Urban traffic distribution analysis method and system based on multi-source big data

Abstract

The invention discloses an urban traffic distribution analysis method and system based on multi-source big data, and the method can comprehensively describe the travel general situation of urban residents through integrating the big data of multiple traffic modes of buses, subways, taxis and shared bikes in a city, avoids the deviation caused by a single data source, and improves the accuracy of urban traffic distribution analysis. According to the data preprocessing, original data are converted into a unified spatial point data format, accurate analysis is ensured, OD extraction not only records a travel starting point and a travel ending point, but also calculates travel duration, a key basis is provided for travel behavior analysis, spatial and temporal distribution feature analysis comprehensively considers time and spatial scales, and a spatial interaction network of various traffic modes is revealed finely. In the step of interaction matrix construction, OD is matched to space units, an OD interaction matrix between stations or grids is constructed, travel behaviors are quantified, travel characteristics are compared to reveal travel differences in different time periods, traffic bottlenecks and hot spots are recognized, and in the step of travel mode recognition, high-frequency OD pairs and interaction areas are found, and scientific guidance and suggestions are provided for urban traffic planning and management.

Description

Technical Field

[0001] The present invention relates to the technical field of urban traffic distribution analysis, and in particular to an urban traffic distribution analysis method and system based on multi-source big data. Background Art

[0002] In the context of rapid urbanization, urban traffic congestion has become increasingly prominent, causing many inconveniences to people's travel. Traditional urban traffic analysis methods mostly rely on limited traffic survey data and empirical judgments, which are difficult to fully and accurately reflect the real situation of urban traffic. With the continuous development of big data technology, collecting and analyzing urban traffic big data has become a new solution.

[0003] However, the existing technologies have the following defects when using big data to analyze urban traffic distribution: (1) Traditional methods often only focus on the data of one or several modes of transportation, such as using only bus card swiping data or taxi GPS data, which makes the analysis results incomplete and difficult to accurately reflect the overall situation of urban traffic; (2) Due to the large amount of data and diverse formats, the existing technologies are often inefficient in steps such as data preprocessing and OD (origin-destination) extraction, which requires a lot of time and computing resources; (3) When calculating the travel time of various modes of transportation, the existing technologies often use simple average speed or fixed path to calculate, ignoring the impact of actual traffic conditions (such as congestion, accidents, etc.) on travel time, resulting in inaccurate calculation results; (4) Even if the data analysis is completed, the existing technologies often find it difficult to directly apply the analysis results to urban traffic planning and optimization, and lack effective connection with related fields such as urban planning and road design. Summary of the invention

[0004] In view of this, the present invention proposes a method and system for analyzing urban traffic distribution based on multi-source big data, which can improve the accuracy and comprehensiveness of urban traffic analysis and provide strong support for urban traffic planning and optimization.

[0005] The technical solution of the present invention is achieved in this way:

[0006] A method for analyzing urban traffic distribution based on multi-source big data, specifically comprising:

[0007] Data collection steps: Collect big data of various modes of transportation in the city, including bus card swiping data, subway travel data, taxi OD data and shared bicycle usage data;

[0008] Data preprocessing step: convert the collected raw data into spatial point data;

[0009] OD extraction step: extract the starting point and end point of the spatial point data, and calculate the travel time of various modes of transportation;

[0010] Steps for analyzing the temporal and spatial distribution characteristics: Combine the scale effects of both time and space to analyze the spatial interaction network distribution characteristics of various transportation modes;

[0011] Interaction matrix construction steps: According to the distribution characteristics of the spatial interaction network, the starting points and end points of various transportation modes are matched to the corresponding spatial units, and the OD interaction matrix between sites or grids is constructed;

[0012] Travel characteristics comparison steps: Compare travel characteristics in different time periods, and analyze the differences in morning and evening peaks, travel frequency, and travel time;

[0013] Travel mode identification steps: Analyze the OD interaction matrix, identify the OD pairs and interaction areas with high frequency interactions, and obtain the rules and patterns of residents' travel;

[0014] Visualization and result output steps: Apply GIS technology to visualize the data, count the number of O and D and the frequency of OD interaction in each spatial unit based on the comparison and recognition results, and display the analysis results in a graphical way to obtain the interactive distribution analysis of urban traffic.

[0015] As a further optional solution of the urban traffic distribution analysis method based on multi-source big data, the conversion of the collected raw data into spatial point data specifically includes:

[0016] Convert the original data into spatial point data in shapefile format;

[0017] During the data conversion process, ensure that key information fields are retained, including card number, boarding / disembarking time, and station / latitude and longitude coordinates;

[0018] The converted data is cleaned to remove obviously abnormal data points, including unreasonable travel time, repeated records or illogical station combinations.

[0019] As a further optional solution of the urban traffic distribution analysis method based on multi-source big data, the extraction of starting points and end points of spatial point data and calculation of travel time of various modes of transportation specifically include:

[0020] Import the converted spatial point data into the data processing software;

[0021] Data processing software identifies the starting and ending points of each trip based on the timestamps and location information in the data;

[0022] The identified OD data is collated and analyzed to generate OD pair combinations, each of which has a unique identifier and includes travel duration.

[0023] As a further optional solution of the urban traffic distribution analysis method based on multi-source big data, the combination of the scale effects of time and space dimensions to analyze the spatial interaction network distribution characteristics of various modes of transportation specifically includes:

[0024] According to the characteristics of transportation modes, appropriate spatial units are selected for analysis, among which buses and subways are based on stations, and shared bicycles and taxis are based on social management grids;

[0025] Analyze the travel time distribution at different time periods throughout the day and identify the travel characteristics of morning and evening peaks;

[0026] Analyze the spatial distribution characteristics of travel frequency of different transportation modes;

[0027] According to the travel characteristics and distribution characteristics, the travel frequencies of different modes of transportation in a week, weekdays and weekends are counted and compared;

[0028] Calculate and compare the average travel time of different modes of transportation based on travel characteristics and distribution features;

[0029] Analyze the interaction intensity between stations or grids based on travel characteristics and distribution characteristics;

[0030] Based on travel frequency, travel time and interaction intensity, the spatial interaction network distribution characteristics of various transportation modes are obtained.

[0031] As a further optional solution of the urban traffic distribution analysis method based on multi-source big data, the spatial interaction network distribution characteristics match the starting points and end points of various transportation modes to the corresponding spatial interaction network distribution characteristics, and construct an OD interaction matrix between sites or grids, specifically including:

[0032] For each mode of transportation, its OD points are matched to the corresponding spatial units, where buses and subways use stations as units, and shared bicycles and taxis use social management grids as units;

[0033] According to the matched OD data, an OD interaction matrix between sites or grids is constructed, wherein the rows and columns of the OD interaction matrix represent different spatial units, and the elements in the matrix represent the OD interaction frequency between spatial units.

[0034] As a further optional solution of the urban traffic distribution analysis method based on multi-source big data, the comparison of travel characteristics in different time periods and the analysis of the differences in morning and evening peaks, travel frequency and travel time specifically include:

[0035] Filter out the travel data on weekdays and weekends from the original data;

[0036] Analyze the time distribution of travel frequency throughout the day on weekdays and weekends to determine the peak hours in the morning and evening;

[0037] Compare the travel frequency on weekdays and weekends to see if there is a difference between the two;

[0038] Calculate the average travel time on weekdays and weekends and compare the difference between the two;

[0039] The constructed OD interaction matrix between sites or grids was used to analyze the changes in interaction frequency between weekdays and weekends.

[0040] As a further optional solution of the urban traffic distribution analysis method based on multi-source big data, the OD interaction matrix is ​​analyzed to identify the OD pairs and interaction areas with high frequency interactions, and obtain the laws and patterns of residents' travel, which specifically includes:

[0041] Perform frequency statistics on each OD pair in the OD interaction matrix and calculate the interaction frequency of each OD pair;

[0042] According to the set threshold, OD pairs with higher interaction frequency are screened out;

[0043] A spatial clustering algorithm was used to cluster the data in the OD interaction matrix, and regions with similar interaction characteristics were divided into the same category to form different interaction regions;

[0044] Combining the analysis results of high-frequency interactive OD pairs and interactive areas, the rules and patterns of residents' travel are obtained.

[0045] An urban traffic distribution analysis system based on multi-source big data, comprising:

[0046] The data collection module is used to collect big data of various modes of transportation in the city, including bus card swiping data, subway travel data, taxi OD data and shared bicycle usage data;

[0047] A data preprocessing module is used to convert the collected raw data into spatial point data;

[0048] OD extraction module, used to extract the starting point and end point of spatial point data and calculate the travel time of various modes of transportation;

[0049] The spatiotemporal distribution characteristics analysis module is used to combine the scale effects of time and space to analyze the spatial interaction network distribution characteristics of various transportation modes;

[0050] The interaction matrix construction module is used to match the starting points and ending points of various transportation modes to the corresponding spatial units according to the distribution characteristics of the spatial interaction network, and to construct the OD interaction matrix between sites or grids;

[0051] The travel characteristics comparison module is used to compare travel characteristics in different time periods and analyze the differences in morning and evening peaks, travel frequency, and travel time;

[0052] The travel mode identification module is used to analyze the OD interaction matrix, identify the OD pairs and interaction areas with high frequency interactions, and obtain the laws and patterns of residents' travel;

[0053] The visualization and result output module is used to apply GIS technology for data visualization. Based on the comparison and recognition results, the number of O and D and the frequency of OD interaction of each spatial unit are counted, and the analysis results are displayed in a graphical way to obtain the interactive distribution analysis of urban traffic.

[0054] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned urban traffic distribution analysis method based on multi-source big data are implemented.

[0055] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned urban traffic distribution analysis method based on multi-source big data.

[0056] The beneficial effects of the present invention are as follows: by collecting big data of various modes of transportation in the city (buses, subways, taxis, shared bicycles), it is possible to comprehensively reflect the overall situation of urban residents' travel and avoid the bias or limitations that may be brought about by a single data source. The data preprocessing step converts the original data into spatial point data, providing a unified and standardized data format for subsequent analysis, ensuring the accuracy of the analysis. The OD extraction step not only extracts the starting point and end point information, but also calculates the travel time of various modes of transportation, providing an important basis for in-depth analysis of travel behavior. The spatiotemporal distribution feature analysis step simultaneously considers the scale effects of both time and space dimensions, and can more finely reveal the spatial interaction network distribution characteristics of different modes of transportation. The interaction matrix The construction step matches the starting point and the end point to the corresponding spatial units respectively, and constructs the OD interaction matrix between sites or grids, which provides a basis for the quantitative analysis of travel behavior. The visualization and result output step uses GIS technology to visualize the data and displays the analysis results in a graphical way, making the analysis results more intuitive and easy to understand, and convenient for decision makers to understand and apply. The travel characteristics comparison step compares the travel characteristics of different time periods, analyzes the differences in morning and evening peaks, travel frequency and travel time, which helps to identify the bottlenecks and hot issues of urban traffic. The travel mode identification step identifies high-frequency interactive OD pairs and interaction areas, obtains the laws and patterns of residents' travel, and provides a scientific basis and guidance for urban traffic planning and management. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, 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 invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0058] Figure 1 A schematic diagram of a flow chart of a method for analyzing urban traffic distribution based on multi-source big data according to the present invention;

[0059] Figure 2 A schematic diagram of the composition of an urban traffic distribution analysis system based on multi-source big data according to the present invention;

[0060] Figure 3 The figure is a schematic diagram of the composition of a computing device according to the present invention. DETAILED DESCRIPTION

[0061] The technical solutions in the embodiments of the present invention are described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0062] refer to Figures 1 to 3 , a method for analyzing urban traffic distribution based on multi-source big data, specifically including:

[0063] Data collection steps: Collect big data of various modes of transportation in the city, including bus card swiping data, subway travel data, taxi OD data and shared bicycle usage data;

[0064] Data preprocessing step: convert the collected raw data into spatial point data;

[0065] OD extraction step: extract the starting point and end point of the spatial point data, and calculate the travel time of various modes of transportation;

[0066] Steps for analyzing the temporal and spatial distribution characteristics: Combine the scale effects of both time and space to analyze the spatial interaction network distribution characteristics of various transportation modes;

[0067] Interaction matrix construction steps: According to the distribution characteristics of the spatial interaction network, the starting points and end points of various transportation modes are matched to the corresponding spatial units, and the OD interaction matrix between sites or grids is constructed;

[0068] Travel characteristics comparison steps: Compare travel characteristics in different time periods, and analyze the differences in morning and evening peaks, travel frequency, and travel time;

[0069] Travel mode identification steps: Analyze the OD interaction matrix, identify the OD pairs and interaction areas with high frequency interactions, and obtain the rules and patterns of residents' travel;

[0070] Visualization and result output steps: Apply GIS technology to visualize the data, count the number of O and D and the frequency of OD interaction in each spatial unit based on the comparison and recognition results, and display the analysis results in a graphical way to obtain the interactive distribution analysis of urban traffic.

[0071] In this embodiment, by collecting big data of various modes of transportation in the city (buses, subways, taxis, and shared bicycles), the overall situation of urban residents' travel can be fully reflected, avoiding the bias or limitations that may be caused by a single data source. The data preprocessing step converts the original data into spatial point data, providing a unified and standardized data format for subsequent analysis, ensuring the accuracy of the analysis. The OD extraction step not only extracts the starting point and end point information, but also calculates the travel time of various modes of transportation, providing an important basis for in-depth analysis of travel behavior. The spatiotemporal distribution feature analysis step considers the scale effects of both time and space dimensions, and can more finely reveal the spatial interaction network distribution characteristics of different modes of transportation. The interaction matrix construction step matches the starting point and end point to the corresponding spatial units respectively, and constructs the OD interaction matrix between sites or grids, which provides a basis for quantitative analysis of travel behavior. The visualization and result output step uses GI S technology is used to visualize data and display the analysis results in a graphical way, making the analysis results more intuitive and easy to understand, and convenient for decision makers to understand and apply. The travel characteristics comparison step compares the travel characteristics of different time periods, analyzes the differences in morning and evening peaks, travel frequency and travel time, which helps to identify the bottlenecks and hot issues of urban traffic. The travel mode identification step identifies high-frequency interactive OD pairs and interactive areas, and obtains the rules and patterns of residents' travel, providing a scientific basis and guiding suggestions for urban traffic planning and management.

[0072] Preferably, the converting the collected raw data into spatial point data specifically includes:

[0073] Convert the original data into spatial point data in shapefile format;

[0074] During the data conversion process, ensure that key information fields are retained, including card number, boarding / disembarking time, and station / latitude and longitude coordinates;

[0075] The converted data is cleaned to remove obviously abnormal data points, including unreasonable travel time, repeated records or illogical station combinations.

[0076] In this embodiment, the original data is converted into spatial point data in shapefile format, which realizes the unification of data format and facilitates subsequent data processing and analysis. This standardized data format improves the readability and operability of the data and lays a solid foundation for the subsequent OD extraction and spatiotemporal distribution feature analysis. In the process of data conversion, key information fields such as card number, boarding / disembarking time, station / latitude and longitude coordinates are ensured to be retained. These key information are crucial for the subsequent OD extraction and travel time calculation, ensuring the accuracy and reliability of the analysis. The converted data is cleaned to remove obviously abnormal data points, such as unreasonable travel time, repeated records or illogical station combinations. This step effectively improves the quality of the data, reduces the analysis deviation caused by data errors or anomalies, and improves the accuracy and credibility of the analysis. The spatial point data after cleaning and format conversion is more suitable for subsequent OD extraction and spatiotemporal distribution feature analysis. This processed data is not only convenient for visual display in spatial analysis software such as GIS, but also provides strong data support for subsequent statistical analysis, model building, etc.

[0077] Preferably, the extraction of starting points and end points of the spatial point data and calculation of travel time of various modes of transportation specifically include:

[0078] Import the converted spatial point data into the data processing software;

[0079] Data processing software identifies the starting and ending points of each trip based on the timestamps and location information in the data;

[0080] The identified OD data is collated and analyzed to generate OD pair combinations, each of which has a unique identifier and includes travel duration.

[0081] In this embodiment, by importing the converted spatial point data into data processing software, such as Access, etc., it is possible to efficiently identify and utilize the timestamp and location information in the data to determine the starting point (O) and end point (D) of each trip. Compared with manual operations, this automated extraction process greatly reduces errors and omissions, and improves the accuracy and efficiency of data processing; based on the identification of OD information, the technical solution further calculates the travel time of each mode of transportation, which is obtained by analyzing the time information in the OD data pair, ensuring the accuracy of the travel time calculation, which is of great significance for the subsequent analysis of the efficiency of traffic behavior, congestion, passenger travel habits, etc.; the identified OD data is sorted and analyzed to generate OD pair combinations with unique identifiers. These combinations not only contain the starting point and end point information of the trip, but also come with key attributes such as travel time. This sorting method helps to simplify the subsequent data processing and analysis process, while ensuring the uniqueness and traceability of each OD pair combination.

[0082] Preferably, the combination of the scale effects of the two dimensions of time and space to analyze the spatial interaction network distribution characteristics of various modes of transportation specifically includes:

[0083] According to the characteristics of transportation modes, appropriate spatial units are selected for analysis, among which buses and subways are based on stations, and shared bicycles and taxis are based on social management grids;

[0084] Analyze the travel time distribution at different time periods throughout the day and identify the travel characteristics of morning and evening peaks;

[0085] Analyze the spatial distribution characteristics of travel frequency of different transportation modes;

[0086] According to the travel characteristics and distribution characteristics, the travel frequencies of different modes of transportation in a week, weekdays and weekends are counted and compared;

[0087] Calculate and compare the average travel time of different modes of transportation based on travel characteristics and distribution features;

[0088] Analyze the interaction intensity between stations or grids based on travel characteristics and distribution characteristics;

[0089] Based on travel frequency, travel time and interaction intensity, the spatial interaction network distribution characteristics of various transportation modes are obtained.

[0090] In this embodiment, according to the characteristics of the transportation modes, stations are selected as analysis units for buses and subways, and social management grids are selected as analysis units for shared bicycles and taxis. This refined spatial unit selection can more accurately reflect the travel characteristics and spatial distribution of different transportation modes, and improve the accuracy and reliability of the analysis; by analyzing the travel time distribution of each period of the day, the scheme can identify the travel characteristics of the morning peak and evening peak, as well as the changes in travel frequency in different time periods, which helps to understand the travel needs and traffic pressure distribution of residents in different time periods, and provides an important basis for traffic planning and management; by analyzing the spatial distribution characteristics of the travel frequency of different transportation modes, it can intuitively display the use of various transportation modes in the city, which helps to discover traffic congestion areas, traffic hotspots and the complementary relationship between transportation modes, and provide strong support for urban transportation planning; by counting and comparing the travel times of different transportation modes in a week, weekdays and weekends, the scheme can identify the travel characteristics of different transportation modes in a week, weekdays and weekends, and can also identify the travel times of different transportation modes in a week, weekdays and weekends. By analyzing the travel frequency, the scheme can reveal the travel patterns and demand changes of residents in different time periods, which is helpful to formulate more scientific and reasonable transportation policies and measures to meet the travel needs of residents; by calculating and comparing the average travel time of different modes of transportation, it can quantitatively evaluate the efficiency and convenience of various modes of transportation, which helps residents make more informed decisions when choosing transportation modes, and also helps urban transportation managers optimize transportation networks and services; by analyzing the interaction intensity between stations or grids, the scheme can reveal the spatial interaction relationship and connection between different modes of transportation, which is helpful to find traffic bottlenecks and congestion points, and provide strong support for urban traffic diversion and optimization; based on multiple dimensions such as travel frequency, travel time and interaction intensity, the scheme can comprehensively derive the spatial interaction network distribution characteristics of various modes of transportation, which helps to form a comprehensive understanding of the urban transportation network and provide a scientific basis and decision-making support for urban transportation planning, management and optimization.

[0091] Preferably, the spatial interaction network distribution features match the starting points and ending points of various modes of transportation to the corresponding spatial interaction network distribution features, respectively, and construct an OD interaction matrix between sites or grids, specifically including:

[0092] For each mode of transportation, its OD points are matched to the corresponding spatial units, where buses and subways use stations as units, and shared bicycles and taxis use social management grids as units;

[0093] According to the matched OD data, an OD interaction matrix between sites or grids is constructed, wherein the rows and columns of the OD interaction matrix represent different spatial units, and the elements in the matrix represent the OD interaction frequency between spatial units.

[0094] In this embodiment, by matching the OD points of each mode of transportation to the corresponding spatial units (buses and subways are based on stations, and shared bicycles and taxis are based on social management grids), and constructing an OD interaction matrix between stations or grids, a quantitative analysis of the distribution characteristics of the spatial interaction network is achieved, which enables researchers to more accurately understand the interaction frequency and mode of different modes of transportation between different spatial units; the OD interaction matrix not only provides information on the interaction frequency between spatial units, but also displays the structure of the spatial interaction network through the rows and columns of the matrix. By analyzing the matrix, it is possible to identify which spatial units have frequent interactions and the spatial distribution patterns of these interactions, which helps to reveal the spatial distribution of urban space. The complexity and diversity of the interaction network between cities; after constructing the OD interaction matrix, the scale effects of both time and space can be further analyzed. For example, the travel time distribution in each period of the day can be analyzed to identify the travel characteristics of the morning and evening peaks; the spatial distribution of the travel frequency of different modes of transportation can also be analyzed. This comprehensive analysis helps to more comprehensively understand the spatiotemporal characteristics of the urban spatial interaction network; the analysis results of the OD interaction matrix can provide a scientific basis for transportation planning and policy formulation. For example, the layout of bus routes and subway stations can be optimized according to the interaction frequency and mode of different modes of transportation; the vehicle deployment strategy and operation plan can also be adjusted according to the travel hotspots of shared bicycles and taxis. These measures help to improve the efficiency and convenience of the urban transportation system.

[0095] Preferably, the comparison of travel characteristics in different time periods and analysis of the differences in morning and evening peaks, travel frequency and travel time specifically includes:

[0096] Filter out the travel data on weekdays and weekends from the original data;

[0097] Analyze the time distribution of travel frequency throughout the day on weekdays and weekends to determine the peak hours in the morning and evening;

[0098] Compare the travel frequency on weekdays and weekends to see if there is a difference between the two;

[0099] Calculate the average travel time on weekdays and weekends and compare the difference between the two;

[0100] The constructed OD interaction matrix between sites or grids was used to analyze the changes in interaction frequency between weekdays and weekends.

[0101] In this embodiment, by analyzing the time distribution diagram of the travel frequency throughout the day on weekdays and weekends, the technical solution can accurately identify the morning and evening peak hours, which is crucial for urban traffic planning and management, and helps relevant departments to take effective traffic diversion measures during peak hours to alleviate traffic congestion; by comparing the travel frequency on weekdays and weekends, the technical solution can clearly show the difference between the two. This difference analysis helps to understand the changes in urban residents' travel needs in different time periods and provide data support for the optimal allocation of public transportation resources; by calculating the average travel time on weekdays and weekends, the technical solution can compare the difference between the two, thereby revealing the changes in traffic efficiency in different time periods, which is of great significance for evaluating the operation status of urban transportation systems and optimizing traffic flows; using the constructed station intervals or The OD interaction matrix between grids, this technical solution can deeply analyze the changes in the interaction frequency between weekdays and weekends. This analysis not only helps to reveal the spatial distribution characteristics of urban residents' travel, but also further understand the interaction between urban spatial structure and traffic travel. By comparing the interaction frequency between weekdays and weekends, it can be found which areas or stations interact more frequently in a specific time period, thereby providing targeted suggestions for urban traffic planning and construction; it can provide multi-dimensional data support for urban traffic planning and management. Whether it is optimizing public transportation routes, adjusting traffic signal control strategies, or formulating urban traffic congestion relief plans, it is necessary to have an in-depth understanding of the spatiotemporal distribution characteristics and laws of urban residents' travel. This technical solution provides a scientific basis for these planning and management decisions by comparing travel characteristics in different time periods.

[0102] Preferably, the OD interaction matrix is ​​analyzed to identify the OD pairs and interaction areas with high frequency interactions, and to obtain the rules and patterns of residents' travel, which specifically includes:

[0103] Perform frequency statistics on each OD pair in the OD interaction matrix and calculate the interaction frequency of each OD pair;

[0104] According to the set threshold, OD pairs with higher interaction frequency are screened out;

[0105] A spatial clustering algorithm was used to cluster the data in the OD interaction matrix, and regions with similar interaction characteristics were divided into the same category to form different interaction regions;

[0106] Combining the analysis results of high-frequency interactive OD pairs and interactive areas, the rules and patterns of residents' travel are obtained.

[0107] In this embodiment, by performing frequency statistics on each OD pair in the OD interaction matrix, the interaction frequency of each OD pair can be accurately calculated, thereby accurately identifying key OD pairs with high interaction frequencies. These high-frequency interaction OD pairs reflect the main travel routes and hot spots of urban residents, providing an important basis for urban traffic planning and optimization; using a spatial clustering algorithm to perform cluster analysis on the data in the OD interaction matrix, it is possible to divide areas with similar interaction characteristics into the same category to form different interaction areas. This division method helps to reveal the spatial distribution characteristics of urban residents' travel and understand the travel connections and interaction intensities between different areas; combining the analysis results of high-frequency interaction OD pairs and interaction areas can fully reveal the laws and patterns of residents' travel. For example, it can be analyzed whether residents travel on weekdays and weekends. The differences in travel frequency, travel characteristics during peak hours in the morning and evening, and travel connections between different areas, etc., all of this information has important reference value for urban traffic management, public transportation optimization, and urban planning. By deeply understanding the laws and patterns of residents' travel, urban traffic resources can be allocated more scientifically and reasonably. For example, bus routes, subway station layouts, and shared bicycle delivery points can be optimized according to the distribution of high-frequency interactive OD pairs and interactive areas to improve the efficiency and convenience of urban traffic. Understanding the laws and patterns of residents' travel can also help urban traffic management departments better predict and respond to emergencies such as traffic congestion and traffic accidents. By formulating response measures and adjusting traffic plans in advance, the quality and level of urban traffic services can be improved, and citizens' travel satisfaction and happiness can be enhanced.

[0108] An urban traffic distribution analysis system based on multi-source big data, comprising:

[0109] The data collection module is used to collect big data of various modes of transportation in the city, including bus card swiping data, subway travel data, taxi OD data and shared bicycle usage data;

[0110] A data preprocessing module is used to convert the collected raw data into spatial point data;

[0111] OD extraction module, used to extract the starting point and end point of spatial point data and calculate the travel time of various modes of transportation;

[0112] The spatiotemporal distribution characteristics analysis module is used to combine the scale effects of time and space to analyze the spatial interaction network distribution characteristics of various transportation modes;

[0113] The interaction matrix construction module is used to match the starting points and ending points of various transportation modes to the corresponding spatial units according to the distribution characteristics of the spatial interaction network, and to construct the OD interaction matrix between sites or grids;

[0114] The travel characteristics comparison module is used to compare travel characteristics in different time periods and analyze the differences in morning and evening peaks, travel frequency, and travel time;

[0115] The travel mode identification module is used to analyze the OD interaction matrix, identify the OD pairs and interaction areas with high frequency interactions, and obtain the laws and patterns of residents' travel;

[0116] The visualization and result output module is used to apply GIS technology for data visualization. Based on the comparison and recognition results, the number of O and D and the frequency of OD interaction of each spatial unit are counted, and the analysis results are displayed in a graphical way to obtain the interactive distribution analysis of urban traffic.

[0117] A computing device includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned urban traffic distribution analysis method based on multi-source big data are implemented.

[0118] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned urban traffic distribution analysis method based on multi-source big data.

[0119] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A method for analyzing urban traffic distribution based on multi-source big data, characterized in that: Specifically include: Data collection steps: Collect big data of various modes of transportation in the city, including bus card swiping data, subway travel data, taxi OD data and shared bicycle usage data; Data preprocessing step: convert the collected raw data into spatial point data; OD extraction step: extract the starting point and end point of the spatial point data, and calculate the travel time of various modes of transportation; Steps for analyzing the temporal and spatial distribution characteristics: Combine the scale effects of both time and space to analyze the spatial interaction network distribution characteristics of various transportation modes; Interaction matrix construction steps: According to the distribution characteristics of the spatial interaction network, the starting points and end points of various transportation modes are matched to the corresponding spatial units, and the OD interaction matrix between sites or grids is constructed; Travel characteristics comparison steps: Compare travel characteristics in different time periods, and analyze the differences in morning and evening peaks, travel frequency, and travel time; Travel mode identification steps: Analyze the OD interaction matrix, identify the OD pairs and interaction areas with high frequency interactions, and obtain the rules and patterns of residents' travel; Visualization and result output steps: Use GIS technology to visualize the data, count the number of O and D and the frequency of OD interactions in each spatial unit based on the comparison and identification results, and display the analysis results in a graphical way to obtain the interactive distribution analysis of urban traffic.

2. The urban traffic distribution analysis method based on multi-source big data according to claim 1 is characterized in that: The step of converting the collected raw data into spatial point data specifically includes: Convert the original data into spatial point data in shapefile format; During the data conversion process, ensure that key information fields are retained, including card number, boarding / disembarking time, and station / latitude and longitude coordinates; The converted data is cleaned to remove obviously abnormal data points, including unreasonable travel time, repeated records or illogical station combinations.

3. The urban traffic distribution analysis method based on multi-source big data according to claim 2 is characterized in that: The extraction of starting and ending points of spatial point data and calculation of travel time of various modes of transportation specifically include: Import the converted spatial point data into the data processing software; Data processing software identifies the start and end points of each trip based on the timestamps and location information in the data; The identified OD data is sorted and analyzed to generate OD pair combinations, each of which has a unique identifier and includes travel duration.

4. The urban traffic distribution analysis method based on multi-source big data according to claim 3 is characterized in that: The above-mentioned combination of the scale effects of time and space dimensions analyzes the spatial interaction network distribution characteristics of various transportation modes, including: According to the characteristics of transportation modes, appropriate spatial units are selected for analysis, among which buses and subways are based on stations, and shared bicycles and taxis are based on social management grids; Analyze the travel time distribution at different time periods throughout the day and identify the travel characteristics of morning and evening peaks; Analyze the spatial distribution characteristics of travel frequency of different transportation modes; According to the travel characteristics and distribution characteristics, the travel frequencies of different modes of transportation in a week, weekdays and weekends are counted and compared; Calculate and compare the average travel time of different modes of transportation based on travel characteristics and distribution features; Analyze the interaction intensity between stations or grids based on travel characteristics and distribution characteristics; Based on travel frequency, travel time and interaction intensity, the spatial interaction network distribution characteristics of various transportation modes are obtained.

5. The urban traffic distribution analysis method based on multi-source big data according to claim 4 is characterized in that: The spatial interaction network distribution features match the starting points and ending points of various modes of transportation to the corresponding spatial interaction network distribution features, and construct an OD interaction matrix between sites or grids, specifically including: For each mode of transportation, its OD points are matched to the corresponding spatial units, where buses and subways use stations as units, and shared bicycles and taxis use social management grids as units; According to the matched OD data, an OD interaction matrix between sites or grids is constructed, wherein the rows and columns of the OD interaction matrix represent different spatial units, and the elements in the matrix represent the OD interaction frequency between spatial units.

6. The urban traffic distribution analysis method based on multi-source big data according to claim 5 is characterized in that: The comparison of travel characteristics in different time periods and analysis of the differences in morning and evening peaks, travel frequency and travel time specifically include: Filter out the travel data on weekdays and weekends from the original data; Analyze the time distribution of travel frequency throughout the day on weekdays and weekends to determine the peak hours in the morning and evening; Compare the travel frequency on weekdays and weekends to see if there is a difference between the two; Calculate the average travel time on weekdays and weekends and compare the difference between the two; The constructed OD interaction matrix between sites or grids was used to analyze the changes in interaction frequency between weekdays and weekends.

7. The urban traffic distribution analysis method based on multi-source big data according to claim 6 is characterized in that: The OD interaction matrix is ​​analyzed to identify high-frequency interactive OD pairs and interactive areas, and to obtain the rules and patterns of residents' travel, specifically including: Perform frequency statistics on each OD pair in the OD interaction matrix and calculate the interaction frequency of each OD pair; According to the set threshold, OD pairs with higher interaction frequency are screened out; A spatial clustering algorithm was used to cluster the data in the OD interaction matrix, and regions with similar interaction characteristics were divided into the same category to form different interaction regions; Combining the analysis results of high-frequency interactive OD pairs and interactive areas, the rules and patterns of residents' travel are obtained.

8. An urban traffic distribution analysis system based on multi-source big data, characterized in that: include: The data collection module is used to collect big data of various modes of transportation in the city, including bus card swiping data, subway travel data, taxi OD data and shared bicycle usage data; A data preprocessing module is used to convert the collected raw data into spatial point data; OD extraction module, used to extract the starting point and end point of spatial point data and calculate the travel time of various modes of transportation; The spatiotemporal distribution characteristics analysis module is used to combine the scale effects of time and space to analyze the spatial interaction network distribution characteristics of various transportation modes; The interaction matrix construction module is used to match the starting points and ending points of various transportation modes to the corresponding spatial units according to the distribution characteristics of the spatial interaction network, and to construct the OD interaction matrix between sites or grids; The travel characteristics comparison module is used to compare travel characteristics in different time periods and analyze the differences in morning and evening peaks, travel frequency, and travel time; The travel mode identification module is used to analyze the OD interaction matrix, identify the OD pairs and interaction areas with high frequency interactions, and obtain the laws and patterns of residents' travel; The visualization and result output module is used to apply GIS technology for data visualization. Based on the comparison and recognition results, the number of O and D and the frequency of OD interaction of each spatial unit are counted, and the analysis results are displayed in a graphical way to obtain the interactive distribution analysis of urban traffic.

9. A computing device, characterized in that The method comprises a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the urban traffic distribution analysis method based on multi-source big data as described in any one of claims 1 to 7 when executing the computer program.

10. A computer-readable storage medium, characterized in that: The storage medium stores a computer program, which, when executed by a processor, implements the steps of the urban traffic distribution analysis method based on multi-source big data as described in any one of claims 1 to 7.

Images