CN109360414B - Identification and screening methods of frequently congested road sections - Google Patents

Abstract

The present invention provides a method for identifying and screening frequently-occurring congested road sections, including: obtaining historical congestion data, counting the daily cumulative congestion time of a certain road section, determining the probability distribution that the cumulative congestion time of the road section obeys, and calculating the cumulative congestion time of the road section. Reliability, when the reliability exceeds the set threshold ε ₁ , it is judged that the road section is a frequently congested road section; in the case of a given reliability, the given reliability of the road section is calculated according to the probability distribution obeyed by the cumulative congestion duration of the road section When the cumulative congestion time of a given reliability exceeds the set threshold ε ₂ , it is judged that the road section is a frequently congested road section. The present invention determines whether it is a frequently congested road section by calculating the reliability that the accumulated congestion duration of the road section exceeds the expected threshold value T ₀ or calculating the cumulative congestion duration of the given reliability under the condition of a given reliability. Investigating the congested road sections in Changfa provides an accurate and powerful scientific basis.

Description

Identification and screening methods of frequently congested road sections

technical field

The invention relates to the technical field of traffic information processing, in particular to a method for identifying and screening frequently congested road sections.

Background technique

Traffic congestion is a problem that major cities are facing, mainly including occasional congestion and frequent congestion. Occasional congestion is caused by emergencies, and frequent congestion is usually caused by uneven traffic supply and demand, defects in the road network and other reasons. For example, traffic planning is not in harmony with urban development, the design capacity of interchange ramps is insufficient, the number of lanes at the junction of high-grade roads and low-grade roads is reduced, the distance between intersections is too large, the setting of U-turns is unreasonable, and the timing of intersection signals is poor. Identifying and screening frequently congested sections of the road network, on the one hand, can provide a reconstruction project library for urban congestion relief projects, provide early warning information for traffic management departments, take timely countermeasures, and use advanced traffic control measures and intelligent guidance information. Relieve traffic jams; on the other hand, it can find unreasonable points in road network planning, and provide scientific basis for traffic and construction departments to re-plan road alignment and improve road infrastructure. Frequently congested road sections have certain regularity and predictability, but there is still a lack of mature and reliable methods for quantifying frequently congested road sections.

The existing identification methods of frequently-occurring congested road sections mainly include:

The first method is to divide the frequently congested road sections into daily congested sections, weekly congested sections, monthly congested sections and annual congested sections. Daily congested road section refers to the road section that is at the fifth-level average interval speed for more than 1 hour (inclusive) during peak hours, and counts according to the morning rush hour and evening rush hour. It is a daily congested road section, which is counted according to the morning rush hour and evening rush hour; the monthly congested road section refers to the weekly congested road section for at least 3 weeks within 4 weeks of January, and the statistics are calculated according to the morning rush hour and evening rush hour; Annually congested road sections refer to the monthly congested road sections for at least 6 months within 12 months of a year, and statistics are calculated according to the morning peak hours and evening peak hours.

The second statistical method is to divide the cumulative number of time periods of congestion for each road segment by the total number of periods of peak time periods during peak hours, and this percentage reflects the normal congestion during peak hours. On expressways, if the percentage is greater than 25%, it is a frequently congested section; on the main and secondary arterial roads, if the percentage is greater than 30%, it is a frequently congested section.

The current identification methods of frequently congested road sections only consider the congestion during peak hours, and cannot identify the overall congestion level of the road section every day, and do not consider the volatility of congestion. Due to differences and fluctuations in the congestion duration of road sections, it is difficult to identify and screen out frequently congested road sections with short congestion time and low reliability in the prior art.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide methods for identifying and screening frequently congested road sections to solve the above problems.

In order to achieve the above objects, the present invention adopts the following technical solutions.

According to an aspect of the present invention, a method for identifying and screening frequently congested road sections is provided, including:

Obtain historical congestion data, and count the cumulative congestion time of a road section every day;

According to the cumulative congestion duration of a certain road section, determine the probability distribution that the cumulative congestion duration of the road section obeys;

Given the cumulative congestion time of the road section, the reliability of the cumulative congestion time of the road section is calculated according to the probability distribution obeyed by the cumulative congestion time of the road section. When the reliability of the cumulative congestion time of the road section exceeds the set threshold When ε is ₁ , it is determined that the road section is a frequently congested road section.

Preferably, the obtaining of historical congestion data and statistics of the accumulated congestion duration of a certain road section every day include:

The daily accumulated congestion time of a certain road section is calculated according to the following formula:

Among them, β _i is the accumulated congestion duration of road segment i in one day, α _{i, j} represents whether road segment i is congested at time j·Δ, j=1, 2, ..., M, M represents the period in the comparison time period number, Δ represents the sampling interval of the data, if the road segment i is congested at time j·Δ, then α _i,j =1; if it is not congested, then α _i,j =0.

Preferably, according to the cumulative congestion duration of a certain road section, determining the probability distribution that the cumulative congestion duration of the road section obeys, including:

其中μ_i为路段累计拥堵时长的均值，

为路段累计拥堵时长的方差；According to the cumulative congestion duration of a certain road section, it is determined that the probability distribution obeyed by the cumulative congestion duration of the road section is a normal distribution,

where μ _i is the mean value of the accumulated congestion duration of the road segment,

is the variance of the accumulated congestion duration of the road segment;

根据如下公式计算：The mean μ _i and variance

Calculated according to the following formula:

Among them, (β _{i, 1} , β _{i, 2} , ..., β _{i, n} ) is a group of samples of the population, and n is the sample size;

According to the following probability distribution formula, calculate the probability distribution obeyed by the cumulative congestion duration of the road section:

Among them, P{a<β _i ≤b} is the probability that the accumulated congestion duration β _i of the road segment i is in the interval (a, b), f(x) is the probability density function of β _i , and Φ(·) represents the standard normal The distribution function of the distribution, a and b are the set time period thresholds.

Preferably, in the case of the cumulative congestion duration of a given road section, according to the probability distribution obeyed by the cumulative congestion duration of the road section, the reliability of the cumulative congestion duration of the road section is calculated, including:

The reliability of the accumulated congestion duration of the road section is calculated according to the following formula:

P{β _i >T ₀ } is the probability that the cumulative congestion duration β _i of the road segment i is greater than the expected threshold T ₀ , and P{β _i >T ₀ } is used as the reliability of the cumulative congestion duration of the road segment.

According to another aspect of the present invention, a method for identifying and screening frequently congested road sections is provided, including:

Obtain historical congestion data, and count the cumulative congestion time of a road section every day;

According to the cumulative congestion duration of a certain road section, determine the probability distribution that the cumulative congestion duration of the road section obeys;

In the case of a given reliability, according to the probability distribution that the cumulative congestion duration of the road section obeys, the cumulative congestion duration of the given reliability of the road section is calculated. When the calculated cumulative congestion of the given reliability of the road section is calculated When the duration exceeds the set threshold ε ₂ , it is determined that the road section is a frequently congested road section.

Preferably, the S10 obtains historical congestion data, and counts the accumulated congestion duration of a certain road section every day, including:

The daily accumulated congestion time of a certain road section is calculated according to the following formula:

Among them, β _i is the accumulated congestion duration of road segment i in one day, α _{i, j} represents whether road segment i is congested at time j·Δ, j=1, 2, ..., M, M represents the period in the comparison time period number, Δ represents the sampling interval of the data, if the road segment i is congested at time j·Δ, then α _i,j =1; if it is not congested, then α _i,j =0.

Preferably, according to the cumulative congestion duration of a certain road section, determining the probability distribution that the cumulative congestion duration of the road section obeys, including:

其中μ_i为路段累计拥堵时长的均值，

为路段累计拥堵时长的方差；According to the cumulative congestion duration of a certain road section, it is determined that the probability distribution obeyed by the cumulative congestion duration of the road section is a normal distribution,

where μ _i is the mean value of the accumulated congestion duration of the road segment,

is the variance of the accumulated congestion duration of the road segment;

根据如下公式计算：The mean μ _i and variance

Calculated according to the following formula:

Among them, (β _{i, 1} , β _{i, 2} , ..., β _{i, n} ) is a group of samples of the population, and n is the sample size;

According to the following probability distribution formula, calculate the probability distribution obeyed by the cumulative congestion duration of the road section:

Among them, P{a<β _i ≤b} is the probability that the accumulated congestion duration β _i of the road segment i is in the interval (a, b), f(x) is the probability density function of β _i , and Φ(·) represents the standard normal The distribution function of the distribution.

Preferably, in the case of a given reliability, according to the probability distribution obeyed by the accumulated congestion time of the road segment, calculating the cumulative congestion duration of the given reliability θ of the road segment, including:

The cumulative congestion duration β _i of the given reliability θ of the road section is calculated according to the following formula:

β _i =Φ ^-1 (1-θ)·σ _i +μ _i (7)

Among them, Φ ^-1 (·) represents the inverse function of the cumulative probability density function of the normal distribution, and the reliability is θ.

From the technical solutions provided by the above embodiments of the present invention, it can be seen that the method for identifying and screening frequently congested road sections according to the embodiments of the present invention utilizes traffic big data to statistically analyze the probability distribution of the cumulative congestion duration of the road section, and calculate the cumulative congestion time of the road section. The probability that the duration exceeds the expected threshold, as well as the congestion duration of the road section under a given reliability, provides an accurate and powerful scientific basis for the traffic management department to screen frequently congested road sections.

Additional aspects and advantages of the present invention will be set forth in part in the following description, which will be apparent from the following description, or may be learned by practice of the present invention.

Description of drawings

In order to illustrate the technical solutions of the embodiments of the present invention more clearly, the following briefly introduces the accompanying drawings used in the description of the embodiments. Obviously, the accompanying drawings in the following description are only an embodiment of the present invention. For those of ordinary skill in the art, other drawings can also be obtained based on this drawing without any creative effort.

FIG. 1 is a processing flowchart of a method for identifying and screening frequently congested road sections provided by an embodiment of the present invention.

Detailed ways

The embodiments of the present invention will be described in detail below, and examples of the embodiments are shown in the accompanying drawings. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present invention, but not to be interpreted as an explanation of the present invention. limit.

It will be understood by those skilled in the art that the singular forms "a", "an", "the" and "the" as used herein can include the plural forms as well, unless expressly stated otherwise. It should be further understood that the word "comprising" used in the description of the present invention refers to the presence of stated features, integers, steps, operations, elements and/or components, but does not exclude the presence or addition of one or more other features, Integers, steps, operations, elements, components and/or groups thereof. It will be understood that when we refer to an element as being "connected" or "coupled" to another element, it can be directly connected or coupled to the other element or intervening elements may also be present. Furthermore, "connected" or "coupled" as used herein may include wirelessly connected or coupled. As used herein, the term "and/or" includes any and all combinations of one or more of the associated listed items.

It will be understood by those skilled in the art that, unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs. It should also be understood that terms such as those defined in the general dictionary should be understood to have meanings consistent with their meanings in the context of the prior art and, unless defined as herein, are not to be taken in an idealized or overly formal sense. explain.

In order to facilitate the understanding of the embodiments of the present invention, the following will take specific embodiments as examples for further explanation and description in conjunction with the accompanying drawings, and the embodiments do not constitute limitations to the embodiments of the present invention.

Example

1 is a process flow diagram of a method for identifying and screening frequently congested road sections provided by an embodiment of the present invention. Referring to FIG. 1 , a method for identifying and screening frequently congested road sections includes:

S10 obtains historical congestion data, and counts the accumulated congestion time of a certain road section every day.

Calculated according to the following formula:

Among them, β _i is the accumulated congestion duration of road segment i in one day, α _{i, j} represents whether road segment i is congested at time j·Δ, j=1, 2, ..., M, M represents the period in the comparison time period number, Δ represents the sampling interval of the data.

Illustratively, the traffic state includes three types: smooth, slow, and congested. Calculate the daily accumulated congestion time of each road segment. If the sampling interval is 5 minutes, there are 288 sampling periods in one day. If the road segment i is congested at time j·Δ, then α _i,j =1; if it is not congested, then α _i,j =0.

S20, according to the accumulated congestion duration of a certain road section, determine the probability distribution to which the accumulated congestion duration of the road section obeys.

即，β_i服从数学期望为μ_i、方差为

的正态分布。其中μ_i为路段累计拥堵时长的均值，

为路段累计拥堵时长的方差，均值μ_i和方差

根据如下公式计算：Further, according to the cumulative congestion duration of a certain road section, it is determined that the probability distribution obeyed by the cumulative congestion duration of the road section is a normal distribution,

That is, β _i obeys the mathematical expectation μ _i , and the variance is

normal distribution. where μ _i is the mean value of the accumulated congestion duration of the road segment,

is the variance of the accumulated congestion duration of the road segment, the mean μ _i and the variance

Calculated according to the following formula:

Among them, (β _{i, 1} , β _{i, 2} , . . . , β _{i, n} ) is a group of samples of the population, and n is the sample size.

Calculate the probability distribution that the cumulative congestion duration of the road section obeys, and calculate according to the following probability distribution formula:

因此得到如下公式：Further, through the statistics of the data, it is obtained that the cumulative congestion duration obeys a normal distribution,

So the following formula is obtained:

Among them, P{a<β _i ≤b} is the probability that the accumulated congestion duration β _i of road segment i is in the interval (a, b), f(x) is the probability density function of β _i , which is fitted according to the historical accumulated congestion duration Obtained, Φ(·) represents the distribution function of the standard normal distribution, and a and b are the set time period thresholds.

S31 Under the circumstance that the cumulative congestion duration of the road section is given, calculate the reliability that the cumulative congestion duration of the road section exceeds an expected threshold according to the probability distribution obeyed by the cumulative congestion duration of the road section, when the reliability of the cumulative congestion duration of the road section is calculated. When the set threshold ε ₁ is exceeded, it is determined that the road section is a frequently congested road section.

Calculate the reliability of the accumulated congestion duration of the road section according to the following formula:

P{β _i >T ₀ } is the probability that the cumulative congestion duration β _i of the road segment i is greater than the expected threshold T ₀ , and P{β _i >T ₀ } is used as the reliability of the cumulative congestion duration of the road segment.

1 is a processing flow chart of a method for identifying and screening frequently congested road sections provided by an embodiment of the present invention. Referring to FIG. 1 , another method for identifying and screening frequently occurring congested road sections is also included, including:

S10 obtains historical congestion data, and counts the accumulated congestion time of a certain road section every day.

Calculated according to the following formula:

Among them, β _i is the accumulated congestion duration of road segment i in one day, α _{i, j} represents whether road segment i is congested at time j·Δ, j=1, 2, ..., M, M represents the period in the comparison time period number, Δ represents the sampling interval of the data.

Illustratively, the traffic state includes three types: smooth, slow, and congested. Calculate the daily accumulated congestion time of each road segment. If the sampling interval is 5 minutes, there are 288 sampling periods in one day. If the road segment i is congested at time j·Δ, then α _i,j =1; if it is not congested, then α _i,j =0.

S20, according to the accumulated congestion duration of a certain road section, determine the probability distribution to which the accumulated congestion duration of the road section obeys.

其中μ_i为路段累计拥堵时长的均值，

为路段累计拥堵时长的方差，均值μ_i和方差

根据如下公式计算：Further, according to the cumulative congestion duration of a certain road section, it is determined that the probability distribution obeyed by the cumulative congestion duration of the road section is a normal distribution,

where μ _i is the mean value of the accumulated congestion duration of the road segment,

is the variance of the accumulated congestion duration of the road segment, the mean μ _i and the variance

Calculated according to the following formula:

Among them, (β _{i, 1} , β _{i, 2} , . . . , β _{i, n} ) is a group of samples of the population, and n is the sample size.

Calculate the probability distribution that the cumulative congestion duration of the road section obeys, and calculate according to the following probability distribution formula:

因此得到如下公式：Further, through the statistics of the data, it is obtained that the cumulative congestion duration obeys a normal distribution,

So the following formula is obtained:

Among them, P{a<β _i ≤b} is the probability that the accumulated congestion duration β _i of road segment i is in the interval (a, b), f(x) is the probability density function of β _i , which is fitted according to the historical accumulated congestion duration Obtained, Φ(·) represents the distribution function of the standard normal distribution.

S32 In the case of a given reliability, according to the probability distribution obeyed by the cumulative congestion duration of the road section, calculate the cumulative congestion duration of the given reliability of the road section, when the calculated cumulative congestion duration of the given reliability of the road section is calculated When the congestion duration exceeds the set threshold ε ₂ , it is determined that the road section is a frequently congested road section.

Calculate the cumulative congestion duration β _i of the given reliability θ of the road section, and calculate according to the following formula:

β _i =Φ ^-1 (1-θ)·σ _i +μ _i (7)

Among them, Φ ^-1 (·) represents the inverse function of the cumulative probability density function of the normal distribution, and the reliability is θ.

To sum up, the method for identifying and screening frequently congested road sections according to the embodiments of the present invention, and the probability-based method for identifying and screening frequently congested road sections, can identify the daily overall congestion level of the road section, and consider the volatility of congestion. . Identify and screen frequently congested road sections by calculating the reliability given the cumulative congestion duration of the road section, or calculate the cumulative congestion duration with the given reliability for the frequent congestion. The identification and screening of congested road sections can provide an accurate and effective reconstruction project library for urban congestion relief projects, provide early warning information for traffic management departments, take timely countermeasures to relieve congested traffic, and can find unreasonable road network planning. It provides a scientific basis for traffic planning and construction departments to re-plan road alignments and improve road infrastructure, so as to achieve the purpose of alleviating road congestion.

From the description of the above embodiments, those skilled in the art can clearly understand that the present invention can be implemented by means of software plus a necessary general hardware platform. Based on this understanding, the technical solutions of the present invention can be embodied in the form of software products in essence or the parts that make contributions to the prior art, and the computer software products can be stored in storage media, such as ROM/RAM, magnetic disks , CD, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods described in various embodiments or some parts of the embodiments of the present invention.

The above description is only a preferred embodiment of the present invention, but the protection scope of the present invention is not limited to this. Substitutions should be covered within the protection scope of the present invention. Therefore, the protection scope of the present invention should be subject to the protection scope of the claims.

Claims (4)

1. a kind of identification and screening method of frequent congestion road section, is characterized in that, comprises: Obtain historical congestion data, and count the cumulative congestion time of a road section every day; According to the cumulative congestion duration of a certain road section, determine the probability distribution that the cumulative congestion duration of the road section obeys; Given the cumulative congestion time of the road section, the reliability of the cumulative congestion time of the road section is calculated according to the probability distribution obeyed by the cumulative congestion time of the road section. When the reliability of the cumulative congestion time of the road section exceeds the set threshold When ε is ₁ , it is determined that the road section is a frequently congested road section; according to the probability distribution obeyed by the cumulative congestion duration of the road section, the reliability of the cumulative congestion duration of the road section is calculated, including: The reliability of the accumulated congestion duration of the road section is calculated according to the following formula:

P{β _i >T ₀ } is the probability that the accumulated congestion duration β _i of the road segment i is greater than the expected threshold T ₀ , and P{β _i >T ₀ } is used as the reliability of the accumulated congestion duration of the road segment. The cumulative congestion duration of a certain road section described above is determined, and the probability distribution that the cumulative congestion duration of the road section obeys is determined, including: According to the cumulative congestion duration of a certain road section, it is determined that the probability distribution obeyed by the cumulative congestion duration of the road section is a normal distribution,

where μ _i is the mean value of the accumulated congestion duration of the road segment,

is the variance of the accumulated congestion duration of the road segment; The mean μ _i and variance

Calculated according to the following formula:

Among them, (β _i,1 ,β _i,2 ,…,β _i,n ) is a group of samples of the population, and n is the sample size; According to the following probability distribution formula, calculate the probability distribution obeyed by the cumulative congestion duration of the road section:

Among them, P{a<β _i ≤b} is the probability that the accumulated congestion duration β _i of the road segment i is in the interval (a, b), f(x) is the probability density function of β _i , and Φ(·) represents the standard normal The distribution function of the distribution, a and b are the set time period thresholds. 2. The identification and screening method of frequently-occurring congested road sections according to claim 1, wherein the acquisition of historical congestion data and the daily cumulative congestion duration of a certain road section include: The daily cumulative congestion time of a certain road section is calculated according to the following formula:

Among them, β _i is the accumulated congestion time of road segment i in one day, α _i,j represents whether road segment i is congested at time j·Δ, j=1,2,...,M,M represents the period in the comparison time period number, Δ represents the sampling interval of the data, if the road segment i is congested at time j·Δ, then α _i,j =1; if it is not congested, then α _i,j =0. 3. A method for identifying and screening frequently congested road sections, characterized in that, comprising: Obtain historical congestion data, and count the cumulative congestion time of a road section every day; According to the cumulative congestion duration of a certain road section, determine the probability distribution that the cumulative congestion duration of the road section obeys; In the case of a given reliability, according to the probability distribution that the cumulative congestion duration of the road section obeys, the cumulative congestion duration of the given reliability of the road section is calculated. When the calculated cumulative congestion of the given reliability of the road section is calculated If the duration exceeds the set threshold ε ₂ , it is determined that the road section is a frequently congested road section; Determining, according to the cumulative congestion duration of a certain road section, the probability distribution that the cumulative congestion duration of the road section obeys, including: According to the cumulative congestion duration of a certain road section, it is determined that the probability distribution obeyed by the cumulative congestion duration of the road section is a normal distribution,

where μ _i is the mean value of the accumulated congestion duration of the road segment,

is the variance of the accumulated congestion duration of the road segment; The mean μ _i and variance

Calculated according to the following formula:

Among them, (β _i,1 ,β _i,2 ,…,β _i,n ) is a group of samples of the population, and n is the sample size; According to the following probability distribution formula, calculate the probability distribution obeyed by the cumulative congestion duration of the road section:

Among them, P{a<β _i ≤b} is the probability that the accumulated congestion duration β _i of the road segment i is in the interval (a, b), f(x) is the probability density function of β _i , and Φ(·) represents the standard normal The distribution function of the distribution; under the condition of a given reliability, according to the probability distribution obeyed by the cumulative congestion time of the road section, the cumulative congestion time of the given reliability θ of the road section is calculated, including: The cumulative congestion duration β _i of the given reliability θ of the road section is calculated according to the following formula: β _i =Φ ^-1 (1-θ)·σ _i +μ _i (7) Among them, Φ ^-1 (·) represents the inverse function of the cumulative probability density function of the normal distribution, and the reliability is θ. 4. The method for identifying and screening frequently-occurring congested road sections according to claim 3, characterized in that, the acquisition of historical congestion data and the daily accumulated congestion duration of a certain road section include: The daily accumulated congestion time of a certain road section is calculated according to the following formula:

Among them, β _i is the accumulated congestion time of road segment i in one day, α _i,j represents whether road segment i is congested at time j·Δ, j=1,2,...,M,M represents the period in the comparison time period number, Δ represents the sampling interval of the data, if the road segment i is congested at time j·Δ, then α _i,j =1; if it is not congested, then α _i,j =0.

Images