CN113688687B - Traffic jam state rapid identification and prediction method based on electric warning data - Google Patents
Traffic jam state rapid identification and prediction method based on electric warning data Download PDFInfo
- Publication number
- CN113688687B CN113688687B CN202110850488.7A CN202110850488A CN113688687B CN 113688687 B CN113688687 B CN 113688687B CN 202110850488 A CN202110850488 A CN 202110850488A CN 113688687 B CN113688687 B CN 113688687B
- Authority
- CN
- China
- Prior art keywords
- road section
- time
- congestion
- average travel
- average
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000004364 calculation method Methods 0.000 claims description 11
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 abstract description 3
- 238000012549 training Methods 0.000 description 6
- 230000006978 adaptation Effects 0.000 description 1
- 238000007792 addition Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biophysics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a traffic jam state rapid identification and prediction method based on electric warning data, which is used for acquiring basic data for identification and prediction based on the electric warning data and avoiding being limited by picture data and floating car data; the prediction of the average travel speed is carried out based on the LSTM model, so that the problem that the prediction accuracy is easily affected by whether the congestion sample distribution in the sample data is uneven when the congestion state is predicted by directly utilizing the LSTM model is avoided, and the prediction output with higher accuracy can be obtained; and the congestion state is judged based on the ratio of the average travel speed to the free flow speed, so that misjudgment caused by overlarge floating of the data value when the congestion state is judged directly based on the average travel speed is reduced, and the recognition and prediction result with high response speed, high instantaneity and high accuracy is obtained.
Description
Technical Field
The application belongs to the technical field of traffic prediction, and particularly relates to a traffic jam state rapid identification prediction method based on electric warning data.
Background
With the development of economy and the promotion of urban level, the maintenance amount of motor vehicles in China is increased year by year, and the following traffic jam problem also brings a plurality of inconveniences to the travel of people. In order to timely conduct traffic control when congestion occurs, road network operation efficiency is improved, and travel cost of people is reduced, rapid identification and prediction of traffic congestion conditions are of great significance.
The existing traffic jam recognition method mainly comprises an algorithm based on image recognition (for example, patent with application number of CN2019102123085 discloses a traffic jam judgment method based on image processing) and an algorithm based on floating car data (for example, patent with application number of CN2014100953892 discloses a city road network dynamic traffic jam prediction method based on floating car data). The image recognition-based algorithm carries out continuous learning training on the traffic jam video image data by establishing a deep learning model, and finally achieves the effect of recognizing the jam; the algorithm based on the floating car data is used for judging the traffic running condition of the road section by calculating and analyzing the traffic parameters of the floating car on the road section.
However, the existing image recognition-based algorithm requires a large amount of picture data and complex model training, and is difficult to predict future traffic jam states; the algorithm based on floating car data is only applicable to road segments with floating car data, and the method fails in road segments without floating car data.
Disclosure of Invention
The application aims to provide a traffic congestion state rapid identification and prediction method based on electric alarm data, which can realize rapid and accurate identification and prediction of the traffic congestion state based on the electric alarm data.
In order to achieve the above purpose, the technical scheme adopted by the application is as follows:
A traffic congestion state rapid identification and prediction method based on electric alarm data comprises the following steps:
step 1, taking a predicted road section to be identified, and recording the length of the predicted road section to be identified as L;
Step 2, enabling the current moment to be T, obtaining a passing data set of the end point of the predicted road section to be recognized, which is driven out in a time period from the T-T1 moment to the T moment, according to the electric warning data, and obtaining a passing data set of the start point of the predicted road section to be recognized, which is driven in a time period from the T-T2 moment to the T moment, and marking the passing data set as N_start;
Step 3, carrying out association matching on vehicles in the passing data sets N_end and N_start according to license plate numbers, recording the number of vehicles successfully subjected to association matching as N, and calculating the time difference of the vehicles subjected to association matching passing through the starting point and the ending point of the predicted road section to be identified as t;
step 4, calculating the average travel speed and the average travel time of the predicted road section to be identified in the time period from the current T-T1 moment to the T moment, and recording the average travel speed and the average travel time as the real-time average travel speed Average travel time/>
Step 5, based on the number n, real-time average stroke speedAverage journey time/>Over-the-vehicle dataset N_end, predicted average trip speed/>, over a specified time period in the future, using a trained LSTM model
Step 6, taking the free flow speed v_free of the predicted road section to be identified, and respectively calculating the real-time average travel speedRatio to free flow velocity v_free and predicted mean travel velocity/>And judging the congestion state of the predicted road section to be identified in real time and within a specified time period in the future according to the ratio of the predicted road section to be identified to the free flow speed v_free, wherein the congestion state comprises smooth, basically smooth, slightly congested, moderately congested and severely congested.
The following provides several alternatives, but not as additional limitations to the above-described overall scheme, and only further additions or preferences, each of which may be individually combined for the above-described overall scheme, or may be combined among multiple alternatives, without technical or logical contradictions.
Preferably, the time T1 and the time T2 satisfy the following relationship:
T2＝2*T_congestion+T1
Where t_ congestion is the average travel time of the predicted link to be identified in a severe congestion state.
Preferably, each data in the passing data set includes the following fields: electric police number, time stamp, road section number, license plate number, vehicle type and weather data;
the said number n based real time average stroke speed Average journey time/>The train passing data sets N_end and N_start are utilized to predict the predicted average journey speed/>, within the future designated time period, by utilizing the trained LSTM modelComprising the following steps:
determining the current weather according to weather data in the passing data set N_end, determining time information according to the current time as T, and determining the real-time average travel speed based on the number N Average journey time/>Current weather and time information input trained LSTM model predicts predicted average trip speed/>, over a specified time period in the future
Preferably, the free flow speed v_free of the predicted link to be identified is determined as follows:
acquiring an average travel speed corresponding to each T1 time period in a historical calculation time period according to a preset historical calculation time period;
Sequencing a plurality of average travel speeds in the acquired historical calculation time period from large to small, and intercepting the first x average travel speeds after sequencing;
Calculating the average value of the intercepted first x average journey speeds and marking the average value as v_avg, wherein the free flow speed v_free of the predicted road section to be identified is as follows:
v_free＝Min(v_avg,v_limit)
In the formula, v_limit is the maximum speed limit of the predicted road section to be identified.
Preferably, the judging the congestion state of the predicted road section to be identified in real time and within a specified future time period according to the ratio includes:
If the ratio sigma satisfies 0.7 < sigma, judging that the congestion state is smooth;
If the ratio sigma satisfies 0.7 to sigma > 0.5, judging that the congestion state is basically smooth;
if the ratio sigma satisfies 0.5 to sigma > 0.4, judging the congestion state as light congestion;
if the ratio sigma satisfies 0.4 to sigma > 0.3, judging the congestion state as medium congestion;
if the ratio sigma satisfies 0.3 or more sigma, judging the congestion state as serious congestion.
According to the traffic jam state rapid identification and prediction method based on the electric warning data, basic data for identification and prediction are obtained based on the electric warning data, and the limitation to picture data and floating car data is avoided; the prediction of the average travel speed is carried out based on the LSTM model, so that the problem that the prediction accuracy is easily affected by whether the congestion sample distribution in the sample data is uneven when the congestion state is predicted by directly utilizing the LSTM model is avoided, and the prediction output with higher accuracy can be obtained; and the congestion state is judged based on the ratio of the average travel speed to the free flow speed, so that misjudgment caused by overlarge floating of the data value when the congestion state is judged directly based on the average travel speed is reduced, and the recognition and prediction result with high response speed, high instantaneity and high accuracy is obtained.
Drawings
Fig. 1 is a flowchart of a traffic congestion state rapid identification prediction method based on electric warning data.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein in the description of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application.
In one embodiment, a method for quickly identifying and predicting traffic congestion states based on electric warning data is provided. Because the current electric police equipment is spread over traffic roads and is acquired and recorded in real time, the embodiment identifies and predicts the traffic jam state based on the electric police data, has a larger use coverage range and avoids being limited by picture data and floating car data.
According to the actual road conditions and driving requirements, the traffic congestion state is divided into five categories, namely smooth, basically smooth, slight congestion, medium congestion and serious congestion, namely the five congestion states are used as identification and prediction targets for expansion.
It will be readily appreciated that the traffic congestion status classification in this embodiment is only one preferred manner provided, and in other embodiments the adaptation may be based on the classification of the present application.
As shown in fig. 1, the method for quickly identifying and predicting traffic congestion state based on electric warning data in this embodiment includes the following steps:
And step 1, taking a predicted road section to be identified, and recording the length of the predicted road section to be identified as L.
In this embodiment, a scheme is described by taking one road section, i.e. a predicted road section to be identified as an example, and the scheme can be applied to a plurality of road sections simultaneously during actual use, so as to identify and predict traffic congestion states of the plurality of road sections. In order to adapt to the recognition and prediction of the scheme on multiple road segments, the road segment number is preferably recorded for each road segment, and the road segment starting and ending numbers are set to be the start_access and the end_access respectively.
It is to be understood that the start point and the end point of a road section are understood to designate the positions of two points of the road section as the start point and the end point, and the two points are intersections of the traffic road section, preferably two intersections adjacent to each other. Considering that intersections of certain road segments may have traffic that is not enabled or otherwise affected, the present embodiment is not limited to two intersections with two adjacent points.
The length L mentioned in this embodiment is the length of the road section between the start and end points of the road section.
And 2, taking the current moment as T, acquiring a passing data set of the end point of the predicted road section to be recognized in the time period from the T-T1 moment to the T moment according to the electric alarm data, and marking the passing data set of the start point of the predicted road section to be recognized in the time period from the T-T2 moment to the T moment as N_start.
T1 is a time scale for identifying and predicting traffic jam conditions, and any time scale within one hour of 5min, 10min and the like can be taken; t2 is a time scale for matching vehicles, in order to ensure that vehicles appearing in the passing data set n_end can be found in the passing data set n_start, in this embodiment, T2 is determined according to the travel time t_ congestion when the predicted road section to be identified is severely congested, that is, the time T1 and the time T2 in this embodiment satisfy the following relationship:
T2＝2*T_congestion+T1
The t_ congestion may be the average travel time of the predicted road section to be identified in the past serious congestion state, or the average travel time of the predicted road section in the latest serious congestion state, which is selected according to the actual situation.
The passing data set of the embodiment contains related data of the vehicle meeting the conditions, and usually contains a plurality of pieces of related data, and each piece of data contains the following fields: electric police numbers, time stamps (including time of year, month, day, time of day), road section numbers, license plate numbers, vehicle types (such as cars, trucks, buses, etc.), weather data (such as cloudy days, rainy days, sunny days, etc.).
And 3, carrying out association matching on vehicles in the passing data sets N_end and N_start according to license plate numbers, recording the number of vehicles successfully subjected to association matching as N, calculating the time difference of the start point and the end point of each vehicle passing through the predicted road section to be recognized as t, namely the road section travel time of each vehicle, and calculating according to the time stamp recorded in the passing data sets.
In order to find the same vehicle in the passing data sets n_end and n_start, the present embodiment performs association matching of vehicles based on license plate numbers. In step 2, T2 is set to ensure that as many vehicles as possible appear in the passing data set n_end can be found in the passing data set n_start, but in practical application, due to unavoidable existence of entrances and exits of a district, a park, etc. between the start and end points of the road section, vehicles appearing in the passing data set n_end may not appear in the passing data set n_start, and vehicles appearing in the passing data set n_start may not appear in the passing data set n_end. The present embodiment is therefore based on the number of vehicles successfully associated with the match.
Step 4, calculating the average travel speed and the average travel time of the predicted road section to be identified in the time period from the current T-T1 moment to the T moment, and recording the average travel speed and the average travel time as the real-time average travel speedAverage travel time/>
Wherein the average travel speed of the road segment is calculated according to the following formula
In the formula, i is the ith vehicle in successful association matching, and t i is the road section travel time of the ith vehicle.
Step 5, based on the number n, real-time average stroke speedAverage journey time/>Over-the-vehicle dataset N_end, predicted average trip speed/>, over a specified time period in the future, using a trained LSTM model
In actual operation, according to the steps 2 to 4, the characteristic index of the road section in each T1 time scale in each day can be recorded. The characteristic indexes of the embodiment include sample flow, namely, the number of vehicles successfully associated and matched, average journey speed (real-time average journey speed is obtained when predicting the current situation), average journey time, time information and current weather. Wherein the current weather is determined according to the weather data in the passing dataset n_end, the time information is determined according to the current time being T, and in order to improve the model prediction accuracy, the time information in this embodiment includes the week (whether the weekend), the hour (24 hours), the minute (the minute is recorded according to the time scale T1, for example, T1 is 5 min), the minute of one hour is divided according to 5min, and the labels are 0 (representing 0 to 5 min), 5 (representing 5 to 10 min), 10 (representing 10 to 15 min), 15 (representing 15 to 20 min)..55 (representing 55 to 60 min)).
If the recorded data has the moment of data missing, filling can be carried out through the average value of the same historical moment; if the historical mean value does not exist, linear interpolation can be carried out according to the values of k moments before and after the moment, and finally a complete data set of the road section at continuous moments is obtained.
When training the LSTM model, firstly, a suitable parameter (for example, a predicted step size) is determined, then, the historical data set of the road section is taken for training, in this embodiment, the sample flow, the average trip speed, the week, the hour and the weather in the data set are used as characteristic variables, and the average trip speed in the later step size is used as a dependent variable for training the model. In this embodiment, a full connection layer is connected after an LSTM model, and respective corresponding weights v when feature variables are input into the LSTM model (LSTM layer) are obtained in the LSTM model training, and optimal values of respective corresponding weights w when values input into the LSTM model are input into the full connection layer are determined. It will be readily appreciated that the feature variables may be varied as desired in practice or determined based on existing methods such as variance selection of the feature method.
The predicted future specified time period in this embodiment is determined according to a step size and a time scale T1, for example, if the step size is 12 and the time scale T1 is 5min, the average travel speed of every 5min in the future one hour is predicted, that is, 12 speed values are output, and each speed value has a corresponding time tag.
Step 6, taking the free flow speed v_free of the predicted road section to be identified, and respectively calculating the real-time average travel speedRatio to free flow velocity v_free and predicted mean travel velocity/>And judging the congestion state of the predicted road section to be identified in real time and in a future appointed time period according to the ratio of the predicted road section to be identified to the free flow speed v_free.
In order to improve accuracy of traffic congestion status recognition and prediction in this embodiment, a determination manner of setting a free flow speed v_free of a predicted road section to be recognized in this embodiment is as follows:
Acquiring an average travel speed corresponding to each T1 time period in a historical calculation time period according to a preset historical calculation time period; the historical calculation time period is usually set to be the month before the current time as a reference, so that the uncertainty of data in a short time is avoided, and the update time of the free flow speed can be set once a day or according to actual requirements.
The plurality of average travel speeds in the acquired historical calculation time period are ranked from large to small, and the first x (for example, 1/9) average travel speeds after ranking are intercepted.
Calculating the average value of the intercepted first x average journey speeds and marking the average value as v_avg, wherein the free flow speed v_free of the predicted road section to be identified is as follows:
v_free＝Min(v_avg,v_limit)
In the formula, v_limit is the maximum speed limit of the predicted road section to be identified.
In this embodiment, the free flow speed is not calculated by taking a constant value, but is set to be associated with historical data, so that the free flow speed is updated regularly, and the traffic jam judgment is ensured to be continuously adapted to new traffic conditions. The method for judging the congestion state of the predicted road section to be identified according to the ratio is provided by the embodiment:
If the ratio sigma satisfies 0.7 < sigma, judging that the congestion state is smooth;
If the ratio sigma satisfies 0.7 to sigma > 0.5, judging that the congestion state is basically smooth;
if the ratio sigma satisfies 0.5 to sigma > 0.4, judging the congestion state as light congestion;
if the ratio sigma satisfies 0.4 to sigma > 0.3, judging the congestion state as medium congestion;
if the ratio sigma satisfies 0.3 or more sigma, judging the congestion state as serious congestion.
The method for identifying and predicting the traffic jam state is simple and easy to understand, high in response speed, strong in model instantaneity and high in accuracy; the method has universality, is suitable for various data types and data formats, and only needs to convert the calculation results of different data into fields meeting the requirements of the embodiment; the traffic congestion state at the current moment can be rapidly identified, and meanwhile, the future traffic congestion state is predicted.
The identification and prediction method of the application is tested, simulated and actual environment tested, and runs normally, thus proving to be feasible; the average accuracy rate of road section level congestion identification reaches more than 85%, the accuracy rate of congestion prediction in the future week is about 70%, and the application requirements are met.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the application. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.
Claims (3)
1. The traffic congestion state rapid identification and prediction method based on the electric alarm data is characterized by comprising the following steps of:
step 1, taking a predicted road section to be identified, and recording the length of the predicted road section to be identified as L;
Step 2, making the current moment be T, obtaining a passing data set of the end point of the predicted road section to be recognized from the time period from the T-T1 moment to the T moment according to the electric alarm data, marking the passing data set of the start point of the predicted road section to be recognized from the time period from the T-T2 moment to the T moment as N_start, wherein each piece of data in the passing data set comprises the following fields: electric alarm number, timestamp, road section number, license plate number, vehicle type, weather data, T1 moment and T2 moment satisfy the following relation:
；
In the method, in the process of the invention, The average travel time of the predicted road section to be identified in the serious congestion state is calculated;
Step 3, carrying out association matching on vehicles in the passing data sets N_end and N_start according to license plate numbers, recording the number of vehicles successfully subjected to association matching as N, and calculating the time difference of the vehicles subjected to association matching passing through the starting point and the ending point of the predicted road section to be identified as t;
step 4, calculating the average travel speed and the average travel time of the predicted road section to be identified in the time period from the current T-T1 moment to the T moment, and recording the average travel speed and the average travel time as the real-time average travel speed Average travel time/>；
Step 5, based on the number n, real-time average stroke speedAverage travel time/>The passing data set N_end is used for predicting the predicted average journey speed/>, within the future designated time period, by utilizing the trained LSTM modelComprising:
Determining the current weather according to the weather data in the passing data set N_end, determining time information according to the current time as T, and determining the number N and the real-time average travel speed Average travel time/>Input of current weather and time information into a trained LSTM model predicts a predicted average trip speed/>, over a specified time period in the future；
Step 6, obtaining the free flow velocity of the predicted road section to be identifiedRespectively calculating real-time average travel speed/>And free flow velocity/>Is a ratio of the predicted average stroke speed/>And free flow velocity/>And judging the congestion state of the predicted road section to be identified in real time and within a specified time period in the future according to the ratio, wherein the congestion state comprises smooth, basically smooth, slight congestion, medium congestion and serious congestion.
2. The traffic congestion status rapid identification and prediction method based on electric warning data as claimed in claim 1, wherein the free flow velocity of the predicted road section to be identifiedThe determination mode of (2) is as follows:
acquiring an average travel speed corresponding to each T1 time period in a historical calculation time period according to a preset historical calculation time period;
Sequencing a plurality of average travel speeds in the acquired historical calculation time period from large to small, and intercepting the first x average travel speeds after sequencing;
calculating the average value of the intercepted first x average stroke speeds to be recorded as The free flow speed/>, of the predicted road section to be identifiedThe method comprises the following steps:
；
In the method, in the process of the invention, And the maximum speed limit of the predicted road section to be identified.
3. The traffic congestion status rapid identification and prediction method based on electric warning data according to claim 1, wherein the judging the congestion status of the predicted road section to be identified in real time and within a specified time period in the future according to the ratio comprises:
If the ratio is Satisfy/>Judging the congestion state as smooth;
If the ratio is Satisfy/>Judging the congestion state as basically smooth;
If the ratio is Satisfy/>Judging the congestion state as light congestion;
If the ratio is Satisfy/>Judging the congestion state as medium congestion;
If the ratio is Satisfy/>And judging the congestion state as serious congestion.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110850488.7A CN113688687B (en) | 2021-07-27 | 2021-07-27 | Traffic jam state rapid identification and prediction method based on electric warning data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110850488.7A CN113688687B (en) | 2021-07-27 | 2021-07-27 | Traffic jam state rapid identification and prediction method based on electric warning data |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113688687A CN113688687A (en) | 2021-11-23 |
| CN113688687B true CN113688687B (en) | 2024-05-28 |
Family
ID=78578241
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110850488.7A Active CN113688687B (en) | 2021-07-27 | 2021-07-27 | Traffic jam state rapid identification and prediction method based on electric warning data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688687B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104157139A (en) * | 2014-08-05 | 2014-11-19 | 中山大学 | Prediction method and visualization method of traffic jam |
| CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
| CN108492555A (en) * | 2018-03-20 | 2018-09-04 | 青岛海信网络科技股份有限公司 | A kind of city road net traffic state evaluation method and device |
| CN109147330A (en) * | 2018-09-19 | 2019-01-04 | 青岛海信网络科技股份有限公司 | A kind of congestion recognition methods and device |
| CN110428613A (en) * | 2019-07-09 | 2019-11-08 | 中山大学 | A kind of intelligent transportation trend prediction method of machine learning |
-
2021
- 2021-07-27 CN CN202110850488.7A patent/CN113688687B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104157139A (en) * | 2014-08-05 | 2014-11-19 | 中山大学 | Prediction method and visualization method of traffic jam |
| CN108335485A (en) * | 2018-01-31 | 2018-07-27 | 夏莹杰 | The method of major issue traffic dynamic emulation congestion prediction based on license plate identification data |
| CN108492555A (en) * | 2018-03-20 | 2018-09-04 | 青岛海信网络科技股份有限公司 | A kind of city road net traffic state evaluation method and device |
| CN109147330A (en) * | 2018-09-19 | 2019-01-04 | 青岛海信网络科技股份有限公司 | A kind of congestion recognition methods and device |
| CN110428613A (en) * | 2019-07-09 | 2019-11-08 | 中山大学 | A kind of intelligent transportation trend prediction method of machine learning |
Non-Patent Citations (1)
| Title |
|---|
| 基于长短期记忆模型的交通拥堵预测方法;吕鲜;《南京理工大学学报》;20200229;26-32+48 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113688687A (en) | 2021-11-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10902719B2 (en) | Method of predicting traffic congestion and controlling traffic signals based on deep learning and server for performing the same | |
| CN108550262B (en) | Urban traffic sensing system based on millimeter wave radar | |
| CN111325978A (en) | Whole-process monitoring and warning system and method for abnormal behaviors of vehicles on expressway | |
| CN114999181B (en) | Highway vehicle speed abnormality identification method based on ETC system data | |
| CN112016735B (en) | Patrol route planning method and system based on traffic violation hotspot prediction and readable storage medium | |
| CN111508094A (en) | Highway congestion finding method based on ETC portal frame and gate traffic data | |
| CN111882858B (en) | Multi-source data-based method for predicting queuing length of highway abnormal event | |
| US12020566B2 (en) | Machine-learning based control of traffic operation | |
| CN113436432A (en) | Method for predicting short-term traffic risk of road section by using road side observation data | |
| CN110889444A (en) | Driving track feature classification method based on convolutional neural network | |
| CN117953693B (en) | Expressway traffic intelligent monitoring system based on video ai | |
| CN111127882A (en) | Tourist attraction parking lot coming vehicle number prediction method based on big data | |
| CN109887285B (en) | Method and device for determining parking reason | |
| CN114005275B (en) | Highway vehicle congestion judging method based on multi-data source fusion | |
| CN118230546A (en) | Urban green traffic management system and method based on multi-source data | |
| CN114360264A (en) | Intelligent city traffic management method based on traffic flow regulation | |
| CN114091581A (en) | Vehicle operation behavior type identification method based on sparse track | |
| CN113919571A (en) | Dangerous chemical transportation premium estimation method based on edge calculation | |
| CN115731693A (en) | Lane dividing method and related device | |
| CN113688687B (en) | Traffic jam state rapid identification and prediction method based on electric warning data | |
| CN116343498A (en) | Big data bus route congestion point-based reminding system | |
| CN113628455B (en) | Intersection signal optimization control method considering number of people in vehicle under Internet of vehicles environment | |
| CN112927497B (en) | Floating car identification method, related method and device | |
| CN115273468A (en) | Traffic congestion control strategy generation method and device | |
| CN115100895A (en) | High-precision map-based networking automobile communication optimization method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |