WO2020192120A1 - 一种基于出行结构的城市路网诱导方案发布方法和系统 - Google Patents

一种基于出行结构的城市路网诱导方案发布方法和系统 Download PDF

Info

Publication number
WO2020192120A1
WO2020192120A1 PCT/CN2019/115057 CN2019115057W WO2020192120A1 WO 2020192120 A1 WO2020192120 A1 WO 2020192120A1 CN 2019115057 W CN2019115057 W CN 2019115057W WO 2020192120 A1 WO2020192120 A1 WO 2020192120A1
Authority
WO
WIPO (PCT)
Prior art keywords
travel
guidance
road
road network
time
Prior art date
Application number
PCT/CN2019/115057
Other languages
English (en)
French (fr)
Inventor
吕伟韬
周东
陈凝
盛旺
Original Assignee
江苏智通交通科技有限公司
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 江苏智通交通科技有限公司 filed Critical 江苏智通交通科技有限公司
Publication of WO2020192120A1 publication Critical patent/WO2020192120A1/zh

Links

Images

Classifications

    • GPHYSICS
    • G08SIGNALLING
    • G08GTRAFFIC CONTROL SYSTEMS
    • G08G1/00Traffic control systems for road vehicles
    • G08G1/01Detecting movement of traffic to be counted or controlled
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/02Services making use of location information
    • H04W4/029Location-based management or tracking services
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04WWIRELESS COMMUNICATION NETWORKS
    • H04W4/00Services specially adapted for wireless communication networks; Facilities therefor
    • H04W4/30Services specially adapted for particular environments, situations or purposes
    • H04W4/40Services specially adapted for particular environments, situations or purposes for vehicles, e.g. vehicle-to-pedestrians [V2P]

Definitions

  • the invention belongs to the technical field of urban road network traffic operation guidance release, and specifically relates to a method and system for issuing urban road network guidance schemes based on a travel structure.
  • traffic guidance issuance is one of the indispensable means of modern intelligent traffic operation and management. It mainly provides urban road network traffic guidance information or instructions for road vehicles, and adjusts the road traffic status through vehicle traffic guidance.
  • the reasonable allocation of demand in the road network is the goal, so as to achieve the purpose of alleviating traffic congestion and facilitating motor vehicle travel; but based on the unpredictability and randomness of traffic operation data, it may lead to the problem of poor traffic guidance release effects, especially real-time Changes in traffic flow require a real-time and effective traffic guidance release method and a corresponding guidance release generation organization to realize an efficient and practical traffic guidance solution.
  • the purpose of the present invention is to propose a method and system for issuing urban road network guidance plan based on travel structure, implement global optimal guidance route search based on real-time traffic flow data, and determine the road network by analyzing the traffic travel structure of the road network
  • the internal guidance plan issuance strategy in order to achieve the effect of the balanced distribution of road network demand, so that travelers can avoid congested road sections and improve the overall traffic efficiency of the road network.
  • a method for issuing an urban road network guidance plan based on a travel structure including:
  • step S1 includes:
  • the spatio-temporal characteristic index includes: trajectory repetition coefficient, daily average number of trips, average daily length of stay in the road network, and departure time similarity; wherein the trajectory point repetition coefficient is used to measure the similarity of the passing trajectory, and the calculation formula for:
  • Track point repetition coefficient number of different track points/number of days of appearance, track points refer to the bayonet recording points in the original historical traffic trajectory, and days of appearance refer to the number of days that a motor vehicle has a travel trajectory;
  • Average number of trips per day total number of trips/number of days of appearance
  • Average daily staying time on the road network total driving time/number of days of appearance, the total driving time is calculated based on the transit time of the complete trajectory corresponding to each motor vehicle;
  • Departure time similarity number of trajectory start time nodes located in different time intervals/number of days of appearance; where, time interval refers to dividing 24 hours a day into several time intervals of equal length, and each interval corresponds to a time interval.
  • the travel mode label includes a rigid demand group and a non-rigid demand group.
  • the rigid demand group is a group of motor vehicles with a specified regularity; and the non-rigid demand group is a group of motor vehicles that do not have a specified regularity. group.
  • step S2 the method for determining the travel mode of each road segment in the travel path set described in step S2 is:
  • step S3 includes: searching for the upstream road section of each congested road section in the congested road section set S according to the road network topology, and setting a threshold K, and calculating the real-time traffic flow and maximum traffic of the upstream road section The capacity ratio v/c, if v/c ⁇ K, the upstream road section is included in the congested road section's influence range set Z s , and the search is further upstream; otherwise, the search is stopped.
  • step S4 generating multiple guidance routes according to the real-time traffic operation conditions of the entire road network and each of the OD points on the travel structure of each component of the travel route set includes:
  • step S5 includes:
  • a travel structure-based urban road network guidance plan publishing system which is applied to the above-mentioned travel structure-based urban road network guidance plan publishing method.
  • the system includes a data access module, a demand structure analysis module, and congestion.
  • Recognition module, inducement path search module, inducement strategy generation module, inducement release module including:
  • the data access module connects the smart bayonet system and the database through a designated interface to obtain the bayonet passing records, dynamically synchronize the real-time passing records of the smart bayonet system, and interact with the database;
  • the demand structure analysis module which retrieves the original historical traffic trajectory from the data access module, is used to reconstruct the trajectory of motor vehicles, analyze the OD point-to-travel path set of the road network, and analyze the OD travel structure and the travel mode of the road section;
  • a congestion identification module which reads real-time synchronization data from the access data access module, is used to identify congested road sections in the road network, generates the congested road section set S, and analyzes the impact range of the congested road sections;
  • the guidance path search module obtains the real-time vehicle passing records of the smart bayonet system from the data access module, obtains the OD travel structure and the travel mode analysis results of the road section from the demand structure analysis module, and receives from the congestion recognition module Into the set of congested road sections; used to calculate the real-time remaining bearing capacity of the road section and the road section travel time; simultaneously generate multiple guidance paths for each of the OD point pairs; and the guidance path search model is set in the guidance path search module ;
  • Guidance strategy generation module from the demand structure analysis module to access the OD point to analyze the results of the travel path set, OD travel structure, and road travel mode, from the congestion identification module to the congested road set and its influence range, and from the guidance path search module Enter the optimal plan, the sub-optimal plan and the remaining bearing capacity of the road section, determine the release location and the content of the optimal guidance plan, the sub-optimal guidance plan, and pass them to the guidance release module;
  • the guidance release module is connected to the guidance strategy generation module and docked with the road guidance screen control card, and is used to publish the guidance plan output position and content of the guidance strategy generation module; transmit the guidance plan to the corresponding control card of the road section, Realize the release of the induction program.
  • the system is composed of a data access module, a demand structure analysis module, a congestion recognition module, a guidance path search module, a guidance strategy generation module, and a guidance release module.
  • the data access module reads the smart bayonet system to obtain the bayonet passing record of the motor vehicle, and dynamically synchronizes the real-time passing record of the smart bayonet system; at the same time, the data access module is also connected to the database and passes through each other Set up the interface for data interaction; the demand structure analysis module will reconstruct the trajectory of the motor vehicle, analyze the OD point of the road network to travel path set, and analyze the OD travel structure and the travel mode of the road section; identify the congestion in the road network by the congestion recognition module Road section, and analyze the impact range of the congested road section according to the congested road section; the guidance path search module calculates the real-time remaining bearing capacity of the road section and the road section travel time, and generates multiple guidance paths corresponding to each OD point pair; the guidance path is generated by the guidance strategy module The search module accesses the optimal plan, the sub-optimal plan and the remaining bearing capacity of the road section, determines the release position and the content of the optimal guide plan, the sub-optimal guide plan, and transmit
  • FIG. 1 is a schematic flowchart of a method for issuing an urban road network guidance plan based on a travel structure in an embodiment of the present invention
  • Fig. 2 is a schematic structural block diagram of the urban road network guidance plan issuing system based on the travel structure in an embodiment of the present invention.
  • a method and system for issuing an urban road network guidance plan based on a travel structure are provided.
  • the method provided by the present invention specifically includes the following steps:
  • Step 1 Obtain the vehicle bayonet passing records of the entire road network within a specified time period, extract the original historical passing trajectory corresponding to each vehicle based on the bayonet passing record, and complete the original historical passing trajectory to obtain a complete history
  • the traffic trajectory, and the travel mode label corresponding to each motor vehicle is obtained according to the complete historical traffic trajectory; specifically, the present invention also needs to determine whether the original historical traffic trajectory corresponding to each motor vehicle is complete in the actual operation process, if not complete , Reconstruction operation is performed through particle swarm algorithm to generate a complete historical traffic trajectory; at the same time, the spatial collection of a complete historical traffic trajectory is carried out for each vehicle one by one, and the historical travel time and space characteristic indexes of the EMU in a specified time period are calculated based on the spatial collection; Then, taking the spatio-temporal characteristic index as the attribute of each motor vehicle, the Gaussian mixture model is used to determine the travel mode label of the motor vehicle for all attributes in the specified time period.
  • the unit of the bayonet passing record in the present invention is recorded in a unit of motor vehicle.
  • the spatio-temporal characteristic indicators include: trajectory repetition coefficient, daily average number of trips, average daily length of stay in the road network, and departure time similarity; wherein the trajectory point repetition coefficient is used to measure the similarity of the passage trajectory, and each time and space
  • the travel mode label includes rigid demand groups and non-rigid demand groups.
  • the travel time and travel space range of motor vehicles have obvious constancy, that is, regularity.
  • this group of motor vehicles constitutes a rigid demand group; on the contrary, the corresponding motor vehicle group constitutes a non-rigid demand group.
  • Step 2 Construct the road network topology, determine the road network OD point pair set C according to the road network topology; determine the travel path set of the OD point pair based on the complete historical traffic trajectory; and determine the travel path according to the travel mode label corresponding to the motor vehicle Collect the travel mode of each component road section; specifically, obtain the traffic demand structure of each OD point pair according to the trajectory space collection and travel mode label corresponding to the vehicle, that is, the ratio of the sample size of the rigid group to the sample size of the non-rigid demand group;
  • the sample size includes the daily average sample size and the average sample size in a short interval.
  • the short interval refers to a number of time intervals divided within 24 hours a day.
  • it can be an equal interval interval, such as 24 hours divided into 24 Equally spaced intervals: [0:00,1:00), [1:00,2:00),...; can also be non-equal spaced intervals: peak hours [6:00,11:00), [16: 30,19:30), flat peak time [0:00,6:00), [11:00,16:30), [19:30,24:00), the specific division can be set according to the actual situation, There are no restrictions and fixes here; then, analyze the daily change of the traffic demand structure of each OD point and the change pattern of each time interval within 24 hours a day; obtain the OD travel structure based on the travel path set, and then calculate the OD point The number of the right rigid demand groups and the number of non-rigid groups are allocated to the composition road sections in the travel route concentration, and the number of rigid demand groups and the number ratio of non-rigid demand groups in each composition road section are calculated, and the number of road sections is determined based on the number ratio. Travel mode, the induced release strategy formulated in this way can be more adapted to the traffic
  • Step 3 Obtain real-time traffic flow data including flow, speed, and headway corresponding to the travel path set, and based on the traffic flow data to correspond to the congested road sections in the travel path set, and generate a congested road section set S and the impact of each congested road section Range set Z s , where s refers to any element in the congested road section set S; specifically search for the upstream road section of each congested road section in the congested road section set S according to the road network topology, and set a threshold K, and calculate the upstream road section
  • the specific traffic flow of each section of the road in the future can be used as a basis for formulating guidance and release strategies for motor vehicles traveling on the road network.
  • Step 4 Construct a globally optimal guidance route search model based on the congested road section set S, and generate multiple guidance routes based on the real-time traffic operation of the entire road network and the travel structure of each component road section of the travel route set of each OD point pair; Among them, the specific steps of generating multiple induction paths for each OD point pair are as follows:
  • the corresponding paths are selected in the effective path set P in turn, and the traffic flow is accumulated for each path Set the cumulative upper limit of traffic flow to 0.9Q ⁇ , if the cumulative value of route traffic flow Then the ending path is selected into the effective path set P, and all paths in the effective path set are determined; then, based on the effective path set
  • Step 5 Determine the guidance release strategy according to the travel structure, and screen the optimal path guidance plan among the multiple guidance paths between OD point pairs; specifically, filter out all OD point pair sets that contain congested road sections in the effective path set P Calculate the corresponding number of rigid demand groups for each OD point pair according to the ratio of the number of rigid demand groups to the number of non-rigid demand groups in the travel structure, and select the OD point pair corresponding to the highest number of rigid demand groups to release the optimal guidance Calculate the number of real-time rigid demand groups and the number of non-rigid demand groups on the road segment according to the travel mode of each road segment in the set Z s of the impact range of the congested road segment; select the remaining number of each road segment For sections with low carrying capacity and a high number of rigid demand groups, the optimal guidance route will be released, and the remaining sections will be issued with the sub-optimal guidance route.
  • the present invention also proposes a travel structure-based urban road network guidance plan publishing system, which is applied to the urban road network guidance plan publishing method based on the travel structure. See Figure 2.
  • the system includes a data access module, a demand structure analysis module, a congestion recognition module, an induction path search module, an induction strategy generation module, and an induction release module; among them, the data access module connects the smart bayonet system and the database through a designated interface for Acquire the bayonet passing record, dynamically synchronize the real-time passing record of the smart bayonet system, and interact with the database;
  • the demand structure analysis module retrieves the original historical passing trajectory from the data access module for checking the vehicle trajectory Reconstruction, road network OD point-to-travel path set analysis, and OD travel structure and travel mode analysis of road sections; congestion recognition module, read real-time synchronization data from the access data access module, used to identify congested road sections in the road network , Generate the set S of congested road sections, and analyze
  • the system is composed of a data access module, a demand structure analysis module, a congestion recognition module, a guidance path search module, a guidance strategy generation module, and a guidance release module.
  • the data access module reads the smart bayonet system to obtain the bayonet passing record of the motor vehicle, and dynamically synchronizes the real-time passing record of the smart bayonet system; at the same time, the data access module is also connected to the database and passes through each other Set up the interface for data interaction; the demand structure analysis module will reconstruct the trajectory of the motor vehicle, analyze the OD point of the road network to travel path set, and analyze the OD travel structure and the travel mode of the road section; identify the congestion in the road network by the congestion recognition module Road section, and analyze the impact range of the congested road section according to the congested road section; the guidance path search module calculates the real-time remaining bearing capacity of the road section and the road section travel time, and generates multiple guidance paths corresponding to each OD point pair; the guidance path is generated by the guidance strategy module The search module accesses the optimal plan, the sub-optimal plan and the remaining bearing capacity of the road section, determines the release position and the content of the optimal guide plan, the sub-optimal guide plan, and transmit

Landscapes

  • Engineering & Computer Science (AREA)
  • Computer Networks & Wireless Communication (AREA)
  • Signal Processing (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Traffic Control Systems (AREA)

Abstract

一种基于出行结构的城市路网诱导方案发布方法和系统,系统包括数据接入模块、需求结构分析模块、诱导路径搜索模块、诱导策略生成模块、诱导发布模块;方法首选通过数据接入模块获取指定时间段内全路网机动车卡口过车记录,并由卡口过车记录获取机动车的出行结构;随后根据出行结构构建路网拓扑结构,得到路网的OD点对集合及对应的出行路径集;然后获取出行路径集的实时交通流量数据,并基于交通流量数据生成拥堵路段集合;同时基于拥堵路段集合构建诱导路径搜索模型,并基于路网的交通运行情况和历史通行轨迹对每一OD点对生成多条诱导路径;最后根据机动车的出行确定最优诱导发布策略和次优诱导发布策略;本系统和方法可提升路网通行效率。

Description

一种基于出行结构的城市路网诱导方案发布方法和系统 技术领域
本发明属于城市路网交通运行诱导发布技术领域,具体涉及一种基于出行结构的城市路网诱导方案发布方法和系统。
背景技术
在城市道路网络中,交通诱导发布是现代化智能交通运行管理必不可少的手段之一,主要面向路面车辆提供城市路网通行引导信息或指令,通过车辆通行的诱导来调整路面交通状态,以交通需求在路网的合理分配为目标,从而达到缓解交通拥堵、方便机动车出行的目的;但是基于交通运行数据的不可预测性和随机性,可能导致交通诱导发布效果不佳的问题,尤其是实时交通流量的变化,因此需要一种实时有效的交通诱导发布方式及对应的诱导发布生成机构来实现高效、实用的交通诱导方案。
发明内容
本发明的目的是提出一种基于出行结构的城市路网诱导方案发布方法和系统,基于实时的交通流数据实施全局最优的诱导路径搜索,并通过对路网交通出行结构的分析确定路网内的诱导方案发布策略,以期达到路网需求均衡分布的效果,使出行者避开拥堵路段,进而提升路网整体通行效率,具体技术方案如下:
一方面,提供一种基于出行结构的城市路网诱导方案发布方法,所述方法包括:
S1、获取指定时间段内全路网机动车卡口过车记录,基于所述卡口过车记录提取对应每一机动车的原始历史通行轨迹,对原始历史通行轨迹进行完整性重构得到完整历史通行轨迹,并根据所述完整历史通行轨迹得到与每一 机动车对应的出行模式标签;
S2、构建路网拓扑结构,根据所述路网拓扑结构确定路网OD点对集合C;并基于所述完整历史通行轨迹确定所述OD点对的出行路径集,并根据机动车对应的出行模式标签确定出行路径集各组成路段的出行模式;
S3、获取与所述出行路径集对应的包含流量、速度、车头时距的实时交通流量数据,基于所述交通流量数据对应所述出行路径集中的拥堵路段,并生成拥堵路段集合S以及所述每一个拥堵路段对应的影响范围集合Z s,其中s指代拥堵路段集合S中的任一个元素;
S4、基于所述拥堵路段集合S构建全局最优的诱导路径搜索模型,并根据全路网实时的交通运行情况及每一所述OD点对所述出行路径集的各组成路段出行结构生成多条诱导路径;
S5、根据所述出行结构确定诱导发布策略,并筛选所述OD点对间的多条诱导路径中的最优路径诱导方案。
进一步的,步骤S1包括:
S11、判断每一机动车对应的所述原始历史通行轨迹是否完整,若不完整,通过粒子群算法进行重构操作,生成完整的通行轨迹;
S12、对每一机动车逐一进行所述完整历史通行轨迹的空间汇集,基于所述空间汇集计算机动车在所述指定时间段内的历史出行时空特征指标;
S13、将所述时空特征指标作为每一机动车的属性,采用高斯混合模型对所述指定时间段内所有所述属性确定机动车的出行模式标签。
进一步的,所述时空特征指标包括:轨迹重复系数、日均出行次数、路网日均逗留时长和出发时刻相似度;其中,所述轨迹点重复系数用于衡量通行轨迹的相似性,计算公式为:
轨迹点重复系数=不同轨迹点数量/出现天数,轨迹点是指所述原始历史通行轨迹中的卡口记录点,出现天数指机动车存在出行轨迹的天数;
日均出行次数=总出行次数/出现天数;
路网日均逗留时长=总行驶时长/出现天数,总行驶时长依据每一机动车对应的完整轨迹的通行时长统计得到;
出发时刻相似度=位于不同时间间隔内的轨迹起始时间节点数量/出现天数;其中,时间间隔是指将一日24小时划分为等长的若干时间区间,每一区间对应一个时间间隔。
进一步的,所述出行模式标签包括刚性需求群体和非刚性需求群体,所述刚性需求群体为具有指定规律性的出行机动车群体;所述非刚性需求群体为不具有指定规律性的出行机动车群体。
进一步的,步骤S2所述的确定出行路径集各组成路段的出行模式方法为:
S21、根据机动车对应的所述轨迹空间汇集和所述出行模式标签得到每一所述OD点对的交通需求结构;
S22、基于所述交通需求结构将所述OD点对的所述刚性需求群体的数量和非刚性群体的数量分配至所述出行路径集中的组成路段,并计算每一所述组成路段中所述刚性需求群体的数量和所述非刚性需求群体的数量比例,得到所述出行路段的出行模式。
进一步的,步骤S3包括:根据所述路网拓扑结构搜索所述拥堵路段集合S中每一拥堵路段的上游路段,并设定一阈值K,并计算所述上游路段的实时交通流量与最大通行能力的比值v/c,若v/c<K,则将所述上游路段纳入所述拥堵路段的影响范围集合Z s,并进一步向上游搜索;否则,停止搜索。
进一步的,步骤S4中所述根据全路网实时的交通运行情况及每一所述OD点对所述出行路径集的各组成路段出行结构生成多条诱导路径,包括:
S41、根据路网的实时交通流数据通过公式
Figure PCTCN2019115057-appb-000001
计算路段(i,j)的剩余承载力,其中,
Figure PCTCN2019115057-appb-000002
表示路段(i,j)的通行能力,q (i,j)为路段(i,j)的实时流量;并获取路段平均行程时间;
S42、根据所述完整历史通行轨迹从所述出行路径集中筛选出有效路径集P:
S421、计算每一所述OD点对对应路径的流量q r,以及总流量Q δ=∑q r,δ表示所述OD点对的序号,且δ∈C;
S422、按从高到低的顺序将每一所述OD点对对应的路径依次选入所述有效路径集P中,并对每一所述路径进行交通流量累加
Figure PCTCN2019115057-appb-000003
S423、设定交通流量累加上限0.9Q δ,若所述路径交通流量累加值
Figure PCTCN2019115057-appb-000004
则结束路径选入所述有效路径集P,并确定所述有效路径集中的全部路径;
S43、基于所述有效路径集P,从所述卡口过车记录中调取设定时间间隔内所述路径的过车记录,并计算机动车在每一所述OD点对的平均行使时间T δ
S44、根据所述有效路径集P获得对应的路段集合C s,根据所述拥堵路段集合S确定最终有效路段集合
Figure PCTCN2019115057-appb-000005
S45、采用所述诱导路径搜索模型针对每一所述OD点对同时生成多条诱导路径。
进一步的,步骤S5包括:
S51、在所述有效路径集P中筛选出包含拥堵路段的所有所述OD点对集合,根据所述出行结构中所述刚性需求群体的数量与所述非刚性需求群体的数量比例计算每一所述OD点对的所述刚性需求群体对应数量,并筛选出所述刚性需求群体的数量最高所对应的所述OD点对发布最优诱导路径,其余所述OD点对发布次优诱导路径;
S52、根据所述拥堵路段的影响范围集合Z s中各路段的出行模式,计算路段实时的所述刚性需求群体的数量与所述非刚性需求群体的数量;选择各路段的所述剩余承载力低且所述刚性需求群体数量高的路段,发布最优诱导路 径,其余路段发布次优诱导路径。
另一方面,提供一种基于出行结构的城市路网诱导方案发布系统,应用于上述的基于出行结构的城市路网诱导方案发布方法,所述系统包括数据接入模块、需求结构分析模块、拥堵识别模块、诱导路径搜索模块、诱导策略生成模块、诱导发布模块,其中:
数据接入模块,通过指定接口连接智能卡口系统与数据库,用于获取卡口过车记录,动态同步所述智能卡口系统实时的过车记录,并与数据库进行数据交互;
需求结构分析模块,从所述数据接入模块调取原始历史通行轨迹,用于对机动车轨迹重构、路网OD点对出行路径集分析,以及OD出行结构与路段的出行模式分析;
拥堵识别模块,从所述接入数据接入模块读取实时同步数据,用于识别路网内的拥堵路段,生成所述拥堵路段集S,并分析拥堵路段影响范围;
诱导路径搜索模块,从所述数据接入模块获取所述智能卡口系统实时的过车记录,从所述需求结构分析模块获取OD出行结构与路段的出行模式分析结果,从所述拥堵识别模块接入拥堵路段集;用于计算实时的路段剩余承载力与路段行程时间;针对每一个所述OD点对同时生成多条诱导路径;且所述诱导路径搜索模型设置在所述诱导路径搜索模块内;
诱导策略生成模块,从需求结构分析模块接入OD点对出行路径集以及OD出行结构、路段出行模式的分析结果,从拥堵识别模块接入拥堵路段集及其影响范围,从诱导路径搜索模块接入诱导路径的最优方案、次优方案以及路段剩余承载力,确定最优诱导方案、次优诱导方案的发布位置以及发布内容,并传递至所述诱导发布模块;
诱导发布模块,连接所述诱导策略生成模块,并与道路诱导屏控制卡对接,用于将所述诱导策略生成模块输出的诱导方案发布位置、内容;将诱导 方案传输至路段相应的控制卡,实现诱导方案的发布。
本发明的基于出行结构的城市路网诱导方案发布方法和系统中,系统由数据接入模块、需求结构分析模块、拥堵识别模块、诱导路径搜索模块、诱导策略生成模块、诱导发布模块构成,通过数据接入模块读取智能卡口系统,以获取机动车的卡口过车记录,并动态同步所述智能卡口系统实时的过车记录;同时,数据接入模块还与数据库连接并相互之间通过设定接口进行数据交互;由需求结构分析模块对机动车轨迹重构、路网OD点对出行路径集分析,以及OD出行结构与路段的出行模式分析;由拥堵识别模块识别路网内的拥堵路段,并根据拥堵路段分析拥堵路段影响范围;由诱导路径搜索模块计算实时的路段剩余承载力与路段行程时间,并生成对应每一OD点对的多条诱导路径;由诱导策略生成模块诱导路径搜索模块接入诱导路径的最优方案、次优方案以及路段剩余承载力,确定最优诱导方案、次优诱导方案的发布位置以及发布内容,并传递至所述诱导发布模块,通过诱导发布模块将诱导方案发布至路网中设置的诱导屏控制卡,实现对路网内机动车的有效诱导;与现有技术相比,本发明可基于路网的实时交通流数据实施全局最优的诱导路径搜索,并通过对路网交通出行结构分析来确定诱导方案的发布策略,以实现路网需求均衡分别,使出行者可避开拥堵路段,提升路网整体的通行效率。
附图说明
图1是本发明实施例中所述基于出行结构的城市路网诱导方案发布方法的流程图示意;
图2是本发明实施例中所述基于出行结构的城市路网诱导方案发布系统的结构框图示意。
具体实施方式
为了使本技术领域的人员更好地理解本发明方案,下面将结合本发明实施例中的附图,对本发明实施例中的技术方案进行清楚、完整地描述。
在本发明实施例中,提供一种基于出行结构的城市路网诱导方案发布方法及系统,参阅图1,本发明提供的方法具体包括步骤如下:
步骤一、获取指定时间段内全路网机动车卡口过车记录,基于卡口过车记录提取对应每一机动车的原始历史通行轨迹,对原始历史通行轨迹进行完整性重构得到完整历史通行轨迹,并根据完整历史通行轨迹得到与每一机动车对应的出行模式标签;具体的,本发明还需在实际操作过程中判断每一机动车对应的原始历史通行轨迹是否完整,若不完整,通过粒子群算法进行重构操作,生成完整历史通行轨迹;同时,对每一机动车逐一进行完整历史通行轨迹的空间汇集,基于空间汇集计算机动车在指定时间段内的历史出行时空特征指标;然后,将时空特征指标作为每一机动车的属性,采用高斯混合模型对指定时间段内所有属性确定机动车的出行模式标签。
优选的,本发明中卡口过车记录的单位以机动车为单位进行记录。
在本发明实施例中,时空特征指标包括:轨迹重复系数、日均出行次数、路网日均逗留时长和出发时刻相似度;其中,轨迹点重复系数用于衡量通行轨迹的相似性,各时空特征指标的计算公式为:轨迹点重复系数=不同轨迹点数量/出现天数,轨迹点是指所述原始历史通行轨迹中的卡口记录点,出现天数指机动车存在出行轨迹的天数;日均出行次数=总出行次数/出现天数;路网日均逗留时长=总行驶时长/出现天数,总行驶时长依据每一机动车对应的完整轨迹的通行时长统计得到;出发时刻相似度=位于不同时间间隔内的轨迹起始时间节点数量/出现天数;其中,时间间隔是指将一日24小时划分为等长的若干时间区间,每一区间对应一个时间间隔;例如,若以1小时为时间间隔长度,那么时间间隔区间划分情况为:[0:00,1:00),[1:00,2:00),……,[23:00,0:00), 共24个区间。
具体的,出行模式标签包括刚性需求群体和非刚性需求群体,在实施例中,机动车由于高频次的出行从而形成机动车的通行时间以及通行空间范围具有明显的恒定性,即有规律性的出行,这种机动车构成的群体为刚性需求群体;反之,对应的机动车群体则构成非刚性需求群体。
步骤二、构建路网拓扑结构,根据路网拓扑结构确定路网OD点对集合C;并基于完整历史通行轨迹确定OD点对的出行路径集;并根据机动车对应的出行模式标签确定出行路径集各组成路段的出行模式;具体的,根据机动车对应的轨迹空间汇集和出行模式标签得到每一OD点对的交通需求结构,即刚性群体的样本量与非刚性需求群体的样本量比值;样本量包括日均样本量、以及短间隔内的平均样本量,其中短间隔指一天24个小时内划分的若干时间区间,在实施例中,可以为等间隔区间,如24小时划分为24个等间距区间:[0:00,1:00),[1:00,2:00),……;也可以为非等间距区间:高峰时段[6:00,11:00)、[16:30,19:30),平峰时段[0:00,6:00)、[11:00,16:30)、[19:30,24:00),具体如何划分可根据实际情况进行设定,在此并不进行限制和固定;随后,分析每一OD点对交通需求结构的日变化及一天二十四小时内各时间间隔的变化模式;基于出行路径集得到OD出行结构,并将OD点对的刚性需求群体的数量和非刚性群体的数量分配至出行路径集中的组成路段,并计算每一组成路段中刚性需求群体的数量和非刚性需求群体的数量比例,基于数量比例确组成路段的出行模式,这样制定的诱导发布策略能够更加适应路网内的交通需求。
步骤三、获取与出行路径集对应的包含流量、速度、车头时距的实时交通流量数据,基于交通流量数据对应出行路径集中的拥堵路段,并生成拥堵路段集合S以及对应每一拥堵路段的影响范围集合Z s,其中s指代拥堵路段集合S中的任一个元素;具体根据路网拓扑结构搜索拥堵路段集合S中每一拥堵路段的上游路段,并设定一阈值K,并计算上游路段的实时交通流量与 最大通行能力的比值v/c,若v/c<K,则将上游路段纳入拥堵路段影响范围集合Z s,并进一步向上游搜索;否则,停止搜索,以此获取路网中各路段的交通流具体情况,后续可以此为依据制定机动车在路网出行的诱导发布策略。
步骤四、基于拥堵路段集合S构建全局最优的诱导路径搜索模型,并根据全路网实时的交通运行情况及每一OD点对的出行路径集的各组成路段出行结构生成多条诱导路径;其中,对每一OD点对生成多条诱导路径具体包括步骤为:
首先,根据路网的实时交通流数据通过公式
Figure PCTCN2019115057-appb-000006
计算路段(i,j)的剩余承载力及通行时间,其中,
Figure PCTCN2019115057-appb-000007
表示路段(i,j)的通行能力,q (i,j)为路段(i,j)的实时流量;然后,根据完整历史通行轨迹从出行路径集中筛选出有效路径集P,具体包括:计算每一OD点对对应路径的流量q r,以及总流量Q δ=∑q r,δ表示所述OD点对的序号,且δ∈C;并按从高到低的顺序将每一OD点对对应的路径依次选入有效路径集P中,并对每一路径进行交通流量累加
Figure PCTCN2019115057-appb-000008
设定交通流量累加上限0.9Q δ,若路径交通流量累加值
Figure PCTCN2019115057-appb-000009
则结束路径选入所述有效路径集P,并确定有效路径集中的全部路径;随后,基于有效路径集P,从卡口过车记录中调取设定时间间隔内路径的过车记录,并计算机动车在每一OD点对的平均行使时间T δ;同时,将有效路径集P转化为路段集合C s,即提取出路径中的所有路段构成路段集合C s,根据拥堵路段集合S确定最终有效路段集合
Figure PCTCN2019115057-appb-000010
最后,采用诱导路径搜索模型针对每一OD点对同时生成多条诱导路径,其中诱导路径搜索模型的优化目标为
Figure PCTCN2019115057-appb-000011
式中N为路网拓扑结构中所有节点集合,i,j均为节点序号,t(i,j)为路段(i,j)上的实时的通行时间,x(i,j)为分配到路段(i,j)上的流量
Figure PCTCN2019115057-appb-000012
其中a指代路段,
Figure PCTCN2019115057-appb-000013
为OD点对δ中路径r的流量,参数
Figure PCTCN2019115057-appb-000014
诱导路径搜索模型的约束条件为:
Figure PCTCN2019115057-appb-000015
其中节点τ∈N,E δ为OD点对δ可忍受的最大时间不便利性;诱导路径搜索模型输出一个最优路径和若干次优路径。
步骤五、根据出行结构确定诱导发布策略,并筛选OD点对间的多条诱导路径中的最优路径诱导方案;具体地,在有效路径集P中筛选出包含拥堵路段的所有OD点对集合,根据出行结构中刚性需求群体的数量与非刚性需求群体的数量比例计算每一OD点对的刚性需求群体对应数量,并筛选出刚性需求群体的数量最高所对应的OD点对发布最优诱导路径,其余OD点对发布次优诱导路径;根据拥堵路段的影响范围集合Z s中各路段的出行模式,计算路段实时的刚性需求群体的数量与非刚性需求群体的数量;选择各路段的剩余承载力低且刚性需求群体数量高的路段,发布最优诱导路径,其余路段发布次优诱导路径。
基于上述提供的城市路网诱导方案发布方法,本发明还提出一种基于出行结构的城市路网诱导方案发布系统,应用于上述基于出行结构的城市路网诱导方案发布方法,参阅图2,所述系统包括数据接入模块、需求结构分析模块、拥堵识别模块、诱导路径搜索模块、诱导策略生成模块、诱导发布模块;其中,数据接入模块,通过指定接口连接智能卡口系统与数据库,用于获取卡口过车记录,动态同步所述智能卡口系统实时的过车记录,并与数据库进行数据交互;需求结构分析模块,从数据接入模块调取原始历史通行轨迹,用于对机动车轨迹重构、路网OD点对出行路径集分析,以及OD出行结构与路段的出行模式分析;拥堵识别模块,从接入数据接入模块读取实时同步数据,用于识别路网内的拥堵路段,生成所述拥堵路段集S,并分析拥堵路段 影响范围;诱导路径搜索模块,从数据接入模块获取智能卡口系统实时的过车记录,从需求结构分析模块获取OD出行结构与路段的出行模式分析结果,从拥堵识别模块接入拥堵路段集;用于计算实时的路段剩余承载力与路段行程时间;针对每一个OD点对同时生成多条诱导路径;且诱导路径搜索模型设置在诱导路径搜索模块内;诱导策略生成模块,从需求结构分析模块接入OD点对出行路径集以及OD出行结构、路段出行模式的分析结果,从拥堵识别模块接入拥堵路段集及其影响范围,从诱导路径搜索模块接入诱导路径的最优方案、次优方案以及路段剩余承载力,确定最优诱导方案、次优诱导方案的发布位置以及发布内容,并传递至诱导发布模块;诱导发布模块,连接诱导策略生成模块,并与道路诱导屏控制卡对接,用于将诱导策略生成模块输出的诱导方案发布位置、内容;将诱导方案传输至路段相应的控制卡,实现诱导方案的发布。
本发明的基于出行结构的城市路网诱导方案发布方法和系统中,系统由数据接入模块、需求结构分析模块、拥堵识别模块、诱导路径搜索模块、诱导策略生成模块、诱导发布模块构成,通过数据接入模块读取智能卡口系统,以获取机动车的卡口过车记录,并动态同步所述智能卡口系统实时的过车记录;同时,数据接入模块还与数据库连接并相互之间通过设定接口进行数据交互;由需求结构分析模块对机动车轨迹重构、路网OD点对出行路径集分析,以及OD出行结构与路段的出行模式分析;由拥堵识别模块识别路网内的拥堵路段,并根据拥堵路段分析拥堵路段影响范围;由诱导路径搜索模块计算实时的路段剩余承载力与路段行程时间,并生成对应每一OD点对的多条诱导路径;由诱导策略生成模块诱导路径搜索模块接入诱导路径的最优方案、次优方案以及路段剩余承载力,确定最优诱导方案、次优诱导方案的发布位置以及发布内容,并传递至所述诱导发布模块,通过诱导发布模块将诱导方案发布至路网中设置的诱导屏控制卡,实现对路网内机动车的有效诱导; 与现有技术相比,本发明可基于路网的实时交通流数据实施全局最优的诱导路径搜索,并通过对路网交通出行结构分析来确定诱导方案的发布策略,以实现路网需求均衡分别,使出行者可避开拥堵路段,提升路网整体的通行效率。
以上仅为本发明的较佳实施例,但并不限制本发明的专利范围,尽管参照前述实施例对本发明进行了详细的说明,对于本领域的技术人员而言,其依然可以对前述各具体实施方式所记载的技术方案进行修改,或者对其中部分技术特征进行等效替换。凡是利用本发明说明书及附图内容所做的等效结构,直接或间接运用在其他相关的技术领域,均同理在本发明专利保护范围之内。

Claims (9)

  1. 一种基于出行结构的城市路网诱导方案发布方法,其特征在于,所述方法包括:
    S1、获取指定时间段内全路网机动车卡口过车记录,基于所述卡口过车记录提取对应每一机动车的原始历史通行轨迹,对原始历史通行轨迹进行完整性重构得到完整历史通行轨迹,并根据所述完整历史通行轨迹得到与每一机动车对应的出行模式标签;
    S2、构建路网拓扑结构,根据所述路网拓扑结构确定路网OD点对集合C;并基于所述完整历史通行轨迹确定所述OD点对的出行路径集,并根据机动车对应的出行模式标签确定出行路径集各组成路段的出行模式;
    S3、获取与所述出行路径集对应的包含流量、速度、车头时距的实时交通流量数据,基于所述交通流量数据对应所述出行路径集中的拥堵路段,并生成拥堵路段集合S以及所述每一个拥堵路段对应的影响范围集合Z s,其中s指代拥堵路段集合S中的任一个元素;
    S4、基于所述拥堵路段集合S构建全局最优的诱导路径搜索模型,并根据全路网实时的交通运行情况及每一所述OD点对的所述出行路径集的各组成路段出行结构生成多条诱导路径;
    S5、根据所述出行结构确定诱导发布策略,并筛选所述OD点对间的多条诱导路径中的最优路径诱导方案。
  2. 如权利要求1所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,步骤S1包括:
    S11、判断每一机动车对应的所述原始历史通行轨迹是否完整,若不完整,通过粒子群算法进行重构操作,生成完整的通行轨迹;
    S12、对每一机动车逐一进行所述完整历史通行轨迹的空间汇集,基于所述空间汇集计算机动车在所述指定时间段内的历史出行时空特征指标;
    S13、将所述时空特征指标作为每一机动车的属性,采用高斯混合模型对 所述指定时间段内所有所述属性确定机动车的出行模式标签。
  3. 如权利要求2所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,所述时空特征指标包括:轨迹重复系数、日均出行次数、路网日均逗留时长和出发时刻相似度;其中,所述轨迹点重复系数用于衡量通行轨迹的相似性,计算公式为:
    轨迹点重复系数=不同轨迹点数量/出现天数,轨迹点是指所述原始历史通行轨迹中的卡口记录点,出现天数指机动车存在出行轨迹的天数;
    日均出行次数=总出行次数/出现天数;
    路网日均逗留时长=总行驶时长/出现天数,总行驶时长依据每一机动车对应的完整轨迹的通行时长统计得到;
    出发时刻相似度=位于不同时间间隔内的轨迹起始时间节点数量/出现天数;其中,时间间隔是指将一日24小时划分为等长的若干时间区间,每一区间对应一个时间间隔。
  4. 如权利要求2所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,所述出行模式标签包括刚性需求群体和非刚性需求群体,所述刚性需求群体为具有指定规律性的出行机动车群体;所述非刚性需求群体为不具有指定规律性的出行机动车群体。
  5. 如权利要求4所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,步骤S2所述的确定出行路径集各组成路段的出行模式方法为:
    S21、根据机动车对应的所述轨迹空间汇集和所述出行模式标签得到每一所述OD点对的交通需求结构;
    S22、基于所述交通需求结构将所述OD点对的所述刚性需求群体的数量和非刚性群体的数量分配至所述出行路径集中的组成路段,并计算每一所述组成路段中所述刚性需求群体的数量和所述非刚性需求群体的数量比例,得到所述出行路段的出行模式。
  6. 如权利要求1所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,步骤S3包括:根据所述路网拓扑结构搜索所述拥堵路段集合S中每一拥堵路段的上游路段,并设定一阈值K,并计算所述上游路段的实时交通流量与最大通行能力的比值v/c,若v/c<K,则将所述上游路段纳入所述拥堵路段的影响范围集合Z s,并进一步向上游搜索;否则,停止搜索。
  7. 如权利要求5所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,步骤S4中所述根据全路网实时的交通运行情况及每一所述OD点对所述出行路径集的各组成路段出行结构生成多条诱导路径,包括:
    S41、根据路网的实时交通流数据通过公式
    Figure PCTCN2019115057-appb-100001
    计算路段(i,j)的剩余承载力,其中,
    Figure PCTCN2019115057-appb-100002
    表示路段(i,j)的通行能力,q (i,j)为路段(i,j)的实时流量;并获取路段平均行程时间;
    S42、根据所述完整历史通行轨迹从所述出行路径集中筛选出有效路径集P:
    S421、计算每一所述OD点对对应路径的流量q r,以及总流量Q δ=∑q r,δ表示所述OD点对的序号,且δ∈C;
    S422、按从高到低的顺序将每一所述OD点对对应的路径依次选入所述有效路径集P中,并对每一所述路径进行交通流量累加
    Figure PCTCN2019115057-appb-100003
    S423、设定交通流量累加上限0.9Q δ,若所述路径交通流量累加值
    Figure PCTCN2019115057-appb-100004
    则结束路径选入所述有效路径集P,并确定所述有效路径集中的全部路径;
    S43、基于所述有效路径集P,从所述卡口过车记录中调取设定时间间隔内所述路径的过车记录,并计算机动车在每一所述OD点对的平均行使时间T δ
    S44、根据所述有效路径集P获得对应的路段集合C s,根据所述拥堵路段集合S确定最终有效路段集合
    Figure PCTCN2019115057-appb-100005
    S45、采用所述诱导路径搜索模型针对每一所述OD点对同时生成多条诱导路径。
  8. 如权利要求7所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,步骤S5包括:
    S51、在所述有效路径集P中筛选出包含拥堵路段的所有所述OD点对集合,根据所述出行结构中所述刚性需求群体的数量与所述非刚性需求群体的数量比例计算每一所述OD点对的所述刚性需求群体对应数量,并筛选出所述刚性需求群体的数量最高所对应的所述OD点对发布最优诱导路径,其余所述OD点对发布次优诱导路径;
    S52、根据所述拥堵路段的影响范围集合Z s中各路段的出行模式,计算路段实时的所述刚性需求群体的数量与所述非刚性需求群体的数量;选择各路段的所述剩余承载力低且所述刚性需求群体数量高的路段,发布最优诱导路径,其余路段发布次优诱导路径。
  9. 一种基于出行结构的城市路网诱导方案发布系统,应用于权利要求1-8任一项所述的基于出行结构的城市路网诱导方案发布方法,其特征在于,所述系统包括数据接入模块、需求结构分析模块、拥堵识别模块、诱导路径搜索模块、诱导策略生成模块、诱导发布模块,其中:
    数据接入模块,通过指定接口连接智能卡口系统与数据库,用于获取卡口过车记录,动态同步所述智能卡口系统实时的过车记录,并与数据库进行数据交互;
    需求结构分析模块,从所述数据接入模块调取原始历史通行轨迹,用于对机动车轨迹重构、路网OD点对出行路径集分析,以及OD出行结构与路段的出行模式分析;
    拥堵识别模块,从所述接入数据接入模块读取实时同步数据,用于识别路网内的拥堵路段,生成所述拥堵路段集S,并分析拥堵路段影响范围;
    诱导路径搜索模块,从所述数据接入模块获取所述智能卡口系统实时的过车记录,从所述需求结构分析模块获取OD出行结构与路段的出行模式分析结果,从所述拥堵识别模块接入拥堵路段集;用于计算实时的路段剩余承载力与路段行程时间;针对每一个所述OD点对同时生成多条诱导路径;且所述诱导路径搜索模型设置在所述诱导路径搜索模块内;
    诱导策略生成模块,从需求结构分析模块接入OD点对出行路径集以及OD出行结构、路段出行模式的分析结果,从拥堵识别模块接入拥堵路段集及其影响范围,从诱导路径搜索模块接入诱导路径的最优方案、次优方案以及路段剩余承载力,确定最优诱导方案、次优诱导方案的发布位置以及发布内容,并传递至所述诱导发布模块;
    诱导发布模块,连接所述诱导策略生成模块,并与道路诱导屏控制卡对接,用于将所述诱导策略生成模块输出的诱导方案发布位置、内容;将诱导方案传输至路段相应的控制卡,实现诱导方案的发布。
PCT/CN2019/115057 2019-03-27 2019-11-01 一种基于出行结构的城市路网诱导方案发布方法和系统 WO2020192120A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201910235483.6 2019-03-27
CN201910235483.6A CN109887288B (zh) 2019-03-27 2019-03-27 一种基于出行结构的城市路网诱导方案发布方法和系统

Publications (1)

Publication Number Publication Date
WO2020192120A1 true WO2020192120A1 (zh) 2020-10-01

Family

ID=66934581

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2019/115057 WO2020192120A1 (zh) 2019-03-27 2019-11-01 一种基于出行结构的城市路网诱导方案发布方法和系统

Country Status (2)

Country Link
CN (1) CN109887288B (zh)
WO (1) WO2020192120A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113052405A (zh) * 2021-05-08 2021-06-29 林兴叶 基于物联网和人工智能的交通拥堵预测与优化方法
CN116110228A (zh) * 2023-04-06 2023-05-12 齐鲁云商数字科技股份有限公司 一种基于区块链的城市交通快速化引导系统

Families Citing this family (17)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109887288B (zh) * 2019-03-27 2021-06-15 江苏智通交通科技有限公司 一种基于出行结构的城市路网诱导方案发布方法和系统
CN110517491A (zh) * 2019-08-23 2019-11-29 长沙理工大学 一种考虑路径冗余和出行效率的路段重要度排序方法
CN111047860B (zh) * 2019-12-02 2021-01-08 安徽百诚慧通科技有限公司 一种车辆运行轨迹提取方法
CN111862587B (zh) * 2019-12-16 2021-11-19 北京嘀嘀无限科技发展有限公司 一种出行引导策略生成方法及装置
CN114664086B (zh) * 2019-12-18 2023-11-24 北京嘀嘀无限科技发展有限公司 控制信息发布的方法、装置、电子设备和存储介质
WO2021196049A1 (zh) * 2020-03-31 2021-10-07 华为技术有限公司 汽车出行规律的分析方法、服务器及系统
CN112015837A (zh) * 2020-08-24 2020-12-01 安徽科力信息产业有限责任公司 一种城市道路高频路径分析方法、系统及存储介质
CN112489433B (zh) * 2020-12-17 2022-11-04 华为技术有限公司 交通拥堵分析方法及装置
CN112767683B (zh) * 2020-12-22 2021-12-21 安徽百诚慧通科技有限公司 一种基于反馈机制的路径诱导方法
CN113207080B (zh) * 2021-03-22 2022-02-25 北京邮电大学 一种vanet中的数据协作传输方法、装置及电子设备
CN112991740B (zh) * 2021-03-23 2022-03-11 苏州蓝图智慧城市科技有限公司 一种基于出行离散度及聚类的车辆引导方法、介质及设备
CN113593220B (zh) * 2021-07-02 2022-07-29 南京泛析交通科技有限公司 一种基于宏观基本图的路网承载力估计方法
CN114313851A (zh) * 2022-01-11 2022-04-12 浙江柯工智能系统有限公司 一种模块化化纤物料转运平台及方法
CN114566041B (zh) * 2022-01-27 2022-12-06 苏州大学 多源数据融合城市拥堵路段多模式出行诱导方法及设备
CN114758514B (zh) * 2022-03-24 2023-07-28 山东省交通规划设计院集团有限公司 一种基于道路使用模式的路径诱导方法及系统
CN114743396B (zh) * 2022-03-29 2023-04-28 江苏拓邮信息智能技术研究院有限公司 基于粒子群优化算法的交通诱导调度系统及其调度方法
CN115830851B (zh) * 2022-11-03 2024-05-31 阿波罗智联(北京)科技有限公司 交通流量调节方法、装置、设备及介质

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009064283A (ja) * 2007-09-07 2009-03-26 Omron Corp 交通情報提供システムおよび交通情報提供方法
US9564048B2 (en) * 2014-12-18 2017-02-07 Sap Se Origin destination estimation based on vehicle trajectory data
CN106384504A (zh) * 2016-09-06 2017-02-08 江苏智通交通科技有限公司 基于数据可视化的城市路网拥堵特性描述分析方法
CN108122069A (zh) * 2017-12-08 2018-06-05 杭州电子科技大学 基于海量交通数据居民出行起点终点矩阵提取方法
CN108717790A (zh) * 2018-07-06 2018-10-30 广州市交通运输研究所 一种基于卡口车牌识别数据的车辆出行分析方法
CN109345823A (zh) * 2018-09-19 2019-02-15 连云港杰瑞电子有限公司 一种基于大数据的智能交通数据分析系统
CN109887288A (zh) * 2019-03-27 2019-06-14 江苏智通交通科技有限公司 一种基于出行结构的城市路网诱导方案发布方法和系统

Family Cites Families (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105070078B (zh) * 2015-08-16 2017-03-22 吉林大学 一种基于车车通信的动态路径诱导方法
CN107146446B (zh) * 2017-07-10 2018-02-09 中南大学 一种基于rfid数据和动态车源的路径诱导方法
CN107591004A (zh) * 2017-11-01 2018-01-16 中原智慧城市设计研究院有限公司 一种基于车路协同的智能交通诱导方法
CN109035766A (zh) * 2018-07-13 2018-12-18 北京工业大学 一种车联网环境下考虑可变周期的动态交通控制与诱导协同优化方法

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2009064283A (ja) * 2007-09-07 2009-03-26 Omron Corp 交通情報提供システムおよび交通情報提供方法
US9564048B2 (en) * 2014-12-18 2017-02-07 Sap Se Origin destination estimation based on vehicle trajectory data
CN106384504A (zh) * 2016-09-06 2017-02-08 江苏智通交通科技有限公司 基于数据可视化的城市路网拥堵特性描述分析方法
CN108122069A (zh) * 2017-12-08 2018-06-05 杭州电子科技大学 基于海量交通数据居民出行起点终点矩阵提取方法
CN108717790A (zh) * 2018-07-06 2018-10-30 广州市交通运输研究所 一种基于卡口车牌识别数据的车辆出行分析方法
CN109345823A (zh) * 2018-09-19 2019-02-15 连云港杰瑞电子有限公司 一种基于大数据的智能交通数据分析系统
CN109887288A (zh) * 2019-03-27 2019-06-14 江苏智通交通科技有限公司 一种基于出行结构的城市路网诱导方案发布方法和系统

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
LI, XIANGYU: "Formation Mechanism of Motor Vehicle Traffic Rapid Diversion Scheme Under Partial Congestion of Road Network", SCIENCE-ENGINEERING (B), CHINA MASTER’S THESES FULL-TEXT DATABASE, 15 March 2018 (2018-03-15), CN, pages 1 - 62, XP009523563 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113052405A (zh) * 2021-05-08 2021-06-29 林兴叶 基于物联网和人工智能的交通拥堵预测与优化方法
CN113052405B (zh) * 2021-05-08 2021-12-17 湖北讯华科技股份有限公司 基于物联网和人工智能的交通拥堵预测与优化方法
CN116110228A (zh) * 2023-04-06 2023-05-12 齐鲁云商数字科技股份有限公司 一种基于区块链的城市交通快速化引导系统
CN116110228B (zh) * 2023-04-06 2023-07-07 齐鲁云商数字科技股份有限公司 一种基于区块链的城市交通快速化引导系统

Also Published As

Publication number Publication date
CN109887288B (zh) 2021-06-15
CN109887288A (zh) 2019-06-14

Similar Documents

Publication Publication Date Title
WO2020192120A1 (zh) 一种基于出行结构的城市路网诱导方案发布方法和系统
Wang et al. A simple baseline for travel time estimation using large-scale trip data
CN103646187B (zh) 一种统计周期内车辆出行路线及od矩阵获取方法
Powell et al. Towards reducing taxicab cruising time using spatio-temporal profitability maps
Li et al. Studying the benefits of carpooling in an urban area using automatic vehicle identification data
CN110298500B (zh) 一种基于出租车数据和城市路网的城市交通轨迹数据集生成方法
WO2019047905A1 (zh) 一种交通路况分析系统、方法以及装置
CN101373559B (zh) 基于浮动车数据评估城市路网交通状态的方法
Wang et al. A big data approach for smart transportation management on bus network
CN107832882A (zh) 一种基于马尔科夫决策过程的出租车寻客策略推荐方法
CN108734955A (zh) 预测路况状态的方法及装置
CN106781479A (zh) 一种基于手机信令数据实时获取高速公路运行状态的方法
CN107331169A (zh) 饱和状态下城市道路交叉口信号配时方案评价方法及系统
CN108230741A (zh) 基于超声波时间序列的停车场车辆轨迹跟踪方法及系统
CN111275965A (zh) 一种基于互联网大数据的实时交通仿真分析系统与方法
CN110836675A (zh) 一种基于决策树的自动驾驶搜索决策方法
CN107248315A (zh) 一种停车导航路径的推荐系统及方法
CN112991755A (zh) 一种基于识别通勤车并构建出行路径选择的方法及系统
CN109489679A (zh) 一种导航路径中的到达时间计算方法
CN106875680A (zh) 基于大数据分析的路口平均等待时间计算方法
WO2023014311A1 (en) Traffic density estimation system and a method thereof
CN105825675B (zh) 一种基于大数据的路段旅行时间计算方法和装置
CN116089744B (zh) 一种基于Transformer动态时空关联的医院停车场推荐方法
CN109448379A (zh) 一种社交媒体数据偶发性交通事件的识别及定位方法
CN111640303B (zh) 城市通勤路径识别方法及设备

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 19921593

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 19921593

Country of ref document: EP

Kind code of ref document: A1

32PN Ep: public notification in the ep bulletin as address of the adressee cannot be established

Free format text: NOTING OF LOSS OF RIGHTS PURSUANT TO RULE 112(1) EPC (EPO FORM 1205A DATED 21/04/2022)

122 Ep: pct application non-entry in european phase

Ref document number: 19921593

Country of ref document: EP

Kind code of ref document: A1