County and rural traffic planning decision-making method and system based on road traffic index

Abstract

The invention discloses a county and rural traffic planning decision-making method and system based on a road traffic index. The method comprises the following steps: acquiring navigation API data, social economic data and POI information related to county and rural traffic planning; the method comprises the following steps: acquiring data, processing the data, then calculating a route growth index, a per-hour time index, a holiday influence index, a broken road index and a planning simulation index, carrying out weighted fusion to obtain a road traffic index, when the road traffic index is calculated, distributing an initial weight for each index, and adopting a self-adaptive weight adjustment algorithm to calculate the road traffic index. Dynamically adjusting the weight of each index according to the real-time traffic data and the simulation result; county and rural traffic planning is carried out by taking reduction of the road traffic index as a target, and a road traffic index difference value before and after planning is calculated as a decision basis. According to the invention, the problem of asymmetry of basic traffic management information is effectively solved, and the connection accuracy of the road network is improved.

Description

Technical Field

[0001] The present invention belongs to the field of intelligent transportation technology and relates to a county and rural transportation planning decision-making method and system based on road traffic index. Background Art

[0002] As an important component of the regional transportation system, county and rural transportation planning is of great significance for promoting urban-rural integration, improving residents' travel conditions, and driving regional economic growth. However, current county and rural transportation planning faces many challenges. County and rural areas are geographically vast and have scattered infrastructure. Traditional transportation planning relies mainly on manual surveys, requiring staff to conduct on-site visits to collect information such as road conditions and traffic flow. This method not only consumes a lot of manpower, material resources, and time, but also makes it difficult to obtain accurate data in a comprehensive and timely manner, resulting in insufficient timeliness and completeness of the data. In addition, traditional planning methods are usually based on a single data source for analysis, such as relying solely on statistical data from the transportation department. This single data source analysis method cannot comprehensively consider the impact of multiple factors on transportation, such as socioeconomic factors, population distribution, and geographical environment. As a result, the analysis results are highly one-sided and difficult to accurately reflect the overall picture of the transportation system.

[0003] Transportation demand in rural and county areas is dynamic. Factors such as seasonal agricultural seasons, holiday travel peaks, and emergencies can significantly impact traffic flow and travel demand. However, traditional planning methods lack dynamic decision-making capabilities, making it difficult to adjust planning schemes based on real-time traffic conditions, resulting in lags and inadequate planning. Furthermore, rural and county transportation has unique characteristics and demands that differ significantly from urban transportation. Poor urban-rural road connectivity and high road accessibility are particularly pronounced. In some areas, dead-end roads and significant differences in road grades exist between urban and rural roads, leading to poor urban-rural connectivity. Road accessibility is high between adjacent villages, towns, and county towns, forcing residents to take longer detours, increasing travel time and costs. Transportation demand in rural and county areas encompasses not only daily commuting but also encompasses diverse functions such as agricultural product transportation, rural tourism, and rural logistics. These demands are unevenly distributed across time and space and significantly impacted by factors such as season and weather, requiring more refined planning approaches to meet them. In addition, the construction of transportation infrastructure in county and rural areas is relatively lagging behind, and problems such as low road grade, poor road conditions, and insufficient supporting facilities are common, making it difficult to directly apply traditional transportation planning models. They need to be optimized and adjusted based on the actual conditions of county and rural transportation.

[0004] The prior art has the following deficiencies: most of the existing traffic planning models are established based on the traffic characteristics of large cities, and are not suitable for the special conditions of county and rural traffic. These models cannot accurately reflect the actual traffic conditions and traffic demand of county and rural roads, and it is difficult to develop a traffic planning scheme that meets the actual situation. At the same time, the traditional method fails to fully tap the potential value behind the data, and lacks scientific and accurate decision-making basis. Therefore, there is an urgent need for a method and system that can integrate multi-source data, build a scientific road traffic index model and provide effective decision support, to solve the limitations of traditional county and rural traffic planning methods and meet the special needs of county and rural traffic. SUMMARY

[0005] In view of the problems of single data, insufficient dynamic adaptability and information asymmetry in the existing county and rural traffic planning method, the present application provides a county and rural traffic planning decision-making method and system based on road traffic index, which integrates multi-source data, builds a scientific road traffic index model, and combines a dynamic weight adjustment mechanism and visual decision support to provide comprehensive and accurate technical support for county and rural traffic planning.

[0006] The present application is realized by the following technical solutions. A county and rural traffic planning decision-making method based on road traffic index, comprising the following steps: S1: collecting navigation API data, social and economic data and POI information related to county and rural traffic planning; S2: cleaning and standardizing the collected data; S3: matching and integrating the standardized data in time and space dimensions; S4: calculating the route growth index, hourly time index, holiday impact index, broken road index and planning simulation index according to the integrated data, and performing weighted fusion to obtain the road traffic index. In the calculation of the road traffic index, an initial weight is assigned to each index, and an adaptive weight adjustment algorithm is used to dynamically adjust the weight of each index according to real-time traffic data and simulation results; S5: displaying the road traffic index and related data, and drawing the road traffic index into a heat map, and carrying out county and rural traffic planning with the road traffic index as the target, and calculating the difference in road traffic index before and after planning as the decision-making basis.

[0007] Specifically, the route growth index , is the straight-line distance between two points, is the navigation distance between two points obtained through navigation API data; The hourly time index , , The estimated travel time for different routes obtained through navigation API data. is the theoretical travel time, is the average speed; Holiday Impact Index , is the average route growth index or hourly time index during holidays. The average route growth index or hourly time index during non-holiday periods; Dead-end Road Index , is the total length of dead-end roads in the area; is the total length of roads in the area; Planning Simulation Index , is the current traffic indicator; To simulate the traffic indicators after planning the plan; Road access index : ; Among them, w1, w2, w3, w4, and w5 are the weights of the route growth index, hourly time index, holiday impact index, dead-end road index, and planning simulation index, respectively.

[0008] Specifically, the steps of the adaptive weight adjustment algorithm are: Step 1: Adjustment of index weights affected by holidays: ; in, is the revised holiday impact index weight, Adjust the intensity index for holiday weights, is the holiday status indicator function, Indicates that it is currently a holiday. Indicates non-holidays, is the average route growth index during holidays, is the average route growth index during non-holiday periods; Step 2: Dead-end Road Index Weight Correction: ; in, is the modified dead-end road index weight, is the normalized dead-end road index, ; is the maximum value of the dead-end road index, is the minimum value of the dead-end road index; Adjust the intensity index for dead-end road weights; Step 3: Weight normalization: Calculate the corrected total weight sum: ; Then normalize: ; in, ; in, is the total weight after adjustment, is the i-th modified weight, is the i-th weight, is the normalized weight of the i-th; Step 4: Weight iteration for real-time data feedback: ; ; in, is the weight matrix at time t, is the weight matrix at time t+1, λ is the adaptive learning rate, is the gradient vector of the road traffic index with respect to the weight.

[0009] Specifically, the complete process of calculating the road traffic index according to the adaptive weight adjustment algorithm is: Step 1: Initialize the weight matrix ; Step 2: At time t: Collect data and calculate various indices: ; According to whether the current holiday and dead-end road index, the first and second steps are performed to obtain and .

[0010] Perform the third step to obtain the normalized weight matrix ; Calculate road traffic index ; Calculating gradients .

[0011] Proceed to the fourth step to obtain the weight matrix at time t+1 ; Step 3: The weight matrix at time t+1 As the initial weight for the next moment, repeat step 2.

[0012] This invention also provides a county and rural transportation planning and decision-making system based on the road access index, comprising a data acquisition module, a data preprocessing module, a multi-source data fusion module, a road access index calculation module, and a decision support system. These modules collaborate through data flows and logical connections, ensuring comprehensive technical support from data acquisition to decision output.

[0013] The data collection module collects navigation API data, socioeconomic data, and POI information related to county and rural transportation planning; The data preprocessing module cleans and standardizes the collected data; The multi-source data fusion module matches and integrates the standardized data in time and space dimensions; The road traffic index calculation module calculates the route growth index, hourly time index, holiday impact index, dead-end road index, and planning simulation index based on the integrated data, and performs weighted fusion to obtain the road traffic index. When calculating the road traffic index, an initial weight is assigned to each index, and an adaptive weight adjustment algorithm is used to dynamically adjust the weight of each index based on real-time traffic data and simulation results. The decision support system displays the road access index and related data, and plots the road access index into a heat map.

[0014] The present invention also provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the computer program implements the steps in the county and rural transportation planning decision-making method based on the road traffic index as described in the above-mentioned embodiment 1.

[0015] The present invention also provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and runnable on the processor. When the processor executes the computer program, the steps in the county and rural transportation planning decision-making method based on the road access index as described in the above-mentioned embodiment 1 are implemented.

[0016] This invention innovatively integrates multimodal data such as navigation API data, socioeconomic data, and POI information, enabling in-depth analysis of county and rural transportation from multiple perspectives. Decision-making algorithms in existing technologies often lack consideration of the unique geographical and transportation characteristics of counties and villages. This invention, based on the characteristics of counties and villages, designs a specialized road access index and dynamic weight adjustment mechanism, taking into account factors such as holiday index and the impact of dead-end roads, so that decision-making results are more in line with the actual needs of counties and villages. This combination of multimodal data fusion and targeted algorithms provides more accurate and comprehensive technical support for county and rural transportation planning decisions.

[0017] This invention has significant practical application in county and rural planning and decision-making. First, it effectively addresses the information asymmetry issue in grassroots traffic management. By collecting and integrating multi-source data, managers can comprehensively and accurately understand the actual status of county and rural traffic, including road conditions, population distribution, and industrial layout, providing strong data support for decision-making.

[0018] Secondly, it improves the problem of poor regional road connectivity. By analyzing various indices, we can accurately identify areas with poor road connectivity and provide targeted improvement suggestions, such as road widening and opening up dead-end roads, thereby improving the accuracy of road network connectivity.

[0019] Furthermore, this invention addresses the lack of quantitative data analysis. By establishing a scientific road access index and quantitatively assessing traffic conditions, it makes the decision-making process more scientific and objective. These benefits have effectively improved the efficiency of county and rural planning and decision-making, and promoted the development of transportation in these areas. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the county and rural transportation planning decision-making method of Example 1.

[0021] Figure 2 This is the framework diagram of the county and rural transportation planning decision system of Example 2. DETAILED DESCRIPTION

[0022] The present invention will be further described in detail below with reference to the accompanying drawings and examples. Example 1

[0023] like Figure 1 As shown in FIG, a county and rural transportation planning decision-making method based on road access index includes the following steps: S1: Collect navigation API data, socioeconomic data, and POI information related to county and rural transportation planning; S2: Clean and standardize the collected data; S3: Match and integrate the standardized data in time and space dimensions; S4: Based on the integrated data, the route growth index, hourly travel time index, holiday impact index, dead-end road index, and planning simulation index are calculated and weighted together to obtain the road access index. When calculating the road access index, an initial weight is assigned to each index. An adaptive weight adjustment algorithm is used to dynamically adjust the weight of each index based on real-time traffic data and simulation results. S5: Display the road access index and related data, and draw the road access index into a heat map. Carry out county and rural transportation planning with the goal of reducing the road access index. Calculate the difference in road access index before and after planning as the basis for decision-making.

[0024] Navigation API Data Collection: When calling the AutoNavi or Baidu Maps API, you must first register as a developer on their open platform and obtain the corresponding API key. For example, to obtain navigation distance, use the route planning API, enter the latitude and longitude of the starting and ending points, and specify the mode of travel (driving, cycling, or walking). Ensure the latitude and longitude are formatted correctly in the request parameters, and set other optional parameters, such as whether to avoid toll roads, according to the API documentation. The call frequency should be controlled within the API's permitted range to avoid request rejections due to frequent calls.

[0025] Socioeconomic Data: Collaborate with local government statistics departments to obtain data on population distribution, industrial layout, and economic development levels. This data is typically stored in tabular form and may include information such as population size, industry type, and output value for different administrative regions. Web crawlers can also be used to extract relevant data from public government websites, statistical yearbooks, and other sources. During the data collection process, attention should be paid to the timeliness and accuracy of the data, and cross-validation should be performed on data from different sources.

[0026] POI Information: Use the POI search interface provided by the Maps API to enter keywords (such as schools, hospitals, shopping malls, factories, etc.) and a search range (which can be a specific administrative region or a latitude and longitude range) to obtain corresponding POI information. POI information includes name, address, latitude and longitude. To ensure data integrity, you can perform multiple searches, expand the search range, or adjust keywords.

[0027] The cleaning in step S2 includes missing value processing, outlier processing and duplicate data processing.

[0028] Missing value handling: For missing values ​​in navigation API data, socioeconomic data, and POI information, we can use mean filling, median filling, or prediction based on other relevant data. For example, if population data for a particular area is missing, we can use the average population density of the administrative region above the area to estimate and fill in the missing values.

[0029] Outlier handling: Identify outliers in the data by drawing box plots, scatter plots, and other methods. Data that significantly deviates from the normal range can be processed by deletion, correction, or replacement. For example, outliers where the ratio of navigation distance to great circle distance is too large or too small can be corrected based on the overall distribution of the data.

[0030] Duplicate data processing: Perform deduplication on collected data to ensure data uniqueness. You can judge based on key information such as latitude, longitude, name, etc. and delete duplicate records.

[0031] Multi-source data fusion: Spatio-temporal matching technology of traffic flow data and population distribution, industrial layout: First, align traffic flow data, population distribution data and industrial layout data according to time and space dimensions. In the time dimension, data can be divided according to the same time period (such as daily, weekly, etc.); In the spatial dimension, data is divided by administrative region or grid. Then, using spatial analysis methods such as buffer analysis, overlay analysis, etc., find the correlation between traffic flow and population distribution, industrial layout. For example, calculate the correlation between population density and traffic flow in each administrative region, and analyze the impact of industrial layout on traffic flow. You can use regression analysis and other methods to establish a mathematical model between traffic flow and population distribution, industrial layout, and predict traffic flow changes in different regions.

[0032] For any two places A and B, get the driving, cycling or walking navigation distance through the API . At the same time, use the latitude and longitude information to calculate the straight-line distance between the two points using the Haversine formula . The Haversine formula is: ; where is the straight-line distance between the two points, R is the radius of the Earth, and are the latitudes of the two points, the latitude difference , the longitude difference , and are the longitudes of the two points.

[0033] Route growth index , is an intermediate variable in the Haversine formula used to calculate the straight-line distance.

[0034] For village-village, township-township, county-county route growth index calculation, all possible routes between different administrative levels are counted. Taking village-village as an example, first determine the latitude and longitude information of all villages, then get the navigation distance and straight-line distance between any two villages through the API, and calculate the route growth index. Aggregate statistics of all village-village route growth indexes are calculated to calculate the mean, median, standard deviation and other statistical quantities to reflect the overall detour between villages. For township-township and county-county route growth index calculation, use the same method for statistics.

[0035] Village-to-village, township-to-township, and county-to-county routes are categorized based on the Route Growth Index. Different thresholds can be set, such as classifying routes with a Route Growth Index less than 1.2 as Level 1, those between 1.2 and 1.5 as Level 2, those between 1.5 and 2 as Level 3, and those greater than 2 as Level 4. These levels reflect varying degrees of detour, with Level 1 representing the least detour and Level 4 representing the most detour.

[0036] Get estimated travel time for different routes using navigation API data , and estimate the theoretical travel time based on straight-line distance and average speed The average speed can be set according to different travel modes (driving, cycling, walking) and road types. , , is the average speed.

[0037] Similarly, the routes are graded according to the hourly time index, with different thresholds set. For example, routes with an hourly time index less than 1.1 are classified as level one, routes between 1.1-1.3 are classified as level two, routes between 1.3-1.5 are classified as level three, and routes greater than 1.5 are classified as level four.

[0038] Collect traffic flow data and navigation distance data during historical holidays to analyze the impact of holidays on traffic conditions. You can calculate indicators such as the average route growth index and hourly time index during different holidays and compare them with data from non-holiday periods. Holiday Impact Index It can be calculated by the following formula: , is the average route growth index or hourly time index during holidays. It is the average route growth index or hourly travel time index during non-holiday periods.

[0039] Through map data and field surveys, dead-end roads in county and township roads are identified. Dead-end roads refer to sections of roads that are not connected to other roads at one end. Dead-end road index The dead-end road index can be calculated based on factors such as the length of the dead-end road and the impact range. For example, the ratio of the total length of the dead-end roads in each administrative area to the total length of the roads in the area can be calculated as the dead-end road index. , is the total length of dead-end roads in the area (km); is the total length of roads in the area (km).

[0040] Set different traffic planning schemes, such as road widening, new road construction, traffic control, etc. For each simulation scenario, recalculate the route growth index, hourly time index, etc. Compare with the current status index to get the planning simulation index , is the current traffic index (such as route growth index, hourly time index); is the traffic index after simulation planning scheme (such as road widening, new road construction). The planning simulation index can reflect the improvement degree of different planning schemes on traffic conditions.

[0041] Considering the route growth index, hourly time index, holiday influence index, and dead-end road index, calculate the road traffic index of each township ; where w1, w2, w3, w4, w5 are the weights of route growth index, hourly time index, holiday influence index, dead-end road index, and planning simulation index. According to the size of road traffic index, the county and township roads are sorted. The larger the index, the worse the road traffic condition, which needs to be improved first.

[0042] When calculating the road traffic index, assign initial weights to each index (route growth index, hourly time index, holiday influence index, dead-end road index, and planning simulation index). During the holiday, dynamically adjust the weight according to the holiday influence index, increase the weight of the holiday influence index, and highlight the impact of the holiday on traffic conditions. For areas with dead-end roads, increase the weight of the dead-end road index to reflect the hindering effect of dead-end roads on traffic. Adaptive weight adjustment algorithm can be used to dynamically adjust the weights of each index according to real-time traffic data and simulation results, so that the road traffic index can more accurately reflect the traffic conditions.

[0043] The steps of adaptive weight adjustment algorithm are: First step, holiday influence index weight correction: ; where is the corrected holiday influence index weight, is the holiday weight adjustment intensity index, which is used to control the adjustment range and is artificially set; is the holiday state indication function, indicates that it is a holiday, indicates that it is not a holiday, is the average route growth index during the holiday, is the average route growth index during non-holiday; Second step, dead-end road index weight correction:​ ; in, is the modified dead-end road index weight, is the normalized dead-end road index, ; is the maximum value of the dead-end road index, is the minimum value of the dead-end road index; Adjust the intensity index for dead-end road weights; Step 3: Weight normalization: Calculate the corrected total weight sum: ; Then normalize: ; in, ; in, is the total weight after adjustment, is the i-th modified weight, is the i-th weight, is the normalized weight of the i-th; In this way, all weights are normalized to sum to 1.

[0044] Step 4: Weight iteration for real-time data feedback: ; ; in, is the weight matrix at time t, is the weight matrix at time t+1, λ is the adaptive learning rate, It is the gradient vector of the road access index with respect to the weight, which is calculated as the partial derivative of the road access index with respect to the weight, and is actually equal to the value of each index; Represents the magnitude (Euclidean norm) of a vector.

[0045] The complete process of calculating the road traffic index according to the adaptive weight adjustment algorithm is: Step 1: Initialize the weight matrix W0 (e.g., evenly distribute, or set based on experience).

[0046] Step 2: At time t: Collect data and calculate various indices: ; According to whether the current holiday and dead-end road index, the first and second steps are performed to obtain and .

[0047] Perform the third step to obtain the normalized weight matrix ; Calculate the road traffic index ; Calculate the gradient .

[0048] Perform the fourth step to obtain the weight matrix Wt+1 at time t+1; Step 3: Take the weight matrix Wt+1 at time t+1 as the initial weight for the next time, and repeat step 2.

[0049] Further, the road traffic index of the township is displayed on the map in the form of a heat map. Different colors are used to represent different traffic index ranges, such as red for high traffic index (poor traffic conditions) and green for low traffic index (good traffic conditions). Through the heat map, the distribution of the township road traffic conditions can be intuitively observed, providing a visual basis for traffic planning decisions.

[0050] Analysis of the predicted impact of road widening schemes on route growth index: First, select the road section that needs to be widened, and determine the width and length of the widening. Then, use a traffic simulation model to simulate the traffic flow distribution and route selection after the road is widened. According to the simulation results, recalculate the route growth index and compare it with the current route growth index to analyze the impact of the road widening scheme on the route growth index. Multiple simulation methods can be used to consider different traffic demand scenarios and widening schemes to obtain more accurate prediction results.

[0051] Comparison of indexes before and after improvement: Before and after implementing improvement measures such as road widening, connecting broken roads, utilizing low-grade paths, and improving local congestion points, calculate indicators such as route growth index, hourly time index, and average running speed, and conduct comparative analysis. For example, calculate the average route growth index difference, average hourly time index difference, and average running speed difference before and after improvement. Through these differences, the effect of improvement measures can be intuitively observed.

[0052] Heat map comparison: Before and after the implementation of improvement measures, draw the heat map of road traffic index and compare it. Observe the color changes in the heat map to analyze the impact of improvement measures on the traffic conditions of different areas. For example, whether the red area (poor traffic conditions) has decreased and the green area (good traffic conditions) has increased.

[0053] Efficiency improvement analysis: In addition to index comparison and heat map comparison, the improvement of traffic efficiency by improvement measures can also be analyzed. For example, calculate the increase in the number of vehicles passing through per unit time after improvement, the reduction in travel time, and other indicators to evaluate the improvement effect of improvement measures on traffic efficiency.

[0054] In a region of Jiangxi Province, adjacent counties, towns, and villages were selected and their road accessibility indexes were calculated and optimized at a tiered level. The indices involved included route growth index, hourly travel time index, holiday impact index, dead-end road index, and planning simulation index. Initially, the region's road accessibility index was 2.1, but through a series of optimization measures, it was successfully reduced to 1.5.

[0055] First, we use navigation API data to obtain actual driving, cycling, and walking distances. We then analyze the region's population distribution, industrial layout, and traffic flow, combined with socioeconomic data and POI information. We then calculate the ratio of driving / cycling / walking distance to straight-line distance to generate a route growth index.

[0056] Classification statistical algorithms are designed for adjacent counties, townships, and villages. The route growth index is calculated using a weighted average method based on the characteristics of each region. The hourly travel time index is determined by the ratio of actual travel time to theoretical travel time. The holiday impact index is set by analyzing traffic flow changes during holidays. The dead-end road index is evaluated based on the number and length of dead-end roads in the region. The planning simulation index is predicted based on future transportation planning and construction projects.

[0057] Based on the calculated results, targeted improvement measures will be developed. For areas with high route growth indices, road widening, opening up dead-end roads, or optimizing traffic signal configurations will be considered. For areas with significant holiday impacts, public transportation capacity will be increased or traffic control measures implemented. Through the implementation of these measures, the road traffic index will be gradually reduced.

[0058] Before and after the optimization measures were implemented, various indices were statistically analyzed and compared. Tables were used to display the changes in the indices before and after the improvements, including multi-dimensional indicators such as average operating speed, heat map comparison, and efficiency improvement. After a period of implementation, the road traffic index decreased from 2.1 to 1.5, demonstrating that the optimization measures have achieved significant results.

[0059] Different parameter configuration strategies need to be adopted in mountainous counties and plain counties in different geographical environments to ensure the effectiveness and adaptability of the system.

[0060] Mountainous counties have complex terrain, steep roads, numerous curves, and relatively low traffic volumes. In terms of data collection, increased monitoring of topography and road conditions, such as slope and curvature, is needed. In calculating the road accessibility index, the weights of the route growth index and hourly travel time index should be appropriately increased to reflect the actual traffic conditions on mountainous roads. Regarding the dead-end road index, due to the limitations of mountainous terrain, there may be a high number of dead-end roads, necessitating greater attention to their improvement and connectivity. During road optimization, priority should be given to the construction of infrastructure such as tunnels and bridges to improve traffic conditions in mountainous areas.

[0061] Pingyuan County has a flat terrain, good road conditions, and relatively high traffic volume. Data collection focused on changes in traffic volume and population distribution. When calculating the road accessibility index, the weights of the holiday impact index and planning simulation index were appropriately increased to address traffic pressure during holidays and future development needs in Pingyuan County. Regarding the dead-end road index, since road construction is relatively easy in plain areas, the number of dead-end roads should be minimized. During road optimization, efforts were focused on optimizing traffic signal settings, increasing public transportation capacity, and developing intelligent transportation systems to improve transportation efficiency in Pingyuan County.

[0062] Through the above different parameter configuration strategies, the system can better adapt to the characteristics of mountainous counties and plain counties, and provide more accurate support for county and township transportation planning decisions in different regions. Example 2

[0063] like Figure 2 As shown, the present invention also provides a county and rural transportation planning and decision-making system based on the road access index, which includes a data acquisition module, a data preprocessing module, a multi-source data fusion module, a road access index calculation module, and a decision support system. These modules collaborate through data flows and logical connections, ensuring technical support for the entire chain from data acquisition to decision output.

[0064] The data collection module collects navigation API data, socioeconomic data, and POI information related to county and rural transportation planning; The data preprocessing module cleans and standardizes the collected data; The multi-source data fusion module matches and integrates the standardized data in time and space dimensions; The road traffic index calculation module calculates the route growth index, hourly time index, holiday impact index, dead-end road index, and planning simulation index based on the integrated data, and performs weighted fusion to obtain the road traffic index. When calculating the road traffic index, an initial weight is assigned to each index, and an adaptive weight adjustment algorithm is used to dynamically adjust the weight of each index based on real-time traffic data and simulation results. The decision support system displays the road access index and related data, and plots the road access index into a heat map. Example 3

[0065] This embodiment provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the steps of the county and rural transportation planning decision-making method based on the road access index as described in the above-mentioned embodiment 1 are implemented. Example 4

[0066] This embodiment provides a computer device, including 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 county and rural transportation planning decision-making method based on the road access index as described in the above-mentioned embodiment 1 are implemented.

[0067] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Thus, the present invention may take the form of hardware embodiments, software embodiments, or embodiments combining software and hardware. Furthermore, the present invention may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to magnetic disk storage and optical storage, etc.) containing computer-usable program code.

[0068] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowcharts and / or block diagrams, as well as combinations of processes and / or blocks in the flowcharts and / or block diagrams, 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 produce 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 flowcharts and / or block diagrams. 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.

[0069] The foregoing description is merely a preferred embodiment of the present invention and is not intended to limit the present invention. Those skilled in the art will readily appreciate that various modifications and variations of the present invention are possible. Any modifications, equivalent substitutions, or improvements made within the spirit and principles of the present invention are intended to be within the scope of protection of the present invention.

Claims

1. A county and rural transportation planning decision-making method based on road access index, characterized by: The following steps are involved: S1: Collect navigation API data, socioeconomic data, and POI information related to county and rural transportation planning; S2: Clean and standardize the collected data; S3: Match and integrate the standardized data in time and space dimensions; S4: Based on the integrated data, the route growth index, hourly travel time index, holiday impact index, dead-end road index, and planning simulation index are calculated and weighted together to obtain the road access index. When calculating the road access index, an initial weight is assigned to each index. An adaptive weight adjustment algorithm is used to dynamically adjust the weight of each index based on real-time traffic data and simulation results. S5: Display the road access index and related data, and draw the road access index into a heat map. Carry out county and rural transportation planning with the goal of reducing the road access index. Calculate the difference in road access index before and after planning as the basis for decision-making.

2. The county and village transportation planning decision-making method according to claim 1 is characterized in that the route Growth Index , is the straight-line distance between two points, It is the navigation distance between two points obtained through navigation API data; Hourly Time Index , , The estimated travel time for different routes obtained through navigation API data. is the theoretical travel time, is the average speed; Holiday Impact Index , is the average route growth index or hourly time index during holidays. The average route growth index or hourly time index during non-holiday periods; Dead-end Road Index , is the total length of dead-end roads in the area; is the total length of roads in the area; Planning Simulation Index , is the current traffic indicator; To simulate the traffic indicators after planning the plan; Road access index : ； Among them, w1, w2, w3, w4, and w5 are the weights of the route growth index, hourly time index, holiday impact index, dead-end road index, and planning simulation index, respectively.

3. The county and rural transportation planning decision-making method according to claim 2 is characterized in that: The steps of the adaptive weight adjustment algorithm are: Step 1: Adjustment of index weights affected by holidays: in, is the revised holiday impact index weight, Adjust the intensity index for holiday weights, is the holiday status indicator function, Indicates that it is currently a holiday. Indicates non-holidays; Step 2: Dead-end Road Index Weight Correction: in, is the modified dead-end road index weight, is the normalized dead-end road index, ; is the maximum value of the dead-end road index, is the minimum value of the dead-end road index; Adjust the intensity index for dead-end road weights; Step 3: Weight normalization: Calculate the corrected total weight sum: ； Then normalize: in, ; in, is the total weight after adjustment, is the i-th modified weight, is the i-th weight, is the normalized weight of the i-th; Step 4: Weight iteration for real-time data feedback: ； ； in, is the weight matrix at time t, is the weight matrix at time t+1, λ is the adaptive learning rate, is the gradient vector of the road traffic index with respect to the weight.

4. The county and rural transportation planning decision-making method according to claim 3 is characterized in that: The complete process of calculating the road traffic index according to the adaptive weight adjustment algorithm is: Step 1: Initialize the weight matrix ; Step 2: At time t: Collect data and calculate various indices: ; According to whether the current holiday and dead-end road index, the first and second steps are performed to obtain and ; Perform the third step to obtain the normalized weight matrix ; Calculate road traffic index ; Calculating gradients ; Proceed to the fourth step to obtain the weight matrix at time t+1 ; Step 3: The weight matrix at time t+1 As the initial weight for the next moment, repeat step 2.

5. A system for implementing the county and rural transportation planning decision-making method according to any one of claims 1 to 4, characterized in that: It includes data acquisition module, data preprocessing module, multi-source data fusion module, road traffic index calculation module and decision support system; The data collection module collects navigation API data, socioeconomic data, and POI information related to county and rural transportation planning; The data preprocessing module cleans and standardizes the collected data; The multi-source data fusion module matches and integrates the standardized data in time and space dimensions; The road traffic index calculation module calculates the route growth index, hourly time index, holiday impact index, dead-end road index, and planning simulation index based on the integrated data, and performs weighted fusion to obtain the road traffic index. When calculating the road traffic index, an initial weight is assigned to each index, and an adaptive weight adjustment algorithm is used to dynamically adjust the weight of each index based on real-time traffic data and simulation results. The decision support system displays the road access index and related data, and plots the road access index into a heat map.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the county and rural transportation planning decision-making method based on road traffic index as described in any one of claims 1 to 4 are implemented.

7. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the county and rural transportation planning decision-making method based on road traffic index as described in any one of claims 1 to 4 are implemented.

Images