CN114495501B - Road safety analysis method based on combined geographic autoregressive matching - Google Patents

Road safety analysis method based on combined geographic autoregressive matching Download PDF

Info

Publication number
CN114495501B
CN114495501B CN202210100208.5A CN202210100208A CN114495501B CN 114495501 B CN114495501 B CN 114495501B CN 202210100208 A CN202210100208 A CN 202210100208A CN 114495501 B CN114495501 B CN 114495501B
Authority
CN
China
Prior art keywords
target road
road
safety
target
optimized
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202210100208.5A
Other languages
Chinese (zh)
Other versions
CN114495501A (en
Inventor
郭延永
许轩畅
丁红亮
刘攀
刘佩
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southeast University
Original Assignee
Southeast University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southeast University filed Critical Southeast University
Priority to CN202210100208.5A priority Critical patent/CN114495501B/en
Publication of CN114495501A publication Critical patent/CN114495501A/en
Application granted granted Critical
Publication of CN114495501B publication Critical patent/CN114495501B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/29—Geographical information databases
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
    • G06F17/10—Complex mathematical operations
    • G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services
    • G06Q50/265—Personal security, identity or safety
    • G—PHYSICS
    • G08—SIGNALLING
    • G08G—TRAFFIC CONTROL SYSTEMS
    • G08G1/00—Traffic control systems for road vehicles
    • G08G1/01—Detecting movement of traffic to be counted or controlled
    • G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
    • G08G1/0125—Traffic data processing
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
    • Y02T10/00—Road transport of goods or passengers
    • Y02T10/10—Internal combustion engine [ICE] based vehicles
    • Y02T10/40—Engine management systems

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Business, Economics & Management (AREA)
  • Theoretical Computer Science (AREA)
  • Data Mining & Analysis (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • Databases & Information Systems (AREA)
  • Human Resources & Organizations (AREA)
  • Chemical & Material Sciences (AREA)
  • Mathematical Optimization (AREA)
  • Operations Research (AREA)
  • Mathematical Analysis (AREA)
  • Pure & Applied Mathematics (AREA)
  • Development Economics (AREA)
  • Mathematical Physics (AREA)
  • Computational Mathematics (AREA)
  • Marketing (AREA)
  • General Engineering & Computer Science (AREA)
  • General Business, Economics & Management (AREA)
  • Analytical Chemistry (AREA)
  • Evolutionary Biology (AREA)
  • Software Systems (AREA)
  • Game Theory and Decision Science (AREA)
  • Algebra (AREA)
  • Probability & Statistics with Applications (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Quality & Reliability (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Computer Security & Cryptography (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Remote Sensing (AREA)
  • Traffic Control Systems (AREA)

Abstract

本发明公开了一种基于组合地理自回归匹配的道路安全分析方法，涉及道路交通安全技术领域，本发明通过采集目标区域上对应各个目标道路的道路信息，各目标道路进行交通事故数量的预测并修正预测结果，利用预测结果对各个目标道路进行道路安全分析，获得各个待优化目标道路的安全优化条件，消除相同目标区域内各个目标道路之间的安全影响，对待优化目标道路进行安全优化。通过本发明的技术方案，能够有效提升交通道路的安全性。

Figure 202210100208

The invention discloses a road safety analysis method based on combined geographic autoregressive matching, and relates to the technical field of road traffic safety. The invention collects road information corresponding to each target road in a target area, and predicts the number of traffic accidents on each target road Correct the prediction results, use the prediction results to analyze the road safety of each target road, obtain the safety optimization conditions of each target road to be optimized, eliminate the safety impact between each target road in the same target area, and optimize the safety of the target road to be optimized. Through the technical solution of the invention, the safety of traffic roads can be effectively improved.

Figure 202210100208

Description

一种基于组合地理自回归匹配的道路安全分析方法A road safety analysis method based on combined geographic autoregressive matching

技术领域technical field

本发明涉及道路交通安全技术领域，具体而言涉及一种基于组合地理自回归匹配的道路安全分析方法。The invention relates to the technical field of road traffic safety, in particular to a road safety analysis method based on combined geographic autoregressive matching.

背景技术Background technique

随着社会经济发展，社会汽车保有量持续上升，与此同时，道路安全等问题也随之产生。为了提高道路安全，交通安全管理政策在许多国家与地区开始实施。与此同时，交通安全管理政策实施后的效果也成为了相关领域的研究热点。其中倾向得分方法成为了研究道路安全管理政策与道路安全因果关系的有效技术手段，该方法的有效性得到了很多研究的认证。但是道路交通系统是一个空间网络结构，相邻交通小区之间是相互制约相互影响的，即在没有任何外界条件的影响下，相邻小区的属性也会导致临近小区产生相应的交通事故，该现象称为地理空间相关性。然而倾向得分方法并没有考虑到该问题的限制在进行因果分析中，从而导致分析结果产生一定的偏差，影响政策的有效性判断。With the development of society and economy, the number of cars in the society continues to rise, and at the same time, problems such as road safety also arise. In order to improve road safety, traffic safety management policies have been implemented in many countries and regions. At the same time, the effect of traffic safety management policy after implementation has also become a research hotspot in related fields. Among them, the propensity score method has become an effective technical means to study the causal relationship between road safety management policies and road safety, and the effectiveness of this method has been certified by many studies. However, the road traffic system is a spatial network structure, and the adjacent traffic areas are mutually restricted and influenced each other, that is, without the influence of any external conditions, the attributes of the adjacent areas will also cause corresponding traffic accidents in the adjacent areas. The phenomenon is called geospatial correlation. However, the propensity score method does not take into account the limitation of this problem in the causal analysis, which leads to certain deviations in the analysis results and affects the judgment of the effectiveness of the policy.

发明内容Contents of the invention

本发明的目的在于提供一种基于组合地理自回归匹配的道路安全分析方法，以解决现有技术中的问题。The purpose of the present invention is to provide a road safety analysis method based on combined geographic autoregressive matching to solve the problems in the prior art.

为实现上述目的，本发明提供如下技术方案：To achieve the above object, the present invention provides the following technical solutions:

一种基于组合地理自回归匹配的道路安全分析方法，基于预设时间周期内所采集的目标区域内各个目标道路的道路信息，对目标区域内各个待优化目标道路进行道路安全分析，获得各个待优化目标道路的安全优化条件，利用安全优化条件，对待优化目标道路进行安全优化，包括以下步骤：A road safety analysis method based on combined geographic autoregressive matching. Based on the road information of each target road in the target area collected within a preset time period, road safety analysis is performed on each target road to be optimized in the target area, and each target road to be optimized is obtained. Optimizing the safety optimization conditions of the target road, using the safety optimization conditions to optimize the safety of the target road to be optimized, including the following steps:

步骤A、在预设时间周期内获取目标区域中各个目标道路的道路信息、以及各个目标道路交通事故发生数量，随后进入步骤B；Step A, obtaining the road information of each target road in the target area and the number of traffic accidents on each target road within a preset time period, and then proceeding to step B;

步骤B、分别针对各个目标道路，基于其所对应的道路信息，提取该目标道路对应的包含交通事故影响因素特征的预设各类型特征的特征值，基于所提取的交通事故影响因素特征对该目标道路进行预处理，预测得到该目标道路对应当前时间周期向未来时间方向的预设时间周期内的交通事故预测数量，随后进入步骤C；Step B. For each target road, based on its corresponding road information, extract the eigenvalues of the preset various types of features corresponding to the target road including the characteristics of traffic accident influencing factors, and based on the extracted characteristics of traffic accident influencing factors. The target road is preprocessed, and the predicted number of traffic accidents in the preset time period corresponding to the current time period to the future time direction of the target road is predicted, and then enters step C;

步骤C、针对各个目标道路，基于各个目标道路的道路信息，计算并得到各个目标道路的安全系数，基于各目标道路分别所对应的安全系数，将各目标道路划分为优化目标道路和待优化目标道路，对该目标区域内的各个优化目标道路和各个待优化目标道路依次进行安全系数匹配，获得安全匹配组，即获得该目标区域对应的各个安全匹配组，随后进入步骤D；Step C. For each target road, calculate and obtain the safety factor of each target road based on the road information of each target road, and divide each target road into an optimized target road and a target to be optimized based on the corresponding safety factors of each target road roads, each optimized target road and each to-be-optimized target road in the target area are sequentially matched with safety coefficients to obtain a safety matching group, that is, to obtain each safety matching group corresponding to the target area, and then enter step D;

步骤D、分别针对各个安全匹配组，计算该安全匹配组所对应的待优化目标道路与优化目标道路之间的安全差距，进一步根据安全系数，获取影响各目标道路安全系数的影响因素，基于该安全匹配组内对应优化目标道路的道路信息、以及该优化目标道路所对应安全系数的影响因素，对待优化目标道路进行安全优化。Step D. For each safety matching group, calculate the safety gap between the target road to be optimized and the optimized target road corresponding to the safety matching group, and further obtain the influencing factors that affect the safety factor of each target road according to the safety factor. Based on the The road information corresponding to the optimized target road in the safety matching group and the influencing factors of the safety coefficient corresponding to the optimized target road are used for safety optimization of the target road to be optimized.

进一步地，前述的道路信息包括目标道路的人流密度D，目标道路的经济水平GDP，目标道路的日交通平均交通量Q、目标道路的道路网密度L，目标道路的公交站点密度B，目标道路的轨道站点密度R，目标道路的交通节点密度S。Further, the aforementioned road information includes the crowd density D of the target road, the economic level GDP of the target road, the average daily traffic volume Q of the target road, the road network density L of the target road, the bus station density B of the target road, the target road The track site density R of the target road, the traffic node density S of the target road.

进一步地，前述的步骤B中，对目标道路进行预处理，根据以下公式：Further, in the aforementioned step B, the target road is preprocessed according to the following formula:

Figure BDA0003492078480000021
Figure BDA0003492078480000021

计算并获得目标道路i的交通事故预测数量，xi为目标道路i对应的交通事故影响因素，βi为该目标道路i的交通事故预测数量对应的回归系数，εi为该目标道路i的交通事故预测数量对应的误差项，

Figure BDA0003492078480000022
表示回归系数βi服从正态分布，基于该目标道路i的交通事故发生数量对所获交通事故预测数量进行修正，获得交通事故修正数量N′i，N′i＝N″i-Ni，其中N″i为交通事故发生数量。Calculate and obtain the predicted number of traffic accidents on the target road i, x i is the traffic accident influencing factor corresponding to the target road i, β i is the regression coefficient corresponding to the predicted number of traffic accidents on the target road i, ε i is the The error term corresponding to the number of traffic accident predictions,
Figure BDA0003492078480000022
Indicates that the regression coefficient β i obeys the normal distribution, based on the number of traffic accidents on the target road i, the predicted number of traffic accidents is corrected to obtain the corrected number of traffic accidents N′ i , N′ i = N″ i -N i , Among them, N″ i is the number of traffic accidents.

进一步地，前述的步骤C中，根据以下公式：Further, in the aforementioned step C, according to the following formula:

Figure BDA0003492078480000023
Figure BDA0003492078480000023

计算目标区域内目标道路i的安全系数pn，其中，

Figure BDA0003492078480000024
为常数系数，μ1-μ7为各类型道路信息分别所对应的回归系数。Calculate the safety factor p n of the target road i in the target area, where,
Figure BDA0003492078480000024
is a constant coefficient, and μ 1 -μ 7 are regression coefficients corresponding to each type of road information.

进一步地，前述的步骤C中，基于目标区域内各个目标道路分别所对应的安全系数，对个优化目标道路和各待优化目标道路依次进行安全系数匹配，即当优化目标道路的安全系数与待优化目标道路的安全系数差最小时，该优化目标道路与该待优化目标道路为安全匹配组。Further, in the aforementioned step C, based on the safety factors corresponding to each target road in the target area, the safety factors of each optimized target road and each to-be-optimized target road are sequentially matched, that is, when the safety factor of the optimized target road is equal to When the safety coefficient difference of the optimized target road is the smallest, the optimized target road and the target road to be optimized are a safety matching group.

进一步地，前述的步骤D中，根据以下公式：Further, in the aforementioned step D, according to the following formula:

Figure BDA0003492078480000031
Figure BDA0003492078480000031

计算并获得目标区域内安全匹配组I中优化目标道路与优化目标道路之间的安全差距ATT，其中，n为该目标区域内所含目标道路的数量，N′iS为该安全匹配组中优化目标道路对应的交通事故修正系数，N′iK为该安全匹配组中待优化目标道路的交通事故修正系数。Calculate and obtain the safety gap ATT between the optimized target road and the optimized target road in the safety matching group I in the target area, where n is the number of target roads contained in the target area, and N′ iS is the optimal road in the safety matching group The traffic accident correction coefficient corresponding to the target road, N′ iK is the traffic accident correction coefficient of the target road to be optimized in the safety matching group.

本发明所述一种基于组合地理自回归匹配的道路安全分析方法，采用以上技术方案与现有技术相比，具有以下技术效果：根据本发明技术方案通过对交通事故数量进行预测，并对预测结果进行修正，使用地理自回归模型消除地理空间影响，能够较为准确的判断交通安全对道路安全事故的影响因素与影响效果，根据所获修正结果，对目标道路进行安全优化，消除因为目标区域内不同道路之前因为自身地理因素互相影响道路安全的问题，有效提升目标道路的安全性。A road safety analysis method based on combined geographic autoregressive matching according to the present invention, compared with the prior art by adopting the above technical scheme, has the following technical effects: according to the technical scheme of the present invention, the number of traffic accidents is predicted, and the predicted The results are corrected, and the geographical autoregressive model is used to eliminate the influence of geographical space, which can accurately determine the influence factors and effects of traffic safety on road safety accidents. The problem that different roads affect road safety due to their own geographical factors can effectively improve the safety of the target road.

附图说明Description of drawings

图1为本发明示例性实施例的一种道路安全分析方法的流程示意图。Fig. 1 is a schematic flowchart of a road safety analysis method according to an exemplary embodiment of the present invention.

具体实施方式Detailed ways

为了更了解本发明的技术内容，特举具体实施例并配合所附图式说明如下。In order to better understand the technical content of the present invention, specific embodiments are given together with the attached drawings for description as follows.

在本公开中参照附图来描述本发明的各方面，附图中示出了许多说明的实施例。本公开的实施例不必定义在包括本发明的所有方面。应当理解，上面介绍的多种构思和实施例，以及下面更加详细地描述的那些构思和实施方式可以以很多方式中任意一种来实施，这是因为本发明所公开的构思和实施例并不限于任何实施方式。另外，本发明公开的一些方面可以单独使用，或者与本发明公开的其他方面的任何适当组合来使用。Aspects of the invention are described in this disclosure with reference to the accompanying drawings, which show a number of illustrated embodiments. Embodiments of the present disclosure are not necessarily defined to include all aspects of the present invention. It should be appreciated that the various concepts and embodiments described above, as well as those described in more detail below, can be implemented in any of numerous ways, since the concepts and embodiments disclosed herein are not limited to any implementation. In addition, some aspects of the present disclosure may be used alone or in any suitable combination with other aspects of the present disclosure.

结合图1，本发明示例性提出一种基于组合地理自回归匹配的道路安全分析方法，基于预设时间周期内所采集的目标区域上对应各个目标道路的道路信息，道路信息包括目标道路的人流密度D，目标道路的经济水平GDP，目标道路的日交通平均交通量Q、目标道路的道路网密度L，目标道路的公交站点密度B，目标道路的轨道站点密度R，目标道路的交通节点密度S，对各个目标道路进行道路安全分析，获得各个待优化目标道路的安全优化条件，对待优化目标道路进行安全优化，包括以下步骤：In conjunction with Figure 1, the present invention exemplarily proposes a road safety analysis method based on combined geographic autoregressive matching, based on the road information corresponding to each target road in the target area collected within a preset time period, and the road information includes the flow of people on the target road Density D, economic level GDP of the target road, average daily traffic volume Q of the target road, road network density L of the target road, bus stop density B of the target road, track site density R of the target road, traffic node density of the target road S, carry out road safety analysis on each target road, obtain the safety optimization conditions of each target road to be optimized, and perform safety optimization on the target road to be optimized, including the following steps:

步骤A、获取目标区域在预设时间周期内对应各个目标道路的道路信息、以及各个目标道路交通事故发生数量，随后进入步骤B。Step A, obtain the road information corresponding to each target road in the target area within a preset time period, and the number of traffic accidents on each target road, and then enter step B.

步骤B、分别针对各个目标道路，基于目标道路所对应的道路信息，提取该目标道路对应的包含交通事故影响因素特征的预设各类型特征的特征值，基于交通事故影响因素对目标道路进行预处理，根据以下公式：Step B. For each target road, based on the road information corresponding to the target road, extract the eigenvalues of the preset various types of features corresponding to the target road including the characteristics of traffic accident influencing factors, and predict the target road based on the traffic accident influencing factors. processed according to the following formula:

Figure BDA0003492078480000041
Figure BDA0003492078480000041

计算并获得目标道路i对应当前时间点向未来时间方向的预设时间周期内的交通事故预测数量，xi为目标道路i对应的交通事故影响因素，βi为该目标道路i的交通事故预测数量对应的回归系数，εi为该目标道路i的交通事故预测数量对应的误差项，

Figure BDA0003492078480000042
为地理回归系数遵循正态分布
Figure BDA0003492078480000043
计算公式如下，Calculate and obtain the predicted number of traffic accidents corresponding to the target road i in the preset time period from the current time point to the future time direction, x i is the traffic accident influencing factor corresponding to the target road i, and β i is the traffic accident prediction of the target road i The regression coefficient corresponding to the number, ε i is the error term corresponding to the predicted number of traffic accidents on the target road i,
Figure BDA0003492078480000042
Follow a normal distribution for the geographic regression coefficients
Figure BDA0003492078480000043
Calculated as follows,

Figure BDA0003492078480000044
Figure BDA0003492078480000044

其中wki取值为1时为该目标区域内目标道路k与目标道路i相邻，反之wki的取值为0，基于该目标道路i的交通事故发生数量对所获交通事故预测数量进行修正，获得交通事故修正数量N′i，N′i＝N″i-Ni，其中N″i为交通事故发生数量，随后进入步骤C。Where w ki takes a value of 1, it means that the target road k in the target area is adjacent to the target road i, otherwise, w ki takes a value of 0, and the number of traffic accidents obtained based on the number of traffic accidents on the target road i is calculated. Correction, obtaining the corrected number of traffic accidents N′ i , N′ i =N″ i −N i , where N″ i is the number of traffic accidents, and then enter step C.

步骤C、基于各个目标道路的道路信息，根据以下公式：Step C, based on the road information of each target road, according to the following formula:

Figure BDA0003492078480000045
Figure BDA0003492078480000045

计算目标区域内目标道路i的安全系数pn，其中，

Figure BDA0003492078480000046
为常数系数，μ1-μ7为各类型道路信息分别所对应的回归系数，并将该目标区域内的安全系数大于预设阈值的目标道路划分为优化目标道路，将安全系数小于预设阈值的目标道路划分为待优化目标道路，Calculate the safety factor p n of the target road i in the target area, where,
Figure BDA0003492078480000046
is a constant coefficient, μ 1 -μ 7 are regression coefficients corresponding to various types of road information, and the target roads with safety factors greater than the preset threshold in the target area are divided into optimization target roads, and the safety factor is smaller than the preset threshold The target road of is divided into the target road to be optimized,

根据优化目标道路和待优化目标道路分别所对应的安全系数，提取影响目标道路安全系数的影响因素，对该目标区域内的优化目标道路和待优化目标道路进行安全系数匹配，当优化目标道路的安全系数与待优化目标道路的安全系数差最小时，该优化目标道路与该待优化目标道路为安全匹配组，即获得该目标区域对应的各个安全匹配组，随后进入步骤D。According to the safety factors corresponding to the optimized target road and the target road to be optimized, the influencing factors that affect the target road safety factor are extracted, and the safety factors are matched between the optimized target road and the target road to be optimized in the target area. When the safety factor difference between the safety factor and the target road to be optimized is the smallest, the optimized target road and the target road to be optimized are a safety matching group, that is, each safety matching group corresponding to the target area is obtained, and then step D is entered.

步骤D、分别针对各个安全匹配组，据以下公式：Step D, for each security matching group, according to the following formula:

Figure BDA0003492078480000047
Figure BDA0003492078480000047

计算并获得目标区域内安全匹配组I中优化目标道路与优化目标道路之间的安全差距ATT，其中，n为该目标区域内所含目标道路的数量，N′iS为该安全匹配组中优化目标道路对应的交通事故修正系数，N′iK为该安全匹配组中待优化目标道路的交通事故修正系数，基于该安全匹配组内对应优化目标道路的道路信息、以及安全系数的影响因素，对待优化目标道路进行安全优化。Calculate and obtain the safety gap ATT between the optimized target road and the optimized target road in the safety matching group I in the target area, where n is the number of target roads contained in the target area, and N′ iS is the optimal road in the safety matching group The traffic accident correction coefficient corresponding to the target road, N′ iK is the traffic accident correction coefficient of the target road to be optimized in the safety matching group, based on the road information corresponding to the optimized target road in the safety matching group and the influencing factors of the safety factor, treat Optimize the target road for safety optimization.

实施例：Example:

采集目标区域内各个目标道路的道路信息，如表1-1所示：Collect the road information of each target road in the target area, as shown in Table 1-1:

表1-1样本数据采集统计表Table 1-1 Statistical table of sample data collection

Figure BDA0003492078480000051
Figure BDA0003492078480000051

基于步骤B中过程，通过以下公式：Based on the process in step B, by the following formula:

Figure BDA0003492078480000052
Figure BDA0003492078480000052

Figure BDA0003492078480000053
Figure BDA0003492078480000053

N′A1＝N″A1-NA1 N′ A1 ＝N″ A1 -N A1

依次获得交通事故预测数量、交通事故修正数量消除地理空间影响条件下的事故数量，该地理空间所带来的影响如区域1与区域2相邻互为匹配，在没有安全优化下，区域2的存在会使区域1本身就产生一定数量的事故，假设A1与C1互为安全匹配组，则满足pA1-pC1＝min(pA1-pCi)的条件。Obtain the number of traffic accident predictions and the number of traffic accident corrections in turn, and the number of accidents under the condition of eliminating the influence of geographic space. The impact of this geographic space is such as that area 1 and area 2 are adjacent to each other. Without safety optimization, the number of accidents in area 2 There will be a certain number of accidents in area 1 itself. Assuming that A1 and C1 are mutually safe matching groups, the condition of p A1 -p C1 =min(p A1 -p Ci ) is satisfied.

基于步骤C中过程，以A1为例，计算并获得道路A1的安全系数：Based on the process in step C, taking A1 as an example, calculate and obtain the safety factor of road A1:

Figure BDA0003492078480000061
Figure BDA0003492078480000061

根据步骤D中所描述过程，According to the procedure described in Step D,

Figure BDA0003492078480000062
Figure BDA0003492078480000062

根据所获安全差距，利用优化目标道路的安全影响因素对待优化目标道路进行安全优化。According to the obtained safety gap, the safety influencing factors of the optimized target road are used to optimize the safety of the target road to be optimized.

虽然本发明已以较佳实施例揭露如上，然其并非用以限定本发明。本发明所属技术领域中具有通常知识者，在不脱离本发明的精神和范围内，当可作各种的更动与润饰。因此，本发明的保护范围当视权利要求书所界定者为准。Although the present invention has been disclosed above with preferred embodiments, it is not intended to limit the present invention. Those skilled in the art of the present invention can make various changes and modifications without departing from the spirit and scope of the present invention. Therefore, the scope of protection of the present invention should be defined by the claims.

Claims (1)

1. A road safety analysis method based on combined geographic autoregressive matching is characterized in that road information corresponding to each target road on a target area acquired within a preset time period is based on, the road information comprises pedestrian flow density D of the target road, economic level GDP of the target road, daily traffic average traffic Q of the target road, road network density L of the target road, bus stop density B of the target road, track stop density R of the target road and traffic node density S of the target road, road safety analysis is carried out on each target road, safety optimization conditions of each target road to be optimized are obtained, and safety optimization is carried out on the target road to be optimized, and the road safety analysis method comprises the following steps:
step A, acquiring road information of each target road corresponding to a target area and the number of traffic accidents of each target road in a preset time period, and then entering step B;
b, respectively aiming at each target road, extracting a preset type characteristic value which comprises traffic accident influence factors and corresponds to the target road based on road information corresponding to the target road, preprocessing the target road based on the traffic accident influence factors, and according to the following formula:
Figure FDA0003856314930000011
calculating and obtaining the predicted quantity x of the traffic accidents of the target road i in the preset time period from the current time point to the future time direction i Is the traffic accident influencing factor, beta, corresponding to the target road i i Regression coefficient, epsilon, corresponding to the predicted number of traffic accidents for the target road i i Error terms corresponding to the predicted number of the traffic accidents of the target road i,
Figure FDA0003856314930000012
following a normal distribution for the geographic regression coefficients
Figure FDA0003856314930000013
The calculation formula is as follows,
Figure FDA0003856314930000014
wherein w ki When the value is 1, the target road k in the target area is adjacent to the target road i, otherwise, w ki Is 0, the obtained predicted number of traffic accidents is corrected based on the number of traffic accidents occurring on the target road i, and a corrected number of traffic accidents N 'is obtained' i ，N′ i ＝N″ i -N i Wherein N ″) i C, the number of the traffic accidents is calculated, and then the step C is carried out;
step C, based on the road information of each target road, according to the following formula:
Figure FDA0003856314930000015
calculating safety factor p of target road i in target area n Wherein, in the step (A),
Figure FDA0003856314930000016
is a constant coefficient, mu 1 -μ 7 The regression coefficients corresponding to the road information of each type are respectively, the target road with the safety factor larger than the preset threshold value in the target area is divided into an optimization target road, the target road with the safety factor smaller than the preset threshold value is divided into a target road to be optimized,
according to the safety factors respectively corresponding to the optimized target road and the target road to be optimized, extracting the influence factors influencing the safety factor of the target road, matching the safety factors of the optimized target road and the target road to be optimized in the target area, and when the difference between the safety factor of the optimized target road and the safety factor of the target road to be optimized is minimum, the optimized target road and the target road to be optimized are safety matched groups, namely, each safety matched group corresponding to the target area is obtained, and then the step D is carried out;
and D, aiming at each safety matching group respectively, according to the following formula:
Figure FDA0003856314930000021
calculating and obtaining a safety gap ATT between an optimization target road and an optimization target road in a safety matching group I in a target area, wherein N is the number of target roads contained in the target area, N' iS Optimizing a traffic accident correction coefficient, N ', corresponding to the target road in the safety matching group' iK And performing safety optimization on the target road to be optimized based on the road information of the corresponding optimized target road in the safety matching group and the influence factor of the safety factor for the traffic accident correction coefficient of the target road to be optimized in the safety matching group.
CN202210100208.5A 2022-01-27 2022-01-27 Road safety analysis method based on combined geographic autoregressive matching Active CN114495501B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210100208.5A CN114495501B (en) 2022-01-27 2022-01-27 Road safety analysis method based on combined geographic autoregressive matching

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210100208.5A CN114495501B (en) 2022-01-27 2022-01-27 Road safety analysis method based on combined geographic autoregressive matching

Publications (2)

Publication Number Publication Date
CN114495501A CN114495501A (en) 2022-05-13
CN114495501B true CN114495501B (en) 2022-11-15

Family

ID=81477028

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210100208.5A Active CN114495501B (en) 2022-01-27 2022-01-27 Road safety analysis method based on combined geographic autoregressive matching

Country Status (1)

Country Link
CN (1) CN114495501B (en)

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20140074402A1 (en) * 2012-09-12 2014-03-13 Lexisnexis Risk Solutions Fl Inc. Systems and methods for determining risks associated with driving routes
CN107909247A (en) * 2017-10-26 2018-04-13 东南大学 A kind of city macroscopic view Road Traffic Safety Factors analysis method based on spatial level Bayesian model
CN109448369B (en) * 2018-10-26 2021-08-03 中交第一公路勘察设计研究院有限公司 Real-time operation risk calculation method for expressway
CN112767697B (en) * 2021-01-19 2021-11-30 东南大学 Traffic safety evaluation method, system and device based on traffic conflict prediction

Also Published As

Publication number Publication date
CN114495501A (en) 2022-05-13

Similar Documents

Publication Publication Date Title
CN107610469B (en) Day-dimension area traffic index prediction method considering multi-factor influence
CN112419709B (en) Expressway accident risk real-time prediction method based on road section heterogeneity
WO2019080367A1 (en) Method for evaluating health status of mechanical device
CN108922168B (en) A Meso-Level Accident-prone Road Discrimination Method
CN114881381B (en) Method and system for predicting urban water level based on improved convolutional neural network
CN104464321A (en) Intelligent traffic guidance method based on traffic performance index development trend
US11550937B2 (en) Privacy trustworthiness based API access
CN109598930B (en) Automatic detect overhead closed system
CN116504050B (en) Special event city partitioning method based on multi-mode public transport trip data
CN108681717B (en) Quality detection method for urban traffic video detection equipment
Zhu et al. Investigation on the driver-victim pairs in pedestrian and bicyclist crashes by latent class clustering and random forest algorithm
CN105023044A (en) Traffic flow cause and effect relation excavation method based on large number of time sequences
CN114446064A (en) Method, device, storage medium and terminal for analyzing traffic of expressway service area
CN114495501B (en) Road safety analysis method based on combined geographic autoregressive matching
CN110288826A (en) A clustering method of traffic control sub-regions based on multi-source data fusion and MILP
Zhou et al. Graph-structured sparse optimization for connected subgraph detection
CN109377755B (en) Lane traffic efficiency optimizing grouping device and method
CN113642162A (en) A Comprehensive Analysis Method of Urban Road Traffic Emergency Plan Simulation
CN115204755B (en) Method, device, electronic equipment, and readable storage medium for measuring and calculating service area entry rate
CN114066431B (en) A method for realizing personnel activity graph based on four-dimensional travel model
CN116434543A (en) An early warning method for traffic hazard points based on accident distribution law and accident causes
Liang et al. Optimizing bus stop spacing using the simulated annealing algorithm with spatial interaction coverage model
Liu A spatial data statistical model of urban road traffic accidents.
CN116030627A (en) Road traffic accident analysis method integrating predicted traffic risk variables
KR102645672B1 (en) System and method for real-time pretreatment of building energy consumption to secure high-quality data in BEMS

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant