CN112489439A - Traffic control method based on big data and storage medium - Google Patents
Traffic control method based on big data and storage medium Download PDFInfo
- Publication number
- CN112489439A CN112489439A CN202011300491.3A CN202011300491A CN112489439A CN 112489439 A CN112489439 A CN 112489439A CN 202011300491 A CN202011300491 A CN 202011300491A CN 112489439 A CN112489439 A CN 112489439A
- Authority
- CN
- China
- Prior art keywords
- traffic flow
- vehicle
- section
- highway
- time period
- 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.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/017—Detecting movement of traffic to be counted or controlled identifying vehicles
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/07—Controlling traffic signals
- G08G1/08—Controlling traffic signals according to detected number or speed of vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a traffic control method and a storage medium based on big data, wherein the method comprises the steps of obtaining a high-speed driving record of a vehicle according to a license plate number when the vehicle drives into any entrance station and predicting an exit station of the vehicle; generating a predicted travel path; acquiring a predicted driving path of each vehicle within a preset historical time, and counting the traffic flow of each road section within a corresponding time period in different time periods; taking the traffic flow corresponding to two adjacent preset time periods of each road section as a sample pair, and taking the sample pair as a training data set to train a traffic flow prediction model; acquiring the traffic flow of each section of the highway at the current time period, inputting the traffic flow into the model, and outputting the traffic flow of each section at the next time period; judging whether the traffic flow of each road section in the next time period is larger than the traffic flow threshold of each road section; and if so, managing and controlling the passing frequency of the entrance station associated with the corresponding road section. The method has a remarkable effect of relieving the traffic flow of the specified road section, and simultaneously has a good effect on controlling the traffic flow of the front road section.
Description
Technical Field
The invention relates to the field of traffic control, in particular to a traffic control method and a storage medium based on big data.
Background
With the increasing popularization of intelligent traffic systems, people effectively integrate and apply advanced information technology, communication technology, sensing technology, computer technology and the like to a high-speed traffic monitoring system, and the supervision and service efficiency is greatly improved. For the traveling personnel, the convenience of traveling can be improved by the application of intelligent transportation.
In order to further improve the intelligent transportation system, the application of the traffic flow monitoring technology therein is also becoming more and more extensive and deep. The traffic flow monitoring technology is characterized in that each expressway station is responsible for collecting a large amount of various data, such as information of getting on and off the station, path information, load information, vehicle charging information and the like of each vehicle, and various information such as traffic flow, operation state and the like can be analyzed and obtained by utilizing the information. The method can enable each station of the highway to have the capacity of analyzing the 'big data', and is beneficial to predicting and analyzing the highway flow. Even so, the current intelligent transportation system still has a great development space. For example, every holiday, high-speed traffic is still often blocked for several hours, and it is seen that the traffic control of the expressway needs to be further improved. Therefore, a traffic control scheme based on big data is needed to be provided, so that an intelligent high-speed traffic system is further optimized, and the high-speed congestion situation is relieved.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the traffic control method based on big data has a remarkable effect of relieving the traffic flow of the specified road section, and can also generate a positive effect on the traffic flow control of the road section in front of the traffic control method, so that the control effect of the high-speed traffic flow is remarkably improved.
In order to solve the technical problems, the invention adopts the technical scheme that:
a traffic control method based on big data comprises the following steps:
when a vehicle drives into any entrance station of the highway, acquiring the license plate number of the vehicle;
acquiring a high-speed driving record of the vehicle according to the license plate number;
predicting an exit station of the vehicle according to the entry station and the high-speed running record of the vehicle;
generating a predicted travel path according to an entrance station and an exit station of the vehicle;
acquiring a predicted driving path corresponding to each vehicle driving into the highway within a preset historical time;
according to the obtained predicted driving path, counting the traffic flow of each section of the highway in the corresponding time period in different time periods;
taking the traffic flow corresponding to two adjacent preset time periods of each road section as a sample pair, and acquiring a sample pair set;
training a traffic flow prediction model by taking the sample pair set as a training data set to obtain a traffic flow prediction model for predicting the traffic flow of each road section in the next time period;
the method comprises the steps of obtaining the traffic flow of each section of the highway in the current time period, inputting the traffic flow into a traffic flow prediction model, and outputting the traffic flow of each section of the highway in the next time period;
judging whether the traffic flow of each section of the highway in the next time period is greater than a preset traffic flow threshold of each section; and if so, managing and controlling the passing frequency of the entrance station associated with the corresponding road section.
The invention provides another technical scheme as follows:
a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, is capable of implementing the steps included in a big data based traffic control method as described above.
The invention has the beneficial effects that: the invention predicts the exit according to the driving record of the inbound vehicle, which accords with the rule and has high accuracy; according to the method, firstly, according to the predicted driving path of each vehicle with the highest speed within the preset historical duration, the traffic flow of each section of road is obtained through time-sharing statistics, then the traffic flow corresponding to two adjacent preset time periods of each section of road is used as a sample pair to be trained, and a traffic flow prediction model for predicting the traffic flow of each section of road corresponding to the next time period is obtained; then, in practical application, after the traffic flow of each road section in the current time period can be obtained in the same way, the traffic flow of each road section in the next time period can be accurately measured by using the traffic flow prediction model; and finally, only by judging whether the traffic flow of each section of road exceeds a threshold value, if so, the traffic flow of the section of road can be effectively relieved by performing linkage management and control on the passing frequency of the entrance station associated with the section of road, and meanwhile, the condition of slow driving of the front section of the section of road can be effectively prevented.
Drawings
Fig. 1 is a schematic flow chart illustrating a traffic control method based on big data according to an embodiment of the present invention;
FIG. 2 is a schematic illustration of an exemplary site between the North office of Xiamen to the North office of Fuzhou, in accordance with an embodiment of the present invention;
fig. 3 is an exemplary diagram of a predicted travel path drawn with reference to a station to which the vehicle is approaching according to the first embodiment of the present invention.
Detailed Description
In order to explain technical contents, achieved objects, and effects of the present invention in detail, the following description is made with reference to the accompanying drawings in combination with the embodiments.
The method has the key concept that the traffic flow of each section of highway can be accurately predicted, the high-speed entrance station is subjected to linkage control, and the traffic flow of the specified road section and the road section in front of the specified road section can be dredged at the same time.
Example one
Referring to fig. 1 and fig. 2, the present embodiment provides a traffic control method based on big data, which may include the following steps:
s1: when the vehicle drives into any entrance station of the highway, the license plate number of the vehicle is obtained.
The license plate number can be acquired in various ways, including image recognition after image pickup or vehicle information scanning and license plate number extraction from the image.
S2: and acquiring the high-speed running record of the vehicle according to the acquired license plate number.
In the prior art, after a vehicle enters a high speed, the entrance station and the exit station register the relevant information (including the license plate number) of the vehicle. Therefore, all historical high-speed driving records (or historical high-speed driving records within a preset time period) can be called according to the license plate number, the high-speed driving records can be easily realized, and the high-speed driving records have both accuracy and comprehensiveness.
S3: according to the entry station where the vehicle currently enters, the exit station of the vehicle at this time can be predicted by combining the high-speed driving record.
Based on the fact that everyone's residence and work are relatively stationary for a long period of time, their relatively stationary life circle and range of daily traffic can be inferred. For example, a person living in a building door may need to go to quan 1-2 times a month in recent years, while a person living in quan may need to go to quan every week. Therefore, if the currently entering entrance station is the north office of mansion based on the high-speed travel record of a acquired in step S2, the exit station is estimated to be the north office of fuzhou.
Preferably, the present exit station of the vehicle is predicted by combining the inbound time of the vehicle, namely the time of acquiring the license plate number, so as to further improve the accuracy of prediction.
Obviously, in the above example, the current day is the working day in fuzhou, and the current day is the holiday in quanzhou. Thus, the activity will also be recorded in the user's high-speed driving record in a time-wise manner; correspondingly, when the prediction is carried out, the time factor is introduced as an important factor to be comprehensively calculated together with other factors, so that the accuracy of the prediction result is greatly improved.
The prediction results corresponding to the above example are reflected in: if the user starts from a mansion station on a working day, the prediction result has higher probability of starting from the northeast of Fuzhou; if the user starts from the north station of mansion gate on holidays, the spring station is the higher probability of the predicted result.
S4: and generating a predicted driving path according to the entrance station and the exit station of the vehicle.
The exit station of the vehicle is obtained through the prediction, and the driving path formed by the vehicle at the high speed at this time can be easily generated. For example, if the entrance site is a building gate and the exit site is fuzhou, the route (route) of the vehicle to be traveled from the building gate to fuzhou can be acquired in association with the route information of the expressway.
Preferably, the traveling path of the present time may be predicted in association with the historical traveling paths corresponding to the entrance station and the exit station in the high-speed travel record of the vehicle. This applies to the case where a path cannot be uniquely determined between an entry site and an exit site. For example, there are also intersections between highways, building stations to fuzhou stations, and there are three routes, one is the way sinking sea high speed and fuzhou south connecting line high speed; secondly, the method is used for building sand high speed and guan high speed; thirdly, sinking sea high speed and guan high speed are achieved. The three are slightly different in time, and at this time, the route which is most frequently (habitually) traveled by the user can be determined by combining the high-speed travel records, so that the accuracy of the predicted travel route is improved.
The following is a process of creating a traffic flow prediction model for predicting the traffic flow of each road segment corresponding to the next time period:
s5: and acquiring a predicted driving path corresponding to each vehicle which drives into the highway within a preset historical time.
This step can be understood as statistical data obtained after accumulating for a certain time by predicting and counting all the vehicles entering the highway in real time according to the above-described steps S1-S4. In practice, the steps S1-S4 may be implemented by asynchronous threads. Referring to fig. 3, which is an exemplary diagram of routes drawn by comparing a part of predicted travel routes with the route stations, in the historical duration, reference numerals 1 to 11 in the diagram respectively correspond to station numbers, arrows point to the travel direction, and a line segment below the arrow point to the predicted travel route of a vehicle, for example, a first line segment indicates that the vehicle starts from station 1 and travels out of a highway after passing through station 1, station 2, and station 3.
Preferably, the historical duration may be a time span of the past month, two months or half a year, which is more consistent with the stable life of people.
S6: and according to the predicted driving path obtained in the previous step, counting the traffic flow of each section of the expressway in the corresponding time period in different time periods.
The step aims to count and obtain the traffic flow conditions of all road sections corresponding to all preset time periods in the historical duration.
The road section refers to a path between two adjacent high-speed exit/entrance on an expressway as a road section. Preferably, each high-speed station is identified by using numbers or other coding forms, and the high-speed stations can also serve as identification road sections. For example, from the north building station to the north of fuzhou station, the first route of S4 is required to travel to 13 exit stations, and referring to fig. 2, assuming that the north building station code X-1 will pass through the stations X-2, X-3, X-4, etc. in sequence to reach the north of fuzhou station.
The time division refers to a result of presetting a fixed time range, such as a preset number of minutes, seconds, hours, dates, and the like, and then dividing in time sequence by taking the fixed time range as a unit. For example, 24 hours a day, the preset time period is 10 minutes, and then 24 is divided into a plurality of 10 minutes.
Corresponding to this step, in a specific example, the following may be implemented:
firstly, generating a blank record table which respectively corresponds to each road section and is used for recording the quantity of vehicles on the upper road of the corresponding road section in the corresponding month, the corresponding date and the corresponding different time periods; then, reading the predicted driving path data corresponding to each vehicle which drives into the highway within the acquired historical duration one by one, and updating the record table according to each station of the required path recorded by the currently read predicted driving path data and the corresponding (predicted) arrival time of the station; when all the predicted driving path data are read, a traffic flow record table of each road section of the time-period statistics corresponding to the historical time period can be obtained.
As shown in Table one below, assume an example record format for the corresponding road segment 2-3 in the traffic record table that corresponds to the example intercept of the site of FIG. 2:
watch 1
S7: and taking the traffic flow corresponding to two adjacent preset time periods of each road section as a sample pair to obtain a sample pair set.
The sample pair includes a sample input and a sample output. The sample pairs are used for model training, and the aim is to train to obtain a designated data B' which can be output to be as close as possible to the expected value data B of the data A after the data A is input.
The sample pair set refers to a set of all sample pairs corresponding to all road segments on the highway.
In this embodiment, for each link, starting from the second column where the vehicle volume starts to be recorded, the vehicle volume recording data of two adjacent upper and lower rows of the corresponding column are respectively used as a sample pair until the last row of the last column of the record is traversed.
Corresponding to the road section in the table I, namely the 2-3 road sections, from 1 month, the traffic flows corresponding to 0:00 and 0:10 of the 1 st are sequentially taken as a sample pair, and the traffic flows corresponding to 0:10 and 0:20 are taken as a sample pair, so that the road sections traverse to 23:40 and 23: 50; and starting from No. 2 of month 1, taking the vehicle amount corresponding to 0:00 and 0:10 of month 2 as a sample pair, and repeating the steps until the last recorded time period is traversed from No. 1 of month 2 after the sample pair of month 1, No. 31, No. 23:40 and 23:50 is obtained.
S8: and training a traffic flow prediction model by taking the sample pair set as a training data set to obtain a traffic flow prediction model for predicting the traffic flow of each road section in the next time period.
Since the model training is carried out by taking the traffic flow of each road section on the expressway in two time periods before and after the sample pair in advance, the trained model can be used for predicting the traffic flow of the road section in the next time period after the traffic flow of the specific road section in the specific time period is input.
S9: and acquiring the traffic flow of each section of the expressway at the current time period, inputting the traffic flow into the traffic flow prediction model, and outputting the traffic flow of each section of the expressway at the next time period.
Wherein, the manner of obtaining the traffic flow of each section of the expressway in the current time period is consistent with the manner described in the above-mentioned S2-S6S. In brief, the predicted driving path corresponding to each vehicle driving into the highway in the current time period is obtained, and the traffic flow of each road section of the highway in the current time period is counted according to the predicted driving path.
Here, the traffic flow per link in the current time period is input to the model, and the predicted traffic flow per link in the next time period is output from the model.
It should be noted that, in this embodiment, the sample pair used for training the model is based on the predicted road traffic flow, and accordingly, when the model is used, the predicted road traffic flow is also used as the input, which can significantly improve the accuracy of the model output.
S10: judging whether the traffic flow of each section of the expressway in the next period output by the model is larger than a preset traffic flow threshold of each section; and if so, managing and controlling the passing frequency of the entrance station associated with the corresponding road section.
In this case, the traffic flow of the sub-sections is monitored by combining the preset traffic flow threshold corresponding to each section of the highway in advance. The value of the traffic threshold is preferably referenced to the amount of traffic that will cause congestion or be traveling slowly.
The entry sites associated with the corresponding road segments refer to all entry sites that need to be routed to the road segments. Because the highway is melted through, the number of the associated entry sites is generally large, the difficulty of management and control is high, and the necessity is avoided, so that the number of the associated entry sites is preferably preset, and when the highway is actually used, the number of the associated entry sites which is preset by the direct entry sites is counted backwards to perform management and control. Based on the characteristics of the highways, a branch is often encountered during forward tracing, and when determining the associated entry stations, the entry stations of different branches need to be considered at the same time, rather than determining the associated entry stations only along one way backwards.
In this embodiment, a specific management and control manner is to control a passing rate of an entry station, so as to relieve a traffic flow of a corresponding road segment.
In a preferred example of this embodiment, the passage frequency will be gradually turned down in reverse order for the determined stations. That is, the more distant from the entry site of the corresponding road section, the less the regulation and control force.
Example two
In accordance with a first embodiment, a computer-readable storage medium is provided, on which a computer program is stored, where the computer program is capable of implementing all steps included in a big data based traffic control method according to the first embodiment when the computer program is executed by a processor. The detailed steps are not repeated here, and refer to the description of the first embodiment for details.
As can be understood from the above description, those skilled in the art can understand that all or part of the processes in the above technical solutions can be implemented by instructing related hardware through a computer program, where the program can be stored in a computer-readable storage medium, and when executed, the program can include the processes of the above methods. The program can also achieve advantageous effects corresponding to the respective methods after being executed by a processor.
The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
The above description is only an embodiment of the present invention, and not intended to limit the scope of the present invention, and all equivalent changes made by using the contents of the present specification and the drawings, or applied directly or indirectly to the related technical fields, are included in the scope of the present invention.
Claims (5)
1. A traffic control method based on big data is characterized by comprising the following steps:
when a vehicle drives into any entrance station of the highway, acquiring the license plate number of the vehicle;
acquiring a high-speed driving record of the vehicle according to the license plate number;
predicting an exit station of the vehicle according to the entry station and the high-speed running record of the vehicle;
generating a predicted travel path according to an entrance station and an exit station of the vehicle;
acquiring a predicted driving path corresponding to each vehicle driving into the highway within a preset historical time;
according to the obtained predicted driving path, counting the traffic flow of each section of the highway in the corresponding time period in different time periods;
taking the traffic flow corresponding to two adjacent preset time periods of each road section as a sample pair, and acquiring a sample pair set;
training a traffic flow prediction model by taking the sample pair set as a training data set to obtain a traffic flow prediction model for predicting the traffic flow of each road section in the next time period;
the method comprises the steps of obtaining the traffic flow of each section of the highway in the current time period, inputting the traffic flow into a traffic flow prediction model, and outputting the traffic flow of each section of the highway in the next time period;
judging whether the traffic flow of each section of the highway in the next time period is greater than a preset traffic flow threshold of each section; and if so, managing and controlling the passing frequency of the entrance station associated with the corresponding road section.
2. The big data-based traffic control method according to claim 1, wherein the controlling of the passing frequency of the entrance station associated with the corresponding road segment includes:
determining direct entry sites of corresponding road sections and associated entry sites with a preset number backwards from the direct entry sites;
and gradually reducing the passing frequency of the determined stations according to the reverse order.
3. The big data-based traffic control method according to claim 1, wherein predicting the exit station of the vehicle according to the entry station and the high speed driving record of the vehicle comprises:
and predicting the exit station of the vehicle according to the entry station of the vehicle, the acquisition time of the license plate number and the high-speed running record.
4. The big data-based traffic control method according to claim 1, wherein the historical duration is more than one month in the past;
the time-interval-based statistics of the traffic flow of each section of the highway in the corresponding time interval comprises the following steps:
and counting the traffic flow of each section of the highway every preset minutes under the corresponding month and the corresponding date.
5. The big data-based traffic control method according to claim 1, wherein the obtaining of the traffic flow of each segment of the highway in the current time period comprises:
acquiring a predicted driving path corresponding to each vehicle driving into the highway in the current time period;
according to the obtained predicted driving path, counting the traffic flow of each section of the highway at the current time period;
a computer-readable storage medium, on which a computer program is stored, wherein the program, when executed by a processor, is capable of implementing the steps included in a big data based traffic control method according to any of claims 1 to 5.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011300491.3A CN112489439A (en) | 2020-11-19 | 2020-11-19 | Traffic control method based on big data and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011300491.3A CN112489439A (en) | 2020-11-19 | 2020-11-19 | Traffic control method based on big data and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112489439A true CN112489439A (en) | 2021-03-12 |
Family
ID=74931858
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011300491.3A Withdrawn CN112489439A (en) | 2020-11-19 | 2020-11-19 | Traffic control method based on big data and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112489439A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113610059A (en) * | 2021-09-13 | 2021-11-05 | 北京百度网讯科技有限公司 | Vehicle control method and device based on regional assessment and intelligent traffic management system |
CN115793548A (en) * | 2023-01-09 | 2023-03-14 | 山东通维信息工程有限公司 | Electromechanical control method and system based on big data cloud service |
-
2020
- 2020-11-19 CN CN202011300491.3A patent/CN112489439A/en not_active Withdrawn
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113610059A (en) * | 2021-09-13 | 2021-11-05 | 北京百度网讯科技有限公司 | Vehicle control method and device based on regional assessment and intelligent traffic management system |
CN113610059B (en) * | 2021-09-13 | 2023-12-05 | 北京百度网讯科技有限公司 | Vehicle control method and device based on regional assessment and intelligent traffic management system |
CN115793548A (en) * | 2023-01-09 | 2023-03-14 | 山东通维信息工程有限公司 | Electromechanical control method and system based on big data cloud service |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN112700072B (en) | Traffic condition prediction method, electronic device, and storage medium | |
CN109887288B (en) | Urban road network guidance scheme publishing method and system based on travel structure | |
CN111966729B (en) | Vehicle track data processing method, device, equipment and storage medium | |
CN109035761B (en) | Travel time estimation method based on auxiliary supervised learning | |
CN101673463B (en) | Traffic information predicting method based on time series and device thereof | |
CN108848460B (en) | Man-vehicle association method based on RFID and GPS data | |
CN107025788B (en) | Travel time prediction method and device | |
CN112489439A (en) | Traffic control method based on big data and storage medium | |
CN116504076A (en) | Expressway traffic flow prediction method based on ETC portal data | |
CN111383449A (en) | Intersection passage estimation method, computer device and computer readable storage medium | |
CN110956807A (en) | Highway flow prediction method based on combination of multi-source data and sliding window | |
CN113379099B (en) | Machine learning and copula model-based highway traffic flow self-adaptive prediction method | |
CN115497299B (en) | ETC-based service area traffic flow prediction method and system and service area | |
CN115331433B (en) | Urban arterial road multi-vehicle track reconstruction method based on multi-source data | |
CN112926768A (en) | Ground road lane-level traffic flow prediction method based on space-time attention mechanism | |
CN116884223B (en) | Smart city traffic guiding system | |
CN111145535B (en) | Travel time reliability distribution prediction method under complex scene | |
CN115188192A (en) | Automatic control parking system and method based on travel prediction | |
CN114037149A (en) | Road section traffic flow time-varying flow prediction method oriented to vehicle-road cooperation | |
CN117877274B (en) | ETC-based provincial expressway network traffic induction method | |
CN111009126A (en) | Vehicle driving track prediction method, system and equipment based on bayonet snapshot data | |
CN115035715B (en) | Expressway flow prediction method based on decision tree and multi-element auxiliary information | |
Ho et al. | Deep Ensemble Learning Model for Long-Term Travel Time Prediction on Highways | |
EP4328888A1 (en) | Method and processing system for processing probe data and probe | |
YooSeok et al. | Application of Deep Learning to Missing Data Imputation: A Case Study of Highway Traffic in South Korea |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210312 |
|
WW01 | Invention patent application withdrawn after publication |