Expressway economic benefit distribution prediction method and system

Abstract

The invention relates to the technical field of highway economic management, in particular to a highway economic benefit distribution prediction method and system, and the method comprises the following steps: collecting highway associated data, classifying and dividing a variable value corresponding to each highway section into a corresponding interval, calculating the density of the value distribution of variables in the interval, and calculating the value distribution of the variables in the interval; and sorting the data of each road section according to density results, and screening variable combinations matched with density intervals to generate a variable density sorting result. According to the method, the density distribution calculation and the variable sorting of the related data of the expressway are introduced, the high-correlation variable group is accurately classified and screened out, and the accuracy and the efficiency of data processing are improved. Through weight distribution and weighted combination calculation of a variable group, relevance processing between variables is optimized, and the data modeling capability is enhanced. Based on weighted data, in combination with the minimum value and the maximum value of the income in the interval, accurate interval feature data is provided for road income estimation.

Description

Technical Field

[0001] The present invention relates to the technical field of economic management, and in particular to a method and system for predicting the distribution of economic benefits of expressways. Background Art

[0002] The field of economic management technology combines mathematical modeling, data analysis, statistical forecasting and other tools to provide decision support for enterprises, organizations and the public sector through the collection, processing and analysis of economic data. Economic management technology plays an important role in improving resource utilization efficiency, optimizing economic operation models and achieving sustainable development.

[0003] Among them, the highway economic benefit distribution prediction method is a method for analyzing and predicting the distribution of economic benefits during highway operation. Its purpose is to scientifically predict the distribution of benefits in different regions or highway sections through data analysis and modeling technology, and help management optimize charging strategies and adjust resource allocation.

[0004] When analyzing the distribution of economic benefits of highways, existing technologies lack the means to accurately calculate and classify the density of interval variables. This limitation leads to low efficiency in extracting key variables, redundancy and weak correlation between variables, and the lack of accuracy in the final analysis results. For the estimation process of interval benefits, existing technologies mostly rely on unified standards or simple models, which are difficult to accurately reflect the subtle differences between intervals. This deficiency may lead to inefficient resource allocation. In the prediction of the distribution of future benefits, existing technologies lack dynamic analysis of changes in traffic flow and toll standards, and can only provide static revenue predictions, which are prone to prediction errors due to ignoring changes between time periods. For example, failure to consider the changing trend of traffic flow in future time periods may underestimate or overestimate the future revenue potential of a certain interval, affecting the flexibility of overall revenue optimization decisions. Summary of the invention

[0005] The purpose of the present invention is to solve the shortcomings of the prior art and to propose a method and system for predicting the distribution of economic benefits of expressways.

[0006] In order to achieve the above object, the present invention adopts the following technical solution: a method for predicting the distribution of economic benefits of expressways, comprising the following steps: S1: Collect highway-related data, classify the variable values ​​corresponding to each highway section and divide them into corresponding intervals, calculate the density of the numerical distribution of the variables in the interval, sort the data of each highway section according to the density results and select the variable combination matching the density interval to generate the variable density sorting result; S2: Based on the variable density ranking result, weights are assigned to the identified variable groups, and weighted combinations are performed according to the variable data after weight assignment to generate weighted variable combination data of the highway section; S3: combining the weight information in the weighted variable combination data of the highway section, and calculating the minimum and maximum estimated values ​​of the highway section revenue in each interval according to the minimum and maximum values ​​of the revenue value in the corresponding interval, and summarizing the calculation results by interval to generate highway section revenue interval characteristic data; S4: Based on the highway section revenue interval estimation data, the revenue estimation value of each highway section is accumulated by interval to obtain the total revenue contribution of the highway section in the corresponding interval, and the overall revenue is analyzed in future time periods by interval to generate a highway revenue distribution prediction result.

[0007] As a further solution of the present invention, the step of obtaining the density of the numerical distribution of the variable in the calculation interval is specifically: S111: Based on the traffic flow data, charging standard data and operation cost data of the expressway, by extracting the numerical information corresponding to each road section, classifying the traffic flow by vehicle type, sorting the road section charging standard and checking the cost data, dividing and classifying the data into intervals, and obtaining the expressway information table; S112: Based on the highway information table, the formula is used: ; Calculate the current interval The variable density value of , get the density information of the numerical distribution; in, Is the interval The frequency or number of occurrences of the internal variable, is the total number of samples of the target variable in all intervals, is the current interval width.

[0008] As a further solution of the present invention, the step of obtaining the variable density ranking result is specifically: S121: Based on the density information of the numerical distribution, the density values ​​of all highway sections are compared, the density value of each section is extracted and arranged in order, the sorting results are segmented and marked, and a density sorting data table is generated; S122: Based on the density sorting data table, extract the data of the intervals and corresponding sections whose density values ​​exceed the preset density screening threshold, and generate variable density sorting results by screening the qualified intervals and variable combinations and re-associating the variable data groups.

[0009] As a further solution of the present invention, the steps of acquiring the weighted variable combination data of the highway section are specifically as follows: S211: Based on the variable density ranking result, the variable data is grouped and sorted, the influence of the variables on the revenue is analyzed, and weights are assigned according to the importance of the traffic volume, charging standards and operating costs, and a weight allocation list is generated; S212: Based on the weight allocation list, the traffic volume, charging standard and operation cost data of each road section are weighted and combined according to the weights to generate weighted variable combination data of the highway section.

[0010] As a further solution of the present invention, the steps for acquiring the highway section revenue interval characteristic data are specifically as follows: S311: Based on the weighted variable combination data of the highway section, the vehicle flow, charging standard and operating cost data in the weighted variable combination data are sorted according to the weight distribution, and the minimum and maximum values ​​in each corresponding interval are marked to obtain the revenue distribution range data in the interval; S312: Based on the income distribution range data within the interval, the formula is used: ; ; Calculate the minimum return estimate separately and the highest revenue estimate , get the minimum and maximum estimated values; in, is the minimum charging standard within the range. is the maximum value of the charging standard within the range. is the average traffic volume in the interval, is the maximum value of the operating cost within the interval, is the minimum value of the operating cost within the interval; S313: The minimum estimated value and the maximum estimated value data are gradually compared and summarized according to the charging standard range, traffic volume and operating cost range of each interval, combined with the interval number, to obtain the highway section revenue interval characteristic data.

[0011] As a further solution of the present invention, the steps for obtaining the total revenue contribution of the highway section in the corresponding interval are specifically as follows: S321: Based on the highway section revenue interval characteristic data, the formula is used: ; Calculate the total revenue of the highway section in all intervals , get the total revenue accumulation result; in, Is the interval The revenue value, is the total number of intervals; S322: Based on the cumulative total revenue result, analyze the positive and negative contributions of the revenue value of each interval, respectively add up the positive and negative parts of the revenue and perform classified statistics, and establish the revenue contribution distribution result of each interval by comparing the proportional relationship between the positive and negative revenues.

[0012] As a further solution of the present invention, the steps of obtaining the highway revenue distribution prediction result are specifically as follows: S411: Based on the income contribution distribution result of each interval, the formula is adopted: ; Calculate total return in future periods , get the cumulative result of future total income; in, Is the interval within the current period The total revenue value, Is the interval within the current period of traffic volume, is the interval in the future period of traffic volume, represents the next period of forecast, Representation interval The growth rate of future traffic volume compared to the current period, Is the interval The charging standards for future periods, Is the interval The operating costs for future periods, is the total number of intervals; S412: Based on the cumulative result of the future total revenue, the revenue contribution value of each interval is extracted, and the revenue benchmark of each interval in all the data is combined to analyze the revenue growth trend of each interval to obtain the highway revenue distribution prediction result.

[0013] A highway economic benefit distribution prediction system, the highway economic benefit distribution prediction system is used to execute the above-mentioned highway economic benefit distribution prediction method, the system comprises: The data classification module extracts the variable values ​​corresponding to each highway section based on the associated data of the highway, divides these variables into multiple intervals according to the data characteristics, and screens the variable combinations that meet the density distribution conditions to generate the variable density ranking results; The variable weighting module assigns weights to the identified variable groups based on the variable density ranking results to generate weighted variable combination data for the highway section; The interval revenue calculation module calculates the minimum estimated value and the maximum estimated value of the highway section revenue in each interval based on the weighted variable combination data of the highway section and the weight information in the interval, and generates highway section revenue interval characteristic data; The revenue accumulation module obtains the total revenue value of all highway sections in the corresponding interval based on the highway section revenue interval characteristic data, and classifies and counts the interval contribution values ​​to generate total revenue contribution data; The revenue distribution prediction module analyzes the future revenue growth trend of each interval based on the total revenue contribution data and all the revenue change data of each interval to generate a highway revenue distribution prediction result.

[0014] Compared with the prior art, the advantages and positive effects of the present invention are: In the present invention, by introducing density distribution calculation and variable sorting of highway-related data, high-correlation variable groups are accurately classified and screened out, thereby improving the accuracy and efficiency of data processing. By allocating weights to variable groups and calculating weighted combinations, the correlation processing between variables is optimized and the data modeling capability is enhanced. Based on weighted data, combined with the minimum and maximum values ​​of the revenue within the interval, the distribution range of the lowest and highest revenues is calculated, providing accurate interval characteristic data for highway revenue estimation. In addition, by using dynamic trend analysis methods and total revenue accumulation results, the positive and negative revenue contribution analysis of the interval is refined, and the revenue distribution prediction results for future time periods are generated by summarizing and organizing, effectively achieving the goal of multi-interval dynamic revenue analysis. The accuracy and practicality of future revenue distribution predictions are improved, providing more targeted data decision support for highway revenue management. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 It is a schematic diagram of the workflow of the present invention; Figure 2 A flow chart for calculating the density of the numerical distribution of a variable within an interval according to the present invention; Figure 3 A flow chart for obtaining variable density ranking results for the present invention; Figure 4 A flow chart for obtaining weighted variable combination data of a highway section according to the present invention; Figure 5 A flow chart of obtaining highway section revenue interval characteristic data according to the present invention; Figure 6 A flow chart for obtaining the total revenue contribution of a highway section within a corresponding interval in the present invention; Figure 7 The present invention is a flow chart for obtaining highway revenue distribution prediction results. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0017] In the description of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, in the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined.

[0018] See also Figure 1 The present invention provides a technical solution: a method for predicting the distribution of economic benefits of expressways, comprising the following steps: S1: Extract traffic volume, charging standards, and operating cost information from highway-related data, classify the variable values ​​corresponding to each highway section and divide them into corresponding intervals, calculate the density of the numerical distribution of the variables in the interval, sort the data of each highway section according to the density results, and select the variable combination matching the density interval to generate the variable density sorting result; S2: Based on the variable density ranking results, weights are assigned to the identified variable groups, and weighted combinations are performed according to the variable data after weight assignment to generate weighted variable combination data of the highway section; S3: Combine the weight information in the weighted variable combination data of the highway section, obtain the revenue distribution data of each highway section according to the quantile of the interval traffic proportion, extract the minimum and maximum values ​​of the revenue value in the corresponding interval, calculate the minimum and maximum estimated values ​​of the highway section revenue in each interval respectively, summarize and organize the calculation results by interval, and generate highway section revenue interval characteristic data; S4: Based on the estimated data of highway section revenue intervals, the estimated revenue value of each highway section is accumulated by interval to obtain the total revenue contribution of the highway section in the corresponding interval, and the overall revenue is analyzed in future time periods by interval to generate the highway revenue distribution prediction result; The variable density sorting results include the traffic flow statistics data, charging standard corresponding data and operating cost data of each road section. The weighted variable combination data of the highway section includes the variable dispersion score, weight value and the contribution evaluation of the target variable to the revenue forecast. The highway section revenue interval characteristic data includes the minimum estimated revenue value, the maximum estimated revenue value and the fluctuation range of the revenue value within the interval. The highway revenue distribution prediction results include the total revenue estimate of each revenue interval, the revenue contribution breakdown of each section and the analysis of future revenue trends.

[0019] See also Figure 2 , the specific steps for obtaining the density of the numerical distribution of the variable in the calculation interval are: S111: Based on the traffic flow data, charging standard data and operation cost data of the expressway, by extracting the numerical information corresponding to each road section, classifying the traffic flow by vehicle type, sorting the road section charging standard and checking the cost data, dividing and classifying the data into intervals, and obtaining the expressway information table; Traffic flow, charging standards, and operating cost data are extracted from highway-related data. First, daily traffic flow data is obtained through the highway traffic management system, and different types of vehicles (such as small cars, large trucks, etc.) are classified and counted, and segmented and recorded in hours. For example, the daily traffic flow of small cars on a certain road section is 1,200 vehicles, which is divided into multiple data segments of 50 vehicles / hour to 200 vehicles / hour. Secondly, the charging standard information per kilometer is extracted from the charging system. For example, the charging standard for small cars on a certain road section is 0.5 yuan / kilometer, and for large trucks is 1.0 yuan / kilometer. These data are sorted into charging standard data sets corresponding to different models. Finally, the operating cost data of each kilometer section is obtained from the operating cost management system. For example, the average daily operating cost of a certain road section is 2,000 yuan. After being disassembled into specific items such as labor cost, maintenance cost, and energy cost, it is summarized as the average cost value per kilometer. When the above three types of data are divided into intervals, the equal distance quantile division method is adopted. The specific operation is as follows: Traffic flow interval division: divide the traffic flow into multiple intervals according to the 10% percentile. For example, if the traffic flow of small cars on a certain road section ranges from 0 to 2,000 vehicles, each interval is 200 vehicles, divided into intervals of 0-200, 200-400, 400-600...1800-2000, etc. Charge standard interval division: divide according to the charge standard with a fixed step length. For example, the charge standard for small cars ranges from 0.4 yuan / km to 1.0 yuan / km, and each 0.1 yuan is an interval, forming intervals of 0.4-0.5 yuan, 0.5-0.6 yuan, 0.6-0.7 yuan...0.9-1.0 yuan. Operation cost interval division: Operation cost data is divided into 20% quantiles. For example, if the operation cost of a certain road section ranges from 1,000 yuan to 3,000 yuan, each interval is 400 yuan, divided into 1,000-1,400 yuan, 1,400-1,800 yuan, 1,800-2,200 yuan... 2,600-3,000 yuan intervals. After the division is completed, the interval data of traffic flow, charging standards and operation costs are stored as independent tables, so that the density calculation and data screening of each interval variable can be performed in the subsequent steps. Through this division method, it can be ensured that the data is evenly distributed in each interval, providing accurate basic data support for the prediction of economic benefit distribution.

[0020] S112: Based on the highway information table, the formula is: ; Calculate the current interval The variable density value of , get the density information of the numerical distribution; in, Is the interval The frequency or number of occurrences of a variable (such as traffic volume, charging standards or operating costs) within a highway. Traffic volume data is obtained through highway traffic volume monitoring equipment (such as ground sensor coils, video monitoring systems). For example, if the traffic volume in a certain section is 100-200 vehicles / hour and 120 vehicles pass through the section, then The charging standard data is obtained from the highway toll system, and the number of passes in different charging intervals for different vehicle types is recorded. For example, the charging standard for a certain interval is 0.4-0.6 yuan / km, and the corresponding number of passes is 80 times. , the operating cost data is extracted from the highway operation system and divided into cost intervals. For example, if the operating cost of a certain interval is 1000-1500 yuan and the number of days recorded is 30 days, then , is the total number of samples of the target variable in all intervals, is the current interval width, which is set by the interval division rule. For example, if the traffic flow interval is 100-200 vehicles / hour, then , the charging standard range is 0.4-0.6 yuan / km, then , the operating cost range is 1000-1500 yuan, then .

[0021] If the traffic volume is between 100 and 200 vehicles per hour, record , total number of samples , interval width . Substituting into the formula: ; If the charging standard range is 0.4-0.6 yuan / km, record , total number of samples , interval width . Substituting into the formula: ; If the operating cost range is 1000-1500 yuan, record , total number of samples , interval width . Substituting into the formula: ; The results show that, assuming the density value of the historical data is , the current density value This indicates that the traffic volume has increased. Assuming that the density value of this interval in the historical data is , the current density value This indicates that the number of vehicles under this charging standard has increased significantly. Assuming that the density value of this interval in historical data is , the current density value This indicates that the distribution of operating costs in this interval has decreased, which may be the result of cost optimization.

[0022] See also Figure 3 , the specific steps for obtaining the variable density sorting results are: S121: Based on the density information of the numerical distribution, the density values ​​of all highway sections are compared, the density value of each section is extracted and arranged in order from large to small, the sorting results are segmented and marked, and a density sorting data table is generated; The density values ​​of all highway sections are compared, and the density value of each interval is extracted and arranged in order from large to small. The density values ​​of three types of data (traffic flow, charging standards and operating costs) are calculated and compared to extract the density value of each interval. For example, the density value calculation result of traffic flow is 0.0012 for the interval of 100-200 vehicles / hour, 0.0008 for 200-300 vehicles / hour, and 0.0005 for 300-400 vehicles / hour; the density value calculation result of charging standard is 0.8 for the interval of 0.4-0.6 yuan / km, 0.6 for 0.6-0.8 yuan / km, and 0.4 for 0.8-1.0 yuan / km; the density value calculation result of operating cost is 0.0003 for the interval of 1000-1500 yuan, 0.0002 for 1500-2000 yuan, and 0.0001 for 2000-2500 yuan. Sort these density values ​​from large to small. For example, the traffic flow density value is ranked as 0.0012>0.0008>0.0005; the charging standard density value is ranked as 0.8>0.6>0.4; the operating cost density value is ranked as 0.0003>0.0002>0.0001. Based on the sorting results, each interval and the corresponding road section are marked in sections, such as "high-density area", "medium-density area" and "low-density area". Finally, a density sorting data table containing density value sorting and interval marking is generated, providing a basis for subsequent screening and analysis.

[0023] S122: Based on the density sorting data table, extract the data of the intervals and corresponding sections whose density values ​​exceed the preset density screening threshold, screen the intervals and variable combinations that meet the conditions, and re-associate the data groups of each variable to generate the variable density sorting result; Assuming that the screening threshold of traffic density is 0.001, the screening threshold of charging standard density is 0.5, and the screening threshold of operating cost density is 0.0002, the intervals that meet the conditions and the corresponding data are screened. For example: Traffic volume: Extract the interval 100-200 vehicles / hour and the traffic volume data of the corresponding sections with a density value exceeding 0.001, and record it as 120 vehicles / hour for section A and 150 vehicles / hour for section B. Charging standard: Extract the interval 0.4-0.6 yuan / km and the charging standard data of the corresponding sections with a density value exceeding 0.5, and record it as 0.5 yuan / km for section A and 0.6 yuan / km for section B. Operating cost: Extract the interval 1000-1500 yuan and the operating cost data of the corresponding sections with a density value exceeding 0.0002, and record it as 1200 yuan for the operating cost of section A and 1300 yuan for the operating cost of section B. By screening the qualified intervals, the interval variables of traffic flow, charging standards and operating costs are regrouped and associated. For example, the traffic flow of 120 vehicles / hour, charging standards of 0.5 yuan / km and operating costs of 1,200 yuan on section A are associated into one data group, and the traffic flow of 150 vehicles / hour, charging standards of 0.6 yuan / km and operating costs of 1,300 yuan on section B are associated into another data group. A data table of variable density sorting results under the density screening conditions is generated, providing a clear basis for variable association for subsequent revenue forecasting and analysis.

[0024] See also Figure 4 , the specific steps for obtaining weighted variable combination data of highway sections are: S211: Based on the variable density sorting results, the variable data is grouped and sorted, the impact of the variables on the revenue is analyzed, and weights are assigned according to the importance of traffic volume, charging standards and operating costs, and a weight distribution list is generated; Assume that the traffic volume, charging standards and operating cost data of sections A and B are grouped and collated, and the basis for weight allocation of each variable is specifically analyzed. For traffic volume, considering its direct impact on traffic efficiency and revenue, the fluctuation of historical traffic volume data is analyzed and combined with the current density ranking results. When it is confirmed that traffic volume accounts for a high proportion of the overall revenue, it is given a higher weight; for charging standards, according to the evaluation standards of the charging market acceptance of the section, the importance of the current charging standards to the revenue contribution is judged, and a medium weight is assigned; for operating costs, by sorting out the cost fluctuation data of each section and combining the analysis of its negative impact on revenue, a lower weight is assigned.

[0025] S212: Based on the weight distribution list, the traffic volume, charging standard and operation cost data of each road section are weighted and combined according to the weights to generate weighted variable combination data of the highway section; Assume that the traffic volume, charging standards and operating cost data of Section A and Section B are extracted, and weighted calculation is performed item by item according to the above weight distribution results. Taking Section A as an example, its traffic volume is 120 vehicles / hour, and the weighted value is ; The charging standard is 0.5 yuan / km, and the weighted value is ; Operating cost is 1200 yuan, weighted value is The weighted value of the traffic volume of 150 vehicles per hour is also calculated for section B. , the weighted value of the charging standard is 0.6 yuan / km , weighted value of operating cost 1300 yuan The weighted values ​​of each road section are sorted into a weighted variable combination data table, where the data of road section A is , the data of section B is , providing input data support for subsequent return distribution analysis.

[0026] See also Figure 5 ,The specific steps for obtaining the characteristic data of highway section revenue interval are as follows: S311: Based on the weighted variable combination data of the highway section, the vehicle flow, charging standard and operating cost data in the weighted variable combination data are sorted according to the weight distribution, and the minimum and maximum values ​​in each corresponding interval are marked to obtain the revenue distribution range data in the interval; Combined with the weight information in the weighted variable combination data of the highway section, the traffic volume, charging standards and operating cost data in the weighted variable combination data are sorted out according to the weight distribution. By extracting the traffic volume proportion of each interval, the standard range of dividing the interval is determined, and the weighted variable combination data in each interval is further called to extract the revenue value in each interval one by one. By analyzing the historical revenue data and the current interval traffic data, the revenue value range of the corresponding interval is sorted out item by item. By sorting and classifying the extracted revenue data, the minimum and maximum values ​​in each interval are marked respectively, the quantile calibration of the revenue distribution interval of each highway section is completed, and the minimum and maximum revenue values ​​in the corresponding interval are recorded.

[0027] S312: Based on the income distribution range data within the interval, the formula is used: ; ; Calculate the minimum return estimate separately and the highest revenue estimate , get the minimum and maximum estimated values; in, It is the minimum value of the charging standard within the interval, indicating the lowest charging standard that may be set within a certain interval. The lowest charging standard in each interval is determined by sorting out the historical charging standard data. For example, by analyzing the charging standard change records in the past year, the lowest charging period is selected and the value is taken. It is the maximum value of the charging standard within the interval, indicating the highest charging standard that may be set within a certain interval. The highest charging standard in each interval is determined by sorting out the historical charging standard data. For example, referring to the charging strategies during different peak periods, the data of the highest charging period is extracted as this value. It is the average value of the traffic flow in the interval, indicating the average flow of vehicles passing through a specific interval. The historical data is collected in real time through the traffic flow monitoring equipment, and the average value in the interval is calculated. For example, the traffic flow monitoring system is called to obtain the traffic records of the past month, and the average value of each group is calculated after grouping by interval. It is the maximum value of the operating cost within the interval, indicating the highest cost of operation under the most unfavorable conditions. It is obtained by the maximum value recorded in the historical cost data, for example, by calculating daily maintenance, personnel expenses and energy consumption, and determining the relevant expenditure records at the time of the highest cost. It is the minimum value of the operating cost within the interval, indicating the lowest cost of operation under optimal conditions. It is obtained by the minimum value recorded in the historical cost data. For example, the data of the period with the lowest maintenance demand is analyzed and the corresponding cost record is extracted as the minimum value.

[0028] For example, setting the parameters , , , , .

[0029] Calculate the minimum return estimate: ; ; Calculate the maximum return estimate: ; ; The results show that the minimum return estimate , the highest estimated return A negative estimate indicates that the cost part of the formula is and The impact on revenue is greater, and the charging standards , and traffic flow The positive contribution to revenue is not enough to cover the cost. The possible reasons are as follows: The charging standard is too low: If the charging standard and The value of is low, while the average value of traffic volume Even within a reasonable range, it still cannot provide enough benefits to offset the high operating costs. High operating costs: Highest operating costs and lowest operating costs The value of may be too high within a specific range, indicating that there is insufficient room for cost reduction under the current operating strategy or environment. Insufficient traffic volume: If the value of is small, it means that the vehicle throughput is limited, so even if the charging standard is moderate, it is difficult to generate sufficient revenue. When the minimum revenue estimate is positive, it means that revenue can still be obtained under the most unfavorable conditions, which shows that the operation of the entire interval has a high stability. The trend of changes in related parameters can be observed to ensure that positive revenue can be maintained in the future. When the maximum revenue estimate is positive, it means that the interval operation has a certain profitability.

[0030] S313: gradually comparing and summarizing the lowest estimated value and the highest estimated value data according to the charging standard range, vehicle flow and operating cost range of each section and the section number to obtain highway section revenue section characteristic data; The calculated minimum and maximum values ​​of the highway section revenue distribution in each interval are summarized and processed. According to the sorting standard of the interval traffic proportion, the minimum and maximum revenue values ​​corresponding to each interval are recorded in a summary table in a unified format. At the same time, the minimum and maximum values ​​of each interval are marked to ensure that the content of the data table is clear and traceable. The correspondence between the interval traffic proportion and the revenue data is further checked to ensure the consistency of all summarized data in interval division and content annotation. The generated revenue interval characteristic data is organized into a table according to the interval number, including the interval number, charging standard range, traffic flow average, operating cost range and the corresponding minimum and maximum revenue values, forming a complete set of revenue interval characteristic data. By comparing the highest and lowest values ​​in the interval revenue characteristic data, the characteristic differences between intervals are further analyzed to identify which intervals have higher revenue potential.

[0031] See also Figure 6 , the steps for obtaining the total revenue contribution of a highway section in the corresponding interval are as follows: S321: Based on the highway section revenue interval characteristic data, the formula is: ; Calculate the total revenue of the highway section in all intervals , get the total revenue accumulation result; in, Is the interval The revenue value of is the total number of intervals, a positive integer, indicating the number of intervals the entire highway is divided into. The specific number is determined by the highway section division rules.

[0032] For example, a highway is divided into five sections, and the revenue values ​​of each section are: , , , , ,but: ; ; The result shows that the current overall highway revenue is negative, with a loss of 150 units of currency value.

[0033] S322: Based on the cumulative total revenue result, analyze the positive and negative contributions of the revenue value of each interval, respectively accumulate the positive and negative parts of the revenue and perform classified statistics, and establish the revenue contribution distribution result of each interval by comparing the proportional relationship between the positive and negative revenues; By analyzing the estimated profit of each interval, the positive and negative parts of the interval profit are extracted respectively. First, each interval number is associated with its corresponding profit value, sorted by the size of profit contribution, and the intervals of the positive part are accumulated to determine its positive contribution to the total profit. At the same time, the intervals of the negative part are accumulated to evaluate its negative impact on the total profit. By comparing the contribution ratio of positive and negative profits, the intervals with better or worse profit performance are determined in combination with the interval number. Finally, based on the interval number, the positive and negative profit contributions are classified and organized into the profit contribution distribution results of each interval.

[0034] See also Figure 7 ,The specific steps for obtaining the highway revenue distribution prediction results are as follows: S411: Based on the revenue contribution distribution results of each interval, the formula is: ; Calculate total return in future periods , get the cumulative result of future total income; in, Is the interval within the current period The total revenue value, Is the interval within the current period The traffic volume is measured in units of vehicles, obtained through real-time data collected by traffic flow monitoring equipment, such as the total number of vehicles passing through the section by time period. is the interval in the future period The traffic volume is expressed in number of vehicles, where represents the next period of the forecast (for example, if If is the current quarter, For the next quarter), it is derived through a prediction model based on historical data, such as combining linear regression analysis to analyze the traffic flow trend in the past three months to predict future traffic flow. Representation interval The growth ratio of future traffic flow compared to the current period is used to reflect the change in traffic flow in the future period. It is calculated based on the traffic flow forecast value and the current traffic flow. Is the interval The charging standard for the future time period, in currency / car, where Indicates the next predicted time period. The peak charging standard is adjusted dynamically through historical charging standard adjustment data and future pricing strategy acquisition. For example, the peak charging standard may increase by 10% according to the adjustment strategy. Is the interval The operating cost for the future period, expressed as a monetary value, where It indicates the next period of time predicted, which is obtained by calculating the future maintenance expenditure, energy consumption and employee salary estimates. For example, the estimated value is adjusted based on the maintenance cost change trend in the past year. is the total number of intervals, determined by the division rule (e.g. by kilometers or stations).

[0035] S412: based on the cumulative result of the total future revenue, extract the revenue contribution value of each interval, combine the revenue benchmark of each interval in all the data, analyze the revenue growth trend of each interval, and obtain the highway revenue distribution prediction result; The future income distribution of each interval is classified according to the interval number. By extracting the income value of each interval, the contribution of each interval to the future income is specifically sorted out. For example, the first interval contributes 30 currency units, the second interval contributes 16 currency units, and the third interval contributes 87.5 currency units. Then, the positive part of all interval income is accumulated to form the positive trend data of the overall income. Further combined with the interval income value of the corresponding period in the historical data, the growth rate of the future income of each interval is analyzed. The income trend is determined by calculating the ratio of the future income value to the historical benchmark value. For example, if the historical benchmark income of the first interval is 25 currency units, the growth rate is , that is, a 20% increase. The results of similar calculations are organized into an interval revenue trend table. Finally, through the statistics of the positive and negative contribution ratios of each interval, the future revenue distribution forecast results of the highway are comprehensively generated.

[0036] A highway economic benefit distribution prediction system, which is used to execute the above-mentioned highway economic benefit distribution prediction method, and the system includes: The data classification module extracts the variable values ​​corresponding to each highway section based on the associated data of the highway, divides these variables into multiple intervals according to the data characteristics, and screens the variable combinations that meet the density distribution conditions to generate the variable density ranking results; The variable weighting module assigns weights to the identified variable groups based on the variable density ranking results to generate weighted variable combination data for the highway section; The interval revenue calculation module calculates the minimum and maximum estimated values ​​of the highway section revenue in each interval based on the weighted variable combination data of the highway section and the weight information in the interval, and generates highway section revenue interval characteristic data; The revenue accumulation module obtains the total revenue value of all highway sections in the corresponding interval based on the highway section revenue interval characteristic data, and classifies and counts the interval contribution values ​​to generate total revenue contribution data; The revenue distribution prediction module is based on the total revenue contribution data and combines the historical revenue change data of each interval to analyze the future revenue growth trend of each interval and generate the highway revenue distribution prediction results.

[0037] The above are only preferred embodiments of the present invention and are not intended to limit the present invention in other forms. Any technician familiar with the profession may use the technical contents disclosed above to change or modify them into equivalent embodiments with equivalent changes and apply them to other fields. However, any simple modification, equivalent change and modification made to the above embodiments based on the technical essence of the present invention without departing from the technical solution of the present invention still falls within the protection scope of the technical solution of the present invention.

Claims

1. A method for predicting the distribution of economic benefits of expressways, characterized in that: The following steps are involved: Collect highway-related data, classify the variable values ​​corresponding to each highway section and divide them into corresponding intervals, calculate the density of the numerical distribution of the variables in the interval, sort the data of each highway section according to the density results and select the variable combinations that match the density intervals to generate the variable density sorting results; Based on the variable density ranking result, weights are assigned to the identified variable groups, and weighted combinations are performed according to the variable data after weight assignment to generate weighted variable combination data of the highway section; Combined with the weight information in the weighted variable combination data of the highway section, according to the minimum and maximum values ​​of the revenue values ​​in the corresponding interval, respectively calculate the minimum estimated value and the maximum estimated value of the highway section revenue in each interval, summarize and organize the calculation results by interval, and generate highway section revenue interval characteristic data; Based on the highway section revenue interval estimation data, the revenue estimation value of each highway section is accumulated by interval to obtain the total revenue contribution of the highway section in the corresponding interval, and the overall revenue is analyzed for future time period trends by interval to generate a highway revenue distribution prediction result.

2. The highway economic benefit distribution prediction method according to claim 1 is characterized in that: The steps for obtaining the density of the numerical distribution of the variables within the calculation interval are specifically as follows: Based on the traffic volume data, charging standard data and operation cost data of the expressway, by extracting the numerical information corresponding to each road section, classifying the traffic volume by vehicle type, sorting the road section charging standard and checking the cost data, the data is divided and classified into intervals to obtain the expressway information table; Based on the highway information table, the formula is adopted: ； Calculate the current interval The variable density value of , get the density information of the numerical distribution; in, Is the interval The frequency or number of occurrences of the internal variable, is the total number of samples of the target variable in all intervals, is the current interval width.

3. The method for predicting the distribution of economic benefits of expressways according to claim 2, characterized in that: The steps for obtaining the variable density ranking result are specifically as follows: Based on the density information of the numerical distribution, the density values ​​of all highway sections are compared, the density value of each section is extracted and arranged in order, the sorting results are segmented and marked, and a density sorting data table is generated; Based on the density sorting data table, data of intervals and corresponding sections whose density values ​​exceed a preset density screening threshold are extracted, and variable density sorting results are generated by screening qualified intervals and variable combinations and re-associating variable data groups.

4. The method for predicting the distribution of economic benefits of expressways according to claim 3, characterized in that: The steps for obtaining the weighted variable combination data of the highway section are specifically as follows: Based on the variable density ranking results, the variable data is grouped and sorted, the impact of the variables on the revenue is analyzed, and weights are assigned according to the importance of traffic volume, charging standards and operating costs to generate a weight distribution list; Based on the weight allocation list, the traffic volume, charging standard and operation cost data of each road section are weighted and combined according to the weights to generate weighted variable combination data of the highway section.

5. The method for predicting the distribution of economic benefits of expressways according to claim 4, characterized in that: The steps for obtaining the highway section revenue interval characteristic data are specifically as follows: Based on the weighted variable combination data of the highway section, the vehicle flow, charging standard and operating cost data in the weighted variable combination data are sorted according to the weight distribution, and the minimum and maximum values ​​in each corresponding interval are marked to obtain the revenue distribution range data in the interval; Based on the income distribution range data within the interval, the formula is used: ； ； Calculate the minimum return estimate separately and the highest revenue estimate , get the minimum and maximum estimated values; in, is the minimum value of the charging standard within the range. is the maximum value of the charging standard within the range. is the average traffic volume in the interval, is the maximum value of the operating cost within the interval, is the minimum value of the operating cost within the interval; The minimum estimated value and the maximum estimated value data are gradually compared and summarized according to the charging standard range, traffic volume and operating cost range of each interval, combined with the interval number, to obtain the highway section revenue interval characteristic data.

6. The highway economic benefit distribution prediction method according to claim 5 is characterized in that: The steps for obtaining the total revenue contribution of the highway section in the corresponding interval are specifically as follows: Based on the characteristic data of the revenue interval of the highway section, the formula is adopted: ； Calculate the total revenue of the highway segment in all intervals , get the total revenue accumulation result; in, Is the interval The revenue value, is the total number of intervals; Based on the cumulative results of the total revenue, the positive and negative contributions of the revenue value of each interval are analyzed, the positive and negative parts of the revenue are accumulated and classified and counted respectively, and the revenue contribution distribution results of each interval are established by comparing the proportional relationship between the positive and negative revenues.

7. The method for predicting the distribution of economic benefits of expressways according to claim 6, characterized in that: The steps for obtaining the highway revenue distribution prediction result are specifically as follows: Based on the revenue contribution distribution results of each interval, the formula is adopted: ； Calculate total return in future periods , get the cumulative result of future total income; in, Is the interval within the current period The total revenue value, Is the interval within the current period of traffic volume, is the interval in the future period of traffic volume, represents the next period of forecast, Representation interval The growth rate of future traffic volume compared to the current period, Is the interval The charging standards for future periods, Is the interval The operating costs for future periods, is the total number of intervals; Based on the cumulative results of the future total revenue, the revenue contribution value of each interval is extracted, and combined with the revenue benchmark of each interval in all the data, the revenue growth trend of each interval is analyzed to obtain the highway revenue distribution prediction result.

8. A highway economic benefit distribution prediction system, characterized in that: According to the method for predicting the distribution of economic benefits of expressways according to any one of claims 1 to 7, the system comprises: The data classification module extracts the variable values ​​corresponding to each highway section based on the associated data of the highway, divides these variables into multiple intervals according to the data characteristics, and screens the variable combinations that meet the density distribution conditions to generate the variable density ranking results; The variable weighting module assigns weights to the identified variable groups based on the variable density ranking results to generate weighted variable combination data for the highway section; The interval revenue calculation module calculates the minimum estimated value and the maximum estimated value of the highway section revenue in each interval based on the weighted variable combination data of the highway section and the weight information in the interval, and generates highway section revenue interval characteristic data; The revenue accumulation module obtains the total revenue value of all highway sections in the corresponding interval based on the highway section revenue interval characteristic data, and classifies and counts the interval contribution values ​​to generate total revenue contribution data; The revenue distribution prediction module analyzes the future revenue growth trend of each interval based on the total revenue contribution data and all the revenue change data of each interval to generate a highway revenue distribution prediction result.

Images