CN115759484A - Traffic flow prediction method, electronic device and storage medium - Google Patents
Traffic flow prediction method, electronic device and storage medium Download PDFInfo
- Publication number
- CN115759484A CN115759484A CN202310015775.5A CN202310015775A CN115759484A CN 115759484 A CN115759484 A CN 115759484A CN 202310015775 A CN202310015775 A CN 202310015775A CN 115759484 A CN115759484 A CN 115759484A
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- road
- flow prediction
- travel time
- information
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 238000000611 regression analysis Methods 0.000 claims abstract description 35
- 238000010801 machine learning Methods 0.000 claims abstract description 33
- 238000012216 screening Methods 0.000 claims abstract description 18
- 230000003993 interaction Effects 0.000 claims abstract description 12
- 230000011664 signaling Effects 0.000 claims abstract description 12
- 238000012549 training Methods 0.000 claims description 21
- 230000015654 memory Effects 0.000 claims description 19
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000012417 linear regression Methods 0.000 claims description 5
- 238000003066 decision tree Methods 0.000 claims description 4
- 238000007637 random forest analysis Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 description 7
- 238000004364 calculation method Methods 0.000 description 5
- 238000004590 computer program Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000007667 floating Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000007477 logistic regression Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 230000001537 neural effect Effects 0.000 description 2
- 238000011176 pooling Methods 0.000 description 2
- 230000001413 cellular effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Landscapes
- Traffic Control Systems (AREA)
Abstract
The application discloses a traffic flow prediction method, an electronic device and a storage medium. The traffic flow prediction method comprises the following steps: taking a road of traffic flow information to be predicted as an appointed road, and screening a road similar or similar to the appointed road as a screening road; establishing a machine learning traffic flow prediction model based on the screened roads; establishing a regression analysis traffic flow prediction model of the specified road based on the specified road; acquiring signaling interaction information of a specified road in predicted time, and collecting characteristics of travel time; inputting the characteristics of travel time into a machine learning traffic flow prediction model to obtain the general traffic flow of the specified road; and inputting the general traffic flow of the specified road into a regression analysis traffic flow prediction model to obtain traffic flow prediction information of the specified road within the prediction time. The method and the device improve the accuracy of the traffic flow information acquisition and also cover the range of more traffic flow information.
Description
Technical Field
The application belongs to the field of machine learning, and particularly relates to a traffic flow prediction method, electronic equipment and a storage medium.
Background
The method is a common prediction method for predicting the traffic flow of a target area in a target time period by obtaining historical traffic flow data, but has good prediction effects on the traffic flow data when the road is smooth and the periodic congestion of the peak at morning and evening, but because the deployment and maintenance costs of detection equipment are very expensive, and the problems of low penetration rate of detection data and the like exist, accurate real-time traffic information cannot be deduced, so that the prediction on the area traffic flow is not comprehensive and accurate, and the traffic flow information is difficult to accurately obtain in practical application.
Disclosure of Invention
The purpose of the invention is as follows: the application provides a traffic flow prediction method, aiming at solving the technical problems of low prediction precision and incomplete prediction range of the related technology; another object of the present application is to provide an electronic device and a storage medium for storing and processing the computer program of the prediction method.
The technical scheme is as follows: the embodiment of the application provides a traffic flow prediction method, which comprises the following steps:
taking a road of traffic flow information to be predicted as an appointed road, and screening a road similar or similar to the appointed road as a screening road;
establishing a machine learning traffic flow prediction model based on the screened roads;
establishing a regression analysis traffic flow prediction model of the specified road based on the specified road;
acquiring signaling interaction information of the specified road within the prediction time, and collecting travel time;
inputting the travel time into the machine learning traffic flow prediction model to obtain the general traffic flow of the specified road;
and inputting the general traffic flow of the specified road into the regression analysis traffic flow prediction model to obtain traffic flow prediction information of the specified road within prediction time.
In some embodiments, the step of building a machine-learned traffic-flow prediction model based on the screened roads includes:
acquiring first travel time of the screened roads, and collecting the first travel time and a label value;
the first travel time and label values are combined into a training set, adjusted through supervised machine learning training, to generate the machine learned traffic flow prediction model.
In some embodiments, the supervised machine learning includes at least one of a support vector machine, a decision tree, a random forest, or a neural network.
In some embodiments, the step of building a regression analysis traffic flow prediction model of the specified road based on the specified road includes:
acquiring second travel time of the specified road, and collecting the second travel time and a label value;
inputting the second travel time and the label value into the machine learning traffic flow prediction model to obtain historical general traffic flow of the specified road;
and performing road type regression analysis training according to the label value of the second travel time and the historical general traffic flow, and establishing a regression analysis traffic flow prediction model of the specified road.
In some embodiments, the signaling interaction information is at least one of user information, base station location information, base station number information, handover information, and call information taken from the base station within the predicted time.
In some embodiments, the tag value for the first travel time and the tag value for the second travel time are taken from at least one of a vehicle or an electronic tag detector, road image recognition, manual road survey.
In some embodiments, the first travel time is a travel time calculated from at least one of user information, base station location information, base station number information, handover information, call information taken from a base station at a past time period; and/or the presence of a gas in the gas,
the second travel time is calculated from at least one of user information, base station position information, base station number information, handover information and call information of the base station in a certain past period.
In some embodiments, the road type regression analysis training uses a technique that is at least one of linear regression, log-probability regression, multiple regression, polynomial regression, multivariate regression, and multidimensional regression.
In some embodiments, the present application further provides an electronic device comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the steps of the traffic flow prediction method.
In some embodiments, the present application further provides a computer readable storage medium having at least one instruction or at least one program stored therein, the at least one instruction or the at least one program being loaded and executed by a processor to implement the steps of the traffic flow prediction method.
Has the advantages that: compared with the prior art, the traffic flow prediction method comprises the following steps: taking a road of traffic flow information to be predicted as an appointed road, and screening a road similar or similar to the appointed road as a screening road; establishing a machine learning traffic flow prediction model based on the screened roads; establishing a regression analysis traffic flow prediction model of the specified road based on the specified road; acquiring signaling interaction information of a specified road in predicted time, and collecting characteristics of travel time; inputting the characteristics of travel time into a machine learning traffic flow prediction model to obtain the general traffic flow of the specified road; and inputting the general traffic flow of the specified road into a regression analysis traffic flow prediction model to obtain traffic flow prediction information of the specified road within the prediction time. The machine learning traffic flow prediction model is established by screening the historical information of the roads, a basis for establishing a regression analysis traffic flow prediction model is provided for the specified roads, the basis for predicting can be provided for the specified roads due to the commonality between the screened roads and the specified roads, the machine learning traffic flow prediction model can be used for predicting the traffic flow of various vehicle types in the practical application process, the traffic flow prediction information is directly obtained through real-time signaling interaction information, the accuracy of obtaining the traffic flow information is improved, and the range of more traffic flow information is covered.
The regression analysis traffic flow prediction model established in the specified road is combined with the machine learning traffic flow prediction model in the screened road, so that the overfitting problem of machine learning in the prior art can be avoided, and the prediction error can be effectively reduced.
It is understood that, compared with the prior art, the electronic device and the storage medium provided in the embodiments of the present application may have all the technical features and advantages of the traffic flow prediction method described above, and are not described herein again.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments 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 based on these drawings without creative efforts.
Fig. 1 is a flowchart of a traffic flow prediction method provided in an embodiment of the present application;
FIG. 2 is a block diagram of an electronic device according to an embodiment of the present disclosure;
figure 3 is a comparison of traffic flow prediction predictions provided by embodiments of the present application,
fig. 4 is a comparison of filter analysis of a convolutional neural network provided by an embodiment of the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application. It is to be understood that the embodiments described are only a few 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.
In the description of the present application, it is noted that the terms "first," "second," and the like are used solely to distinguish one from another, and are not to be construed as indicating or implying relative importance.
Referring to fig. 1, there is provided a traffic flow prediction method including:
s101: taking a road of traffic flow information to be predicted as an appointed road, and screening a road similar or similar to the appointed road as a screening road;
s102: establishing a machine learning traffic flow prediction model based on the screened roads;
s103: establishing a regression analysis traffic flow prediction model of the specified road based on the specified road;
s104: acquiring signaling interaction information of a specified road in the prediction time, and collecting travel time;
s105: inputting the characteristics of travel time into a machine learning traffic flow prediction model to obtain the general traffic flow of the specified road;
s106: and inputting the general traffic flow of the specified road into a regression analysis traffic flow prediction model to obtain traffic flow prediction information of the specified road within the prediction time.
In some embodiments, the designated road is a road whose traffic flow needs to be predicted, the screening road is a road similar to or close to the designated road, and the similar road has at least one characteristic same as that of the designated road, for example, the screening road and the designated road are both roads in a city or a country, or the distance between the screening road and the designated road (for example, calculated by longitude and latitude) is less than a preset value, or the screening road and the designated road have similar characteristics (for example, market, sightseeing spot, government offices) and the like.
In some embodiments, in step S102, the step of establishing a machine-learned traffic-flow prediction model based on the screened roads includes: acquiring first travel time of a screened road, and collecting the first travel time and a label value; and forming a training set by the first travel time and the label value, and adjusting through supervised machine learning training to generate a machine learning traffic flow prediction model.
The first travel time of the screened road is the travel time calculated by one or the combination of user information, base station position information, base station number information, switching information and call information which are taken from a base station in a certain past time period.
In some embodiments, obtaining the first travel time of the screened road specifically means: for example, the first travel time and the tag of the screened road per unit time may be acquired. The first travel time is the length of time that the mobile device has traveled on a similar road. In addition, the tag value of the screened road is a traffic flow, and may be, for example, the number of single or multiple vehicles (such as trucks, buses, cars, etc.) passing through similar roads in each unit time of the time period. The tag value may be taken from at least one of a vehicle or electronic tag detector, road image recognition, and millimeter wave radar of similar roads.
The specific steps for acquiring the real travel time are as follows:
dividing the road network of the target area into grids with the size of 100m multiplied by 100m, and mapping the collected floating car data to the grids corresponding to the target road section according to the time interval of every 2 min. And assuming that the traffic conditions within each square are homogeneous, the average speed of the sample vehicles within the square is calculated while ensuring a sample amount of floating vehicles within the square (typically at least 5). And taking the average speed value of the sample vehicles in the square grids as the speed value of the traffic state of the road section, thereby obtaining the speed value of each 100m and each 2 minutes of the target path and expanding the speed value to the whole path and all moments.
Based on the speed data of the floating vehicle from six morning to ten night in one day, a space-time speed matrix with the size of 320 multiplied by 480 can be obtained, 320 represents 320 100m, and the total number is 32km;480 represent 480 2 minute time intervals totaling 16h. The daily floating car data corresponds to a space-time velocity matrix. According to the space-time velocity matrix, the real travel time of any departure time (specifically, the travel time from seven points in the morning to nine points in the evening) through the whole target path can be calculated. The real travel time of a given departure time is the real travel time of a vehicle passing through all fixed road sections of the target route with the given departure time as the departure time. When the real travel time is calculated, the speed of the vehicle is ensured to be dynamically updated after the vehicle enters different squares, namely, the square where the vehicle passes through the next fixed road section is positioned according to the calculated real travel time of the first square where the vehicle passes through, namely, the second square where the vehicle passes through, and the real travel time of the vehicle passing through the second square is calculated according to the speed value in the second square; in the same way, all the squares that the vehicle passes through and that contain the target path are located in turn, and finally the real travel time through the entire path is obtained by adding up the real travel time of each square that the vehicle passes through.
In some embodiments, the first travel time and the tag value are combined into a training set, and the training set is adjusted by supervised machine learning training to generate a machine learning traffic flow prediction model, wherein the supervised machine learning may be a support vector machine (support vector machine), a decision tree (decision tree), a random forest (random forest) or a neural network (neural network). Preferably, a Neural Network-like technology may be used, and the Neural Network-like technology may be a Back Propagation Neural Network (BPNN), a Recurrent Neural Network (RNN), a Deep Neural Network (DNN), a Convolutional Neural Network (CNN), or a Long Short Term Memory (LSTM) Network.
In some embodiments, the preferred supervised machine learning is Convolutional Neural Network (CNN).
Because the mutual dependence and the mutual influence relationship exist among the road sections, the linear regression algorithm and the logistic regression algorithm can not analyze the problem of factor dependence, the current travel time information and the historical travel time information of each road section are modeled into input layer data of the convolutional neural network by adopting a convolutional neural network method, and then the output layer is set as the travel time of the target road section at the next time point. The proposed travel time prediction method mainly collects travel times of x road segments, considers the travel times of the current road segments and the previous y time points, and establishes a travel time set as a (x) x (y + 1) size matrix to be input into the convolutional layer for feature extraction. Wherein the travel time of the road section i at the jth time point is T i,j Setting a target road section as a road section z, and predicting the travel time of the road section z at the j +1 th time point as T z,j+1 . In the convolutional layer calculation, a plurality of filters are generated, and road condition characteristics are analyzed through each filter; wherein, referring to fig. 4, (a) indicates that the filter will mainly analyze the correlation between the travel time of each link at each time point and the travel time of the next time point of the target link; (b) The representation filter mainly can analyze the relevance of the travel time of each time point in each road section and the travel time of the next time point of the target road section; (c) And (d) the correlation between the travel time when the traffic circulation is transferred from different roads to other roads and the travel time of the next time point of the target road section can be analyzed. Therefore, after the analysis of the filters, the overall road condition association can be established, and the key characteristics which have more influence on the target road section are obtained. When the convolution layer calculation is completed, the method will beThe pooling layer is adopted to reduce the dimension, reduce the amount of calculation data and improve the calculation speed so as to meet the requirement of an online system. And finally, receiving the neural network, analyzing the correlation between the characteristic values obtained by the convolutional layer and the pooling layer and the target value (namely the travel time of the road section z at the j +1 th time point), learning the combination of the weight value and the error item value in the neural network, and outputting a prediction result.
In some embodiments, the step of building a regression analysis traffic flow prediction model of the specified road based on the specified road in step S103 includes: acquiring second travel time of the specified road, and collecting the second travel time and a label value; inputting the second travel time and the label value into a machine learning traffic flow prediction model to obtain historical general traffic flow of the specified road; and performing road type regression analysis training according to the label value of the second travel time and the historical general traffic flow, and establishing a regression analysis traffic flow prediction model of the specified road.
Wherein, the second travel time of the specified road is the travel time calculated by one or the combination of the user information, the base station position information, the base station number information, the switching information and the call information which are taken from the base station in a certain past time period. The tag value of the second travel time is the traffic flow, and may be, for example, the number of single or multiple vehicles (such as trucks, buses, cars, etc.) passing through similar roads in each unit time of the time period. The tag value may be taken from at least one of a vehicle or electronic tag detector of a similar road, road image recognition, and millimeter wave radar. The second travel time and tag value for the specified link is similar to the first travel time and tag value for the screened link.
In some embodiments, the characteristics of the specified road are input into the trained machine-learned traffic flow prediction model generated at step S102 to predict a historical general-purpose traffic flow for the specified road. And performing road type regression analysis training according to the label value of the specified road and the historical general traffic flow to generate a regression analysis traffic flow prediction model of the specified road. The technology used in the road type regression analysis training may be linear regression (linear regression), logistic regression (logistic regression), multiple regression (multiple regression), polynomial regression (multivariate regression), multivariate regression (multiple-variable regression), or multidimensional regression (multiple-variable regression). Preferably, the technique used for the road type regression analysis training is polynomial regression (polynomial regression).
In some embodiments, step S104 is a specific application phase that may be used to predict the traffic flow for a given link at any prediction (e.g., on the fly). Firstly, signaling interaction information of a specified road within a prediction time is obtained, and the prediction time can be any time period. The signaling interaction information of the specified road is one of user information, base station position information, base station number information, switching information and call information which are taken from the base station in the prediction time. Then, the travel time of the specified link is acquired, and for example, the travel time of the specified link per unit time of the predicted time may be acquired. Then, the feature of the specified road is input to the machine-learned traffic flow prediction model generated at step S102 to predict the general-purpose traffic flow of the specified road. Next, the general-purpose traffic flow of the specified road is input to the regression analysis traffic flow prediction model of the specified road generated in step 103 to generate traffic flow prediction information of the specified road within the prediction time using the road type regression analysis technique. The traffic-flow prediction information includes the number of various vehicles passing through a specified road per unit time of the prediction time.
In some embodiments, the MAPE of the present invention is 12.8% using a Mean Absolute Percentage Error (MAPE) calculation, which achieves better accuracy by the following formula:
the target road section is a road section z, and the travel time of the road section z at the j +1 th time point is T z,j+1 And the travel time of the predicted road section z at the j +1 th time point is T z,j+1 ’。
In some embodiments, referring to fig. 2, the internal block diagram of a computer device provided in this embodiment is a computer device, where the computer device may be a server or a terminal, and includes a processor, a memory, and a communication interface, where the processor is used to provide control computing power of the computer device; the memory has stored thereon a computer program that, when executed by the processor, implements a traffic flow prediction method. The memory includes a computer storage medium which is a nonvolatile storage medium storing an operating system and a computer program, and an internal memory which provides an environment for the operating system and the computer program to run. The communication interface of the computer device is used for carrying out wired or wireless communication with an external terminal, and the wireless communication can be achieved through WIFI, a mobile cellular network and the like.
In some embodiments, the structure shown in fig. 2 is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation to the computer device applied in the present application, and a specific electronic device may further include more or less components than those in fig. 2, or have different arrangements of components connected, or some components combined, and the like.
In some embodiments, an electronic device is provided, which includes a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the steps of the traffic flow prediction method; a traffic flow prediction method comprising:
s101: taking a road of traffic flow information to be predicted as an appointed road, and screening a road similar or similar to the appointed road as a screening road;
s102: establishing a machine learning traffic flow prediction model based on the screened roads;
s103: based on the specified road, establishing a regression analysis traffic flow prediction model of the specified road;
s104: acquiring signaling interaction information of a specified road in the prediction time, and collecting travel time;
s105: inputting the characteristics of travel time into a machine learning traffic flow prediction model to obtain the general traffic flow of the specified road;
s106: and inputting the general traffic flow of the specified road into a regression analysis traffic flow prediction model to obtain traffic flow prediction information of the specified road within the prediction time.
In some embodiments, a computer-readable storage medium is provided, in which at least one instruction or at least one program is stored, the at least one instruction or the at least one program being loaded and executed by a processor to implement the steps of the traffic flow prediction method.
In some embodiments, all or part of the processes of the traffic flow prediction method may be implemented by a computer program, which may be stored in a non-volatile computer readable storage medium, and when executed, may include the processes of the embodiments of the methods. Any reference to memory, database, or other medium used in the embodiments provided herein may include at least one of non-volatile and volatile memory. The nonvolatile Memory may include Read Only Memory (ROM), magnetic tape, floppy disk, flash Memory, optical Memory, high density embedded nonvolatile Memory, resistive random access Memory, and the like. Volatile Memory can include Random Access Memory (RAM), external cache Memory, and the like. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM), for example.
A specific implementation is provided:
firstly, in a training stage, one to three roads in a certain area are acquired as first travel time of a screening road in a specific time period. The specific time period may be 1 to 12 months. Then, a characteristic value of travel time during which one to three of the fixed time periods (e.g. every five minutes) are obtained, for example, the first travel time period is divided by a unit time of the fixed time period (e.g. five minutes), each day is divided into 288 time points, characteristics of the travel time corresponding to the 288 time points are obtained, and traffic flow of one or more vehicles detected by the millimeter wave radar is used as a tag value.
Then, the first travel time and the tag value are combined into a training set, and a machine learning traffic flow prediction model is generated by training and adjusting the machine learning traffic flow prediction model through supervised machine learning.
On the other hand, a second travel time of a specified road during a certain working day is acquired, and also with a fixed time (e.g., five minutes) as a unit time, characteristics of the second travel time every five minutes during the period are acquired, and traffic flow of various vehicles (e.g., trucks, cars, etc.) is identified as a tag value by using a traffic flow image video.
Then, the generated machine-learned traffic flow prediction model is extracted, and the acquired feature of the second travel time is input to predict the historical general-purpose traffic flow of the specified road. Then, the label value of the second travel time of the road and the predicted historical general traffic flow are input, and road type regression analysis training is carried out to generate a regression analysis traffic flow prediction model of the specified road.
Then, entering an application stage, taking a specific time period of a certain working day as a predicted time, acquiring signaling interaction information of the specified road at the predicted time, and similarly taking fixed time (such as five minutes) as unit time, acquiring the travel time of every five minutes of the specified road within the predicted time. Travel time is input into the generated machine-learned traffic flow prediction model to predict general traffic flow for the specified link. Then, the generated general-purpose traffic flow is input into the generated regression analysis traffic flow prediction model, and the traffic flow prediction information of the specified link during the prediction time is generated by using the link type regression analysis technology.
In this embodiment, the traffic flow prediction of the vehicle is shown in fig. 3, wherein the horizontal axis represents time and the vertical axis represents the traffic flow through the specified road. Fig. 3 also includes real values of various traffic flows detected simultaneously according to the road image, wherein the dotted line represents the result predicted by the classical model, and the improved model represents the result predicted by the method of the present embodiment. Compared with the actual value, the predicted result of the embodiment is closer to the actual value, and the traffic flow prediction method of the embodiment still has better accuracy.
In the foregoing embodiments, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
The traffic flow prediction method, the electronic device, and the storage medium provided in the embodiments of the present application are introduced in detail, and a specific example is applied to illustrate the principle and the implementation of the present application, and the description of the embodiments is only used to help understand the technical solutions and the core ideas of the present application; those of ordinary skill in the art will understand that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications or substitutions do not depart from the spirit and scope of the present disclosure as defined by the appended claims.
Claims (10)
1. A traffic flow prediction method is characterized by comprising the following steps:
taking a road of traffic flow information to be predicted as an appointed road, and screening a road similar or similar to the appointed road as a screening road;
establishing a machine learning traffic flow prediction model based on the screened roads;
establishing a regression analysis traffic flow prediction model of the specified road based on the specified road;
acquiring signaling interaction information of the specified road within the prediction time, and collecting travel time;
inputting the travel time into the machine learning traffic flow prediction model to obtain the general traffic flow of the specified road;
and inputting the general traffic flow of the specified road into the regression analysis traffic flow prediction model to obtain the traffic flow prediction information of the specified road within the prediction time.
2. The traffic-flow prediction method according to claim 1, wherein the step of establishing a machine-learned traffic-flow prediction model based on the screened roads includes:
acquiring first travel time of the screened roads, and collecting the first travel time and a label value;
the first travel time and label values are combined into a training set, adjusted through supervised machine learning training, to generate the machine learned traffic flow prediction model.
3. The method of claim 2, wherein the supervised machine learning includes at least one of support vector machines, decision trees, random forests or neural networks.
4. The traffic flow prediction method according to claim 2, wherein the step of building a regression analysis traffic flow prediction model for the specified road based on the specified road comprises:
acquiring second travel time of the specified road, and collecting the second travel time and a label value;
inputting the second travel time and the label value into the machine learning traffic flow prediction model to obtain historical general traffic flow of the specified road;
and performing road type regression analysis training according to the label value of the second travel time and the historical general traffic flow, and establishing a regression analysis traffic flow prediction model of the specified road.
5. The traffic flow prediction method according to claim 4, wherein the signaling interaction information is at least one of user information, base station location information, base station number information, handover information, and call information, which are taken from the base station at the prediction time.
6. The traffic flow prediction method according to claim 4, wherein the label value of the first travel time and the label value of the second travel time are taken from at least one of a vehicle or an electronic label detector, road image recognition, and artificial road survey.
7. The traffic flow prediction method according to claim 5,
the first travel time is calculated from at least one of user information, base station position information, base station number information, switching information and call information of a base station in a certain past period; and/or the presence of a gas in the gas,
the second travel time is calculated from at least one of user information, base station position information, base station number information, handover information and call information of the base station in a certain past period.
8. The method of claim 4, wherein the road type regression analysis training employs at least one of linear regression, log-probability regression, multiple regression, polynomial regression, multivariate regression, and multidimensional regression.
9. An electronic device comprising a processor and a memory, wherein at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the steps of the traffic flow prediction method according to any one of claims 1 to 8.
10. A computer-readable storage medium, wherein at least one instruction or at least one program is stored in the computer-readable storage medium, and the at least one instruction or the at least one program is loaded by a processor and executed to implement the steps of the traffic flow prediction method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310015775.5A CN115759484A (en) | 2023-01-06 | 2023-01-06 | Traffic flow prediction method, electronic device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310015775.5A CN115759484A (en) | 2023-01-06 | 2023-01-06 | Traffic flow prediction method, electronic device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115759484A true CN115759484A (en) | 2023-03-07 |
Family
ID=85348267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310015775.5A Pending CN115759484A (en) | 2023-01-06 | 2023-01-06 | Traffic flow prediction method, electronic device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115759484A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228808A (en) * | 2016-08-05 | 2016-12-14 | 北京航空航天大学 | City expressway travel time prediction method based on Floating Car space-time grid data |
| CN106981198A (en) * | 2017-05-24 | 2017-07-25 | 北京航空航天大学 | Deep learning network model and its method for building up for predicting travel time |
| CN109087509A (en) * | 2018-09-04 | 2018-12-25 | 重庆交通大学 | A kind of road grid traffic operating status prediction technique |
| CN111047078A (en) * | 2019-11-25 | 2020-04-21 | 中山大学 | Traffic characteristic prediction method, system and storage medium |
| CN111862592A (en) * | 2020-05-27 | 2020-10-30 | 浙江工业大学 | Traffic flow prediction method based on RGCN |
| TWI748514B (en) * | 2020-06-12 | 2021-12-01 | 中華電信股份有限公司 | Method and system for estimating traffic |
-
2023
- 2023-01-06 CN CN202310015775.5A patent/CN115759484A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106228808A (en) * | 2016-08-05 | 2016-12-14 | 北京航空航天大学 | City expressway travel time prediction method based on Floating Car space-time grid data |
| CN106981198A (en) * | 2017-05-24 | 2017-07-25 | 北京航空航天大学 | Deep learning network model and its method for building up for predicting travel time |
| CN109087509A (en) * | 2018-09-04 | 2018-12-25 | 重庆交通大学 | A kind of road grid traffic operating status prediction technique |
| CN111047078A (en) * | 2019-11-25 | 2020-04-21 | 中山大学 | Traffic characteristic prediction method, system and storage medium |
| CN111862592A (en) * | 2020-05-27 | 2020-10-30 | 浙江工业大学 | Traffic flow prediction method based on RGCN |
| TWI748514B (en) * | 2020-06-12 | 2021-12-01 | 中華電信股份有限公司 | Method and system for estimating traffic |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tekouabou et al. | Improving parking availability prediction in smart cities with IoT and ensemble-based model | |
| Ali et al. | Exploiting dynamic spatio-temporal graph convolutional neural networks for citywide traffic flows prediction | |
| Gao et al. | Optimize taxi driving strategies based on reinforcement learning | |
| Gilik et al. | Air quality prediction using CNN+ LSTM-based hybrid deep learning architecture | |
| Shou et al. | Optimal passenger-seeking policies on E-hailing platforms using Markov decision process and imitation learning | |
| Provoost et al. | Predicting parking occupancy via machine learning in the web of things | |
| CN113591380B (en) | Traffic flow prediction method, medium and equipment based on graph Gaussian process | |
| Li et al. | Coupling simulation and optimization to solve planning problems in a fast-developing area | |
| CN110826244B (en) | Conjugated gradient cellular automaton method for simulating influence of rail transit on urban growth | |
| CN110598917B (en) | Destination prediction method, system and storage medium based on path track | |
| CN115600833A (en) | Smart city restriction scheme determination method, internet of things system, device and medium | |
| Chmiel et al. | Intelligent route planning system based on interval computing | |
| Yang et al. | Short-term prediction of airway congestion index using machine learning methods | |
| Turukmane et al. | Multispectral image analysis for monitoring by IoT based wireless communication using secure locations protocol and classification by deep learning techniques | |
| CN114372830A (en) | Network taxi booking demand prediction method based on space-time multi-graph neural network | |
| Qiu et al. | RPSBPT: A route planning scheme with best profit for taxi | |
| CN114169659A (en) | Criminal spatiotemporal risk prediction and decision scheduling method and device | |
| Manibardo et al. | A graph-based methodology for the sensorless estimation of road traffic profiles | |
| Ara et al. | Ride Hailing Service Demand Forecast by Integrating Convolutional and Recurrent Neural Networks. | |
| CN115759484A (en) | Traffic flow prediction method, electronic device and storage medium | |
| Salamanis et al. | Evaluating the effect of time series segmentation on STARIMA-based traffic prediction model | |
| CN115640756A (en) | Parking demand prediction model and method based on multi-source data and application thereof | |
| Ajani et al. | Dynamic path planning approaches based on artificial intelligence and machine learning | |
| CN114048886A (en) | Effective berthage combination prediction method based on neural network, terminal and storage medium | |
| Jiang et al. | Cruising or waiting: A shared recommender system for taxi drivers |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20230307 |