determined as the second impact data. The unit time can be within 5 minutes, within 10 minutes, or within 30 minutes.

[0077] In addition, when improving the traffic layout, for example, there will be an evening rush hour in the evening time period, and during the evening rush hour, it is possible to set up different roads according to the type of car, the purpose of the car or the size of the car; the type of car can be a small car taking a certain road, a transport vehicle taking a road and a bus taking a road, the purpose of the car can be private cars taking a certain road, buses and transport vehicles taking a road, and according to the size of the car, vehicles with a certain width and length can take a lane, for example, a car with a width of 1.3 meters and a length of 3 meters can take a road with a width limit of 1.4 meters and a length of 3.5 meters, and others that exceed the width need to take the lane next to it that meets their size. This can reduce the situation of being squeezed in and reduce the congestion in Jiangxi Copper, but it is only determined during the morning rush hour or the evening rush hour. The rest of the time can be selected according to the traffic jam situation, and no specific restrictions are made here.

[0078] S214, obtaining time factor data according to the first influencing data and the second influencing data.

[0079] Exemplarily, the number of traffic congestion in the traffic infrastructure area in the morning and evening time periods indicated by the first impact data is accumulated to obtain the number of congestion, and the number of traffic congestion of different vehicle characteristics indicated by the second impact data in the infrastructure area is accumulated to obtain the number of congestion, and the two congestion numbers are added to obtain the total number of congestion, and the total number of congestion is determined as the time factor data. If the moving distance of the vehicle within a unit time (such as 1 minute, 2 minutes or 5 minutes, etc.) is less than the preset moving distance, it is traffic congestion; if the vehicle's driving speed is 0 once within a unit time (2 minutes or 10 minutes), it proves that there is one traffic congestion; if the vehicle's driving speed is 0 multiple times within a unit time, it proves that the frequency of traffic congestion is high.

[0080] S220, performing a second traffic factor analysis on the data to be analyzed to obtain weather factor data; wherein the weather factor data is used to reflect the impact of weather conditions on traffic within the traffic infrastructure area indicated by the data to be analyzed.

[0081] For example, weather factor analysis is performed on the data to be analyzed according to the multiple linear regression analysis method to obtain weather factor data. The multiple linear regression analysis method can use weather factors such as temperature, humidity, precipitation, wind speed, etc. as independent variables and traffic flow as dependent variables. Based on historical data, the degree of influence of each weather factor on traffic flow is determined through statistical analysis. Real-time or predicted weather data can be input to predict changes in traffic flow under specific weather conditions, providing a scientific basis for traffic management.

[0082] In addition, it is also possible to analyze weather forecasts or real-time weather conditions on mobile phones or other network devices, as well as detect the current air and environment to see whether there is an impact on traffic infrastructure. For example, smog has a greater impact on traffic infrastructure, because it will cause drivers to be unable to see or see the traffic infrastructure clearly, causing traffic congestion and traffic accidents, and then the specific impact of smog on traffic can be obtained; rain and snow will reduce the friction coefficient between traffic infrastructure and vehicles, which will definitely cause traffic congestion. Based on this situation, the specific impact of rain or snow on traffic can be obtained.

[0083] In a possible implementation, S220, performing a second traffic factor analysis on the data to be analyzed to obtain weather factor data includes:

[0084] S221, acquiring weather status data in real time, and obtaining ground condition data based on the weather status data; wherein the weather status data is used to reflect the current weather conditions, and the ground condition data is used to indicate the current ground state, which includes a dry state, a slippery state, a waterlogged state, a muddy state, a snow-covered state, or an icy state.

[0085] It can be understood that the real-time acquisition of weather status data can be obtained in real time on the same day, and the weather conditions every hour need to be obtained in real time. For example, it is currently 10 o'clock in the morning, and now it is necessary to obtain weather information at 11 o'clock, 12 o'clock, and until 24 o'clock on a mobile phone or computer. In addition, it is now 10 o'clock in the morning, and the approximate data of the next day can also be obtained; the approximate data can be the weather data of the next day closest to 10 o'clock. For example, 1 o'clock in the morning of the next day is closest to the current 10 o'clock, so the weather status at 1 o'clock in the morning can be obtained. It should be noted that the current weather and the weather of the next day can be obtained on a mobile phone or computer, because the weather conditions have been released, but they will change at any time, so it is necessary to obtain the weather status again every minute or 10 minutes (1 minute, 10 minutes or other time can be selected according to needs). Exemplarily, real-time acquisition of weather status data can be obtained through a mobile phone, TV, computer or other network device.

[0086] Exemplarily, after obtaining the weather conditions indicated by the weather status data, the current ground state indicated by the ground condition data corresponding to the weather conditions is matched in the database according to the current weather conditions; the database is established by recording the actual ground state conditions mapped by previous actual weather conditions, and the database includes the dry state corresponding to when the weather condition is sunny, the snow-covered state corresponding to when the weather condition is snowing, and the slippery state corresponding to when the weather condition is rainy, etc.

[0087] S222, obtaining state influence data according to the ground state indicated by the ground state data; wherein the state influence data is used to reflect the friction coefficient when the ground state indicated by the ground state data is one of a dry state, a slippery state, a waterlogged state, a muddy state, a snow-covered state or an icy state.

[0088] Exemplarily, the friction coefficient analysis is performed according to the ground state indicated by the ground condition data to obtain the state influence data; the friction coefficient analysis can be an analysis method based on a physical model, by establishing a relationship model between ground materials and meteorological parameters, simulating the ground state under different meteorological conditions, and using the physical relationship between the friction coefficient and the ground state, combined with real-time meteorological data, to calculate the corresponding friction coefficient under a specific ground state. For example, in a dry state, the ground friction coefficient is high, while in a wet or icy state, the friction coefficient will be reduced. The difference between the friction coefficients can be obtained, and different measures can be obtained for different states, so that the friction coefficient can be improved, traffic congestion can be reduced, and traffic safety can be improved, which can provide a basis for road safety, traffic planning, and disaster prevention and mitigation.

[0089] S223, obtaining visible data based on the weather status data; wherein the visible data is used to reflect the visible conditions ahead.

[0090] Exemplarily, weather analysis is performed on weather status data to obtain visibility data; wherein, weather analysis may be performed by using an analysis method based on a statistical model. The analysis method based on a statistical model may be to collect historical weather data and visibility records, establish a statistical relationship model between weather status and visibility, and use the statistical relationship model in combination with real-time weather data to predict visibility ahead under specific weather conditions. For example, visibility will decrease on foggy or rainy days, while visibility will be higher on clear days. By comparing the two situations, it is possible to obtain how much visibility will decrease on foggy or rainy days, and the value of the visible distance, so as to obtain the visibility ahead.

[0091] S224, obtaining weather factor data according to the state impact data and the visible data.

[0092] Exemplarily, the friction coefficient indicated by the state influence data and the visibility indicated by the visibility data are determined as the weather influence data.

[0093] Such a setting, through weather factor data and consideration of additional conditions, can provide accurate visibility forecasts. In this way, it can lay the foundation for road safety, traffic planning and disaster prevention and mitigation, improve the smoothness of traffic and reduce the occurrence of accidents.

[0094] S230, performing a third traffic factor analysis on the data to be analyzed to obtain event factor data; wherein the event factor data is used to reflect the traffic impact within the traffic infrastructure area indicated by the data to be analyzed according to the event status.

[0095] It can be understood that the event status can be an emergency or a holiday event or a game event, etc. Among them, the emergency event can be a traffic accident or construction ahead, etc., but not limited to this. Holiday events can be the Spring Festival, National Day or Mid-Autumn Festival, etc., but not limited to this. Game events can be sports games, marathons or concerts, etc., but not limited to this. Exemplarily, event factor analysis is performed on the data to be analyzed to obtain event factor data; wherein, the event factor analysis can be combined with real-time traffic event data and traffic infrastructure data to predict the traffic conditions in the traffic infrastructure area under the influence of specific event factors. For example, event factors such as traffic accidents, construction, special events, etc. will have an impact on traffic flow and speed. These factors can be combined to provide a more accurate prediction of traffic impact.

[0096] In one possible implementation, see Figure 6 S230, performing a third traffic factor analysis on the data to be analyzed to obtain event factor data, including:

[0097] S231, obtaining current date data and all event data; wherein the current date data is used to indicate the current year, month and day, and the all event data is used to indicate all events in the current year and the years, months and days corresponding to each event.

[0098] It can be understood that the current year, month, and day can be the date of the day, such as May 8, 2010; all events in the current year can be all events in the current year, such as all events on the calendar of 2010, and the year, month, and day corresponding to each event are the dates corresponding to a certain event in the current year; for example, the National Day in 2010, the time corresponding to the National Day is October 1, 2010;

[0099] For example, it can also be combined with time series analysis to effectively extract relevant data from the database. Specifically, timestamp tags can be used to track and record the specific time points when events occur, thereby building a time series model. The model can analyze the frequency of events (events with frequency can be concert events, competition events, etc.), periodicity, and trends. In addition, the potential connections between different events and their association patterns with specific dates can be discovered, which can not only help us understand the temporal characteristics of events, but also obtain the current date data and full event data through the calendar on the mobile phone, the calendar on the computer, or through manually viewed calendars.

[0100] S232, performing date matching based on the current year, month and day indicated by the current date data and the years, months and days corresponding to each event indicated by the full event data, and determining the event data when the current year, month and day indicated by the current date data and the years, months and days corresponding to each event indicated by the full event data match; wherein the event data is used to indicate one of the events in the full event data.

[0101] Exemplarily, time series analysis and association rule mining methods can be used to match dates. Time series analysis can identify time patterns and periodicity in historical data, which helps predict the occurrence of future events. Association rule mining technology is used to find the correlation between different events and the potential connection between specific dates. Through comprehensive analysis, the current date can be effectively matched with historical event data, thereby determining event data related to the current date. For example, the current year, month, and day is October 1, 2010, then October 1, 2010 is compared with the year, month, and day corresponding to each event indicated by the full event data. If the year, month, and day corresponding to each event is October 1, it is proved that the two are the same, so the year, month, and day corresponding to each event is October 1, and the event corresponding to October 1 can be obtained.

[0102] S233, based on the event data, analyze the influencing objects around the transportation infrastructure area indicated by the urban data to be analyzed to obtain event impact data; wherein the event impact data is used to reflect the impact of the influencing objects on the transportation infrastructure area indicated by the urban data to be analyzed.

[0103] It can be understood that the analysis of the influencing object is performed by detecting the driving speed of the vehicle in the traffic infrastructure area indicated by the urban data to be analyzed and the length of the traffic infrastructure area occupied by the influencing object, and calculating the driving time according to the driving speed of the vehicle and the length of the influencing object to obtain the driving time required for the vehicle to pass the influencing object. If the required driving time exceeds the preset driving time, the length of the exceeded time is recorded as percentages of different sizes, and the percentages of different sizes are determined as event impact data. For example, if the exceeded time is 1 minute, the percentage can be recorded as 20%, if the exceeded time is 3 minutes, the percentage can be recorded as 70%, and if the exceeded time is 5 minutes, the percentage can be recorded as 100%.

[0104] Exemplarily, the analysis of influencing objects may be to classify influencing objects, and then classify them according to their dangerousness to obtain the impact of the influencing objects; the classification of influencing objects may be to divide the influencing objects into movable and immovable, for example, movable objects may be people, animals, cars, etc., and immovable objects may be stones, construction fences, etc.; people and animals may be classified as having high impact, cars as having average impact, and stones and construction fences as having high impact, thus obtaining the impact of the transportation infrastructure area.

[0105] S234, obtaining event factor data according to the event impact data.

[0106] Exemplarily, through statistical analysis, statistical features such as frequency, intensity and duration are extracted from event impact data. Through the causal relationship between different influencing factors and the degree of impact on the transportation infrastructure area, it is possible to effectively identify which factors are the key factors that cause the impact on the transportation infrastructure area, and obtain event factor data reflecting these key factors.

[0107] In one possible implementation, see Figure 7 , S234, obtaining event factor data according to the event impact data, including:

[0108] S2341, obtaining position data of a stationary object; wherein the position data is used to indicate the coordinates of the stationary object in the traffic infrastructure area indicated by the urban data to be analyzed, and the stationary object includes an artificial obstacle, a construction fence, or a traffic sign to be repaired.

[0109] For example, obtaining the location data of a stationary object can be achieved by integrating the global positioning system (GPS) technology with the geographic information system (GIS). GPS technology can provide accurate geographic location information, while GIS is used to store, analyze and display these geographic data. In the process of obtaining the location data of a stationary object, the GPS device is used to locate the stationary object, and then these coordinate data are input into the GIS system. The GIS system accurately identifies the specific location of the stationary object in a specific transportation infrastructure area by superimposing and analyzing the geographic information of the urban transportation infrastructure. In addition, the GIS system can also be combined with other data sources, such as urban planning maps and real-time traffic flow data, to further analyze the impact of stationary objects on traffic flow. It is also possible to manually view the transportation infrastructure area.

[0110] S2342, performing a first influencing factor analysis on the event impact data based on the location data to obtain static impact data; wherein the static impact data is used to indicate the distance value from the stationary object to the traffic infrastructure area indicated by the urban data to be analyzed and the total number of stationary objects.

[0111] It can be understood that the stationary object can be a stone, an obstacle or a construction fence, etc., but is not limited thereto. The distance value from the stationary object to the traffic infrastructure area indicated by the urban data to be analyzed can be the distance of the obstacle (stone or construction fence) from the traffic infrastructure area, the total number of stationary objects, the number of obstacles of the same type (stone or construction fence) in this area, etc., but is not limited thereto.

[0112] Exemplarily, the influencing factors of stationary objects are analyzed on the event impact data based on the location data to obtain static impact data; the influencing factors analysis of stationary objects can be performed through spatial analysis methods, which can process and analyze geographic spatial data. The spatial relationship between stationary objects and transportation infrastructure can be calculated through the GIS system, including distance and quantity. Specifically, the GIS system will use a buffer analysis method to create a virtual buffer centered on the transportation infrastructure, and then count the number of stationary objects falling within this virtual buffer. At the same time, the shortest distance from each stationary object to the buffer boundary can also be calculated to obtain static impact data, which provides quantitative indicators for evaluating the specific impact of stationary objects on traffic flow.

[0113] S2343, obtaining the position data of the moving object; wherein the position data is used to indicate the coordinates of the moving object in the traffic infrastructure area indicated by the urban data to be analyzed, and the moving object includes a person, an animal, or a vehicle that has temporarily stopped moving.

[0114] For example, the location data of moving objects can be obtained by using real-time positioning technology, which can track the movement trajectory and position of moving objects. By integrating multiple positioning methods such as GPS, Wi-Fi positioning, and Bluetooth beacons, the precise location information of moving objects can be captured in real time. After these data are processed by algorithms, the movement paths and stop points of moving objects in the transportation infrastructure area can be depicted. In addition, the potential impact of moving objects on traffic flow can be analyzed based on their movement speed and direction.

[0115] The transportation infrastructure area can also be inspected manually.

[0116] S2344, performing a second influencing factor analysis on the event impact data based on the orientation data to obtain dynamic impact data; wherein the dynamic impact data is used to indicate the distance value from the active object to the transportation infrastructure area indicated by the urban data to be analyzed and the total number of active objects.

[0117] It can be understood that the total number of moving objects can be the number of moving objects, for example, the number of people or animals in the area of ​​the traffic infrastructure and the distances of the people or animals to the area of ​​the traffic infrastructure. The moving directions of the people or animals can be indirectly determined by the number and distance (the moving directions of the people or animals can be determined by detecting the facial orientation of the people or animals), and whether the moving directions can cause traffic congestion or affect the normal operation of traffic signals.

[0118] Exemplarily, the influencing factors of active objects are analyzed on the event impact data based on the orientation data to obtain dynamic impact data; the influencing factors of active objects can be analyzed using a spatial analysis method, which can take into account the moving speed, direction, and relative position of the active objects to the traffic infrastructure. By calculating the parameters, the dynamic impact of active objects on traffic flow can be evaluated. For example, it can be determined whether it is likely to cause traffic congestion or affect the normal operation of traffic signals. In addition, by combining historical data and real-time data, the algorithm can also predict the potential impact of active objects on traffic flow within a specific time period.

[0119] S2345, obtaining event factor data according to the static impact data and the dynamic impact data.

[0120] Exemplarily, the distance value of the stationary object indicated by the static impact data to the basic traffic area is compared with the preset distance value of the stationary object to obtain static impact data greater than the preset distance value of the stationary object or static impact data less than the preset distance value of the stationary object, and the distance value of the moving object indicated by the dynamic impact data to the basic traffic area is compared with the preset distance value of the animal body to obtain dynamic impact data greater than the preset distance value of the animal body or dynamic impact data less than the preset distance value of the animal body, and the distance value indicated by the static impact data greater than the preset distance value of the stationary object and the distance value indicated by the dynamic impact data greater than the preset distance value of the animal body are confirmed as event factor data. The preset distance value of the stationary object is a standard distance value at which the stationary object will not affect the basic traffic area; the preset distance value of the animal body is a standard distance value at which the animal body will not affect the basic traffic area.

[0121] Such a setting will help improve the overall operating efficiency of the road network, reduce traffic delays, and enhance the public travel experience. Urban planners can better understand traffic patterns and predict possible future traffic development trends, which can reduce traffic congestion and thus improve traffic efficiency.

[0122] S240, analyzing one or more of the time factor data, the weather factor data, and the event factor data to obtain factor influence data.

[0123] Exemplarily, an analysis of one of the time factor data, weather factor data, and event factor data can be to identify the periodicity and trend in the data, and analyze the outliers at specific time points to obtain the impact of the event on traffic. For weather factor data, weather variables can be used as independent variables, and certain indicators of the event can be used as dependent variables to determine the specific impact of different weather conditions on traffic. Event factor data evaluates the impact of specific events (sports events, concerts, marathons, etc.) on traffic by comparing the changes in data before and after the event. The analysis of multiple or all of the time factor data, weather factor data, and event factor data needs to be combined with the above three situations to determine the impact on traffic, which helps to improve the reliability and effectiveness of the analysis results and better understand and predict the development trend of future events.

[0124] In a possible implementation, S240, analyzing one or more of the time factor data, the weather factor data, and the event factor data to obtain factor impact data includes:

[0125] S241: If the influencing factor data is time factor data, weather factor data or event factor data, the influencing factor data is determined as factor influencing data.

[0126] It can be understood that influencing factor data is determined as factor influencing data. For example, there is currently no influence of time, no influence of events, only snow in the weather conditions. Then, only snow has an impact on traffic, and the weather factor data can be determined as factor influencing data.

[0127] Exemplarily, if the influencing factor data is time factor data, weather factor data or event factor data, that is, if there is only one influencing factor data, if the influencing factor data is time factor data, then the time factor data is determined as factor influence data; if the influencing factor data is weather factor data, then the weather factor data is determined as factor influence data; if the influencing factor data is event factor data, then the event factor data is determined as factor influence data.

[0128] S242: If the influencing factor data are two of the time factor data, the weather factor data and the event factor data, two of the influencing factor data are determined as factor influencing data.

[0129] It can be understood that two of the influential factor data are determined as factor influence data. For example, the current situation is the peak period in the evening, there is no impact of events, and there is snowing in the weather conditions. Then, only the peak period in the evening and snowing have an impact on traffic. The weather factor data and the time factor data can be determined together as factor influence data.

[0130] Exemplarily, if the influencing factor data is two of the time factor data, weather factor data or event factor data, that is, if there are two influencing factor data, if the influencing factor data is the time factor data and the weather factor data, then the time factor data and the weather factor data are determined as factor influence data; if the influencing factor data is the weather factor data and the event factor data, then the weather factor data and the event factor data are determined as factor influence data; if the influencing factor data is the event factor data and the time factor data, then the event factor data and the time factor data are determined as factor influence data.

[0131] S243: If the influencing factor data are time factor data, weather factor data and event factor data, the time factor data, weather factor data and event factor data are combined and analyzed to determine as factor influencing data.

[0132] It can be understood that the time factor data, weather factor data and event factor data are combined and analyzed to determine the factor influence data. For example, the current peak period in the morning, there is a city exhibition, and there is snow in the weather conditions. Then, only the peak period in the evening, the exhibition conditions and snow have an impact on traffic, and the time factor data, weather factor data and event factor data can be determined as factor influence data. Exemplarily, if the influencing factor data are time factor data, weather factor data and event factor data, that is, the factor influence data are time factor data, weather factor data and event factor data.

[0133] S300, generating factor result data of urban space form according to the factor impact data; wherein the factor result data is used to indicate a solution obtained according to the traffic impact situation.

[0134] For example, by using satellite remote sensing images and geographic information system (GIS) technology, the centerline of urban roads, the number of lanes, the road slope, the curvature and other information can be accurately drawn, and regularly updated to reflect the construction and reconstruction of roads. Detailed marking of urban land use types, not only distinguishing commercial areas, residential areas, and industrial areas, but also subdividing subtypes within various functional areas, such as large shopping malls, ordinary residential communities, high-tech industrial parks, etc., to analyze the differences in traffic attraction and generation of different subtypes. Collect urban public transportation infrastructure data, including bus station locations and route directions, subway entrance and exit distribution, bicycle lane network layout, etc., to evaluate its connection with road traffic and transfer convenience. By using a multivariate linear regression model, analyze the quantitative relationship between traffic flow (dependent variable) and weather factors (independent variables, such as rainfall, temperature, visibility), and determine the change trend and elasticity coefficient of traffic flow under different weather conditions. Use time series analysis methods to study the fluctuation pattern of traffic flow before and after holidays and during emergencies, compare the data of normal working days, and identify abnormal change points and time periods of traffic flow. Based on the spatial analysis function of GIS, the traffic congestion data and urban spatial morphology data are superimposed and analyzed to calculate the correlation coefficient between spatial indicators such as road density, intersection density, and land use mix and the degree of traffic congestion. The urban road network can also be divided into different congestion clustering areas according to the time characteristics of traffic congestion (the duration of congestion during peak hours in the morning and evening, and the frequency of congestion during off-peak hours) and spatial characteristics (the geographical location and spread of congested sections). Combined with the hierarchical clustering method, multi-level clustering of urban functional areas is performed to analyze the traffic connection and congestion transmission mechanism within and between functional areas at different levels (such as municipal commercial centers, district-level commercial sub-centers, and community-level commercial service points). For example, the result data of the factors that generate the urban spatial form can be used to calculate the congestion index and build a comprehensive congestion index model. In addition to considering the traditional factors such as the ratio of traffic volume to road capacity and the speed ratio, it also includes weather correction coefficients (such as the slippery road coefficient in rainy days and the visibility reduction coefficient in foggy days) and road spatial form influencing factors (such as the bottleneck coefficient at narrow roads and the complexity coefficient of intersections). Different types of vehicles are given weights according to the occupation of road resources and the degree of traffic impact. For example, buses have a higher weight to reflect their consideration of public transportation priority, and trucks have a weight determined according to their impact on road carrying capacity and driving speed. For example, the traffic management strategy generated by the solution can be to accurately set the start and end times and variable lane directions of tidal lanes in areas with severe tidal congestion during peak hours in the morning and evening, based on the analysis results, and achieve dynamic timing optimization through an intelligent traffic signal system.In bad weather, the intelligent traffic platform can be used to push road condition warning information to the vehicle navigation system, mobile map APP and other terminals in real time to guide drivers to plan routes or adjust travel methods in advance; at the same time, snow and ice removal equipment and drainage facilities are deployed in advance on sections prone to water accumulation and ice, and temporary traffic control and detour plans are set up. In response to traffic congestion caused by holidays and emergencies, a cross-departmental emergency command center is established to integrate the resources of multiple departments such as traffic police, transportation, fire protection, and medical care to achieve information sharing and coordinated disposal; special traffic control plans are formulated, such as implementing time-based and regional traffic control and diversion measures on roads around event venues during large-scale events. It can also be a spatial optimization strategy, which can be based on the correlation analysis results of traffic congestion and urban spatial form, and optimize the local road network in areas with severe congestion and unreasonable spatial layout. For example, widen bottleneck sections, increase the number of intersection entrance lanes, and optimize road linear design to improve driving sight distance and safety; reasonably plan multi-story parking lots, underground parking garages or parking transfer facilities around traffic attractions such as commercial centers, schools, and hospitals to reduce the interference of roadside parking on dynamic traffic. Combined with urban renewal and new district planning projects, the urban functional layout and land use planning can be optimized from a macro level. For example, the balance between work and residence can be promoted to reduce the volume of long-distance commuting across districts; a small-scale, dense road network can be constructed in the planning of new urban districts to improve road connectivity and traffic evacuation capabilities; a green travel-oriented urban space can be created, a continuous network of pedestrian and bicycle paths can be built, and seamlessly connected with public transportation stations to encourage residents to adopt green travel methods and alleviate road traffic pressure.

[0135] Such a setting can provide more accurate traffic flow forecasts, urban planners can better understand traffic patterns, and can also help decision makers evaluate the effectiveness of existing traffic management measures and predict possible future traffic development trends, providing a scientific basis for the formulation of long-term traffic strategies, which can reduce traffic congestion and thus improve traffic efficiency.

[0136] In one possible implementation, see Figure 8 , S300, based on the factor influencing data, generate the factor result data of the urban space form, including:

[0137] S310, acquiring sample factor data, and generating sample result data according to the sample factor data.

[0138] For example, by collecting key indicator data such as traffic flow, population density, and commercial activity intensity in different areas of the city, a sample data set can be formed. After processing this data, the key factors affecting changes in urban spatial form can be identified. The sample data can be analyzed to reveal the interactions and degree of influence between different factors. Based on these analysis results, sample result data can be generated to provide data support for the optimization of urban spatial form.

[0139] S320, taking the sample factor data as input and the corresponding sample result data as expected output, the initial machine learning model is trained to obtain an urban space morphology analysis model.

[0140] For example, the initial machine learning model can be trained by using supervised learning methods. During the training process, by learning the mapping relationship between sample factor data and sample result data, the internal parameters (the relative relationship between input and output) are continuously adjusted to minimize the error between the predicted results and the actual results, and then iterative calculations are performed until the prediction performance of the model reaches the predetermined accuracy standard. After the training is completed, the model can predict new input data, thereby providing decision support for urban planners and helping them better understand and predict the changing trends of urban spatial forms.

[0141] S330, using the urban space form analysis model to perform model analysis on the factor influence data, and generate factor result data of the urban space form.

[0142] For example, model analysis of factor impact data can be performed through the influence of multiple factor variables on urban spatial form, and the relationship between factors and urban spatial form can be quantified by establishing a mathematical model. It is possible to obtain which factors have an impact on the change of urban spatial form and the relationship between factors and urban spatial form, so as to identify planning variables and improve the efficiency of urban spatial form data analysis.

[0143] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0144] Corresponding to the urban space morphology data analysis method based on machine learning described in the above embodiment, the embodiment of the present application also provides an urban space morphology data analysis system based on machine learning, and each unit of the system can implement each step of the urban space morphology data analysis method based on machine learning. Fig. 9 A structural block diagram of an urban space morphology data analysis system based on machine learning provided in an embodiment of the present application is shown. For ease of explanation, only the parts related to the embodiment of the present application are shown.

[0145] Reference Fig. 9 , the urban spatial morphology data analysis system based on machine learning includes:

[0146] A determination unit, used to determine the urban data to be analyzed of the urban spatial form; wherein the urban data to be analyzed is used to indicate the transportation infrastructure area in the urban spatial form;

[0147] The analysis unit is used to perform multi-factor analysis on the data to be analyzed to obtain factor impact data; wherein the factor impact data is used to reflect the impact of multiple factors on traffic in the traffic infrastructure area;

[0148] The result unit is used to generate factor result data of urban space form according to the factor impact data; wherein the factor result data is used to indicate the solution obtained according to the traffic impact situation.

[0149] It should be noted that the information interaction, execution process, etc. between the above-mentioned systems / units are based on the same concept as the method embodiment of the present application. Their specific functions and technical effects can be found in the method embodiment part and will not be repeated here.

[0150] Those skilled in the art can clearly understand that, for the convenience and simplicity of description, only the division of the above-mentioned functional units and modules is used as an example for illustration. In practical applications, the above-mentioned function allocation can be completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above. The functional units and modules in the embodiment can be integrated in a processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of software functional units. In addition, the specific names of the functional units and modules are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of this application. The specific working process of the units and modules in the above-mentioned system can refer to the corresponding process in the aforementioned method embodiment, which will not be repeated here.

[0151] The present application also provides a machine learning-based urban spatial morphology data analysis device. Fig.10 This is a schematic diagram of the structure of an urban space morphology data analysis device based on machine learning provided in an embodiment of the present application. Fig.10 As shown, the urban space morphology data analysis device 6 based on machine learning in this embodiment includes: at least one processor 60 ( Fig.10 Only one is shown), at least one memory 61 ( Fig.10 Only one is shown in the figure) and a computer program 62 stored in the at least one memory 61 and executable on the at least one processor 60. When the processor 60 executes the computer program 62, the urban space morphology data analysis device 6 based on machine learning implements the steps in any of the above-mentioned urban space morphology data analysis method embodiments based on machine learning, or the urban space morphology data analysis device 6 based on machine learning implements the functions of each module / unit in the above-mentioned system embodiments.

[0152] Exemplarily, the computer program 62 may be divided into one or more modules / units, which are stored in the memory 61 and executed by the processor 60 to complete the present application. The one or more modules / units may be a series of computer program instruction segments capable of completing specific functions, which are used to describe the execution process of the computer program 62 in the urban spatial morphology data analysis device 6 based on machine learning.

[0153] The urban space form data analysis device 6 based on machine learning can be a computing device such as a desktop computer, a notebook, etc. The urban space form data analysis device based on machine learning can include, but is not limited to, a processor 60 and a memory 61. Those skilled in the art can understand that Fig.10 It is only an example of the urban space morphology data analysis device 6 based on machine learning, and does not constitute a limitation of the urban space morphology data analysis device 6 based on machine learning. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, buses, etc.

[0154] The processor 60 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0155] In some embodiments, the memory 61 may be an internal storage unit of the urban space morphology data analysis device 6 based on machine learning, such as a hard disk or memory of the urban space morphology data analysis device 6 based on machine learning. In other embodiments, the memory 61 may also be an external storage device of the urban space morphology data analysis device 6 based on machine learning, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped on the urban space morphology data analysis device 6 based on machine learning. Further, the memory 61 may also include both the internal storage unit and the external storage device of the urban space morphology data analysis device 6 based on machine learning. The memory 61 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program, etc. The memory 61 may also be used to temporarily store data that has been output or is to be output.

[0156] An embodiment of the present application provides a computer program product. When the computer program product runs on an urban space morphology data analysis device based on machine learning, the urban space morphology data analysis device based on machine learning implements the steps in any of the above-mentioned method embodiments.

[0157] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the processes in the above-mentioned embodiment method, which can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned various method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may at least include: any entity or device that can carry the computer program code to the urban spatial morphology data analysis device based on machine learning, recording medium, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), electric carrier signal, telecommunication signal and software distribution medium. For example, a USB flash drive, a mobile hard disk, a magnetic disk or an optical disk. In some jurisdictions, according to legislation and patent practice, computer-readable media cannot be electric carrier signals and telecommunication signals.

[0158] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described or recorded in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0159] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel may use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0160] In the embodiments provided in the present application, it should be understood that the disclosed urban space morphology data analysis system, device and method based on machine learning can be implemented in other ways. For example, the above-described urban space morphology data analysis system and device embodiments based on machine learning are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be an indirect coupling or communication connection through some interfaces, devices or units, which can be electrical, mechanical or other forms. The unit described as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place, or it may be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the scheme of this embodiment.

[0161] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A method for analyzing urban spatial morphology data based on machine learning, characterized in that: include: Determine the urban data to be analyzed of the urban spatial form; wherein the urban data to be analyzed is used to indicate the transportation infrastructure area in the urban spatial form; Performing a multi-factor analysis on the data to be analyzed to obtain factor impact data; wherein the factor impact data is used to reflect the impact of multiple factors on traffic in the traffic infrastructure area; Generate factor result data of urban space form according to the factor impact data; wherein the factor result data is used to indicate a solution obtained according to the traffic impact situation; The urban data to be analyzed for determining the urban spatial form include: Acquire the territory standard data and all the morphological data in the urban space; wherein the territory standard data is used to indicate the territory height on the ground in the current urban space, and the morphological data is used to indicate all the morphological areas in the urban space; Performing contour processing on the morphological area indicated by the morphological data to obtain first processed data; wherein the first processed data is used to indicate the contour shape of the morphological area indicated by each morphological data; Processing the morphological data based on the territory standard data to obtain second processed data; wherein the second processed data is used to reflect the connectivity of objects within the morphological area indicated by each morphological data; The city data to be analyzed is obtained according to the first processed data and the second processed data.

2. The urban space morphology data analysis method based on machine learning according to claim 1, characterized in that: The multi-factor analysis is performed on the data to be analyzed to obtain factor impact data, including: Performing a first traffic factor analysis on the data to be analyzed to obtain time factor data; wherein the time factor data is used to reflect the traffic impact in the traffic infrastructure area indicated by the data to be analyzed according to the time condition; Performing a second traffic factor analysis on the data to be analyzed to obtain weather factor data; wherein the weather factor data is used to reflect the impact of weather conditions on traffic in the traffic infrastructure area indicated by the data to be analyzed; Performing a third traffic factor analysis on the data to be analyzed to obtain event factor data; wherein the event factor data is used to reflect the traffic impact of the event status on the traffic infrastructure area indicated by the data to be analyzed; The factor influence data is obtained by analyzing one or more of the time factor data, the weather factor data and the event factor data.

3. The urban space morphology data analysis method based on machine learning according to claim 2, characterized in that: The performing a first traffic factor analysis on the data to be analyzed to obtain time factor data includes: Acquire time period data; wherein the time period data includes morning period data and evening period data, the morning period data is used to indicate the morning period of the day, and the evening period data is used to indicate the evening period of the day; Traffic flow identification is performed on the data to be analyzed according to the early data and the late data to obtain first impact data; wherein the first impact data is used to indicate the frequency of traffic congestion in the traffic infrastructure area indicated by the data to be analyzed during the morning time period and the evening time period; Performing a vehicle type analysis on vehicles in the traffic infrastructure area indicated by the data to be analyzed based on the first impact data to obtain second impact data; wherein the second impact data is used to reflect the frequency of traffic congestion in the traffic infrastructure area indicated by the data to be analyzed in the city under different vehicle characteristics; Time factor data is obtained according to the first impact data and the second impact data.

4. The urban space morphology data analysis method based on machine learning according to claim 3 is characterized in that: The performing vehicle type analysis on vehicles in the traffic infrastructure area indicated by the data to be analyzed to obtain second impact data includes: Acquire data on vehicle types that are passable in the traffic infrastructure area indicated by the data to be analyzed; wherein the vehicle type data is used to indicate the types of vehicles that are allowed to pass in the traffic infrastructure area indicated by the data to be analyzed, and the types of vehicles that are allowed to pass include at least three types of vehicles from among cars, trucks, buses, transport vehicles and passenger cars; Acquire width data of the traffic infrastructure area indicated by the data to be analyzed and vehicle size data of the vehicle type; wherein the width data is used to indicate the width value of the traffic infrastructure area indicated by the data to be analyzed, and the vehicle size data is used to indicate the vehicle width value and the vehicle length value; The width data and the vehicle size data are subjected to a traffic analysis to obtain second influencing data.

5. The urban space morphology data analysis method based on machine learning according to claim 2, characterized in that: The performing a second traffic factor analysis on the data to be analyzed to obtain weather factor data includes: Acquire weather status data in real time, and obtain ground condition data based on the weather status data; wherein the weather status data is used to reflect the current weather conditions, and the ground condition data is used to indicate the current ground state, and the ground state includes a dry state, a slippery state, a waterlogged state, a muddy state, a snow-covered state, or an icy state; The state influence data is obtained according to the ground state indicated by the ground state data; wherein the state influence data is used to reflect the friction coefficient when the ground state indicated by the ground state data is one of a dry state, a slippery state, a waterlogged state, a muddy state, a snow-covered state or an icy state; Obtaining visible data based on the weather status data; wherein the visible data is used to reflect the visible conditions ahead; The weather factor data is obtained according to the state impact data and the visible data.

6. The urban space morphology data analysis method based on machine learning according to claim 2, characterized in that: The performing of a third traffic factor analysis on the data to be analyzed to obtain event factor data includes: Obtaining current date data and all event data; wherein the current date data is used to indicate the current year, month, and day, and the all event data is used to indicate all events in the current year and the years, months, and days corresponding to each event; Performing date matching according to the current year, month and day indicated by the current date data and the years, months and days corresponding to the events indicated by the full event data, and determining event data when the current year, month and day indicated by the current date data and the years, months and days corresponding to the events indicated by the full event data match; wherein the event data is used to indicate one of the events in the full event data; Based on the event data, an influence object analysis is performed on the surroundings of the transportation infrastructure area indicated by the city data to be analyzed to obtain event impact data; wherein the event impact data is used to reflect the impact of the influence object on the transportation infrastructure area indicated by the city data to be analyzed; The event factor data is obtained according to the event impact data.

7. The urban space morphology data analysis method based on machine learning according to claim 6, characterized in that: The obtaining the event factor data according to the event impact data includes: Acquire location data of a stationary object; wherein the location data is used to indicate the coordinates of the stationary object in the traffic infrastructure area indicated by the data to be analyzed in the city, and the stationary object includes an artificially set obstacle, a construction fence, or a traffic sign to be repaired; Performing a first influencing factor analysis on the event impact data based on the location data to obtain static impact data; wherein the static impact data is used to indicate the distance value from the stationary object to the traffic infrastructure area indicated by the city data to be analyzed and the total number of stationary objects; Acquire the position data of the moving object; wherein the position data is used to indicate the coordinates of the moving object in the traffic infrastructure area indicated by the data to be analyzed in the city, and the moving object includes a person, an animal, or a vehicle that has temporarily stopped moving; Performing a second influencing factor analysis on the event impact data based on the orientation data to obtain dynamic impact data; wherein the dynamic impact data is used to indicate the distance value from the moving object to the traffic infrastructure area indicated by the city data to be analyzed and the total number of moving objects; The event factor data is obtained according to the static influence data and the dynamic influence data.

8. The urban space morphology data analysis method based on machine learning according to claim 7, characterized in that: The step of analyzing one or more of the time factor data, the weather factor data, and the event factor data to obtain factor influence data includes: If the influencing factor data is the time factor data, the weather factor data or the event factor data, the influencing factor data is determined as the factor influencing data; If the influencing factor data is two of the time factor data, the weather factor data and the event factor data, two of the influencing factor data are determined as the factor influencing data; If the influencing factor data are the time factor data, the weather factor data and the event factor data, the time factor data, the weather factor data and the event factor data are combined and analyzed to determine as the factor influencing data.

9. The urban space morphology data analysis method based on machine learning according to claim 1, characterized in that: The step of generating factor result data of urban space form according to the factor influence data includes: Acquire sample factor data, and generate sample result data according to the sample factor data; Taking the sample factor data as input and the corresponding sample result data as expected output, the initial machine learning model is trained to obtain an urban space morphology analysis model; The urban space form analysis model is used to perform model analysis on the factor influence data to generate the factor result data of the urban space form.

10. An urban space morphology data analysis system based on machine learning, characterized in that: include: A determination unit, used to determine the urban data to be analyzed of the urban spatial form; wherein the urban data to be analyzed is used to indicate the transportation infrastructure area in the urban spatial form; An analysis unit, configured to perform a multi-factor analysis on the data to be analyzed to obtain factor impact data; wherein the factor impact data is used to reflect the impact of multiple factors on traffic in the traffic infrastructure area; A result unit, used to generate factor result data of urban space form according to the factor impact data; wherein the factor result data is used to indicate a solution obtained according to the traffic impact situation; Wherein, the determining unit is further used for: Acquire the territory standard data and all the morphological data in the urban space; wherein the territory standard data is used to indicate the territory height on the ground in the current urban space, and the morphological data is used to indicate all the morphological areas in the urban space; Performing contour processing on the morphological area indicated by the morphological data to obtain first processed data; wherein the first processed data is used to indicate the contour shape of the morphological area indicated by each morphological data; Processing the morphological data based on the territory standard data to obtain second processed data; wherein the second processed data is used to reflect the connectivity of objects within the morphological area indicated by each morphological data; The city data to be analyzed is obtained according to the first processed data and the second processed data.

Images