CN114708728B - Method for identifying traffic peak period, electronic equipment and storage medium - Google Patents
Method for identifying traffic peak period, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114708728B CN114708728B CN202210290685.2A CN202210290685A CN114708728B CN 114708728 B CN114708728 B CN 114708728B CN 202210290685 A CN202210290685 A CN 202210290685A CN 114708728 B CN114708728 B CN 114708728B
- Authority
- CN
- China
- Prior art keywords
- acquisition point
- sub
- data acquisition
- identification
- flow
- 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
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
- 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
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G08G1/0133—Traffic data processing for classifying traffic situation
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0141—Measuring and analyzing of parameters relative to traffic conditions for specific applications for traffic information dissemination
-
- 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
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
- G08G1/0145—Measuring and analyzing of parameters relative to traffic conditions for specific applications for active traffic flow control
Abstract
The method comprises the steps of carrying out area division on an identification area based on flow distance coefficients of a first reference flow sequence of each data acquisition point location and a second reference flow sequence in the identification area, determining each sub-area, determining the flow change state of each data acquisition point location in the sub-area based on the first reference flow sequence of each data acquisition point location in the sub-area aiming at any sub-area, and determining each key acquisition point location corresponding to the sub-area based on the flow change state of each data acquisition point location in the sub-area, wherein traffic operation data related to each key acquisition point location is used for judging the traffic rush hour of the sub-area. Therefore, the scheme can effectively dredge the traffic road sections possibly having traffic jam in time by accurately identifying the traffic peak time of each traffic road section in any sub-area in advance.
Description
Technical Field
The present application relates to the field of urban traffic management technologies, and in particular, to a method, an electronic device, and a storage medium for identifying a traffic rush hour.
Background
The relief of urban commuting congestion is a great civil demand, so that early-late peak traffic control for working days is the key point of daily work of urban traffic management and is also an important basis for measuring urban traffic management work. City operation monitoring analysis platform helps commander length to pay close attention to commuting trunk operation condition in morning and evening peak period, traffic flow steadily rises when the whole city, and make urban traffic pressure surge, the system reminds commander length morning and evening peak to be forthcoming, changeable to morning and evening peak mode, pay close attention to commuting trunk operation condition, then on duty through road surface traffic commander, command center remote signal, unusual incident is handled to the mode of induced intervention, alleviate the pressure of morning and evening peak commuting traffic with this, thereby can promote road network efficiency and intelligent management and control level, and can improve the trip quality, promote commuting happiness.
However, in the prior art, when identifying the peak of the urban traffic in the morning and the evening, the data factor considered for identifying the peak in the morning and the evening is missing, such as only adopting a certain data factor, and not considering other key data factors, so that the accuracy of identifying the peak in the morning and the evening for the traffic road section is low.
In summary, there is a need for a method for identifying a traffic peak period, so as to implement accurate early identification of the early and late peaks of each traffic section in an identification area, thereby effectively performing grooming on each traffic section.
Disclosure of Invention
The application provides a method, an electronic device and a storage medium for identifying a traffic peak period, so as to implement accurate identification in advance for early and late peaks of each traffic section in an identification area, thereby effectively performing grooming for each traffic section.
In a first aspect, an exemplary embodiment of the present application provides a method for identifying a traffic rush hour, including:
determining a first reference flow sequence of each data acquisition point location and a second reference flow sequence in an identification region according to m-day vehicle flow sequences acquired by each data acquisition point location in the identification region;
based on the flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point location, performing region division on the identification region to determine each sub-region;
for any sub-area, determining the flow change state of each data acquisition point in the sub-area based on the first reference flow sequence of each data acquisition point in the sub-area, and determining each key acquisition point corresponding to the sub-area based on the flow change state of each data acquisition point in the sub-area; the traffic operation data associated with each key acquisition point position is used for judging the traffic peak period of the sub-area;
the vehicle flow sequence of each data acquisition point on any day is used for representing the vehicle flow data acquired by the data acquisition point according to each set time period in the day; the data acquisition point is used for indicating the installation position of traffic monitoring equipment which is arranged on a traffic road section and used for acquiring traffic flow data.
In the technical scheme, by analyzing the historical vehicle flow sequence in the identification area, each sub-area in the identification area is determined, and current vehicle flow data of each key acquisition point in any sub-area is analyzed, so that the specific time period in which the sub-area starts to enter the traffic peak can be accurately determined, and accordingly, advanced accurate early warning of the traffic peak of each traffic road section in the sub-area can be realized, and therefore, each traffic road section in the sub-area can be effectively dredged, the normal operation of the traffic of each traffic road section in the sub-area can be ensured, and powerful support can be provided for effectively relieving traffic jam. Specifically, a first reference flow sequence of each data acquisition point and a second reference flow sequence of each data acquisition point in an identification region can be determined according to a m-day vehicle flow sequence acquired by each data acquisition point in the identification region, so that the identification region can be divided into regions based on a flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point, that is, each sub-region (each sub-region comprises at least one data acquisition point, and a certain distance relationship is satisfied between the at least one data acquisition point) can be accurately determined, accurate judgment of a traffic peak period of the sub-region can be finished through some data acquisition points in the sub-region in a subsequent targeted manner, effective support is provided, meanwhile, judgment of a traffic peak period of the identification region can be finished through each sub-region divided according to real historical data acquired by each data acquisition point in the identification region, an actual traffic scene can be fitted, a more actual traffic condition can be met, and early warning of the traffic peak period of the identification region can be finished, so that early warning of the traffic peak period can be provided for finding traffic congestion in advance and traffic congestion can be dredged in time. Then, for any sub-area, based on the first reference flow sequence of each data acquisition point in the sub-area, the flow change state of each data acquisition point in the sub-area is determined, and based on the flow change state of each data acquisition point in the sub-area, each key acquisition point corresponding to the sub-area (that is, a data acquisition point having a relatively large influence on the traffic peak period in the sub-area) can be accurately determined, so that the traffic peak period of the sub-area can be accurately determined by the traffic operation data (for example, the vehicle flow data of each key acquisition point in the early peak period identification period or the congestion information of each traffic road segment associated with each key acquisition point in the late peak period identification period) associated with each key acquisition point, thereby being beneficial to reducing the data calculation amount and improving the identification efficiency of the traffic peak period of the sub-area. Therefore, the scheme can effectively dredge the traffic road sections possibly having traffic jam in time by accurately identifying the traffic peak time of each traffic road section in any sub-area in advance (namely identifying the entering time period of the traffic peak time of each traffic road section in advance), thereby effectively relieving the traffic jam.
In some exemplary embodiments, the determining a first reference traffic sequence of each data collection point and a second reference traffic sequence in the identification area according to the m-day vehicle traffic sequence collected by each data collection point in the identification area includes:
for each data acquisition point location, determining a first reference flow value of the data acquisition point location in the set time period through vehicle flow data of the data acquisition point location in the set time period in the m days in each set time period, and determining a first reference flow sequence of the data acquisition point location according to the first reference flow value of the data acquisition point location in each set time period;
and determining a second reference flow value corresponding to the set time interval according to the first reference flow value of each data acquisition point position in the set time interval in each set time interval, and determining a second reference flow sequence in the identification area according to the second reference flow value corresponding to each set time interval.
In the above technical solution, in order to accurately partition the identification region and determine the flow rate change state of each data acquisition point in the identification region, first, a vehicle flow sequence of m days acquired by each data acquisition point in the identification region needs to be correspondingly processed, so as to accurately determine a first reference flow sequence (that is, a vehicle flow data of one data acquisition point in any set time period of m days determines a flow rate average value of the data acquisition point in the set time period) and a second reference flow sequence (that is, a flow rate average value of each data acquisition point in each set time period determined by each data acquisition point in common), which are used for assisting in partitioning the identification region and determining the flow rate change state of each data acquisition point, so that the first reference flow sequence of each data acquisition point and the second reference flow sequence of the identification region can be used as data bases for partitioning the identification region or determining the flow rate change state, so as to complete accurate identification in advance of a traffic peak period of each traffic section in the identification region.
In some exemplary embodiments, performing region division on the identification region based on a traffic distance coefficient between a first reference traffic sequence and a second reference traffic sequence of each data acquisition point location, and determining each sub-region includes:
for each data acquisition point location, determining a flow distance coefficient of the data acquisition point location according to a first reference flow sequence of the data acquisition point location and a second reference flow sequence in the identification area, and determining a spatial distance coefficient of the data acquisition point location based on a two-dimensional spatial coordinate of the data acquisition point location;
and carrying out region division on the identification region through the flow distance coefficient and the space distance coefficient of each data acquisition point position to determine each sub-region.
In the above technical solution, the identification area is divided by using the traffic distance coefficient (such as a traffic distribution distance value) and the spatial distance coefficient (such as a longitude and latitude coordinate distance value) of each data acquisition point as data bases for dividing the identification area, that is, using the attribute information (i.e., the traffic attribute and the spatial position attribute) of each data acquisition point as the division bases, so that the identification area can be accurately divided into sub-areas.
In some exemplary embodiments, said determining a traffic distance coefficient of said data acquisition point location according to a first reference traffic sequence of said data acquisition point location and a second reference traffic sequence within said identified region includes:
determining a reference flow difference value of the data acquisition point position in each set time period according to a second reference flow value corresponding to the set time period and a first reference flow value of the data acquisition point position in the set time period;
determining a flow distance coefficient of the data acquisition point according to the reference flow difference value of the data acquisition point at each set time interval;
determining a spatial distance coefficient of the data acquisition point location based on the two-dimensional spatial coordinates of the data acquisition point location includes:
determining a mean value of two-dimensional space coordinates in the identification area according to the two-dimensional space coordinates of the data acquisition point locations;
determining a spatial distance coefficient of the data acquisition point location according to the two-dimensional space coordinate mean value in the identification area and the two-dimensional space coordinate of the data acquisition point location;
the method comprises the following steps of carrying out region division on the identification region through the flow distance coefficient and the space distance coefficient of each data acquisition point location to determine each sub-region, wherein the method comprises the following steps:
generating a distance vector of each data acquisition point according to a flow distance coefficient and a space distance coefficient of the data acquisition point for each data acquisition point;
and performing cluster analysis on each data acquisition point location based on the distance vector of each data acquisition point location, and dividing the identification area into each sub-area.
In the above technical solution, in each set time period, a reference flow difference between a first reference flow value of any data acquisition point in the set time period and a reference flow difference before a second reference flow value corresponding to the set time period is determined, so that a flow distance coefficient of the data acquisition point can be accurately calculated by using the reference flow difference of the data acquisition point in each set time period, that is, a flow attribute of the data acquisition point is determined. And the spatial distance coefficient of the data acquisition point can be accurately calculated through the two-dimensional space coordinates (such as longitude and latitude coordinates) of the data acquisition point and the two-dimensional space coordinate mean value (such as the two-dimensional space coordinate mean value formed by the longitude mean value and the latitude mean value) jointly determined by the data acquisition points, namely, the spatial position attribute of the data acquisition point is determined. Therefore, the flow attribute and the spatial position attribute of each data acquisition point are used as data bases for area division, so that the identification area can be accurately divided, sub-areas (namely key sub-areas needing early warning in the rush hour) which are more fit with an actual traffic scene are obtained, early warning in the rush hour of key sub-areas in the identification area is more convenient to accurately carry out, and traffic jam can be effectively led in advance for traffic road sections (or important commuting road sections) which are possibly jammed in the key sub-areas in time, so that the traffic jam can be effectively relieved.
In some exemplary embodiments, said determining a flow rate change state of each data acquisition point location within said sub-area based on said first reference flow rate sequence of each data acquisition point location within said sub-area comprises:
for any data acquisition point location in the sub-region, determining a gradient vector of the data acquisition point location through a first reference flow sequence of the data acquisition point location; the gradient vector comprises a plurality of first gradient values; the first gradient value is used for representing the vehicle flow change degree of the data acquisition point position between the ith set time period and the (i-1) th set time period;
determining the flow variation coefficient of the data acquisition point according to the plurality of first gradient values; the flow change coefficient of the data acquisition point location is used for representing the flow change state of the data acquisition point location;
the determining each key acquisition point location corresponding to the sub-region based on the flow change state of each data acquisition point location in the sub-region comprises:
determining a flow reference value corresponding to each data acquisition point position in the sub-area through the vehicle flow sequence acquired by each data acquisition point position in the sub-area for n days;
sequencing the flow rate change coefficients of the data acquisition points in the sub-area in a descending order, taking the data acquisition points positioned in the first p positions as first candidate points, sequencing the flow rate reference values corresponding to the data acquisition points in the sub-area in a descending order, and taking the data acquisition points positioned in the first q positions as second candidate points;
and determining t intersection point positions between the p first candidate point positions and the q second candidate point positions, and taking the t intersection point positions as key acquisition point positions.
In the above technical solution, the key acquisition points are determined together by performing comprehensive analysis on the flow change coefficient and the flow reference value of each data acquisition point in the sub-region, so that the determined key acquisition points better conform to the actual traffic condition of the sub-region and can represent the influence degree on the traffic peak period determination of the sub-region, that is, the determined key acquisition points are data acquisition points having relatively large influence on the traffic peak period in the sub-region, and meanwhile, the accuracy of the determined key acquisition points can be ensured.
In some exemplary embodiments, each first gradient value is determined by:
determining a reference flow mean value corresponding to the data acquisition point location according to the first reference flow sequence of the data acquisition point location;
determining the flow difference value of the data acquisition point position between the ith set time period and the (i-1) th set time period;
and determining the first gradient value according to the reference flow mean value and the flow difference value.
In the above technical solution, through the flow change (i.e. multiple first gradient values) of the data acquisition point location in any adjacent set time period, the overall flow change degree of the data acquisition point location in one day can be accurately determined, and the overall flow change degree can reflect the influence degree of the data acquisition point location on the traffic peak period judgment of the sub-area, so as to provide data support for whether the data acquisition point location can be used as a key acquisition point location of the sub-area.
In some exemplary embodiments, the rush hour includes early peak;
the determination is made for the early peak of the subregion by:
setting a first identification time period for identifying whether a sub-region enters an early peak or not, and acquiring vehicle flow data of any key acquisition point in the sub-region in any first sub-identification time period aiming at any first sub-identification time period in the first identification time period; the first sub-identification period is a jth set period;
determining whether the key acquisition point enters an early peak or not in the first sub-identification period according to the vehicle traffic data of the key acquisition point in the first sub-identification period;
counting a first number of at least one key acquisition point position entering an early peak in the first sub-identification period in each key acquisition point position in the sub-area, counting a second number of each key acquisition point position in the sub-area, and determining a ratio of the first number to the second number;
if the ratio is larger than or equal to a preset threshold, determining that the sub-region enters an early peak in the first sub-identification period, and if the ratio is smaller than the preset threshold, determining that the sub-region does not enter the early peak in the first sub-identification period.
In the above technical solution, when performing early peak judgment for a sub-area, first, it is judged whether each key acquisition point in the sub-area enters an early peak in a current sub-identification period (that is, a certain sub-identification period in a first identification period belonging to early peak identification), and after the judgment for each key acquisition point is completed, a first number of at least one key acquisition point in each key acquisition point entering an early peak in the current sub-identification period is counted, and when a ratio of the first number to a total number (that is, a second number) of each key acquisition point is greater than or equal to a preset threshold, it can be accurately determined that the sub-area enters an early peak in the current sub-identification period, an early peak duty post can be laid in advance for the sub-area, so as to provide effective guarantee for ensuring that traffic of the sub-area can normally operate, otherwise it is determined that the sub-area does not enter an early peak in the current sub-identification period.
In some exemplary embodiments, said determining whether said critical collection point is entering early peak at said first sub-identified period from said vehicle traffic data of said critical collection point at said first sub-identified period comprises:
determining a vehicle flow mean value corresponding to the key acquisition point location according to a vehicle flow sequence of the key acquisition point location in the last day before the first sub-identification period;
determining a second gradient value and a third gradient value corresponding to the key acquisition point in the first sub-identification period according to the vehicle flow data of the key acquisition point in the first sub-identification period; the second gradient value is used for representing the vehicle flow change degree of the key acquisition point between the jth set time period and the jth-1 set time period; the third gradient value is used for representing the vehicle flow change degree of the key collection point between the jth set time period and the jth-2 set time period;
if the vehicle flow data of the key acquisition point in the first sub-identification period is greater than or equal to the vehicle flow mean value, the second gradient value is greater than or equal to a first gradient threshold value, and the third gradient value is greater than or equal to a second gradient threshold value, determining that the key acquisition point enters an early peak in the first sub-identification period, otherwise determining that the key acquisition point does not enter the early peak in the first sub-identification period.
In the above technical solution, for any key collection point in a sub-region, it can be determined that the key collection point enters an early peak in the current sub-identification period only by calculating a second gradient value and a third gradient value of the key collection point in the current sub-identification period and performing comprehensive judgment in combination with vehicle traffic data of the key collection point in the current sub-identification period, that is, it is determined that the key collection point enters the early peak in the current sub-identification period only if three conditions, that is, the second gradient value is greater than or equal to the first gradient threshold value, the third gradient value is greater than or equal to the second gradient threshold value, and the vehicle traffic data in the current sub-identification period is greater than or equal to the vehicle traffic mean value, are satisfied at the same time.
In some exemplary embodiments, the rush hour of traffic includes late peak;
the determination is made for the late peak of the subregion by:
determining each traffic road section associated with each key acquisition point in the sub-area through each key acquisition point corresponding to the sub-area, and setting a second identification time period for identifying whether the sub-area enters a late peak or not;
acquiring congestion information of each traffic section in a second sub-identification period aiming at any second sub-identification period in the second identification period, and converting the congestion information of the traffic section in the second sub-identification period into a corresponding congestion numerical value according to a congestion information conversion rule;
determining a congestion mean value corresponding to the sub-area in the second sub-identification period according to the congestion numerical value corresponding to each traffic section in the second sub-identification period;
and if the congestion mean value is larger than or equal to a congestion threshold, determining that the sub-region enters late peak in the second sub-identification period, and if the congestion mean value is smaller than the congestion threshold, determining that the sub-region does not enter late peak in the second sub-identification period.
In the technical scheme, when the late peak is judged for a sub-region, firstly, each traffic section associated with each key acquisition point in the sub-region is determined, congestion information of each traffic section in the current sub-identification time period (namely, congestion information of a certain sub-identification time period in the second identification time period belonging to the late peak identification) is obtained, whether the sub-region enters the late peak in the current sub-identification time period or not can be accurately judged through comprehensive analysis of the congestion information of each traffic section in the current sub-identification time period, and then, an late peak duty post can be laid in advance for the sub-region, so that effective guarantee can be provided for normal operation of traffic of the sub-region, otherwise, the sub-region is determined not to enter the late peak in the current sub-identification time period.
In a second aspect, an electronic device is provided in an exemplary embodiment of the present application, which includes a processor and a memory, the processor being connected to the memory, the memory storing a computer program, which when executed by the processor, causes the electronic device to perform: determining a first reference flow sequence of each data acquisition point and a second reference flow sequence in an identification region according to m-day vehicle flow sequences acquired by each data acquisition point in the identification region; performing region division on the identification region based on the flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point location to determine each sub-region; for any sub-region, determining the flow change state of each data acquisition point in the sub-region based on the first reference flow sequence of each data acquisition point in the sub-region, and determining each key acquisition point corresponding to the sub-region based on the flow change state of each data acquisition point in the sub-region; the traffic operation data associated with each key acquisition point position is used for judging the traffic peak period of the sub-area; the vehicle flow sequence of each data acquisition point on any day is used for representing the vehicle flow data acquired by the data acquisition point according to each set time period in the day; the data acquisition point is used for indicating the installation position of traffic monitoring equipment which is arranged on a traffic road section and used for acquiring traffic flow data.
In some exemplary embodiments, the electronic device is specifically configured to perform:
for each data acquisition point, determining a first reference flow value of the data acquisition point in a set time period through vehicle flow data of the data acquisition point in the set time period in m days in each set time period, and determining a first reference flow sequence of the data acquisition point according to the first reference flow value of the data acquisition point in each set time period;
and determining a second reference flow value corresponding to the set time interval according to the first reference flow value of each data acquisition point position in the set time interval in each set time interval, and determining a second reference flow sequence in the identification area according to the second reference flow value corresponding to each set time interval.
In some exemplary embodiments, the electronic device is specifically configured to perform:
for each data acquisition point location, determining a flow distance coefficient of the data acquisition point location according to a first reference flow sequence of the data acquisition point location and a second reference flow sequence in the identification area, and determining a spatial distance coefficient of the data acquisition point location based on a two-dimensional spatial coordinate of the data acquisition point location;
and carrying out region division on the identification region through the flow distance coefficient and the space distance coefficient of each data acquisition point position to determine each sub-region.
In some exemplary embodiments, the electronic device is specifically configured to perform:
determining a reference flow difference value of the data acquisition point position in each set time period according to a second reference flow value corresponding to the set time period and a first reference flow value of the data acquisition point position in the set time period;
determining a flow distance coefficient of the data acquisition point according to the reference flow difference value of the data acquisition point at each set time interval;
the electronic device is specifically configured to perform:
determining a mean value of two-dimensional space coordinates in the identification area according to the two-dimensional space coordinates of the data acquisition point locations;
determining a spatial distance coefficient of the data acquisition point location according to the two-dimensional space coordinate mean value in the identification area and the two-dimensional space coordinate of the data acquisition point location;
the electronic device is specifically configured to perform:
generating a distance vector of each data acquisition point according to a flow distance coefficient and a space distance coefficient of the data acquisition point for each data acquisition point;
and performing cluster analysis on each data acquisition point location based on the distance vector of each data acquisition point location, and dividing the identification area into each sub-area.
In some exemplary embodiments, the electronic device is specifically configured to perform:
for any data acquisition point location in the sub-region, determining a gradient vector of the data acquisition point location through a first reference flow sequence of the data acquisition point location; the gradient vector comprises a plurality of first gradient values; the first gradient value is used for representing the vehicle flow change degree of the data acquisition point position between the ith set time period and the (i-1) th set time period;
determining a flow variation coefficient of the data acquisition point according to the plurality of first gradient values; the flow change coefficient of the data acquisition point location is used for representing the flow change state of the data acquisition point location;
the electronic device is specifically configured to perform:
determining a flow reference value corresponding to each data acquisition point position in the sub-area through the vehicle flow sequence acquired by each data acquisition point position in the sub-area for n days;
sequencing the flow rate change coefficients of the data acquisition points in the sub-area in a descending order, taking the data acquisition points positioned in the first p positions as first candidate points, sequencing the flow rate reference values corresponding to the data acquisition points in the sub-area in a descending order, and taking the data acquisition points positioned in the first q positions as second candidate points;
and determining t intersection point positions between the p first candidate point positions and the q second candidate point positions, and taking the t intersection point positions as key acquisition point positions.
In some exemplary embodiments, the electronic device is specifically configured to perform:
determining a reference flow mean value corresponding to the data acquisition point location according to the first reference flow sequence of the data acquisition point location;
determining the flow difference value of the data acquisition point position between the ith set time period and the (i-1) th set time period;
and determining the first gradient value through the reference flow mean value and the flow difference value.
In some exemplary embodiments, the traffic peak periods include early peak;
the electronic device is specifically configured to perform:
setting a first identification time period for identifying whether a sub-region enters an early peak or not, and acquiring vehicle flow data of any key acquisition point in the sub-region in any first sub-identification time period aiming at any first sub-identification time period in the first identification time period; the first sub-identification period is a jth set period;
determining whether the key acquisition point enters an early peak or not in the first sub-identification period according to the vehicle traffic data of the key acquisition point in the first sub-identification period;
counting a first number of at least one key acquisition point position entering an early peak in the first sub-identification period in each key acquisition point position in the sub-area, counting a second number of each key acquisition point position in the sub-area, and determining a ratio of the first number to the second number;
if the ratio is larger than or equal to a preset threshold, determining that the sub-region enters an early peak in the first sub-identification period, and if the ratio is smaller than the preset threshold, determining that the sub-region does not enter the early peak in the first sub-identification period.
In some exemplary embodiments, the electronic device is specifically configured to perform:
determining a vehicle flow mean value corresponding to the key acquisition point location according to a vehicle flow sequence of the key acquisition point location in the last day before the first sub-identification period;
determining a second gradient value and a third gradient value corresponding to the key acquisition point in the first sub-identification period according to the vehicle flow data of the key acquisition point in the first sub-identification period; the second gradient value is used for representing the vehicle flow change degree of the key acquisition point between the jth set time period and the jth-1 set time period; the third gradient value is used for representing the vehicle flow change degree of the key collection point between the jth set time period and the jth-2 set time period;
if the vehicle flow data of the key acquisition point in the first sub-identification period is greater than or equal to the vehicle flow mean value, the second gradient value is greater than or equal to a first gradient threshold value, and the third gradient value is greater than or equal to a second gradient threshold value, determining that the key acquisition point enters an early peak in the first sub-identification period, otherwise determining that the key acquisition point does not enter the early peak in the first sub-identification period.
In some exemplary embodiments, the rush hour of traffic includes late peak;
the electronic device is specifically configured to perform:
determining each traffic road section associated with each key acquisition point in the sub-area through each key acquisition point corresponding to the sub-area, and setting a second identification time period for identifying whether the sub-area enters a late peak or not;
acquiring congestion information of each traffic section in a second sub-identification period aiming at any second sub-identification period in the second identification period, and converting the congestion information of the traffic section in the second sub-identification period into a corresponding congestion numerical value according to a congestion information conversion rule;
determining a congestion mean value corresponding to the sub-area in the second sub-identification time period according to the congestion numerical value corresponding to each traffic section in the second sub-identification time period;
and if the congestion mean value is larger than or equal to a congestion threshold, determining that the sub-region enters late peak in the second sub-identification period, and if the congestion mean value is smaller than the congestion threshold, determining that the sub-region does not enter late peak in the second sub-identification period.
In a third aspect, embodiments of the present application provide a computer-readable storage medium storing a computer program executable by a computing device, the program, when executed on the computing device, causing the computing device to perform the method for identifying peak traffic periods as described in any of the first aspects above.
Drawings
In order to more clearly illustrate the technical solutions of the present application, the drawings needed to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
FIG. 1 is a schematic flow chart diagram of a method for identifying rush hour traffic in accordance with some embodiments of the present application;
fig. 2 is a schematic structural diagram of an electronic device according to some embodiments of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be described in further detail with reference to the accompanying drawings, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 schematically shows a flow of a method for identifying a traffic rush hour according to an embodiment of the present application, and the flow may be executed by an electronic device. The electronic device may be a server, or a component (such as a chip or an integrated circuit) capable of supporting the server to implement the functions required by the method, or may be other devices having the functions required by the method, such as a traffic management platform.
As shown in fig. 1, the process specifically includes:
In the embodiment of the application, in order to accurately divide the identification region and determine the flow rate change state of each data acquisition point in the identification region in the following process, a vehicle flow sequence acquired by each data acquisition point in the identification region for m days needs to be correspondingly processed, so that a first reference flow sequence (that is, a flow rate mean value of one data acquisition point in any set time period determined by vehicle flow data of the data acquisition point in m days in the set time period) and a second reference flow sequence (that is, a flow rate mean value of each data acquisition point in each set time period determined by the data acquisition points in common) for assisting in dividing the identification region and determining the flow rate change state of each data acquisition point are accurately determined. Wherein m is an integer greater than 1; the vehicle flow sequence of each data acquisition point on any day is used for representing the vehicle flow data acquired by the data acquisition point according to each set time period in the day; the data acquisition point is used for indicating the installation position of traffic monitoring equipment which is arranged on a traffic road section and used for acquiring traffic flow data. Specifically, for any identification area (such as a city or a county), in order to monitor a traffic flow condition (or a traffic congestion condition) of a traffic road segment in time, a traffic monitoring device (such as a gate device or an electronic police device) is usually disposed on each traffic road segment to collect traffic passing data passing through the traffic road segment, and the traffic passing data is processed, so that convenience is brought to subsequent data processing. For example, the passing information may include passing time, driving direction, etc. of the vehicle passing through a gate device or an electronic police device, and the vehicle characteristics may include a license plate number, a vehicle color, a vehicle type, etc. Then, the vehicle flow sequence of m days collected by each collection point (such as I1, I2, I3, …, in) In the identification area is obtained first, that is, the vehicle flow data of each data collection point In each set time period In m days is obtained. The traffic monitoring equipment can collect the vehicle passing data of the traffic road section in real time, so that for convenience of subsequent calculation, when the vehicle passing data are processed, the vehicle passing data collected by the traffic monitoring equipment on the traffic road section are filtered and cleaned firstly, then the filtered vehicle passing data are subjected to statistical processing according to a plurality of set time intervals, for example, the time of one day is from zero to twenty-four, the set time interval is 15 minutes, and the time of one day can be divided into 96 set time intervals. Alternatively, the time of day may be divided into 72 set periods with one set period of 20 minutes per interval. Specifically, the setting of the set time period may be performed according to an actual application scenario, which is not limited in the embodiment of the present application. Therefore, the vehicle passing data acquired by the traffic monitoring equipment in real time in one day can be subjected to statistical processing according to the determined set time intervals, and the vehicle flow data corresponding to the traffic monitoring equipment in the set time intervals can be obtained. For example, a certain traffic monitoring device collects vehicle passing data of a traffic road section in every 5 seconds, every 10 seconds, and the like, and assuming that the vehicle passing data of the traffic road section in which the traffic monitoring device collects in a day is statistically processed according to a set time period of every 15 minutes, the vehicle passing data in 15 minutes from the zero point of the traffic monitoring device (i.e., the vehicle passing data in the interval 0. For example, the number of vehicles collected every 5 seconds within the 15 minutes is summed, and the summed number of vehicles may be used as the vehicle flow data corresponding to the 15 minutes, or may be converted into the number of vehicles per minute, and the converted value may also be used as the vehicle flow data corresponding to the 15 minutes, so that the subsequent data processing amount may be reduced, and the data error may be reduced. Of course, it should be understood by those skilled in the art that the traffic monitoring device may also collect the vehicle-passing data of the traffic road segment according to a preset time period, for example, a certain traffic monitoring device may collect the vehicle-passing data of the traffic road segment according to 5 minutes every other, 10 minutes every other, 15 minutes every other, or 20 minutes every other.
Then, after vehicle flow data of each data acquisition point in the identification area within m days (for example, 5 days, 7 days, or 10 days) at each set time period is obtained, for each data acquisition point, statistical processing may be performed on the vehicle flow data of the data acquisition point belonging to the same set time period within m days, that is, summing and averaging processing may be performed on the vehicle flow data of the data acquisition point belonging to the same set time period within m days, so that a first reference flow value of the data acquisition point at each set time period may be obtained, and thus a first reference flow sequence of the data acquisition point is constructed through the first reference value of the data acquisition point at each set time period. For example, taking the data collection point location I1 as an example, assuming that the data collection point location I1 counts the vehicle flow data for a set time interval every 15 minutes, the data collection point location I1 can count the vehicle flow data corresponding to 96 set time intervals, that is, the vehicle flow data corresponding to 96 set time intervals is C 1 1 、C 2 1 、C 3 1 、…、C 96 1 And assuming that the vehicle flow data of the data acquisition point at each set time interval within 5 days is acquired, the first reference flow value at the first set time interval is Q 1 I1 ＝(C 1 1 +C 1 2 +C 1 3 +C 1 4 +C 1 5 ) At the second set time intervalThe first reference flow value of 2 I1 (C 2 1 +C 2 2 +C 2 3 +C 2 4 +C 2 5 ) And/5, by analogy, first reference flow values of the data acquisition point I1 in 96 set time periods can be calculated. Meanwhile, in each set time interval, a second reference flow value corresponding to the set time interval can be determined through the first reference flow value of each data acquisition point position in the set time interval, and a second reference flow sequence in the identification area can be determined according to the second reference flow value corresponding to each set time interval. For example, assuming that there are 5 data acquisition points, that is, the data acquisition point location I1, the data acquisition point location I2, the data acquisition point location I3, the data acquisition point location I4, and the data acquisition point location I5, then according to the first reference flow values of the 5 data acquisition points in the first set time period, the second reference flow value corresponding to the first set time period may be calculated to be u1= (Q) 1 I1 +Q 1 I2 +Q 1 I3 +Q 1 I4 +Q 1 I5 ) And/5, calculating a second reference flow value u2= (Q) corresponding to a second set time interval according to the first reference flow values of the 5 data acquisition points in the second set time interval respectively 2 I1 +Q 2 I2 +Q 2 I3 +Q 2 I4 +Q 2 I5 ) And/5, and by analogy, calculating second reference flow values of the identification areas in 96 set time periods respectively.
102, performing region division on the identification region based on the flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point location, and determining each sub-region.
In the embodiment of the application, after the first reference flow sequence of each data acquisition point location and the second reference flow sequence in the identification area are determined, for each data acquisition point location, the flow distance coefficient of the data acquisition point location is determined according to the first reference flow sequence of the data acquisition point location and the second reference flow sequence in the identification area, and the space distance coefficient of the data acquisition point location is determined based on the two-dimensional space coordinate of the data acquisition point location. Then, through the flow distance coefficient and the space distance coefficient of each data acquisition point, the area division can be carried out on the identification area, and therefore each sub-area can be accurately determined. Wherein each sub-region includes at least one data acquisition point location.
And determining the reference flow difference value of the data acquisition point position in the set time period by the second reference flow value corresponding to the set time period and the first reference flow value of the data acquisition point position in the set time period in each set time period. Therefore, the flow distance coefficient of the data acquisition point can be accurately calculated through the reference flow difference value of the data acquisition point at each set time interval, namely the flow attribute of the data acquisition point is determined. Illustratively, assume that there are 3 data acquisition points, namely data acquisition point I1, data acquisition point I2 and data acquisition point I3, wherein the first reference flow sequence of data acquisition point I1 is [ Q ] 1 I1 ,Q 2 I1 ,Q 3 I1 ,…,Q 96 I1 ]The first reference flow sequence of the data acquisition point location I2 is [ Q ] 1 I2 ,Q 2 I2 ,Q 3 I2 ,…,Q 96 I2 ]The first reference flow sequence of the data acquisition point location I3 is [ Q ] 1 I3 ,Q 2 I3 ,Q 3 I3 ,…,Q 96 I3 ]. Through the respective first reference traffic sequence of the 3 data acquisition points, the second reference traffic sequence in the identification region can be calculated as [ u1, u2, u3, …, u96]. Wherein each second reference flow value in the second reference flow sequence is calculated by:
furthermore, for any data acquisition point Ij, the flow distance coefficient E of the data acquisition point Ij can be determined in the following manner Ij Namely:
or the above formula can be transformed into:
the number of the setting time periods in the above formula may be adjusted according to the number of the setting time periods determined by the specific actual requirements, for example, if the determined number of the setting time periods is 72, the above formula may be changed to:
or the above formula can be transformed into:
in addition, according to the two-dimensional space coordinates of each data acquisition point location, the mean value of the two-dimensional space coordinates in the identification area is determined, and the spatial distance coefficient of the data acquisition point location, that is, the spatial position attribute of the data acquisition point location, can be determined through the mean value of the two-dimensional space coordinates in the identification area and the two-dimensional space coordinates of the data acquisition point location. For example, for any data acquisition point Ij, two-dimensional space coordinates of the data acquisition point Ij, that is, ij (longitudeIj, latitudeIj), may be obtained, where longitude is used to represent a longitude of the data acquisition point Ij, and latitude is used to represent a latitude of the data acquisition point Ij. Thus, the spatial distance coefficient S of the data acquisition point Ij can be calculated in the following way Ij Namely:
or the above formula can be transformed into:
wherein the content of the first and second substances,
represents an average longitudinal coordinate of each data collection point, and->
And the average latitude coordinate of each data acquisition point is represented.
Then, for each data acquisition point, according to the flow distance coefficient and the spatial distance coefficient of the data acquisition point, a distance vector of the data acquisition point can be generated, and based on the distance vector of each data acquisition point, clustering analysis is performed on each data acquisition point, that is, the identification region can be divided into sub-regions. Illustratively, for a data collection point Ij, a flow distance coefficient E according to the data collection point Ij Ij And a spatial distance coefficient S Ij I.e. a hybrid distance vector, i.e. a two-dimensional vector D, can be generated Ij [E Ij ,S Ij ]Thus, the mixed distance vector { D) of all the data acquisition point positions can be obtained I1 ,D I2 ,…,D In }. Based on this, two data acquisition points (e.g., D) are further computed I1 And D I2 ) The formula for calculating the mixing distance D is as follows:
where Σ is the n-dimensional mixed-distance vector { D I1 ,D I2 ,…,D In The covariance matrix of.
Finally, based on the mixed distance D between any two data acquisition points in all the data acquisition points, all the data acquisition points are clustered by using a clustering algorithm (such as a K-means clustering algorithm, a density-based clustering method, and the like), that is, the data acquisition points of the same category are classified into one sub-region according to a clustering result, so as to form a plurality of sub-regions (that is, key sub-regions), for example, using the K-means clustering algorithm, the number of clusters K may be set according to an actual application scenario or experience of a person skilled in the art, and generally the number of clusters K is set to 4,5,6 and the like.
103, for any sub-region, determining a flow change state of each data acquisition point in the sub-region based on the first reference flow sequence of each data acquisition point in the sub-region, and determining each key acquisition point corresponding to the sub-region based on the flow change state of each data acquisition point in the sub-region.
In this embodiment of the application, for any sub-region, for any data acquisition point location in the sub-region, a gradient vector of the data acquisition point location may be determined through a first reference flow sequence of the data acquisition point location, where the gradient vector may include a plurality of first gradient values; the first gradient value is used for representing the vehicle flow change degree of the data acquisition point between the ith set time period and the (i-1) th set time period. Then, according to a plurality of first gradient values, the flow change coefficient of the data acquisition point location can be determined; and the flow change coefficient of the data acquisition point is used for representing the flow change state of the data acquisition point.
According to the first reference flow sequence of the data acquisition point location, the reference flow mean value corresponding to the data acquisition point location can be determined, and the flow difference value of the data acquisition point location between the ith set time period and the (i-1) th set time period is determined. Then, the first gradient value can be accurately determined by referring to the flow mean value and the flow difference value.
Illustratively, for any data acquisition point Ik in a sub-region, a gradient vector [ g ] of the data acquisition point Ik is calculated 1 Ik ,g 2 Ik ,…,g 96 Ik ]Wherein g is 1 Ik ＝0，g 2 Ik ,…,g 96 Ik The data acquisition point Ik has the following flow variation degrees between the following values of 0. Wherein, g 2 Ik ,…,g 96 Ik The calculation can be performed in the following manner.
Wherein the content of the first and second substances,
represents the gradient value corresponding to the data acquisition point Ik in a certain set time period (such as the ith set time period), i is an integer greater than 1, and/or>
And the flow difference value of the data acquisition point Ik in two adjacent set time periods is represented.
The above formula can also be transformed into:
after the gradient value corresponding to the data acquisition point Ik at each set time interval is calculated, the flow rate change coefficient C of the data acquisition point Ik can be calculated according to the gradient value corresponding to the data acquisition point Ik at each set time interval Ik . Specifically, the calculation can be performed in the following manner.
Meanwhile, acquiring the vehicle flow sequence of n days collected by each data collection point position in the sub-area, and determining the flow reference value corresponding to each data collection point position in the sub-area through the vehicle flow sequence of n days collected by each data collection point position in the sub-area. For example, obtain the childThe vehicle flow sequence of each data acquisition point in the area within 3 days (or 5 days, etc.), and for each data acquisition point, the vehicle flow sequence of the data acquisition point within 3 days (or 5 days, etc.) is subjected to averaging processing, so that the vehicle flow mean value of the data acquisition point within one day can be obtained, or the vehicle flow sequence of each data acquisition point within the sub-area within the day closest to the identification period can be used, and for each data acquisition point, the maximum vehicle flow is determined from the vehicle flow sequence of the data acquisition point within the day closest to the identification period and is used for representing the vehicle flow trend degree of the data acquisition point within one day. Thus, the flow reference value of each data acquisition point in the subarea can be calculated to be { Q I1 ,Q I2 ,…,Q Ik }。
Then, sorting the flow rate change coefficients of the data acquisition points in the sub-area according to a descending order, taking the data acquisition points which are sorted in the first p positions as first candidate points, sorting the flow rate reference values corresponding to the data acquisition points in the sub-area according to a descending order, and taking the data acquisition points which are sorted in the first q positions as second candidate points. And determining t intersection point positions between the p first candidate point positions and the q second candidate point positions, and taking the t intersection point positions as key acquisition point positions. Wherein t is an integer of 1 or more. Illustratively, the flow rate change coefficient { C ] of each data acquisition point in the subregion I1 ,C I2 ,…,C Ik Sorting according to the descending order, and sorting the data acquisition points (I) positioned at the first p data acquisition points 1 r ,I 2 r ,…,I p r As a first candidate point location set, where the value range of p is [2,10 ]]Certainly, the value can also be 0.5k, and the value can be set according to the size of the sub-region, and the larger the sub-region is, the larger the value of p is. Meanwhile, the flow reference value { Q) corresponding to each data acquisition point in the subarea is determined I1 ,Q I2 ,…,Q Ik Sorting according to the descending order, and sorting the data acquisition point positions (I) positioned at the first q 1 r ,I 2 r ,…,I q r As a second candidate point location set, wherein the value range of q is [2,10 ] in general]Of course, the value may also be 0.5k, and the value may be set according to the size of the sub-region, and the larger the sub-region is, the larger the value q is. Then, a first set of candidate point bits { I } is computed 1 r ,I 2 r ,…,I p r With a second set of alternative point locations I 1 r ,I 2 r ,…,I q r The intersection of { I }, i.e. { I } 1 r ,I 2 r ,…,I p r }∩{I 1 r ,I 2 r ,…,I q r And determining t intersection point positions which serve as key acquisition point positions.
After determining each key acquisition point location corresponding to the sub-area, the traffic operation data (such as vehicle flow data or congestion information) associated with each key acquisition point location may be used to determine the traffic peak time of the sub-area. Specifically, the traffic peak period comprises an early peak and a late peak, when the early peak of the sub-region is judged, a first identification time period for identifying whether the sub-region enters the early peak is set firstly, and vehicle flow data of any key collection point in the sub-region in the first sub-identification time period is acquired aiming at any first sub-identification time period in the first identification time period; the first sub-identification period is a jth set period, that is, a current sub-identification period. Then, whether the key acquisition point enters an early peak in the first sub-identification period or not can be determined through the vehicle flow data of the key acquisition point in the first sub-identification period, after whether the key acquisition point enters the early peak in the first sub-identification period or not is judged, a first quantity of at least one key acquisition point entering the early peak in the first sub-identification period in each key acquisition point in the sub-area can be counted, a second quantity of each key acquisition point in the sub-area is counted, the ratio of the first quantity to the second quantity is determined, if the ratio is larger than or equal to a preset threshold value, the sub-area can be determined to enter the early peak in the first sub-identification period, an early peak duty can be laid in advance for the sub-area, so that effective guarantee can be provided for ensuring normal operation of traffic of the sub-area, and if the ratio is smaller than a preset threshold value, the sub-area can be determined not enter the early peak in the first sub-identification period. The preset threshold may be set according to experience of a person skilled in the art, or may be set according to results obtained from multiple experiments, or may be set according to an actual application scenario, which is not limited in the embodiment of the present application.
When a certain key acquisition point enters an early peak in a first sub-identification period, firstly, according to a vehicle flow sequence of the key acquisition point in the last day before the first sub-identification period, a vehicle flow mean value corresponding to the key acquisition point can be determined, and a second gradient value and a third gradient value corresponding to the key acquisition point in the first sub-identification period are determined according to vehicle flow data of the key acquisition point in the first sub-identification period, wherein the second gradient value is used for representing the vehicle flow change degree of the key acquisition point between a jth set period and a jth-1 set period; and the third gradient value is used for representing the vehicle flow change degree of the key collection point between the jth set time period and the jth-2 set time period. Then, whether the key acquisition point enters the early peak or not in the first sub-identification period can be accurately determined according to the magnitude relation between the vehicle flow data of the key acquisition point in the first sub-identification period and the vehicle flow mean value, the magnitude relation between the second gradient value and the first gradient threshold value, and the magnitude relation between the third gradient value and the second gradient threshold value. If the vehicle flow data of the key acquisition point in the first sub-identification period is greater than or equal to the vehicle flow mean value, the second gradient value is greater than or equal to the first gradient threshold value, and the third gradient value is greater than or equal to the second gradient threshold value, determining that the key acquisition point enters an early peak in the first sub-identification period, namely determining that the key acquisition point enters the early peak in the first sub-identification period when determining that the key acquisition point meets the three conditions at the same time, otherwise determining that the key acquisition point does not enter the early peak in the first sub-identification period. So, through the early peak to the subregion judge in advance, discover in advance to possible early warning in advance, just so can lay early peak duty post to this subregion in advance, the early peak needs to carry out the roll call to the personnel on duty before coming, confirms the out-of-office early peak post condition in place, then command center video patrol and examine the post and begin to carry out the round trip to important commuting highway section, with this guarantee key road normal operating. When the abnormal traffic events are found through various means such as video inspection, radio stations and the like, the severity of the events needs to be evaluated, if the abnormal traffic events are general police conditions, the processing department directly sends the police officers to handle the abnormal traffic events, and when the abnormal traffic events are serious, the police officers need to pay attention and conduct the abnormal traffic events in a unified way by a command leader, and the abnormal traffic events are handled by intervention means such as signal control, induced release and the like.
Illustratively, a first identification period for identifying whether the sub-area enters the early peak or not may be set, such as an identification period from 6 to 10 in the morning of each day for judging the early peak, or an identification period from 6 to 11 in the morning of each day for judging the early peak, for example, the identification period from 6 to 00 to 15 in the morning of each day is set, and the setting of the identification period may be specifically set according to an actual application scenario or according to experience of a person skilled in the art, and is not limited in the embodiment of the present application. And aiming at any key acquisition point Ii in a certain sub-area, acquiring the position of the key acquisition point Ii in the first sub-identification period (namely the current sub-identification period Q) i d ) The last day before vehicle flow sequence, i.e. [ Q ] 1 d-1 ,Q 2 d-1 ,…,Q 96 d-1 ]That is, the average value of the vehicle flow corresponding to the key collection point Ii, i.e. (Q) 1 d-1 +Q 2 d-1 +…+Q 96 d-1 )/96. Then, the second gradient value of the key acquisition point Ii in the first sub-identification period j may be calculated as follows.
Wherein the content of the first and second substances,
represents a second gradient value corresponding to the data acquisition point Ik in a certain sub-identification period (e.g., the jth set period), j is an integer greater than 1, and/or is greater than or equal to>
And the flow difference of the data acquisition point Ii in two adjacent set time periods is represented.
Meanwhile, the third gradient value of the key acquisition point Ii in the first sub-identification period j may be calculated as follows.
Wherein the content of the first and second substances,
represents a third gradient value corresponding to the data acquisition point Ik in a certain sub-identification period (e.g., the jth set period), j is an integer greater than 1, and/or is greater than or equal to>
And the flow difference of the data acquisition point Ii at two set time intervals is shown.
Then, vehicle flow data corresponding to the critical acquisition point Ii in the first sub-identification period j is judged
The second gradient value->
A third gradient value->
And when the following conditions are met, the key acquisition point position Ii can be judged to enter an early peak in the first sub-identification period j.
Wherein, a and b can be set according to the practical application scenario or experience of those skilled in the art, for example, a can be set to 0.2, and b can be set to 0.3.
After judging whether each key acquisition point in the sub-area enters the early peak in the first sub-identification period or not, determining whether the key acquisition point enters the early peak in the first sub-identification period or not for the key acquisition point, if so, marking 1 for the key acquisition point, and marking 1 for all subsequent sub-identification periods for the key acquisition point. Then, counting a first number alpha of at least one key acquisition point position entering an early peak in the first identification time period in each key acquisition point position in the sub-region, counting the total number t of each key acquisition point position in the sub-region, judging whether alpha is larger than or equal to delta t, if so, judging that the sub-region enters the early peak in the first sub-identification time period, and otherwise, judging that the sub-region does not enter the early peak in the first sub-identification time period. Wherein δ is a determination threshold, the value range is [0.5,1], the value is generally 0.6, the smaller the threshold, the higher the representative sensitivity, and the specific adjustment can be performed according to the actual situation.
In addition, when the late peak of the sub-region is judged, a second identification time period for identifying whether the sub-region enters the late peak or not is set, and each traffic road section associated with each key acquisition point in the sub-region can be accurately determined through each key acquisition point corresponding to the sub-region. And then, aiming at any second sub-identification time interval in the second identification time interval, obtaining the congestion information of each traffic section in the second sub-identification time interval, and converting the congestion information of the traffic section in the second sub-identification time interval into a corresponding congestion numerical value according to a congestion information conversion rule. Then, according to the congestion value of each traffic section corresponding to the second sub-identification time interval, the congestion mean value of the sub-area corresponding to the second sub-identification time interval can be determined, and whether the sub-area enters the late peak or not in the second sub-identification time interval can be accurately determined according to the size relation between the congestion mean value and the congestion threshold. If the average congestion value is greater than or equal to the congestion threshold, it can be determined that the sub-area enters the late peak in the second sub-identification period, then a late peak duty guard can be laid for the sub-area in advance so as to provide effective guarantee for ensuring that the traffic of the sub-area can normally operate, and if the average congestion value is less than the congestion threshold, it can be determined that the sub-area does not enter the late peak in the second sub-identification period. So, through the judgement in advance to the late peak of subregion, discover in advance to accomplish early warning in advance, just so can lay late peak duty post to this subregion in advance, the late peak needs to carry out the roll call to the personnel on duty before coming, confirms the outdoor evening peak post condition of in place, then command center video patrol and examine the post and begin to carry out the round trip to important commuting highway section, with this guarantee key road normal operating. When the traffic abnormal events are found by various means such as video inspection, radio stations and the like, the severity of the events needs to be evaluated, if the events are general police conditions, a processing department directly sends duty personnel to handle the events, and when the events are serious, a command leader needs to pay attention and conduct in a unified mode, and the handling is finished by intervention means such as signal control, induced release and the like.
For example, the late peak identification for the sub-area cannot be calculated according to the change rate of the flow, and the late peak identification for the sub-area should be calculated according to the congestion information of each traffic section associated with each key acquisition point in the sub-area. Specifically, first, a first identification period for identifying whether a subregion enters the late peak or not may be set, such as that from 16 to 20 pm daily. Then, through each key acquisition point in the sub-area, a plurality of traffic road sections { R ] associated with each key acquisition point in the sub-area can be screened out from each traffic road section in the identification area 1 ,R 2 ,…,R n Get togetherAnd the congestion information of the plurality of traffic road sections in the second sub-identification period is used for judging the late peak aiming at the sub-area. Then, congestion information (such as congestion index or other congestion status data) of each traffic road segment in a certain sub-identification period (such as a period spaced by 15 minutes or a period spaced by 20 minutes) may be obtained through some approaches (such as a traffic control platform, the internet or high-level software), for example, taking the period spaced by 15 minutes as an example, a day is from zero to twenty-four points, a setting period is set at 15 minutes, a day may be divided into 96 setting periods, and congestion information of each traffic road segment in each setting period in a certain day d is { S } S 1 d ,S 2 d ,…,S 96 d Or, taking a time interval of 20 minutes as an example, the time of day may be divided into 72 set time intervals, and the congestion information of each traffic road segment in each set time interval in a certain day d is { S } 1 d ,S 2 d ,…,S 72 d }。
After the congestion information of each traffic section in each set time period in a certain day d is obtained, the congestion information of the traffic section in each set time period can be converted into the corresponding congestion numerical value according to the congestion information conversion rule. For example, the conversion may be performed according to the following conversion rules, that is:
wherein the content of the first and second substances,
for indicating a converted congestion value, <' > or>
For indicating congestion information for the ith set period.
In addition, the congestion mean value corresponding to the sub-area in the second sub-identification period can be determined in the following manner
Namely:
wherein, the method is used for representing the number of each traffic road section associated with each key acquisition point in the sub-area,
for representing traffic sections R i Corresponding congestion values.
For example, assuming that each key collection point of a certain sub-area is associated with 3 traffic road segments, i.e., a traffic road segment R1, a traffic road segment R2 and a traffic road segment R3, and assuming that the current sub-identification time period belonging to the late peak is s, after the congestion information of the 3 traffic road segments in the current sub-identification time period s is respectively converted into corresponding congestion values in the above manner, i.e., the congestion value of the traffic road segment R1 in the current sub-identification time period s is s
The congestion value of the traffic section R2 corresponding to the current sub-identification period s is ≥>
The congestion value corresponding to the traffic section R3 in the current sub-identification period s is ≥>
After determining the congestion values of the 3 traffic road segments corresponding to the current sub-identification time period s, the average road condition of the 3 traffic road segments can be calculated (i.e. calculating the congestion average value of the sub-region corresponding to the current sub-identification time period s), that is, the average road condition is the average road condition
If the average road condition of the 3 traffic road sections
The condition that the sub-region enters late peak at the current sub-identification period s is satisfied.
Wherein λ is used to represent a congestion threshold, and the larger the value is, the lower the sensitivity is, the value range is generally [0.2,1], and of course, the value range can also be adjusted according to actual conditions.
The above embodiments show that, according to the technical scheme in the application, each sub-area in the identification area is determined by analyzing the historical vehicle flow sequence in the identification area, and the current vehicle flow data of each key acquisition point in any sub-area is analyzed, so that the specific time period in which the sub-area starts to enter the traffic peak can be accurately determined, and therefore, accurate early warning in advance for the traffic peak of each traffic road section in the sub-area can be realized, and therefore, traffic of each traffic road section in the sub-area can be effectively dredged, the normal operation of the traffic of each traffic road section in the sub-area can be ensured, and powerful support can be provided for effective relief of traffic jam. Specifically, a first reference flow sequence of each data acquisition point and a second reference flow sequence of each data acquisition point in an identification region can be determined according to a m-day vehicle flow sequence acquired by each data acquisition point in the identification region, so that the identification region can be divided into regions based on a flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point, that is, each sub-region (each sub-region comprises at least one data acquisition point, and a certain distance relationship is satisfied between the at least one data acquisition point) can be accurately determined, accurate judgment of a traffic peak period of the sub-region can be finished through some data acquisition points in the sub-region in a subsequent targeted manner, effective support is provided, meanwhile, judgment of a traffic peak period of the identification region can be finished through each sub-region divided according to real historical data acquired by each data acquisition point in the identification region, an actual traffic scene can be fitted, a more actual traffic condition can be met, and early warning of the traffic peak period of the identification region can be finished, so that early warning of the traffic peak period can be provided for finding traffic congestion in advance and traffic congestion can be dredged in time. Then, for any sub-area, based on the first reference flow sequence of each data acquisition point in the sub-area, the flow change state of each data acquisition point in the sub-area is determined, and based on the flow change state of each data acquisition point in the sub-area, each key acquisition point corresponding to the sub-area (that is, a data acquisition point having a relatively large influence on the traffic peak period in the sub-area) can be accurately determined, so that the traffic peak period of the sub-area can be accurately determined by the traffic operation data (for example, the vehicle flow data of each key acquisition point in the early peak period identification period or the congestion information of each traffic road segment associated with each key acquisition point in the late peak period identification period) associated with each key acquisition point, thereby being beneficial to reducing the data calculation amount and improving the identification efficiency of the traffic peak period of the sub-area. Therefore, the scheme can effectively dredge the traffic road sections possibly having traffic jam in time by accurately identifying the traffic peak time of each traffic road section in any sub-area in advance (namely identifying the entering time period of the traffic peak time of each traffic road section in advance), thereby effectively relieving the traffic jam.
Based on the same technical concept, fig. 2 exemplarily shows an electronic device provided in an embodiment of the present application, and the electronic device may execute a flow of a method for identifying a traffic peak period. The electronic device may be a server, or a component (such as a chip or an integrated circuit) capable of supporting the server to implement the functions required by the method, or may be other devices having the functions required by the method, such as a traffic management platform.
As shown in fig. 2, the electronic device includes a processor 201 and a memory 202. In the embodiment of the present application, a specific connection medium between the processor 201 and the memory 202 is not limited, and the processor 201 and the memory 202 in fig. 2 are connected through a bus as an example. The bus may be divided into an address bus, a data bus, a control bus, etc. The memory 202 stores a computer program that, when executed by the processor 201, causes the electronic device to perform: determining a first reference flow sequence of each data acquisition point location and a second reference flow sequence in an identification region according to m-day vehicle flow sequences acquired by each data acquisition point location in the identification region; performing region division on the identification region based on the flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point location to determine each sub-region; for any sub-region, determining the flow change state of each data acquisition point in the sub-region based on the first reference flow sequence of each data acquisition point in the sub-region, and determining each key acquisition point corresponding to the sub-region based on the flow change state of each data acquisition point in the sub-region; the traffic operation data associated with each key acquisition point position is used for judging the traffic peak period of the sub-area; the vehicle flow sequence of each data acquisition point on any day is used for representing the vehicle flow data acquired by the data acquisition point according to each set time period in the day; the data acquisition point is used for indicating the installation position of traffic monitoring equipment which is arranged on a traffic road section and used for acquiring traffic flow data.
In some exemplary embodiments, the electronic device is specifically configured to perform:
for each data acquisition point location, determining a first reference flow value of the data acquisition point location in the set time period through vehicle flow data of the data acquisition point location in the set time period in the m days in each set time period, and determining a first reference flow sequence of the data acquisition point location according to the first reference flow value of the data acquisition point location in each set time period;
and determining a second reference flow value corresponding to the set time interval according to the first reference flow value of each data acquisition point position in the set time interval in each set time interval, and determining a second reference flow sequence in the identification area according to the second reference flow value corresponding to each set time interval.
In some exemplary embodiments, the electronic device is specifically configured to perform:
for each data acquisition point location, determining a flow distance coefficient of the data acquisition point location according to a first reference flow sequence of the data acquisition point location and a second reference flow sequence in the identification area, and determining a spatial distance coefficient of the data acquisition point location based on a two-dimensional spatial coordinate of the data acquisition point location;
and carrying out region division on the identification region through the flow distance coefficient and the space distance coefficient of each data acquisition point position to determine each sub-region.
In some exemplary embodiments, the electronic device is specifically configured to perform:
determining a reference flow difference value of the data acquisition point position in each set time period according to a second reference flow value corresponding to the set time period and a first reference flow value of the data acquisition point position in the set time period;
determining a flow distance coefficient of the data acquisition point according to the reference flow difference value of the data acquisition point at each set time period;
the electronic device is specifically configured to perform:
determining a mean value of two-dimensional space coordinates in the identification area according to the two-dimensional space coordinates of the data acquisition point locations;
determining a spatial distance coefficient of the data acquisition point location according to the two-dimensional space coordinate mean value in the identification area and the two-dimensional space coordinate of the data acquisition point location;
the electronic device is specifically configured to perform:
generating a distance vector of each data acquisition point according to a flow distance coefficient and a space distance coefficient of the data acquisition point for each data acquisition point;
and performing cluster analysis on each data acquisition point location based on the distance vector of each data acquisition point location, and dividing the identification area into each sub-area.
In some exemplary embodiments, the electronic device is specifically configured to perform:
determining a gradient vector of any data acquisition point location in the sub-region through a first reference flow sequence of the data acquisition point location; the gradient vector comprises a plurality of first gradient values; the first gradient value is used for representing the vehicle flow change degree of the data acquisition point position between the ith set time period and the (i-1) th set time period;
determining a flow variation coefficient of the data acquisition point according to the plurality of first gradient values; the flow change coefficient of the data acquisition point location is used for representing the flow change state of the data acquisition point location;
the electronic device is specifically configured to perform:
determining a flow reference value corresponding to each data acquisition point in the sub-area through the vehicle flow sequence acquired by each data acquisition point in the sub-area for n days;
sequencing the flow rate change coefficients of the data acquisition points in the sub-area in a descending order, taking the data acquisition points positioned in the first p positions as first candidate points, sequencing the flow rate reference values corresponding to the data acquisition points in the sub-area in a descending order, and taking the data acquisition points positioned in the first q positions as second candidate points;
and determining t intersection point positions between the p first candidate point positions and the q second candidate point positions, and taking the t intersection point positions as key acquisition point positions.
In some exemplary embodiments, the electronic device is specifically configured to perform:
determining a reference flow mean value corresponding to the data acquisition point location according to the first reference flow sequence of the data acquisition point location;
determining the flow difference value of the data acquisition point position between the ith set time period and the (i-1) th set time period;
and determining the first gradient value through the reference flow mean value and the flow difference value.
In some exemplary embodiments, the traffic peak periods include early peak;
the electronic device is specifically configured to perform:
setting a first identification time period for identifying whether a sub-region enters an early peak or not, and acquiring vehicle flow data of any key acquisition point in the sub-region in any first sub-identification time period aiming at any first sub-identification time period in the first identification time period; the first sub-identification period is a jth set period;
determining whether the key acquisition point enters an early peak or not in the first sub-identification period according to the vehicle traffic data of the key acquisition point in the first sub-identification period;
counting a first number of at least one key acquisition point position entering an early peak in the first sub-identification period in each key acquisition point position in the sub-area, counting a second number of each key acquisition point position in the sub-area, and determining a ratio of the first number to the second number;
if the ratio is greater than or equal to a preset threshold, determining that the sub-region enters an early peak in the first sub-identification period, and if the ratio is smaller than the preset threshold, determining that the sub-region does not enter the early peak in the first sub-identification period.
In some exemplary embodiments, the electronic device is specifically configured to perform:
determining a vehicle flow mean value corresponding to the key acquisition point location according to a vehicle flow sequence of the key acquisition point location in the last day before the first sub-identification period;
determining a second gradient value and a third gradient value corresponding to the key acquisition point in the first sub-identification period according to the vehicle flow data of the key acquisition point in the first sub-identification period; the second gradient value is used for representing the vehicle flow change degree of the key acquisition point between the jth set time period and the jth-1 set time period; the third gradient value is used for representing the vehicle flow change degree of the key acquisition point between the jth set time period and the jth-2 set time period;
if the vehicle traffic data of the key acquisition point in the first sub-identification period is greater than or equal to the vehicle traffic mean value, the second gradient value is greater than or equal to a first gradient threshold value, and the third gradient value is greater than or equal to a second gradient threshold value, determining that the key acquisition point enters an early peak in the first sub-identification period, otherwise determining that the key acquisition point does not enter the early peak in the first sub-identification period.
In some exemplary embodiments, the rush hour includes late peak;
the electronic device is specifically configured to perform:
determining each traffic road section associated with each key acquisition point in the sub-area through each key acquisition point corresponding to the sub-area, and setting a second identification time period for identifying whether the sub-area enters a late peak or not;
acquiring congestion information of each traffic section in a second sub-identification period aiming at any second sub-identification period in the second identification period, and converting the congestion information of the traffic section in the second sub-identification period into a corresponding congestion numerical value according to a congestion information conversion rule;
determining a congestion mean value corresponding to the sub-area in the second sub-identification period according to the congestion numerical value corresponding to each traffic section in the second sub-identification period;
and if the congestion mean value is larger than or equal to a congestion threshold, determining that the sub-region enters late peak in the second sub-identification period, and if the congestion mean value is smaller than the congestion threshold, determining that the sub-region does not enter late peak in the second sub-identification period.
In the embodiment of the present application, the memory 202 stores instructions executable by the at least one processor 201, and the at least one processor 201 can execute the steps included in the method for identifying a traffic peak period by executing the instructions stored in the memory 202.
The processor 201 is a control center of the electronic device, and may be connected to various parts of the electronic device through various interfaces and lines, and implement data processing by executing or executing instructions stored in the memory 202 and calling data stored in the memory 202. Optionally, the processor 201 may include one or more processing units, and the processor 201 may integrate an application processor and a modem processor, where the application processor mainly processes an operating system, a user interface, an application program, and the like, and the modem processor mainly processes an issued instruction. It will be appreciated that the modem processor described above may not be integrated into the processor 201. In some embodiments, the processor 201 and the memory 202 may be implemented on the same chip, or in some embodiments, they may be implemented separately on separate chips.
The processor 201 may be a general-purpose processor, such as a Central Processing Unit (CPU), a digital signal processor, an Application Specific Integrated Circuit (ASIC), a field programmable gate array or other programmable logic device, discrete gate or transistor logic, discrete hardware components, or any combination thereof, and may implement or perform the methods, steps, and logic blocks disclosed in the embodiments of the present Application. A general purpose processor may be a microprocessor or any conventional processor or the like. The steps of the disclosed method in connection with the method embodiments for identifying rush hour may be embodied directly in a hardware processor, or may be implemented as a combination of hardware and software modules in a processor.
As will be appreciated by one skilled in the art, embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to the application. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
While the preferred embodiments of the present application have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. Therefore, it is intended that the appended claims be interpreted as including preferred embodiments and all alterations and modifications as fall within the scope of the application.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present application without departing from the spirit and scope of the application. Thus, if such modifications and variations of the present application fall within the scope of the claims of the present application and their equivalents, the present application is intended to include such modifications and variations as well.
Claims (9)
1. A method of identifying rush hour traffic, comprising:
determining a first reference flow sequence of each data acquisition point and a second reference flow sequence in an identification region according to m-day vehicle flow sequences acquired by each data acquisition point in the identification region;
based on the flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point location, performing region division on the identification region to determine each sub-region;
for any sub-region, determining the flow change state of each data acquisition point in the sub-region based on the first reference flow sequence of each data acquisition point in the sub-region, and determining each key acquisition point corresponding to the sub-region based on the flow change state of each data acquisition point in the sub-region; the traffic operation data associated with each key acquisition point position is used for judging the traffic peak period of the sub-area; the key acquisition point is used for representing a data acquisition point with relatively large influence on the traffic rush hour in the sub-area;
the vehicle flow sequence of each data acquisition point on any day is used for representing the vehicle flow data acquired by the data acquisition point according to each set time period in the day; the data acquisition point is used for indicating the installation position of traffic monitoring equipment which is arranged on a traffic road section and acquires traffic flow data;
the determining the flow change state of each data acquisition point location in the sub-region based on the first reference flow sequence of each data acquisition point location in the sub-region includes:
determining a gradient vector of any data acquisition point location in the sub-region through a first reference flow sequence of the data acquisition point location; the gradient vector comprises a plurality of first gradient values; the first gradient value is used for representing the vehicle flow change degree of the data acquisition point position between the ith set time period and the (i-1) th set time period;
determining a flow variation coefficient of the data acquisition point according to the plurality of first gradient values; the flow change coefficient of the data acquisition point location is used for representing the flow change state of the data acquisition point location;
the determining each key acquisition point location corresponding to the sub-region based on the flow change state of each data acquisition point location in the sub-region comprises:
determining a flow reference value corresponding to each data acquisition point position in the sub-area through the vehicle flow sequence acquired by each data acquisition point position in the sub-area for n days;
sequencing the flow rate change coefficients of the data acquisition points in the sub-area in a descending order, taking the data acquisition points positioned at the first p positions as first candidate points, sequencing the flow rate reference values corresponding to the data acquisition points in the sub-area in a descending order, and taking the data acquisition points positioned at the first q positions as second candidate points;
and determining t intersection point positions between the p first candidate point positions and the q second candidate point positions, and taking the t intersection point positions as key acquisition point positions.
2. The method of claim 1, wherein determining a first reference flow sequence for each data acquisition point location within an identification region and a second reference flow sequence within the identification region based on m-day vehicle flow sequences acquired by each data acquisition point location within the identification region comprises:
for each data acquisition point location, determining a first reference flow value of the data acquisition point location in the set time period through vehicle flow data of the data acquisition point location in the set time period in the m days in each set time period, and determining a first reference flow sequence of the data acquisition point location according to the first reference flow value of the data acquisition point location in each set time period;
and determining a second reference flow value corresponding to the set time interval according to the first reference flow value of each data acquisition point position in the set time interval in each set time interval, and determining a second reference flow sequence in the identification area according to the second reference flow value corresponding to each set time interval.
3. The method of claim 2, wherein the determining each sub-region by performing region division on the identification region based on the traffic distance coefficients of the first reference traffic sequence and the second reference traffic sequence of each data acquisition point location comprises:
for each data acquisition point location, determining a flow distance coefficient of the data acquisition point location according to a first reference flow sequence of the data acquisition point location and a second reference flow sequence in the identification area, and determining a spatial distance coefficient of the data acquisition point location based on a two-dimensional spatial coordinate of the data acquisition point location;
and carrying out region division on the identification region through the flow distance coefficient and the space distance coefficient of each data acquisition point position to determine each sub-region.
4. The method of claim 3, wherein said determining traffic distance coefficients for said data acquisition points from a first reference traffic sequence for said data acquisition points and a second reference traffic sequence within said identified region comprises:
determining a reference flow difference value of the data acquisition point position in the set time period according to a second reference flow value corresponding to the set time period and a first reference flow value of the data acquisition point position in the set time period in each set time period;
determining a flow distance coefficient of the data acquisition point according to the reference flow difference value of the data acquisition point at each set time period;
determining a spatial distance coefficient of the data acquisition point location based on the two-dimensional spatial coordinates of the data acquisition point location, including:
determining a mean value of two-dimensional space coordinates in the identification area according to the two-dimensional space coordinates of the data acquisition point locations;
determining a spatial distance coefficient of the data acquisition point location according to the two-dimensional space coordinate mean value in the identification area and the two-dimensional space coordinate of the data acquisition point location;
the method comprises the following steps of carrying out region division on the identification region through the flow distance coefficient and the space distance coefficient of each data acquisition point location to determine each sub-region, wherein the method comprises the following steps:
generating a distance vector of each data acquisition point according to a flow distance coefficient and a space distance coefficient of the data acquisition point for each data acquisition point;
and performing cluster analysis on each data acquisition point location based on the distance vector of each data acquisition point location, and dividing the identification area into each sub-area.
5. The method of claim 1, wherein each first gradient value is determined by:
determining a reference flow mean value corresponding to the data acquisition point location according to the first reference flow sequence of the data acquisition point location;
determining the flow difference value of the data acquisition point position between the ith set time period and the (i-1) th set time period;
and determining the first gradient value through the reference flow mean value and the flow difference value.
6. The method of any one of claims 1 to 5, wherein the traffic peak periods include early peak periods;
the determination is made for the early peak of the subregion by:
setting a first identification time period for identifying whether a sub-region enters an early peak or not, and acquiring vehicle flow data of any key acquisition point in the sub-region in any first sub-identification time period aiming at any first sub-identification time period in the first identification time period; the first sub-identification period is a jth set period;
determining whether the key acquisition point enters an early peak or not in the first sub-identification period according to the vehicle traffic data of the key acquisition point in the first sub-identification period;
counting a first number of at least one key acquisition point position which enters an early peak in the first sub-identification period in each key acquisition point position in the sub-area, counting a second number of each key acquisition point position in the sub-area, and determining a ratio of the first number to the second number;
if the ratio is larger than or equal to a preset threshold, determining that the sub-region enters an early peak in the first sub-identification period, and if the ratio is smaller than the preset threshold, determining that the sub-region does not enter the early peak in the first sub-identification period.
7. The method of claim 6, wherein said determining whether said critical acquisition point is early peaking during said first sub-identification period from vehicle traffic data of said critical acquisition point during said first sub-identification period comprises:
determining a vehicle flow mean value corresponding to the key acquisition point location according to a vehicle flow sequence of the key acquisition point location in the last day before the first sub-identification period;
determining a second gradient value and a third gradient value corresponding to the key acquisition point in the first sub-identification period according to the vehicle flow data of the key acquisition point in the first sub-identification period; the second gradient value is used for representing the vehicle flow change degree of the key acquisition point between the jth set time period and the jth-1 set time period; the third gradient value is used for representing the vehicle flow change degree of the key acquisition point between the jth set time period and the jth-2 set time period;
if the vehicle flow data of the key acquisition point in the first sub-identification period is greater than or equal to the vehicle flow mean value, the second gradient value is greater than or equal to a first gradient threshold value, and the third gradient value is greater than or equal to a second gradient threshold value, determining that the key acquisition point enters an early peak in the first sub-identification period, otherwise determining that the key acquisition point does not enter the early peak in the first sub-identification period.
8. The method of any one of claims 1 to 5, wherein the rush hour of traffic comprises late peak;
the determination is made for late peaks of the sub-area by:
determining each traffic road section associated with each key acquisition point in the sub-area through each key acquisition point corresponding to the sub-area, and setting a second identification time period for identifying whether the sub-area enters a late peak or not;
acquiring congestion information of each traffic section in a second sub-identification period aiming at any second sub-identification period in the second identification period, and converting the congestion information of the traffic section in the second sub-identification period into a corresponding congestion numerical value according to a congestion information conversion rule;
determining a congestion mean value corresponding to the sub-area in the second sub-identification time period according to the congestion numerical value corresponding to each traffic section in the second sub-identification time period;
and if the congestion mean value is larger than or equal to a congestion threshold, determining that the sub-region enters late peak in the second sub-identification period, and if the congestion mean value is smaller than the congestion threshold, determining that the sub-region does not enter late peak in the second sub-identification period.
9. An electronic device comprising a processor and a memory, the processor being coupled to the memory, the memory storing a computer program that, when executed by the processor, causes the electronic device to perform: determining a first reference flow sequence of each data acquisition point location and a second reference flow sequence in an identification region according to m-day vehicle flow sequences acquired by each data acquisition point location in the identification region; based on the flow distance coefficient of the first reference flow sequence and the second reference flow sequence of each data acquisition point location, performing region division on the identification region to determine each sub-region; for any sub-region, determining the flow change state of each data acquisition point in the sub-region based on the first reference flow sequence of each data acquisition point in the sub-region, and determining each key acquisition point corresponding to the sub-region based on the flow change state of each data acquisition point in the sub-region; the traffic operation data associated with each key acquisition point position is used for judging the traffic peak period of the sub-area; the key acquisition point is used for representing a data acquisition point with relatively large influence on the traffic rush hour in the sub-area; the vehicle flow sequence of each data acquisition point on any day is used for representing the vehicle flow data acquired by the data acquisition point according to each set time period in the day; the data acquisition point is used for indicating the installation position of traffic monitoring equipment which is arranged on a traffic road section and acquires traffic flow data;
the electronic device is specifically configured to perform:
determining a gradient vector of any data acquisition point location in the sub-region through a first reference flow sequence of the data acquisition point location; the gradient vector comprises a plurality of first gradient values; the first gradient value is used for representing the vehicle flow change degree of the data acquisition point position between the ith set time period and the (i-1) th set time period;
determining a flow variation coefficient of the data acquisition point according to the plurality of first gradient values; the flow change coefficient of the data acquisition point location is used for representing the flow change state of the data acquisition point location;
the electronic device is specifically configured to perform:
determining a flow reference value corresponding to each data acquisition point in the sub-area through the vehicle flow sequence acquired by each data acquisition point in the sub-area for n days;
sequencing the flow rate change coefficients of the data acquisition points in the sub-area in a descending order, taking the data acquisition points positioned in the first p positions as first candidate points, sequencing the flow rate reference values corresponding to the data acquisition points in the sub-area in a descending order, and taking the data acquisition points positioned in the first q positions as second candidate points;
and determining t intersection point positions between the p first candidate point positions and the q second candidate point positions, and taking the t intersection point positions as key acquisition point positions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210290685.2A CN114708728B (en) | 2022-03-23 | 2022-03-23 | Method for identifying traffic peak period, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210290685.2A CN114708728B (en) | 2022-03-23 | 2022-03-23 | Method for identifying traffic peak period, electronic equipment and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114708728A CN114708728A (en) | 2022-07-05 |
| CN114708728B true CN114708728B (en) | 2023-04-18 |
Family
ID=82168729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210290685.2A Active CN114708728B (en) | 2022-03-23 | 2022-03-23 | Method for identifying traffic peak period, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114708728B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117095539B (en) * | 2023-10-16 | 2024-01-09 | 江西时励朴华数字技术有限公司 | Traffic jam processing method, processing system, data processing device and storage medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113593262B (en) * | 2019-11-14 | 2022-09-27 | 北京百度网讯科技有限公司 | Traffic signal control method, traffic signal control device, computer equipment and storage medium |
| CN112509318B (en) * | 2020-11-11 | 2021-12-24 | 青岛海信网络科技股份有限公司 | Traffic control area division method and server |
| CN112819325A (en) * | 2021-01-29 | 2021-05-18 | 北京嘀嘀无限科技发展有限公司 | Peak hour determination method, peak hour determination device, electronic equipment and storage medium |
| CN113256973B (en) * | 2021-05-11 | 2022-03-25 | 青岛海信网络科技股份有限公司 | Peak start time prediction method, device, equipment and medium |
| CN113257002B (en) * | 2021-05-11 | 2022-03-25 | 青岛海信网络科技股份有限公司 | Peak start time prediction method, device, equipment and medium |
| CN113870564B (en) * | 2021-10-26 | 2022-09-06 | 安徽百诚慧通科技股份有限公司 | Traffic jam classification method and system for closed road section, electronic device and storage medium |
-
2022
- 2022-03-23 CN CN202210290685.2A patent/CN114708728B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN114708728A (en) | 2022-07-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108346292B (en) | Urban expressway real-time traffic index calculation method based on checkpoint data | |
| CN103150900B (en) | Traffic jam event automatic detecting method based on videos | |
| CN110751828B (en) | Road congestion measuring method and device, computer equipment and storage medium | |
| CN104750800A (en) | Motor vehicle clustering method based on travel time characteristic | |
| CN113591824B (en) | Traffic violation data entry anomaly detection method and device | |
| CN112598169B (en) | Traffic operation situation assessment method, system and device | |
| CN114708728B (en) | Method for identifying traffic peak period, electronic equipment and storage medium | |
| CN114781768B (en) | Parking lot facility planning method, device and equipment based on urban resource data | |
| CN113487877A (en) | Road vehicle illegal parking monitoring method | |
| CN112652168B (en) | Major traffic accident early warning method, system and storage medium | |
| CN114067326A (en) | License plate number complementing method and device | |
| CN111369790B (en) | Vehicle passing record correction method, device, equipment and storage medium | |
| CN111951544A (en) | Method and device for determining monitoring point | |
| CN117251722A (en) | Intelligent traffic management system based on big data | |
| CN115273468B (en) | Traffic jam control strategy generation method and device | |
| CN113947392B (en) | Abnormity determining method and device in traffic data auditing task | |
| CN110826897A (en) | Regional safety evaluation method, device, equipment and storage medium | |
| CN112766567B (en) | Evaluation method, system and storage medium for urban road network planning implementation effect | |
| CN113256973B (en) | Peak start time prediction method, device, equipment and medium | |
| CN115358595A (en) | Laboratory task management method, device, equipment and readable storage medium | |
| Haryono et al. | Accuracy in Object Detection Based on Image Processing at the Implementation of Motorbike Parking on the Street | |
| CN112199454A (en) | Directed graph-based method and device for setting interception points of control vehicles | |
| CN112598912B (en) | Bayonet interval acquisition method and device, computer equipment and storage medium | |
| CN116703132B (en) | Management method and device for dynamic scheduling of shared vehicles and computer equipment | |
| CN117392869A (en) | Parking data fusion method and system based on integrated algorithm |
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 |