CN114999162A

CN114999162A - Road traffic flow obtaining method and device

Info

Publication number: CN114999162A
Application number: CN202210919257.1A
Authority: CN
Inventors: 云旭; 高永�; 朱丽云
Original assignee: Beijing Jiaoyan Intelligent Technology Co ltd
Current assignee: Beijing Jiaoyan Intelligent Technology Co ltd
Priority date: 2022-08-02
Filing date: 2022-08-02
Publication date: 2022-09-02
Anticipated expiration: 2042-08-02
Also published as: CN114999162B

Abstract

The invention provides a method and a device for acquiring road traffic flow, and relates to the field of traffic flow prediction. The method comprises the following steps: preprocessing multi-source fusion data to which the obtained vehicles belong, and determining a driving track of each vehicle and N pieces of check line data corresponding to the section flow check points, wherein N is an integer larger than 1, first vehicle data passing through the section flow check points and second vehicle data not passing through the section flow check points; determining a first weight set corresponding to each check line in the first vehicle data according to the N check line data and the first vehicle data; determining a second weight set corresponding to second vehicle data according to the first weight set, the mobile phone signaling data and the second vehicle data; and determining the sample expansion flow on each vehicle route according to the first weight set, the second weight set and the driving track of each vehicle. The scheme of the invention solves the problem of poor prediction accuracy in the prior art.

Description

Road traffic flow obtaining method and device

Technical Field

The invention relates to the field of traffic flow prediction, in particular to a road traffic flow obtaining method and a road traffic flow obtaining device.

Background

Origin-Destination (OD) flow of a vehicle is used as an important data basis for road traffic control and important input parameters of various medium and micro traffic models and simulation platforms, and the estimation problem of the OD flow has gradually developed into an important research content in the traffic field. With the rapid development of intelligent transportation systems, the modern transportation operation and management and control are more emphasized in refinement and real-time performance, and therefore, dynamic traffic flow OD estimation has become a research focus in the problem of origin-destination traffic flow estimation.

The traditional method for acquiring the traffic of the whole road network is generally based on an OD reverse-deducing technology, namely, an optimization model is established for continuous iterative solution through a macroscopic traffic demand prediction model on the basis of acquiring the road network attribute and partial section traffic, the OD distribution of a traffic cell is acquired, and the traffic of the whole road network is acquired through a traffic distribution method. The method has practical application cases, but the solution optimization model is generally solved by adopting an intelligent algorithm, and the optimal solution cannot be obtained; in addition, the requirement on input data is high, the method is generally realized based on simulation software in the large-scale road network deduction process, and certain requirements are provided for a road grid mode. In the prior art, relevant factors of a vehicle running track are not considered in an OD (origin destination) reverse-deducing method, namely, a route selection behavior is generally solved for a traffic distribution stage in a traffic demand prediction model, and an actual floating vehicle running track is not referred.

On the other hand, with the continuous development of the acquisition technology, the big data is more widely applied in various business fields of comprehensive transportation. With the improvement of informatization level and data acquisition capacity, a large amount of mobile internet data, GPS data and other multi-source vehicle running data are accumulated. In the prior art, a data fusion road full-flow back-pushing method adopts machine learning algorithms such as a neural network and the like, and predicts traffic volume sections by inputting multi-source data such as weather data, accident data, floating car data and the like, so that the back-pushing of traffic flow of a whole road network is realized, but for a large-scale road network, even if the road grades are the same and the speed limit is the same, the flow rate may be greatly different due to different located regions, and the modeling process does not consider the point; in addition, the constraint condition of the overall trip total amount of the large-scale road network is not considered, so that the total number of vehicles reversely pushed out on the road network is greatly different from the trip total amount.

Disclosure of Invention

The invention aims to provide a road traffic flow obtaining method and a device, which are used for avoiding the influence of the problem of poor prediction accuracy caused by less considered traffic flow influence factors in the prior art.

In order to achieve the above object, an embodiment of the present invention provides a method for acquiring a road traffic flow, including:

acquiring multi-source fusion data of a vehicle, wherein the multi-source fusion data comprises mobile phone signaling data, vehicle GPS data and a cross-section flow check point arranged on a road network section;

preprocessing the multi-source fusion data, and determining a driving track of each vehicle and N pieces of check line data corresponding to the section flow check points, wherein N is an integer larger than 1, first vehicle data passing through the section flow check points and second vehicle data not passing through the section flow check points;

determining a first weight set corresponding to each check line in the first vehicle data according to the N pieces of check line data and the first vehicle data;

determining a second weight set corresponding to the second vehicle data according to the first weight set, the mobile phone signaling data and the second vehicle data;

and determining sample expansion flow on each vehicle route according to the first weight set, the second weight set and the driving track of each vehicle.

Optionally, determining, according to the N check lines and the first vehicle data, a first weight set corresponding to each check line in the first vehicle data, includes:

determining the total number of vehicles passing through each check line and the total number of floating vehicles according to the N pieces of check line data and the first vehicle data;

determining a first initial weight set corresponding to each check line in the first vehicle data according to the ratio of the total number of the vehicles to the total number of the floating vehicles;

determining the weight sum corresponding to each section flow check point in each check line according to the first initial weight set;

determining a relative error value of the vehicle corresponding to each section flow check point in each check line according to the total number of the vehicles and the total weight;

and determining a first weight set corresponding to each check line in the first vehicle data according to the relative vehicle error value and a first preset algorithm.

Optionally, determining, according to the vehicle relative error value and a first preset algorithm, a first weight set corresponding to each check line in the first vehicle data, includes:

determining third vehicle data corresponding to the fact that the absolute value of the vehicle relative error value is larger than a first threshold value; the third vehicle data belongs to the first vehicle data;

carrying out weight correction on the third vehicle data according to the first preset algorithm, and determining the weight of the corrected third vehicle data;

and determining a first weight set corresponding to each check line in the first vehicle data according to the weight of the vehicle corresponding to the condition that the absolute value of the relative error value of the vehicle is smaller than a first threshold value and the weight of the corrected third vehicle data.

Optionally, performing weight correction on the third vehicle data according to the first preset algorithm, and determining a weight of the corrected third vehicle data, including:

obtaining a difference value between a first maximum initial weight and a first minimum initial weight in the first initial weight set;

determining a first correction weight step length according to the ratio of the difference value to a preset minimum weight interval;

according to the first preset algorithm, if the vehicle relative error value is larger than zero, determining the smaller value of the sum of the current weight of the third vehicle data and the first correction weight step length and the first maximum initial weight, and determining the smaller value as the weight of the corrected third vehicle data;

or, according to the first preset algorithm, if the vehicle relative error value is smaller than zero, determining a larger value between the difference between the current weight of the third vehicle data and the first correction weight step length and the first minimum initial weight as the weight of the corrected third vehicle data.

Optionally, determining a second weight set corresponding to the second vehicle data includes:

determining the total traffic volume of a traffic cell to which each vehicle belongs according to the mobile phone signaling data;

determining the traffic cell to which each vehicle belongs according to the total travel volume of the traffic cell to which each vehicle belongs;

determining a second initial weight set corresponding to the second vehicle data according to the traffic cell to which each vehicle belongs, the first weight set and the second vehicle data;

and determining a second weight set corresponding to the second vehicle data according to the second initial weight set and a second preset algorithm.

Optionally, determining a second initial weight set corresponding to the second vehicle data includes:

determining a first traffic generation amount of a traffic cell corresponding to the first vehicle data according to the first weight set and the traffic cell to which each vehicle belongs;

determining a second traffic generation amount of a traffic cell corresponding to second vehicle data according to the second vehicle data and the first traffic generation amount;

and determining a second initial weight set corresponding to the second vehicle data according to the second traffic volume.

Optionally, determining a second weight set corresponding to the second vehicle data according to the second initial weight set and a second preset algorithm includes:

determining a relative error value of the actual traffic generation amount and the statistical traffic generation amount of each traffic cell according to the second initial weight set, the first traffic generation amount and the second traffic generation amount;

and determining a second weight set corresponding to the second vehicle data according to the relative error value of the production quantity, a second threshold value and a second preset algorithm.

Optionally, determining a second weight set corresponding to the second vehicle data according to the relative error value of the production amount, a second threshold and a second preset algorithm includes:

determining fourth vehicle data corresponding to the fact that the absolute value of the production quantity relative error value is larger than a second threshold value; the fourth vehicle data belongs to the second vehicle data;

performing weight correction on the fourth vehicle data according to the second preset algorithm, and determining the weight of the corrected fourth vehicle data;

and determining a second weight set corresponding to the second vehicle data according to the weight of the vehicle corresponding to the condition that the absolute value of the production quantity relative error value is smaller than a second threshold value and the weight of the corrected fourth vehicle data.

Optionally, performing weight correction on the fourth vehicle data according to the second preset algorithm, and determining the weight of the corrected fourth vehicle data, includes:

acquiring a second maximum initial weight and a second minimum initial weight in the second initial weight set;

determining a second correction weight step size according to the second maximum initial weight and the second minimum initial weight;

according to the second preset algorithm, if the relative error value of the production quantity is greater than zero, determining the larger value of the difference between the current weight of the fourth vehicle data and the step length of the second correction weight and the second minimum initial weight as the weight of the corrected fourth vehicle data;

according to the second preset algorithm, if the relative error value of the production amount is smaller than zero, the smaller value of the sum of the current weight of the fourth vehicle data and the second correction weight step length and the second maximum initial weight is determined as the weight of the corrected fourth vehicle data.

Optionally, the preprocessing the multi-source fusion data includes:

acquiring a driving track of each vehicle according to the vehicle GPS data and a preset road network section;

dividing N pieces of checking line data according to the section flow checking points and the preset road network sections; n is an integer greater than 1;

and acquiring first vehicle data passing through a section flow check point and second vehicle data not passing through the section flow check point according to the N check line data and the vehicle GPS data.

In order to achieve the above object, an embodiment of the present invention further provides a road traffic flow obtaining apparatus, including:

the system comprises an acquisition module, a storage module and a processing module, wherein the acquisition module is used for acquiring multi-source fusion data of a vehicle, and the multi-source fusion data comprises mobile phone signaling data, vehicle GPS data and a cross section flow check point arranged on a road network section;

the first processing module is used for preprocessing the multi-source fusion data, determining a driving track of each vehicle and N check line data corresponding to the section flow check points, wherein N is an integer larger than 1, the first vehicle data passes through the section flow check points, and the second vehicle data does not pass through the section flow check points;

the second processing module is used for determining a first weight set corresponding to each check line in the first vehicle data according to the N pieces of check line data and the first vehicle data;

the third processing module is used for determining a second weight set corresponding to the second vehicle data according to the first weight set, the mobile phone signaling data and the second vehicle data;

and the fourth processing module is used for determining the sample expansion flow on each vehicle route according to the first weight set, the second weight set and the driving track of each vehicle.

To achieve the above object, an embodiment of the present invention also provides a readable storage medium on which a program or instructions are stored, the program or instructions, when executed by a processor, implementing the steps in the road traffic flow acquiring method according to any one of the above.

The technical scheme of the invention has the following beneficial effects:

according to the technical scheme, the method comprises the steps of preprocessing multi-source fusion data of obtained vehicles, determining a driving track of each vehicle and N check line data corresponding to the cross-section flow check point, wherein N is an integer larger than 1, first vehicle data passing through the cross-section flow check point and second vehicle data not passing through the cross-section flow check point; acquiring the total trip amount of the traffic cell by using the mobile phone signaling data, and calculating to obtain the total car trip amount of the traffic cell according to the car sharing rate of the traffic cell; meanwhile, a first weight set corresponding to each check line in the first vehicle data is determined based on the first vehicle data and the N pieces of check line data, and a second weight set corresponding to the second vehicle data is determined through multiple iterative computations according to the first weight set, the mobile phone signaling data and the second vehicle data; and finally, determining the sample expansion flow on each vehicle route according to the first weight set, the second weight set and the driving track of each vehicle.

The invention solves the problem of low flow caused by counting the road network flow by using the floating car data, and by adopting the technical scheme of the invention, the full data of the large road network flow can be more accurately mastered, so that the method can be further applied to urban traffic planning, road traffic management, traffic policy control and the like.

Drawings

Fig. 1 is a flowchart of a road traffic flow acquisition method according to an embodiment of the present invention;

FIG. 2 is a diagram illustrating a first initial weight set according to an embodiment of the present invention;

fig. 3 is a structural diagram of a road traffic flow acquisition apparatus according to an embodiment of the present invention.

Detailed Description

In order to make the technical problems, technical solutions and advantages of the present invention more apparent, the following detailed description is given with reference to the accompanying drawings and specific embodiments.

It should be appreciated that reference throughout this specification to "one embodiment" or "an embodiment" means that a particular feature, structure or characteristic described in connection with the embodiment is included in at least one embodiment of the present invention. Thus, the appearances of the phrases "in one embodiment" or "in an embodiment" in various places throughout this specification are not necessarily all referring to the same embodiment. Furthermore, the particular features, structures, or characteristics may be combined in any suitable manner in one or more embodiments.

In various embodiments of the present invention, it should be understood that the sequence numbers of the following processes do not mean the execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.

It should be known that, in the prior art, a data-fused road full-flow back-pushing method adopts machine learning algorithms such as neural networks and the like, and traffic volume sections are predicted by inputting multi-source data such as weather data, accident data, floating car data and the like, so that the back-pushing of the traffic flow of the whole road network is realized, but for a large-scale road network, even if the road grades are the same and the speed limit is the same, the flow difference is large due to different located positions, and the modeling process does not consider the point; in addition, constraint conditions of the total trip amount of the large-scale road network are not considered, so that the total number of vehicles reversely pushed out on the road network is greatly different from the total trip amount.

In the prior art, an OD reverse-deducing method generally reflects the difference between distributed flow and observed flow of a detection point or the difference between OD of a traffic zone in an optimization solving process; relevant factors of the vehicle running track are not considered, namely the route selection behavior is generally solved for a traffic distribution stage in a traffic demand prediction model, and the actual floating vehicle running track is not referred.

In order to solve the technical problem, the invention provides a road traffic flow obtaining method and a road traffic flow obtaining device.

As shown in fig. 1, a method for acquiring a road traffic flow according to an embodiment of the present invention includes:

step 100, obtaining multi-source fusion data of a vehicle, wherein the multi-source fusion data comprises mobile phone signaling data, vehicle GPS (global positioning system) data and a cross section flow check point arranged on a road network section;

here, the multi-source fusion data includes, but is not limited to: mobile phone signaling data, section flow survey point data and vehicle GPS track data all day.

200, preprocessing the multi-source fusion data, and determining a driving track of each vehicle and N check line data corresponding to the section flow check point, wherein N is an integer greater than 1, first vehicle data passing through the section flow check point and second vehicle data not passing through the section flow check point;

specifically, the step 200 includes:

step 210, acquiring a driving track of each vehicle according to the vehicle GPS data and a preset road network section;

step 220, dividing N pieces of check line data according to the section flow check points and preset road network sections; n is an integer greater than 1;

and step 230, acquiring first vehicle data passing through a cross-section flow check point and second vehicle data not passing through the cross-section flow check point according to the N check line data and the vehicle GPS data.

In this embodiment, the preset network section is a standard road network map, and the GPS data of the vehicle is mapped onto the standard road network map, so that the driving track of each vehicle can be obtained; mapping the cross section flow survey points to a preset standard road network map to obtain a plurality of survey points on the standard road network map, and dividing the plurality of survey points into N pieces of check line data according to a preset rule; the section flow investigation point can be set as point location data for investigation every 15 minutes all day, wherein the time division of the section flow investigation point can be set according to specific requirements, and is not specifically limited; here, N check line data are already determined on the standard road network map, and then based on the GPS data of the vehicles, that is, the running track of each vehicle is matched with the N check line data, the first vehicle data passing through the cross-sectional flow rate check point and the second vehicle data not passing through the cross-sectional flow rate check point can be determined.

It should be noted that the first vehicle data and the second vehicle data include, but are not limited to: a serial number of a travel track of each vehicle, a time stamp of the travel track of each vehicle, and the like; the first vehicle data and the second vehicle data are aggregate data of vehicles, where the first vehicle data is defined as an aggregate

Defining the second vehicle data as a set

。

Step 300, determining a first weight set corresponding to each check line in the first vehicle data according to the N pieces of check line data and the first vehicle data;

step 400, determining a second weight set corresponding to the second vehicle data according to the first weight set, the mobile phone signaling data and the second vehicle data;

and 500, determining sample expansion flow on each vehicle route according to the first weight set, the second weight set and the driving track of each vehicle.

In this embodiment, a first weight set is determined by GPS data and first vehicle data, a second weight set is determined by mobile phone signaling, the first weight set, and second vehicle data, and finally, for a travel track of each vehicle, that is, any travel track in a standard road network section, data expansion may be performed through the first weight set and the second weight set, so that the road traffic flow after the data expansion may be calculated. The invention is especially applied to large roads and has the best effect.

According to the technical scheme, the problem of low flow caused by the fact that floating car data are used for counting the flow of a road network is solved by combining various fused data such as GPS data, mobile phone signaling and section flow survey points.

Specifically, in step 500, a set of vehicles passing through a vehicle trajectory may be determined according to the driving trajectory of each vehicle

The vehicle set

Including the first vehicle data and/or the second vehicle data, the road traffic flow after calculating the road sample expansion is represented by formula (1):

Q _linki =

（car’∈

) Formula (1);

wherein Q is _linki The flow rate after road sample expansion is obtained;

is the weight of each vehicle, wherein when the vehicle is a floating vehicle, the vehicle is a floating vehicle

Is determined from a first set of weights and the second set of weights; car' is a vehicle passing through a vehicle track, so that the invention can obtain the vehicle sample expansion flow of the whole road network by depending on a small amount of floating vehicle GPS data, mobile phone signaling data and a cross-section flow survey point.

Optionally, the step 300 includes:

step 310, determining the total number of vehicles passing through each check line and the total number of floating vehicles according to the N pieces of check line data and the first vehicle data;

step 320, determining a first initial weight set corresponding to each check line in the first vehicle data according to the ratio of the total number of the vehicles to the total number of the floating vehicles;

in the embodiment, as shown in fig. 2, a set corresponding to a target vehicle car1 passing through a cross-sectional flow rate survey point in first vehicle data according to the present invention is set as Sn, each data in Sn is data corresponding to the target vehicle passing through a cross-sectional flow rate survey point, and a target survey line is determined from N pieces of survey line data according to the target vehicle; acquiring a total number Fn of vehicles and a total number Fn 'of floating cars corresponding to the target cross-section flow survey point on the target survey line, and calculating a ratio of the total number Fn of vehicles and the total number Fn' of floating cars, to obtain aggregate data of (Fn/Fn '), specifically as shown in fig. 2, determining a first initial weight aggregate corresponding to each survey line in the first vehicle data by the aggregate data of (Fn/Fn'), that is:

a first set of initial weights = { F1/F1'; F2/F2'; F3/F3'; …, respectively; Fn/Fn', the first initial weight set is set to

。

Step 330, determining a weight sum corresponding to each cross-section flow check point in each check line according to the first initial weight set;

in this embodiment, the first set of initial weights

And sequentially acquiring an initial weight set corresponding to all vehicles passing through the check line for each check line by virtue of an initial weight set corresponding to one vehicle in the cross-section flow check points, determining the initial weight of all vehicles passing through each cross-section flow check point on the check line, and summing to determine the weight sum corresponding to each cross-section flow check point.

Specifically, the set of cross-sectional flow survey points in each survey line is set to Si, and the sum of weights is represented by formula (2):

sum of weights =

Equation (2);

where cari denotes the vehicles passing each cross-sectional flow survey point in each survey line.

Step 340, determining a relative error value of the vehicle passing through each section flow check point in each check line according to the total number of the vehicles and the total weight;

here, the vehicle relative error value is represented by equation (3):

relative vehicle error value erri =

Equation (3), where Fn represents the total number of vehicles.

Step 350, determining a first weight set corresponding to each check line in the first vehicle data according to the vehicle relative error value and a first preset algorithm.

In the embodiment, the cross-section flow adjustment point set Si in each check line is calculated according to a first preset algorithm, the first preset algorithm is an iterative optimization algorithm for solving a vehicle sample expansion coefficient by using floating vehicle track data and check line data, and a first weight set corresponding to each check line in first vehicle data is determined, so that technical support can be provided for full sample data of subsequent sample expansion large-scale road network flow.

Optionally, the step 350 includes:

step 351, determining third vehicle data corresponding to the fact that the absolute value of the vehicle relative error value is larger than a first threshold value; the third vehicle data belongs to the first vehicle data;

here, the first threshold is preferably set to 20%, in this embodiment, if the absolute value of the vehicle relative error value is greater than 20%, a time slot and a check line corresponding to the absolute value of the vehicle relative error value being greater than the first threshold are determined, and third vehicle data, which passes through the check line at the same time, are acquired

Belonging to a first vehicle data set

。

Step 352, performing weight correction on the third vehicle data according to the first preset algorithm, and determining the weight of the corrected third vehicle data;

step 353, determining a first weight set corresponding to each check line in the first vehicle data according to the weight of the vehicle corresponding to the absolute value of the vehicle relative error value smaller than the first threshold and the weight of the corrected third vehicle data.

According to the method, the absolute value of the relative error value of the vehicle is larger than the third vehicle data corresponding to the first threshold, weight correction is carried out through the first preset algorithm to obtain the weight of the corrected third vehicle data meeting the standard, and the first weight set corresponding to each check line in the first vehicle data is determined through cumulative addition by combining the weight of the vehicle which is not larger than the first threshold.

Specifically, the step 352 includes:

step 3521, obtaining a difference value between a first maximum initial weight and a first minimum initial weight in the first initial weight set;

step 3522, determining a first correction weight step length according to the ratio of the difference to a preset minimum weight interval;

step 3523, according to the first preset algorithm, if the vehicle relative error value is greater than zero, determining the smaller value of the sum of the current weight of the third vehicle data and the first correction weight step length and the first maximum initial weight as the weight of the corrected third vehicle data;

Optionally, the third vehicle data may be

In each vehicle data setting zone bit

If the third vehicle data is acquired

Zone bit of middle vehicle

If the value is 0, the vehicle data is determined not to be detected or adjusted, and if the value is the zone bit

If the absolute value of the relative error value of the vehicle data is 1, the absolute value of the relative error value of the vehicle data is determined to be smaller than a first threshold value, or the vehicle data after weight correction is performed, secondary calculation of the vehicle data is prevented, and the data processing speed is increased.

In this embodiment, in steps 3521 to 3523, the first correction weight step size is first set, and the first correction step size is expressed by formula (4):

=

equation (4);

b is a preset minimum weight interval and is taken according to the actual condition;

representing a first largest initial weight of the first set of initial weights;

representing a first minimum initial weight of the first set of initial weights;

representing the first correction step. In step 3523, if the vehicle relative error value erri is smaller than 0, determining the weight of the corrected third vehicle data according to formula (5);

weight of corrected third vehicle data = max (m) ((m))

-

,

) Equation (5);

wherein the content of the first and second substances,

a current weight representing the third vehicle data, taken when first calculated

=

。

If the vehicle relative error value erri is greater than 0, determining the weight of the corrected third vehicle data by formula (6);

weight of corrected third vehicle data = min (b) ((b))

+

,

) Equation (6);

wherein the content of the first and second substances,

=

。

If the vehicle data in the third vehicle data is corrected or the absolute value of the relative error value of the vehicle is smaller than the first threshold, the step 3523 is stopped, and the third vehicle data is searched

The steps 3521 to 3523 are repeated until the absolute values of all the vehicle relative error values are less than the first threshold, and the algorithm is terminated. Here, technical support is provided for subsequent calculation of the first set of weights.

Optionally, the step 400 includes:

step 410, determining the total traffic volume of the traffic district to which each vehicle belongs according to the mobile phone signaling data;

in step 410, the present invention needs to preprocess the signaling data of the mobile phone: based on the mobile phone signaling data, acquiring a corresponding base station ID, segmenting a journey by setting a threshold value, and according to the corresponding relation between the base station ID and the traffic cell, counting and calculating to obtain a starting traffic cell and an ending traffic cell of each journey, and further counting to obtain an OD distribution table of each traffic cell in the area.

In this embodiment, according to the mobile phone signaling data, the total traffic yield of the traffic cell i can be determined

And total suction volume of traffic

(the total number of the traffic districts is N), and in addition, the traffic mode sharing rate of each traffic district is obtained according to the traffic big investigation data

. Calculated for each traffic cell due to cell phone signalling data

And

the total travel amount (real value) of cars in each traffic cell can be calculated through the following formula (7) and formula (8), namely, the total travel amount of the traffic cell to which each car belongs is determined;

equation (7);

equation (8);

wherein the content of the first and second substances,

traffic generation quantity and representing traffic cell to which each vehicle belongs

Indicating the amount of traffic attraction of the traffic cell to which each vehicle belongs.

It should be noted that the total traveling volume of the traffic cell to which each vehicle belongs includes the traffic generation volume of the traffic cell to which each vehicle belongs and the traffic attraction volume of the traffic cell to which each vehicle belongs.

Step 420, determining the traffic cell to which each vehicle belongs according to the total travel volume of the traffic cell to which each vehicle belongs;

in this embodiment, the traffic cell to which each vehicle belongs is determined according to the total travel volume of the traffic cell to which each vehicle belongs, the floating vehicle GPS data, and the divided traffic cell geographic files.

Step 430, determining a second initial weight set corresponding to the second vehicle data according to the traffic cell to which each vehicle belongs, the first weight set and the second vehicle data;

specifically, the step 430 includes:

step 431, determining a first traffic generation amount of a traffic cell corresponding to the first vehicle data according to the first weight set and the traffic cell to which each vehicle belongs;

here, the first traffic generation amount determined based on the first weight set may be determined as the first traffic generation amount by the first weight set W1 and the traffic cell to which each vehicle belongs

. Similarly, the first traffic attraction is

。

Step 432, determining a second traffic generation amount of a traffic cell corresponding to second vehicle data according to the second vehicle data and the first traffic generation amount;

the sum of the second traffic generation amount and the first traffic generation amount is the traffic generation amount of the traffic cell to which each vehicle belongs

Therefore, by

-

) The second traffic volume may be determined

. Similarly, the second traffic suction amount

=

-

。

And 433, determining a second initial weight set corresponding to the second vehicle data according to the second traffic volume.

It should be noted that, for each traffic cell, in the time granularity of hours, the total departure amount of the cell and the attraction amount of the arriving cell may not be equal.

In the present invention, the second vehicle data

Each car of the vehicles in the range of the second minimum initial weight

To the second largest initial weight

In which the first and second substrates are, wherein,

wherein the content of the first and second substances,

representing the second vehicle data

Actually returning the vehicle data of the corresponding traffic cell.

In this embodiment, it is determined that the second initial weight set corresponding to the second vehicle data is

Preferably a

。

Step 440, determining a second weight set corresponding to the second vehicle data according to the second initial weight set and a second preset algorithm.

In this embodiment, the invention determines the second weight set corresponding to the second vehicle data by using the mobile phone signaling data, the second preset algorithm and the like, thereby determining the weight of the vehicle that does not pass through the cross-section flow investigation point, and providing data support for the subsequent calculation of the full-scale road network flow.

Specifically, the step 440 includes:

step 441, determining a relative error value between the actual traffic production and the statistical traffic production of each traffic cell according to the second initial weight set, the first traffic production and the second traffic production;

step 442, determining a second weight set corresponding to the second vehicle data according to the generated quantity relative error value, a second threshold value and a second preset algorithm.

In this embodiment, for each traffic cell, a relative error value of the actual traffic volume to the statistical traffic volume for each traffic cell is determined

The relative error value of the generated quantity

Expressed by equation (9), equation (9) is:

in the above-mentioned formula (9),

representing a traffic generation amount of a traffic cell to which each vehicle belongs; the above-mentioned

Representing a first traffic production;

represents the above

The sum of all initial weights; according to the method, the relative error value is compared with the second threshold value, the second preset algorithm is applied, the second weight set corresponding to the second vehicle data meeting the preset requirement is determined, and the accuracy of the second weight set is improved.

Optionally, the step 442 includes:

step 4421, determining fourth vehicle data corresponding to the absolute value of the relative error value of the production quantity being greater than a second threshold; the fourth vehicle data belongs to the second vehicle data;

in the present invention, the value of the second threshold is preferably 30%, and the data of the second threshold may be adjusted in real time according to a specific embodiment, which is not limited in the present invention.

Step 4422, performing weight correction on the fourth vehicle data according to the second preset algorithm, and determining the weight of the corrected fourth vehicle data;

step 4423, determining a second weight set corresponding to the second vehicle data according to the weight of the vehicle corresponding to the absolute value of the relative error of the production quantity smaller than a second threshold and the weight of the corrected fourth vehicle data.

In this embodiment, if the maximum relative error isDifference between

If the number of the hours is larger than the second threshold (30%), recording the corresponding hour as hour (30% sets the threshold according to actual specific cases), recording the corresponding traffic cell number i, adjusting the weight of all travel vehicles based on the hour, and determining the weight of the corrected fourth vehicle data; and combining the weights of the vehicles corresponding to the data less than a second threshold (30%) to determine a second set of weights corresponding to the second vehicle data.

Specifically, the step 4422 includes:

obtaining a second maximum initial weight in the second initial weight set

And a second minimum initial weight

；

Determining a second correction weight step size based on the second maximum initial weight and the second minimum initial weight

；

According to the second preset algorithm, if the relative error value of the production quantity is larger than zero, determining the current weight of the fourth vehicle data

And the larger of the difference between the second correction weight step size and the second minimum initial weight is determined as the weight of the corrected fourth vehicle data;

In this embodimentIf the generated quantity is relative error value

Greater than 0, weight of the corrected fourth vehicle data

= max{(

-

)/

,

(ii) a Wherein the content of the first and second substances,

the set fixed threshold value is adjusted according to specific cases. If the relative error value of the generated quantity

If the weight of the fourth vehicle data is less than 0, the corrected weight of the fourth vehicle data is obtained

；

Wherein the content of the first and second substances,

=min{(

+

)/

,

。

here, the weight of the corrected fourth vehicle data

And repeating the specific steps of step 4422 to obtain the weight of the corrected fourth vehicle data

。

In summary, the invention carries out multi-source data fusion on mobile phone signaling data, vehicle driving track data, cross-section flow survey points or statistical data, obtains the total trip amount of a traffic community by using the mobile phone signaling data, and calculates the total trip amount of the cars of the traffic community according to the car sharing rate of a priori traffic community; meanwhile, sample expansion coefficients of each vehicle are determined based on vehicle running tracks, section traffic volume survey data or statistical data, the vehicles are divided into two groups according to whether the vehicles pass through section survey points, the difference between the sum of the sample expansion coefficients and the section survey traffic volume, the difference between the total trip amount of a traffic cell and the difference between the trip production amount and the attraction amount of the traffic cell are used as constraints, the optimal sample expansion coefficients of the vehicles are obtained through repeated iterative calculation, and finally sample expansion is carried out to obtain the full sample flow of the large road network.

In another embodiment, a city road network is explained as a case, data sources are floating car GPS data, mobile phone signaling data and section flow survey data of a certain day, the whole road network flow is subjected to sample expansion according to a proposed algorithm, partial sections are extracted before and after the sample expansion to perform sample expansion traffic and compare with a real traffic survey result, errors are calculated, and the result is as follows: the average relative error was calculated to be about 20%. According to the method for acquiring the full-sample of the network flow of the large road, which is disclosed by the invention, through the multi-source data fusion calculation, the input multi-source data is subjected to correlation correction and sample expansion, so that the network flow of the full sample is identified, and the accuracy of predicting the network flow of the large road is improved.

As shown in fig. 3, an alternative embodiment of the present invention further provides a road traffic flow acquiring apparatus, including:

the system comprises an acquisition module 10, a traffic analysis module and a traffic analysis module, wherein the acquisition module is used for acquiring multi-source fusion data of a vehicle, and the multi-source fusion data comprises mobile phone signaling data, vehicle GPS data and a cross section flow check point arranged on a road network section;

the first processing module 20 is configured to pre-process the multi-source fusion data, and determine a driving track of each vehicle and N check line data corresponding to the cross-section flow check point, where N is an integer greater than 1, first vehicle data passing through the cross-section flow check point, and second vehicle data not passing through the cross-section flow check point;

the second processing module 30 is configured to determine, according to the N check line data and the first vehicle data, a first weight set corresponding to each check line in the first vehicle data;

the third processing module 40 is configured to determine, according to the first weight set, the mobile phone signaling data, and the second vehicle data, a second weight set corresponding to the second vehicle data;

and the fourth processing module 50 is configured to determine the sample expansion flow rate on each vehicle route according to the first weight set, the second weight set and the driving trajectory of each vehicle.

Optionally, the second processing module 30 includes:

the first determining submodule is used for determining the total number of vehicles passing through each checking line and the total number of floating vehicles according to the N pieces of checking line data and the first vehicle data;

the second determining submodule is used for determining a first initial weight set corresponding to each check line in the first vehicle data according to the ratio of the total number of the vehicles to the total number of the floating vehicles;

the third determining submodule is used for determining the weight sum corresponding to each cross section flow check point in each check line according to the first initial weight set;

the fourth determining submodule is used for determining a relative error value of the vehicle passing through each section flow check point in each check line according to the total number of the vehicles and the total weight;

and the fifth determining submodule is used for determining a first weight set corresponding to each check line in the first vehicle data according to the relative vehicle error value and a first preset algorithm.

Optionally, the fifth determining sub-module includes:

the first determining unit is used for determining that the absolute value of the vehicle relative error value is larger than the third vehicle data corresponding to a first threshold value; the third vehicle data belongs to the first vehicle data;

the second determining unit is used for carrying out weight correction on the third vehicle data according to the first preset algorithm and determining the weight of the corrected third vehicle data;

and the third determining unit is used for determining a first weight set corresponding to each check line in the first vehicle data according to the weight of the vehicle corresponding to the condition that the absolute value of the relative vehicle error value is smaller than the first threshold and the weight of the corrected third vehicle data.

Optionally, the second determining unit includes:

a first obtaining subunit, configured to obtain a difference between a first maximum initial weight and a first minimum initial weight in the first initial weight set;

the first determining subunit is used for determining a first correction weight step length according to the ratio of the difference value to a preset minimum weight interval;

a first processing subunit, configured to, according to the first preset algorithm, determine, if the vehicle relative error value is greater than zero, a smaller value of a sum of the current weight of the third vehicle data and the first correction weight step length and the first maximum initial weight, and determine the sum as a weight of the corrected third vehicle data;

Optionally, the third processing module 40 includes:

a sixth determining submodule, configured to determine, according to the mobile phone signaling data, a total travel amount of a traffic cell to which each vehicle belongs;

a seventh determining submodule, configured to determine a traffic cell to which each vehicle belongs according to the total travel amount of the traffic cell to which each vehicle belongs;

the eighth determining submodule is used for determining a second initial weight set corresponding to the second vehicle data according to the traffic cell to which each vehicle belongs, the first weight set and the second vehicle data;

and the ninth determining submodule is used for determining a second weight set corresponding to the second vehicle data according to the second initial weight set and a second preset algorithm.

Optionally, the eighth determining sub-module includes:

a fourth determining unit, configured to determine, according to the first weight set and a traffic cell to which each vehicle belongs, a first traffic generation amount of the traffic cell corresponding to the first vehicle data;

a fifth determining unit, configured to determine, according to the second vehicle data and the first traffic volume, a second traffic volume of a traffic cell corresponding to the second vehicle data;

and the sixth determining unit is used for determining a second initial weight set corresponding to the second vehicle data according to the second traffic generation amount.

Optionally, the ninth determining sub-module includes:

a seventh determining unit, configured to determine a relative error value between the actual traffic generation amount and the statistical traffic generation amount of each traffic cell according to the second initial weight set, the first traffic generation amount, and the second traffic generation amount;

the eighth determining unit is configured to determine a second weight set corresponding to the second vehicle data according to the relative error value of the production amount, a second threshold, and a second preset algorithm.

Optionally, the eighth determining unit includes:

the second determining subunit is used for determining that the absolute value of the relative error value of the production quantity is greater than fourth vehicle data corresponding to a second threshold value; the fourth vehicle data belongs to the second vehicle data;

the third determining subunit is configured to perform weight correction on the fourth vehicle data according to the second preset algorithm, and determine a weight of the corrected fourth vehicle data;

and the fourth determining subunit is configured to determine a second weight set corresponding to the second vehicle data according to the weight of the vehicle corresponding to the fact that the absolute value of the production quantity relative error value is smaller than the second threshold and the weight of the corrected fourth vehicle data.

Optionally, the third determining subunit is specifically configured to:

according to the second preset algorithm, if the relative error value of the production amount is smaller than zero, determining the smaller value of the sum of the current weight of the fourth vehicle data and the second correction weight step length and the second maximum initial weight, and determining the smaller value as the weight of the corrected fourth vehicle data.

Optionally, the first processing module 20 includes:

the first processing submodule is used for acquiring the running track of each vehicle according to the vehicle GPS data and a preset road network section;

the second processing submodule is used for dividing N pieces of check line data according to the section flow check point and a preset road network section; n is an integer greater than 1;

and the third processing submodule is used for acquiring first vehicle data passing through a section flow check point and second vehicle data not passing through the section flow check point according to the N check line data and the vehicle GPS data.

The readable storage medium of the embodiment of the present invention stores a program or an instruction thereon, and the program or the instruction when executed by the processor implements the steps in the road traffic flow obtaining method described above, and can achieve the same technical effects, and the details are not repeated here in order to avoid repetition.

The processor is the processor in the road traffic flow obtaining method in the above embodiment. The readable storage medium includes a computer readable storage medium, such as a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk.

In embodiments of the present invention, modules may be implemented in software for execution by various types of processors. An identified module of executable code may, for instance, comprise one or more physical or logical blocks of computer instructions which may, for instance, be constructed as an object, procedure, or function. Nevertheless, the executables of an identified module need not be physically located together, but may comprise disparate instructions stored in different bits which, when joined logically together, comprise the module and achieve the stated purpose for the module.

Indeed, a module of executable code may be a single instruction, or many instructions, and may even be distributed over several different code segments, among different programs, and across several memory devices. Similarly, operational data may be identified within modules, and may be embodied in any suitable form and organized within any suitable type of data structure. The operational data may be collected as a single data set, or may be distributed over different locations including over different storage devices, and may exist, at least partially, merely as electronic signals on a system or network.

When a module can be implemented by software, considering the level of existing hardware technology, a module implemented by software may build a corresponding hardware circuit to implement a corresponding function, without considering cost, and the hardware circuit may include a conventional Very Large Scale Integration (VLSI) circuit or a gate array and an existing semiconductor such as a logic chip, a transistor, or other discrete components. A module may also be implemented in programmable hardware devices such as field programmable gate arrays, programmable array logic, programmable logic devices or the like.

The exemplary embodiments described above are described with reference to the drawings, and many different forms and embodiments of the invention may be made without departing from the spirit and teaching of the invention, therefore, the invention is not to be construed as limited to the exemplary embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the invention to those skilled in the art. In the drawings, the size and relative sizes of elements may be exaggerated for clarity. The terminology used herein is for the purpose of describing particular example embodiments only and is not intended to be limiting. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "comprises" and/or "comprising," when used in this specification, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Unless otherwise indicated, a range of values, when stated, includes the upper and lower limits of the range and any subranges therebetween.

While the foregoing is directed to the preferred embodiment of the present invention, it will be understood by those skilled in the art that various changes and modifications may be made without departing from the spirit and scope of the invention as defined in the appended claims.

Claims

1. A road traffic flow obtaining method is characterized by comprising the following steps:

2. The method of claim 1, wherein determining a first set of weights for each check line in the first vehicle data based on the N check line data and the first vehicle data comprises:

3. The method of claim 2, wherein determining a first set of weights for each check line in the first vehicle data based on the vehicle relative error value and a first predetermined algorithm comprises:

4. The method according to claim 3, wherein performing weight correction on the third vehicle data according to the first preset algorithm, and determining the weight of the corrected third vehicle data comprises:

or according to the first preset algorithm, if the vehicle relative error value is smaller than zero, determining the difference between the current weight of the third vehicle data and the first correction weight step length, and determining the larger value of the first minimum initial weight and the difference as the weight of the corrected third vehicle data.

5. The method of claim 1, wherein determining the second set of weights for the second vehicle data comprises:

6. The method of claim 5, wherein determining a second initial set of weights for the second vehicle data comprises:

and determining a second initial weight set corresponding to the second vehicle data according to the second traffic generation amount.

7. The method according to claim 6, wherein determining a second weight set corresponding to the second vehicle data according to the second initial weight set and a second preset algorithm comprises:

8. The method according to claim 7, wherein determining a second weight set corresponding to the second vehicle data according to the relative error value of the production amount, a second threshold value and a second preset algorithm comprises:

9. The method according to claim 8, wherein the weight correction of the fourth vehicle data is performed according to the second preset algorithm, and the determination of the weight of the corrected fourth vehicle data comprises:

10. The method of claim 1, wherein preprocessing the multi-source fusion data comprises:

and acquiring first vehicle data passing through a section flow rate check point and second vehicle data not passing through the section flow rate check point according to the N check line data and the vehicle GPS data.

11. A road traffic flow obtaining apparatus, characterized by comprising:

12. A readable storage medium on which a program or instructions are stored, the program or instructions, when executed by a processor, implementing the steps in the road traffic flow acquisition method according to any one of claims 1 to 10.