Road network accessibility analysis method based on multi-source data fusion

Abstract

The invention discloses a road network accessibility analysis method based on multi-source data fusion. The method comprises the following steps: for a target research area, acquiring multi-source data, and preprocessing the multi-source data; by utilizing the multi-source data and adopting a SpaceP method, constructing an expressway complex network by taking each prefecture-level city as a network node, expressway sections among the cities as connecting edges and freight traffic among the cities as edge weights; based on the highway complex network, carrying out freight reachability analysis by using an improved gravity model, and determining the freight reachability of each city; and according to the freight reachability of each city, determining the freight reachability of the target research area. According to the scheme provided by the invention, the application of big data and Internet technologies in road traffic transportation can be promoted, data support is provided for road network accessibility analysis, and the construction of a safe, efficient, green and unblocked provincial intelligent road transportation logistics network is facilitated.

Description

Technical Field

[0001] The present invention relates to the field of intelligent transportation technology, and in particular to a highway network accessibility analysis method based on multi-source data fusion. Background Art

[0002] Road logistics has entered the era of big data, and advanced data collection equipment has promoted the informatization of the transportation and logistics industry. Smart roads and smart logistics systems have emerged, bringing new opportunities and challenges to the planning and management of modern road transportation and logistics networks. Data generated in various road transportation and logistics operations, as well as data related to road logistics characteristics, are of great significance to the green and sustainable development of modern road transportation and logistics networks.

[0003] Transportation plays a role in safeguarding and supporting the development of regional social economy. With the continuous improvement of scientific and technological levels, the increasing specialization of social division of labor, and the globalization of the configuration of various production factors, the transportation network, as one of the important ways to support the flow of material products and personnel in time and space, has experienced unprecedented development. At the same time, the demand for transportation networks in regional social and economic development is increasing and becoming more diversified. To a certain extent, the development level of the transportation network can reflect the development level of regional social economy, and the level of regional social and economic development reflects the construction capacity of the transportation network system. Therefore, sorting out and clarifying the evolution laws and characteristics of the development level of the transportation network and its accessibility spatial pattern is of great reference significance for the planning and layout of the transportation network.

[0004] However, existing traffic network accessibility analysis mainly conducts data mining analysis on a single type of data and focuses on the field of urban transportation. There is a lack of relevant research on the combination of highway traffic data with other multi-source data. In addition, existing technologies mainly study the basic characteristics, topological structure and evolution of traffic networks, but there are few multi-level studies on highway networks. Based on this, there is still a lot of room for improvement in existing traffic network accessibility analysis methods. Summary of the invention

[0005] In order to solve the above technical problems, an embodiment of the present invention provides a road network accessibility analysis method based on multi-source data fusion.

[0006] The technical solution of the embodiment of the present invention is achieved as follows: The embodiment of the present invention provides a highway network accessibility analysis method based on multi-source data fusion, the method comprising: acquiring multi-source data for a target study area, and preprocessing the multi-source data; the multi-source data comprises highway network data, truck trajectory data, natural resource data, highway network data, social and economic data, and land space data; using the multi-source data, adopting the SpaceP method, taking each prefecture-level city as a network node, the highway sections between cities as connecting edges, and the freight flow between cities as edge weights, to construct a highway complex network; based on the highway complex network, using an improved gravity model to perform freight accessibility analysis to determine the freight accessibility of each city; determining the freight accessibility of the target study area according to the freight accessibility of each city; Wherein, the improved gravity model is: in, Indicates the city accessibility; For the city Quality indicators; For freight nodes Quality indicators; For freight nodes To the city The distance, according to the distance matrix and Calculate, distance matrix For the city The distance matrix from all freight nodes to the administrative center of the city, the distance matrix is the distance matrix between all cities in the study area; is the parameter of the impedance function.

[0007] The method of this embodiment has the following beneficial effects: This embodiment takes the trajectory data of highway logistics operation vehicles as the starting point, integrates multi-source data such as transportation data, social and economic data, and land and space data, and constructs a two-level planning problem to study the evaluation and improvement strategy of highway network accessibility by fully mining and analyzing the data, and combines multiple machine algorithms to obtain the optimal solution. This embodiment can promote the application of big data and Internet technology in highway transportation, provide data support for highway network accessibility analysis, and facilitate the construction of a safe, efficient, green and smooth provincial-level smart highway transportation logistics network. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 A schematic diagram of a process of a highway network accessibility analysis method based on multi-source data fusion according to an embodiment of the present invention; Figure 2This is a thermal diagram of the trajectory data distribution after preprocessing according to an embodiment of the present invention; Figure 3 This is a schematic diagram of the freight connection strength between cities in Hunan Province according to an embodiment of the present invention; Figure 4 This is a schematic diagram of the weighted network topology structure of freight flow in Hunan Province according to an embodiment of the present invention; Figure 5 1 is a diagram showing the internal structure of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The present invention will be described in further detail below with reference to the accompanying drawings and embodiments.

[0010] The embodiment of the present invention provides a road network accessibility analysis method based on multi-source data fusion, such as Figure 1 As shown, the method includes: Step 101: for a target research area, obtaining multi-source data and preprocessing the multi-source data; the multi-source data includes highway network data, truck trajectory data, natural resource data, highway network data, socio-economic data and land space data; Step 102: Using the multi-source data and adopting the SpaceP method, a complex highway network is constructed with each prefecture-level city as a network node, the highway sections between cities as edges, and the freight flow between cities as edge weights; Step 103: Based on the complex highway network, a freight accessibility analysis is performed using an improved gravity model to determine the freight accessibility of each city; Step 104: Determine the freight accessibility of the target study area based on the freight accessibility of each city.

[0011] The method of this embodiment can promote the application of big data and Internet technology in road transportation, provide data support for road network accessibility analysis, and be conducive to the construction of a safe, efficient, green and smooth provincial smart road transportation logistics network.

[0012] Next, the Hunan Provincial Highway Network will be taken as a research object to introduce this embodiment scheme in detail.

[0013] This embodiment constructs an accessibility evaluation measurement model, analyzes and summarizes the spatial distribution pattern and evolution law of the accessibility level of the highway network in Hunan Province, which can enrich the research content and research theory of transportation network accessibility to a certain extent, and provide theoretical reference for the planning and layout of the transportation network in Hunan Province.

[0014] This embodiment mainly includes the following contents: 1. Data Processing and Analysis This embodiment takes Changsha as the research object and deeply analyzes urban traffic data, including coil data, taxi GPS data, Bluetooth data, automatic license plate recognition data, and Internet map traffic situation data. The integration of these data sources provides a multi-dimensional perspective for a comprehensive understanding of urban traffic flow. This embodiment uses a variety of data processing techniques, such as sliding smoothing, wavelet analysis methods, and Kalman filtering algorithms to pre-process the data so that the data can be effectively analyzed later. These algorithms not only effectively remove outliers in the data, but also accurately interpolate missing data, greatly improving the integrity and availability of the data.

[0015] 2. Construction of road network This embodiment uses a complex network analysis method to conduct an in-depth topological network construction and analysis of the highway system in Hunan Province. It not only involves the identification of nodes and edges of the highway network, but also the detailed mapping of the connection patterns between them. Through this method, this embodiment can abstract the actual highway network into a network model composed of nodes (representing the intersection points or important cities of the highway) and edges (representing the highway itself).

[0016] The focus of this embodiment is to analyze the static characteristics and centrality of the network from the perspective of small-world characteristics. A small-world network is a special type of network characterized by a short average path length, which can quickly transmit information or traffic between any two nodes in the network while maintaining a high clustering coefficient, that is, the nodes in the network tend to be closely connected to each other to form clusters.

[0017] 3. Road network accessibility assessment The smoothness and connection strength of the transportation network, the scale of urban freight nodes, and the comprehensive economic strength are factors that affect regional connectivity. This embodiment comprehensively considers the actual road network between regions, the importance parameters of network nodes, and the freight attraction index of cities and counties, and improves the gravity model to calculate regional accessibility. The calculation formula is: (1) in, Indicates the city accessibility; For the city Quality indicators; For freight nodes Quality indicators; For freight nodes To the city The distance, according to the distance matrix and Calculate, distance matrix For the city The distance matrix from all freight nodes to the administrative center of the city, the distance matrix is the distance matrix between all cities in the study area; is the parameter of the impedance function.

[0018] The accessibility of the road network in Hunan Province is evaluated using the values ​​calculated by the gravity model.

[0019] The following will introduce the above three parts in detail.

[0020] 1. Data Processing and Analysis In the process of in-depth research on highway network accessibility, we need to comprehensively consider and analyze various types of big data. The detailed collection and careful analysis of these data are crucial to fully understand the feasibility and scientificity of highway projects, especially the impact on network accessibility.

[0021] Specifically, referring to Table 1, the following data were collected in this embodiment: Table 1 In the above data, since the trajectory data is collected through the signal transmission of the positioning satellite, it is inevitable that the data will be affected by external and human factors during the collection process, such as weather, equipment failure, and improper operation of personnel, which will cause errors. Therefore, the collected raw data often contains abnormal data, and direct application in data analysis and scientific research is likely to lead to deviations in analysis conclusions. The raw data needs to be preprocessed to improve the consistency and validity of the data. This embodiment mainly performs the following preprocessing on the raw data: (1) Removing invalid field information. Delete the platform input information fields that are not relevant to this embodiment, and retain the device record information that is useful to this embodiment, such as speed and location, etc. This can greatly reduce the amount of data to be processed and speed up the processing speed.

[0022] (2) Filter valid information based on the location field. The main research area of ​​this embodiment is Hunan Province, whose longitude and latitude range is: 108°47′-114°15′ east longitude, 24°38′-30°08′ north latitude. Therefore, according to the longitude and latitude field information, the data outside the research area is deleted. In this way, data is filtered based on location, and data with serious position deviation is deleted to a certain extent.

[0023] (3) Processing redundant data. According to the above overview of the factors that cause error data, redundant data is mostly generated because the signal is reflected by obstacles on the path during transmission, resulting in multiple records. Therefore, for records with the same vehicle number and time in the original data, they need to be deleted and only the first record is retained.

[0024] (4) Processing abnormal data. This embodiment defines abnormal data as data where the recorded field information exceeds the range it should be within. For example, in the vehicle speed field, because this embodiment uses the track data of a truck, the recorded information where the speed field exceeds 120 km / h can be considered abnormal data; for the recorded driving direction field information, if the data is not between 0-360°, it can be considered abnormal data, and so on.

[0025] (5) Handling missing data. For all records, if any valid field information is missing in the record, the record will be deleted. Because if the valid field information is missing, the record will not be determined as a track point in a certain track, which will affect the subsequent extraction of trip information.

[0026] (6) Filter data based on vehicle number and time fields. First, arrange the data of the same vehicle number in chronological order to obtain the travel trajectory points of a vehicle within a day. For the data sorted in chronological order, if there are less than 20 original records of the same vehicle in a continuous time, or the total travel time is less than 10 minutes, then all the records in this section need to be deleted. This is because this vehicle can be considered not to have started a formal freight trip during this period of record time, and no subsequent analysis is required.

[0027] After the above preprocessing operations, about 16% of the records in the original data set were deleted, and there were about 210 million records remaining in the processed data set. Figure 2 It is a heat map of trajectory data distribution after preprocessing, which reflects the degree of spatial coverage and concentration of trajectory data.

[0028] In addition, for highway toll data, the following data preprocessing steps can be used: First, check the basic information of the data, including column names, data types, missing values, outliers, etc., to understand the overall situation of the data. Then, clean the data, including deleting missing values ​​in the data, detecting and deleting duplicate data rows, identifying outliers and correcting or deleting them, etc. Next, perform data format conversion, such as converting text types to numeric types, date and time type conversion, etc. Finally, process incomplete data, detect incomplete or meaningless data entries, fill in or delete incomplete data entries, for example: the "axle type and axle weight" information in the original data of highway network toll collection is mostly 0, so this column of information is deleted.

[0029] In this embodiment, a series of data preprocessing work is performed to address the problem of noisy data that may exist in the data source, thereby obtaining a relatively low-noise data set that can meet research needs.

[0030] 2. Construction of road network This embodiment uses the SpaceP method to construct the topological structure of the expressway network in Hunan Province. The specific construction method is as follows: (1) The freight flow between cities is calculated based on the freight vehicle trajectory data in Hunan Province. Based on the trajectory data, the OD value of freight travel connection intensity between grids is extracted at the grid level of the study area. At the city and county level of administrative divisions, the grid is matched to the administrative scope of each city to obtain the OD value of freight connection intensity between cities, such as Figure 3 shown.

[0031] (2) Taking each prefecture-level city in Hunan Province as the network node , the highway sections between cities are connected , with freight flow between cities as edge weight , construct a weighted topological model of highway network traffic in Hunan Province.

[0032] (3) The expressway network topology was constructed using Python programming language and visualized using software such as Gephi and Pajek. The Hunan expressway network topology diagram with 14 nodes and 64 edges was obtained, as shown in the figure below. Figure 4 shown. Figure 4 In the graph, the size of the node reflects the node degree value, and the node color is distributed according to the node's betweenness centrality.

[0033] The SpaceP method can not only reflect the spatial layout and connection pattern of the highway network, but also reveal the potential structural characteristics in the network, such as the importance of nodes and the connectivity of the network. These characteristics are crucial for understanding and evaluating the accessibility of the highway network. The Hunan Provincial Highway Network Model constructed by the SpaceP method provides a solid model foundation for evaluating highway accessibility. This model not only helps to identify key nodes and vulnerable links in the network, but also provides a scientific basis for traffic planning and management. In addition, the model can also support further analysis, such as traffic flow prediction, network optimization, and the formulation of emergency response strategies.

[0034] 3. Road network accessibility assessment Accessibility is an indicator to measure the convenience of interconnection between regions, while transportation accessibility further quantifies this connection and can be used to measure the convenience of interconnection between regions through transportation networks. It reflects the ease of movement of people, goods, etc. between different regions, and can cover multiple modes of transportation such as roads, railways, and aviation at the same time. The study of transportation accessibility requires comprehensive consideration of the interaction and impact of multiple factors. This embodiment comprehensively considers multiple factors such as space, transportation infrastructure, and socio-economic factors to analyze inter-regional transportation travel demand and transportation attraction potential, thereby evaluating the freight accessibility of the region.

[0035] Analyzing regional transportation accessibility is of great significance to improving the transportation network structure and transportation network planning. At the administrative level, the province is composed of multiple prefecture-level cities, and the regions are connected by transportation networks.

[0036] This embodiment uses the gravity model to analyze regional traffic accessibility. The gravity model regards the travel time or distance between regions as travel impedance and is a commonly used spatial accessibility assessment model.

[0037] This embodiment proposes an accessibility assessment model based on potential traffic attraction, which refers to the gravity model to assess the potential traffic attraction from other regions. As a classic spatial accessibility assessment method, the gravity model considers all regions within the study scope and regards the travel time or distance between regions as travel impedance. The model was originally proposed by Hansen, as shown in the following formula (2): (2) In the formula, Indicates area accessibility; Indicates area Areas outside Quality indicators, usually land area or population, etc. Indicates area and Region The travel impedance between them, usually travel time or distance; is the coefficient of the impedance function.

[0038] Although the gravity model shown in formula (2) above has certain application value, it also has obvious shortcomings. Specifically, the model focuses on the accessibility assessment of a single study area and does not take into account the competitive relationship between different regions in actual situations. Potential traffic attraction, as an important indicator for measuring the interaction between regions, is not only affected by the quality of urban functions, but also closely related to the distance between regions. In order to overcome these limitations, an improved method for the gravity model has been proposed in the prior art, as shown in formula (3): (3) In the formula, Indicates area accessibility; and Representing the study area and The quality index of the region is the economic quality index of the region in the literature; It is the impedance function between the study areas, usually using an exponential decay function, as ; Indicates area and Region The travel impedance between is the parameter of the impedance function.

[0039] The smoothness and connection strength of the transportation network, the scale of urban freight nodes, the comprehensive economic strength, etc. are factors that affect regional connectivity. This embodiment comprehensively considers the actual road network between regions, the importance parameters of network nodes, and the freight attractiveness indicators of cities and counties, and improves the above formula (3) to calculate regional accessibility. By calculating the accessibility of the region in combination with freight-related parks (freight nodes), the transportation efficiency of goods between regions can be reflected. The specific calculation steps are as follows: (1) First, we use Amap to obtain the distance matrix from all freight nodes in each city to the administrative center of the city. And sum to get , and the distance matrix between all cities in Hunan Province ; (2) Calculate the quality index of each freight node , as shown in formula (4): (4) In the formula, is the economic quality index of the node. and Normalization is performed to eliminate the dimension effect; (3) Calculate the attractiveness of each node to other cities, as shown in formula (5): (5) In the formula, Indicates the city accessibility; It is the quality indicator of the city; For freight nodes Quality indicators; For freight nodes To the city The distance, according to the distance matrix and calculate; is the parameter of the impedance function; (4) The above steps are repeated for each city to obtain the freight accessibility distribution of the study area.

[0040] The following is a supplementary explanation of the above calculation steps: In step (2), the proportion is calculated The meaning of is to add up the distance between each target city and all nodes and the economic quality of the city, and use it as an indicator to measure the proportion of the city in attractiveness. Distance is an important factor affecting the attractiveness between cities, while economic quality reflects the economic strength and attractiveness of the city. Combining distance and economy can comprehensively consider the dual influencing factors between freight nodes and cities to a certain extent, which helps to more accurately evaluate the proportion and influence of the node in the city to which it belongs.

[0041] According to the accessibility calculation method proposed in this embodiment, namely, formula (5), three types of indicators are required to calculate the freight traffic accessibility of the region, namely, the quality indicators of the city , Quality indicators of freight nodes and distance indicators between cities and freight nodes Among them, the quality indicators of freight nodes In this example, it refers to the economic development index of the freight node, which can be reflected by the node's income. It can be obtained through the Amap online map API. The key indicator to be calculated is the quality indicator of the city. The urban quality index in formula (5) is , the numerical value of this indicator needs to intuitively reflect the attractiveness of the city to other cities, and also represents the importance of the city in the entire transportation network. This embodiment selects topological indicators based on complex network theory as quality indicators. The complex network topological indicators used in this embodiment include: betweenness centrality, degree centrality and PageRank ranking. The three indicators are comprehensively weighted to calculate the city quality index.

[0042] Betweenness centrality mainly reflects the global characteristics of the network and can reflect the importance of a node in the network communication process. Betweenness centrality measures the role of a node as an intermediary in the shortest path, that is, the frequency of the node being located in the shortest path in the network. The higher the betweenness centrality of a node, the higher the frequency of the node being located in the shortest path in the network. The specific calculation method is shown in formula (6): (6) In the formula, For Node The betweenness centrality value of Represents a slave node To Node The number of all shortest paths, For all shortest paths, nodes Number of times it appears as an intermediary.

[0043] Degree centrality mainly reflects the local characteristics of the network. The greater the degree of a node and the more adjacent nodes it has, the more important the node is in the network. The concept of degree centrality is relatively intuitive and the calculation is relatively simple. In a network, the more direct connections a node has, the higher the degree centrality of the node is, which also means that the node is more important and influential in the network. The specific calculation method is shown in formula (7): (7) In the formula, represents the degree centrality value of the node, is the node degree value, is the number of nodes in the network.

[0044] PageRank is an algorithm for evaluating the importance of web pages, and can be used to evaluate the importance of nodes in the network. In a directed graph, the PageRank value represents the probability of a node being selected, which depends on the number and importance of other nodes to the node. Nodes with higher PageRank values ​​are considered to be more important nodes in the network because they contribute more to the entire network and have greater influence.

[0045] In order to make full use of the network node characteristics reflected by the topological indicators, this embodiment uses the TOPSIS model based on the entropy weight method to comprehensively evaluate the quality indicators of cities and counties in Hunan Province. The calculation steps are as follows: (1) Determine the decision matrix: Calculate the topological index values ​​of each node in the constructed traffic-weighted network, and construct a decision matrix in the form of determinants, where each row represents a city and each column represents an index; (2) Standardized decision matrix: Each element in the decision matrix is ​​standardized to eliminate the dimension and unit differences between the indicators. This embodiment uses the maximum and minimum value normalization method for standardization, as shown in formula (8); (8) In the formula, Indicates Cities in The standardized values ​​on the indicators are Indicates Cities in The initial value of the indicator, is the number of cities; (3) Determine the weight vector: Use the entropy weight method to calculate the weight of each indicator to reflect the influence of each indicator on the comprehensive evaluation result. The specific calculation steps are as follows: a. Calculate the entropy value of each indicator: For each column of indicators, calculate the entropy value of the proportion of the indicator value of all cities, as shown in formula (9). The larger the entropy value, the greater the difference in the indicator, that is, the greater the impact of the indicator on the comprehensive evaluation results; (9) In the formula, Indicates The entropy value of an indicator, Indicates Cities in The proportion of each indicator; b. Calculate the weight of each indicator: Use the entropy value to calculate the weight vector of each indicator, as shown in formula (10), to reflect the influence of each indicator on the comprehensive evaluation results; (10) In the formula, Indicates The weight of the indicator, is the number of indicators; (4) Determine the positive and negative ideal solutions: Calculate the maximum and minimum values ​​in the decision matrix, which are the positive and negative ideal solutions, respectively, as shown in Equation (11); (11) In the formula, and Respectively represent Positive and negative ideal solutions for each indicator; The value after assigning weights to each indicator is calculated as follows: , Indicates Cities in The standardized values ​​on the indicators are Indicates The weight of the indicator, is the number of cities; (5) Calculating distance: Calculate the distance between each city and the positive and negative ideal solutions to reflect the degree of closeness of each city to the ideal solution in terms of multiple indicators. The Euclidean distance measurement method is used for calculation, as shown in Formula (12). (12) In the formula, and Respectively represent The Euclidean distance of each city to the positive and negative ideal solutions; (6) Calculate the comprehensive score: Based on the distance between each city and the positive and negative ideal solutions, calculate the comprehensive score of each city and sort them from high to low according to the score to obtain the final city quality index. The calculation method is shown in formula (13): (13) In the formula, Indicates The comprehensive score of a city, which is also the quality index of the city. The comprehensive score is the ratio of the distance of each city to the negative ideal solution to the sum of the distance to the positive and negative ideal solutions. The closer the ratio is to 1, the closer the city is to the positive ideal solution and the better its performance in the overall evaluation; the closer it is to 0, the closer the city is to the negative ideal solution and the worse its performance in the overall evaluation.

[0046] This embodiment takes the trajectory data of highway logistics operation vehicles as the starting point, integrates multi-source data such as transportation data, social and economic data, and land and space data, and constructs a two-level planning problem to study the evaluation and improvement strategy of highway network accessibility by fully mining and analyzing the data, and combines multiple machine algorithms to obtain the optimal solution. This embodiment can promote the application of big data and Internet technology in highway transportation, provide data support for highway network accessibility analysis, and facilitate the construction of a safe, efficient, green and smooth provincial-level smart highway transportation logistics network.

[0047] The construction of a multi-level highway transportation network proposed in this embodiment can consider the transportation efficiency of the highway network at different spatial feature levels, providing a new research perspective for the analysis of highway network performance. Taking the Hunan Provincial Highway Network as the research object, by constructing an accessibility evaluation measurement model, analyzing and summarizing the spatial distribution pattern and evolution law of the accessibility level of the Hunan Provincial Highway Network, it can enrich the research content and research theory of transportation network accessibility to a certain extent, and provide theoretical reference for the planning and layout of the Hunan Provincial Transportation Network.

[0048] In order to implement the method of an embodiment of the present invention, an embodiment of the present invention also provides a highway network accessibility analysis system based on multi-source data fusion, including: a processor and a memory for storing a computer program that can be run on the processor; wherein, when the processor is used to run the computer program, it executes the steps of the above-mentioned method.

[0049] The above-mentioned system provided in this embodiment belongs to the same concept as the above-mentioned method embodiment. The specific implementation process thereof is detailed in the method embodiment and will not be repeated here.

[0050] In order to implement the method of the embodiment of the present invention, the embodiment of the present invention also provides a computer program product, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device reads the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device performs the steps of the above method.

[0051] Based on the hardware implementation of the above program modules, and in order to implement the method of the embodiment of the present invention, the embodiment of the present invention further provides an electronic device (computer device). Specifically, in one embodiment, the computer device may be a terminal, and its internal structure diagram may be as follows: Figure 5 As shown. The computer device includes a processor A01, a network interface A02, a display screen A04, an input device A05 and a memory (not shown in the figure) connected through a system bus. Among them, the processor A01 of the computer device is used to provide computing and control capabilities. The memory of the computer device includes an internal memory A03 and a non-volatile storage medium A06. The non-volatile storage medium A06 stores an operating system B01 and a computer program B02. The internal memory A03 provides an environment for the operation of the operating system B01 and the computer program B02 in the non-volatile storage medium A06. The network interface A02 of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor A01, the method of any one of the above embodiments is implemented. The display screen A04 of the computer device can be a liquid crystal display screen or an electronic ink display screen, and the input device A05 of the computer device can be a touch layer covered on the display screen, or a key, trackball or touchpad set on the computer device housing, or an external keyboard, touchpad or mouse, etc.

[0052] Those skilled in the art will understand that Figure 5 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0053] The device provided by an embodiment of the present invention includes a processor, a memory, and a program stored in the memory and executable on the processor. When the processor executes the program, the method of any one of the above embodiments is implemented.

[0054] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0055] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0056] These computer program instructions may also be stored in a computer readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer readable memory produce an article of manufacture including an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0057] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process in the computer or other programmable device. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0058] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0059] The memory may include non-permanent memory in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.

[0060] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0061] It can be understood that the memory of the embodiment of the present invention can be a volatile memory or a non-volatile memory, and can also include both volatile and non-volatile memories. Among them, the non-volatile memory can be a read-only memory (ROM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), a magnetic random access memory (FRAM), a flash memory, a magnetic surface memory, an optical disc, or a read-only optical disc (CD-ROM); the magnetic surface memory can be a disk memory or a tape memory. The volatile memory can be a random access memory (RAM), which is used as an external cache. By way of example but not limitation, many forms of RAM are available, such as static random access memory (SRAM), synchronous static random access memory (SSRAM), dynamic random access memory (DRAM), synchronous dynamic random access memory (SDRAM), double data rate synchronous dynamic random access memory (DDRSDRAM), enhanced synchronous dynamic random access memory (ESDRAM), synchronous link dynamic random access memory (SLDRAM), direct memory bus random access memory (DRRAM). The memory described in the embodiments of the present invention is intended to include but is not limited to these and any other suitable types of memory.

[0062] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0063] The above are only embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included within the scope of the claims of the present application.

Claims

1. A road network accessibility analysis method based on multi-source data fusion, characterized in that: The method comprises: For the target research area, multi-source data is obtained and pre-processed; the multi-source data includes highway network data, truck trajectory data, natural resource data, highway network data, socio-economic data and land space data; By using the multi-source data and adopting the SpaceP method, a complex highway network is constructed with each prefecture-level city as a network node, the highway sections between cities as the connecting edges, and the freight flow between cities as the edge weight; Based on the complex highway network, a freight accessibility analysis is performed using an improved gravity model to determine the freight accessibility of each city; Determine the freight accessibility of the target study area based on the freight accessibility of each city; Wherein, the improved gravity model is: in, Indicates the city accessibility; For the city Quality indicators; For freight nodes Quality indicators; For freight nodes To the city The distance, according to the distance matrix and Calculate, distance matrix For the city The distance matrix from all freight nodes to the administrative center of the city, the distance matrix is the distance matrix between all cities in the study area; is the parameter of the impedance function.

2. The highway network accessibility analysis method based on multi-source data fusion according to claim 1 is characterized in that: The improved gravity model of freight nodes Quality indicators The calculation formula is: in, For the Quality indicators of freight nodes, For the Economic quality indicators of freight nodes, For the The sum of the distance matrices from freight nodes to the city administrative center.

3. The highway network accessibility analysis method based on multi-source data fusion according to claim 2 is characterized in that: The improved gravity model of cities Quality indicators The calculation method includes: Based on the highway complex network, determining complex network topology indicators, the complex network topology indicators including calculating betweenness centrality, degree centrality and PageRank ranking; According to the complex network topology index, a complex network topology index value is calculated; the complex network topology index value includes a calculated betweenness centrality value, a degree centrality value and a PageRank ranking value; The complex network topology index values ​​are comprehensively weighted and calculated to obtain the city quality index.

4. The highway network accessibility analysis method based on multi-source data fusion according to claim 3 is characterized in that: The calculation formula of the betweenness centrality is: in, For Node The betweenness centrality value of Represents a slave node To Node The number of all shortest paths, For all shortest paths, nodes Number of times it appears as an intermediary.

5. The highway network accessibility analysis method based on multi-source data fusion according to claim 3 is characterized in that: The calculation formula of the degree centrality is: in, represents the degree centrality value of the node, is the node degree value, is the number of nodes in the network.

6. The highway network accessibility analysis method based on multi-source data fusion according to claim 3 is characterized in that: The weights of the betweenness centrality, the degree centrality and the PageRank ranking are determined as follows: The complex network topology index value of each node in the highway complex network is used to form a decision matrix in the form of a determinant, wherein each row represents a city and each column represents an index; Each element in the decision matrix is ​​standardized to eliminate the dimension and unit differences between indicators; The entropy weight method is used to calculate the weight of each indicator; According to the weight of each indicator, the maximum value and the minimum value in the decision matrix are calculated, and the positive and negative ideal solutions are determined according to the maximum value and the minimum value; The comprehensive score of each city is calculated based on the distance from each city to the positive and negative ideal solutions; the city quality index is obtained based on the comprehensive score.

7. The highway network accessibility analysis method based on multi-source data fusion according to claim 6 is characterized in that: Each element in the decision matrix is ​​standardized, including: Each element in the decision matrix is ​​standardized using the following calculation formula: in, Indicates Cities in The standardized values ​​on the indicators are Indicates Cities in The initial value of the indicator, is the number of cities.

8. The highway network accessibility analysis method based on multi-source data fusion according to claim 6 is characterized in that: The entropy weight method is used to calculate the weight of each indicator, including: For each column of indicators, the entropy value of the proportion of each indicator value in all cities is calculated using the following formula: in, Indicates The entropy value of an indicator, Indicates Cities in The proportion of each indicator; is the number of cities; According to the entropy value of the proportion of each indicator value in all cities, the weight of each indicator is calculated using the following formula: in, Indicates The weight of the indicator, is the number of indicators, Indicates The entropy value of an indicator.

9. The highway network accessibility analysis method based on multi-source data fusion according to claim 6 is characterized in that: The positive and negative ideal solutions are determined using the following calculations, including: in, and Respectively represent The positive and negative ideal solutions of the indicators, The value after assigning weights to each indicator is calculated as follows: , Indicates Cities in The standardized values ​​on the indicators are Indicates The weight of the indicator, is the number of cities.

10. The highway network accessibility analysis method based on multi-source data fusion according to claim 6 is characterized in that: The distances of each city to the positive and negative ideal solutions are calculated using the following formulas, including: in, and Respectively represent The Euclidean distance of each city to the positive and negative ideal solutions; and Respectively represent The positive and negative ideal solutions of the indicators, The value after assigning weights to each indicator is calculated as follows: , Indicates Cities in The standardized values ​​on the indicators are Indicates The weight of the indicator, is the number of indicators; According to the distance of each city to the positive and negative ideal solutions, the comprehensive score of each city is calculated using the following formula: in, Indicates The comprehensive score of the city, and Respectively represent The Euclidean distance from each city to the positive and negative ideal solutions.

Images