CN116189425A - Traffic road condition prediction method and system based on Internet of vehicles big data - Google Patents
Traffic road condition prediction method and system based on Internet of vehicles big data Download PDFInfo
- Publication number
- CN116189425A CN116189425A CN202211738591.3A CN202211738591A CN116189425A CN 116189425 A CN116189425 A CN 116189425A CN 202211738591 A CN202211738591 A CN 202211738591A CN 116189425 A CN116189425 A CN 116189425A
- Authority
- CN
- China
- Prior art keywords
- data
- traffic
- detected
- vehicles
- track data
- 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 79
- 238000012545 processing Methods 0.000 claims abstract description 102
- 238000010219 correlation analysis Methods 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims abstract description 12
- 238000003062 neural network model Methods 0.000 claims description 35
- 206010039203 Road traffic accident Diseases 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 20
- 238000004364 calculation method Methods 0.000 claims description 19
- 230000006870 function Effects 0.000 claims description 19
- 238000004458 analytical method Methods 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 12
- 230000008859 change Effects 0.000 claims description 11
- 230000004913 activation Effects 0.000 claims description 9
- 238000004140 cleaning Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000007613 environmental effect Effects 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 5
- 230000009466 transformation Effects 0.000 claims description 5
- 238000012300 Sequence Analysis Methods 0.000 claims description 4
- 238000013135 deep learning Methods 0.000 claims description 4
- 230000003203 everyday effect Effects 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000003672 processing method Methods 0.000 claims description 2
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000004891 communication Methods 0.000 description 9
- 238000003860 storage Methods 0.000 description 7
- 238000004590 computer program Methods 0.000 description 5
- 230000005236 sound signal Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 239000011159 matrix material Substances 0.000 description 3
- 241000282326 Felis catus Species 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000018109 developmental process Effects 0.000 description 2
- 230000005251 gamma ray Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000013139 quantization Methods 0.000 description 2
- KLDZYURQCUYZBL-UHFFFAOYSA-N 2-[3-[(2-hydroxyphenyl)methylideneamino]propyliminomethyl]phenol Chemical compound OC1=CC=CC=C1C=NCCCN=CC1=CC=CC=C1O KLDZYURQCUYZBL-UHFFFAOYSA-N 0.000 description 1
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 201000001098 delayed sleep phase syndrome Diseases 0.000 description 1
- 208000033921 delayed sleep phase type circadian rhythm sleep disease Diseases 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000012535 impurity Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000033772 system development Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2465—Query processing support for facilitating data mining operations in structured databases
-
- 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"
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Chemical & Material Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Fuzzy Systems (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Traffic Control Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Mathematical Physics (AREA)
- Analytical Chemistry (AREA)
- Computational Linguistics (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Software Systems (AREA)
Abstract
The invention provides a traffic road condition prediction method and a traffic road condition prediction system based on Internet of vehicles big data, which relate to the technical field of intelligent traffic and comprise the steps of obtaining historical track data of an area to be detected in a preset time period before the current moment; respectively acquiring first track data and second track data of traffic road conditions in a region to be detected; processing the first track data and the second track data based on three-dimensional vectors to obtain flow information of all vehicle tracks, and carrying out gray correlation analysis to obtain a correlation value of each flow information and the historical track data; and processing to obtain traffic condition prediction information. The road condition prediction method has the beneficial effects that the road condition prediction accuracy is improved, the traffic jam is effectively reduced, the traveler is facilitated to select a proper traffic route for traveling, the time is saved, the existing road traffic efficiency is improved, the road jam condition is improved, the urban traffic jam phenomenon is slowed down, and the urban road traffic comprehensive management level is improved.
Description
Technical Field
The invention relates to the technical field of traffic, in particular to a traffic road condition prediction method and system based on internet of vehicles big data.
Background
With the development of social economy, urban traffic networks are becoming larger in scale, and in order to be able to manage urban traffic networks more scientifically and intelligently, it is necessary to effectively monitor and predict urban traffic conditions. The Internet of vehicles is an important intersection of two fields of Internet of things and intelligent automobiles in strategic emerging industries, and is a key component of urban intelligent traffic. The concept of the internet of vehicles is derived from the internet of things, and technologies such as sensors, communication networks, system integration and the like are adopted to realize network interconnection and information intercommunication among people, vehicles and roads, and intelligent traffic management is realized through intelligent management and control of the people, the vehicles and the roads.
In the current common technical means, the prediction input is complex, the change rule of the traffic road condition is difficult to embody from date attribute data, the reference data is relatively single, and the prediction accuracy is difficult to be ensured.
Disclosure of Invention
The invention aims to provide a traffic road condition prediction method and system based on internet of vehicles big data, so as to solve the problems. In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
In a first aspect, the present application provides a traffic condition prediction method based on internet of vehicles big data, including:
acquiring historical track data of the region to be detected in a preset time period before the current moment;
respectively acquiring first track data and second track data of traffic road conditions in an area to be detected, wherein the first track data is the total number of vehicles in all vehicle tracks, which are not in the area to be detected at the previous moment of the vehicles but are in the area to be detected at the current moment; the second track data is the total number of vehicles in all the vehicle tracks, wherein the vehicles are in the region to be detected at the previous moment and are not in the region to be detected at the current moment;
processing the first track data and the second track data based on three-dimensional vectors to obtain flow information of all vehicle tracks of each time point to be detected in all the areas to be detected, wherein the flow information comprises relative traffic flow among all vehicles, relative traffic flow change rate, uncertain information of traffic accidents and environmental factors of current roads;
carrying out gray correlation analysis on the flow information and the historical track data to obtain a correlation value of each flow information and the historical track data;
And processing the relevance value, the flow information and the historical track data according to a pre-trained road condition prediction model to obtain traffic road condition prediction information, wherein the road condition prediction model is obtained by training according to the traffic road conditions in the to-be-tested area in a historical period.
In a second aspect, the application further provides a traffic road condition prediction system based on internet of vehicles big data, which comprises a first acquisition module, a second acquisition module, a first processing module, an analysis module and a second processing module, wherein:
a first acquisition module: the method comprises the steps of acquiring historical track data of the region to be detected in a preset time period before the current moment;
and a second acquisition module: the method comprises the steps of respectively obtaining first track data and second track data of traffic road conditions in an area to be detected, wherein the first track data is the total number of vehicles in all vehicle tracks, the vehicles are not in the area to be detected at the previous moment and are in the area to be detected at the current moment; the second track data is the total number of vehicles in all the vehicle tracks, wherein the vehicles are in the region to be detected at the previous moment and are not in the region to be detected at the current moment;
a first processing module: the method comprises the steps of processing the first track data and the second track data based on three-dimensional vectors to obtain flow information of all vehicle tracks of each time point to be detected in all the areas to be detected, wherein the flow information comprises relative traffic flow among all vehicles, relative traffic flow change rate, uncertain information of traffic accidents and environmental factors of a current road;
And an analysis module: the gray correlation analysis is used for carrying out gray correlation analysis on the flow information and the historical track data to obtain a correlation value of each flow information and the historical track data;
and a second processing module: and the traffic road condition prediction model is obtained by training the traffic road conditions in the to-be-tested area in a history period.
In a third aspect, the present application further provides a traffic condition prediction device based on internet of vehicles big data, including:
a memory for storing a computer program;
and the processor is used for realizing the traffic road condition prediction method based on the Internet of vehicles big data when executing the computer program.
In a fourth aspect, the present application further provides a readable storage medium, where a computer program is stored, where the computer program when executed by a processor implements the steps of the traffic condition prediction method based on internet of vehicles big data.
The beneficial effects of the invention are as follows: the method has the advantages that the historical estimated data, the first track data and the second track data are obtained, the data are processed based on three-dimensional vectors, the proportion of images is determined based on an analytic hierarchy process, the data are analyzed by utilizing gray correlation analysis and a neural network model, sustainable prediction optimization of the model is maintained, the accuracy of road condition prediction is improved, traffic jam is effectively reduced, the traffic condition of a target intersection to be reached by a target vehicle is predicted, urban road travel prediction is provided for travelers, the travelers can select proper traffic routes to travel, time is saved, point congestion is avoided, the existing road traffic efficiency is improved, road congestion is improved, urban traffic jam phenomenon is relieved, and urban road traffic comprehensive management level is improved.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be apparent from the description, or may be learned by practice of the embodiments of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims thereof as well as the appended drawings.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present invention and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a schematic flow chart of a traffic condition prediction method based on internet of vehicles big data according to an embodiment of the present invention;
fig. 2 is a schematic structural diagram of a traffic condition prediction system based on internet of vehicles big data according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a traffic condition prediction device based on internet of vehicles big data according to an embodiment of the present invention.
701, a first acquisition module; 702. a second acquisition module; 7021. an acquisition unit; 7022. an identification unit; 7023. a first determination unit; 7024. a selecting unit; 703. a first processing module; 704. an analysis module; 7041. an analysis unit; 7042. a first processing unit; 7043. a calculation unit; 7044. a determination unit; 705. a second processing module; 7051. a classification unit; 70511. a second setting unit; 70512. a cleaning unit; 70513. a conversion unit; 7052. a first setting unit; 7053. an optimizing unit; 7054. a second processing unit; 7055. a comparison unit; 800. traffic road condition prediction equipment based on big data of the Internet of vehicles; 801. a processor; 802. a memory; 803. a multimedia component; 804. an I/O interface; 805. a communication component.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present invention more apparent, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention, and it is apparent that the described embodiments are some embodiments of the present invention, but not all embodiments of the present invention. The components of the embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
It should be noted that: like reference numerals and letters denote like items in the following figures, and thus once an item is defined in one figure, no further definition or explanation thereof is necessary in the following figures. Meanwhile, in the description of the present invention, the terms "first", "second", and the like are used only to distinguish the description, and are not to be construed as indicating or implying relative importance.
Example 1:
the embodiment provides a traffic road condition prediction method based on internet of vehicles big data.
Referring to fig. 1, the method is shown to include steps S100, S200, S300, S400, and S500.
S100, acquiring historical track data of the region to be detected in a preset time period before the current moment.
It can be understood that in this step, the historical track data of the user may be stored in a database in advance according to the prior art, and when in use, the historical track data of the user may be obtained from the database according to the identification of the user, and of course, the time or the region may be used as a limiting condition, or the current mature road condition prediction model may also be used, and the previously stored historical track data may be input into the prediction model to be processed, so as to obtain a relatively accurate historical processing result, and recorded as the historical track data.
S200, respectively acquiring first track data and second track data of traffic conditions in an area to be detected, wherein the first track data is the total number of vehicles in all vehicle tracks, which are not in the area to be detected at the previous moment of the vehicles but are in the area to be detected at the current moment; the second track data is the total number of vehicles in all the vehicle tracks, wherein the vehicles are in the region to be detected at the previous moment and are not in the region to be detected at the current moment.
It will be appreciated that in this step, the flow data is calculated by converting the collected GPS data into outflow and inflow forms having regional characteristics.
Specifically, the area to be detected is regarded as a whole, and the whole is divided into 16×16 small areas, so that a traffic data is predicted according to the in-out situation of the vehicle. For example, for a certain area (x, y), counting first track data of the area, namely, in all vehicle tracks, the total number of vehicles in the area to be tested at the current moment and not in the area to be tested at the previous moment of the vehicle, and judging the inflow flow; and counting second track data of the area, namely, the total number of vehicles in the area to be detected at the previous moment of the vehicles and not in the area to be detected at the current moment in all vehicle tracks, and judging the outflow flow. Taking a certain area (x, y) as an example, at the previous time, namely, at time t-1, neither the vehicle a nor the vehicle B is in the area, only the vehicle C is in the area, and at time t, both the vehicle a and the vehicle B are in the area, and the vehicle C is not in the area. As a result, the vehicles a and B are inflow vehicles, the vehicle C is outflow vehicle, and coordinate points can be marked in the region (x, y). According to the form of marking, flow information in the area to be detected can be counted.
S300, processing the first track data and the second track data based on three-dimensional vectors to obtain flow information of all vehicle tracks of each time point to be detected in all the areas to be detected, wherein the flow information comprises relative traffic flow among all vehicles, relative traffic flow change rate, uncertain information of traffic accidents and environmental factors of current roads.
Specifically, the whole area obtained is divided into 16×16, so that a three-dimensional vector of each moment data of the area to be detected can be represented according to the three-dimensional vector, and flow information of all vehicle tracks of each time point to be detected can be obtained according to the acquired data period.
The relative traffic flow, the relative traffic flow change rate, the uncertain information of the traffic accident and the current road environment factors are all important factors influencing the traffic flow information.
The relative traffic flow is the number of traffic entities passing through a certain place, a certain section or a certain lane of a road in a selected time period, and consists of the inflow data and the outflow data, and the relative traffic flow is obtained by subtracting the inflow data from the outflow data. The relative traffic flow rate is a rate of change of the path, such as congestion, queuing of vehicles, etc., when a traffic accident occurs on the traffic road, and is generated with respect to the previous time. The current road environment factors are related to the bearing capacity of the current road as the name implies, namely whether the current road is crowded or not, whether traffic accidents occur or not. The uncertain information of the traffic accident is obtained by processing the relative traffic flow, the relative flow change rate and the road bearing degree.
It can be understood that the acquisition process of the uncertain information of the traffic accident in the present step S300 includes S301, S302, S303, and S304, in which:
s301, acquiring traffic road condition image information of each time point to be detected in the region to be detected by adopting a camera device;
in order to grasp the running state of vehicles at each traffic intersection, the camera device is often erected at a proper position of the traffic intersection, such as a median above a road and in the center of the road, and the running condition of the vehicles on each traffic intersection is monitored in real time, wherein the running condition of the vehicles comprises information such as queuing condition of the vehicles, waiting condition of traffic lights, parking time, left and right turns of the vehicles and the like. In order to enable the video processing center to acquire the traffic state of each road through the video image of each intersection shot by the camera, after the video image of the running condition of the vehicle on each traffic intersection road is shot by the camera, the video image is transmitted to the background video processing center so as to enable the video processing center to acquire the video image, and the video image is analyzed and processed to finally obtain the traffic road condition image information.
S302, carrying out image preprocessing on the traffic road condition image information, and identifying the preprocessed images based on a Yo l ov3 network to obtain a plurality of groups of coincident images, wherein the plurality of groups of coincident images are at least three groups, and the coincident images comprise at least two tracks with the same steering information and are divided into the same image track set;
The method is characterized in that the image is preprocessed, the preprocessed image is identified based on a convolution network, the unclear places such as shadows, impurities and the like of some images are removed, optimization and image comparison are performed, the image marked by the Yolov3 network is the closest to the image, namely the images overlapped with each other, a plurality of tracks exist in the overlapped image, and any track consists of a plurality of track points. The overlapping images are the heat information of the historical heat for measuring the traffic road conditions. For example, classifying multiple groups of coincident images to obtain multiple categories: the first category, the second category, the third category, and so on, images of the same track are added to the corresponding categories, i.e., are divided into the same set of image tracks.
S303, performing hierarchical analysis on all the coincident images to determine the proportion of the same steering image information in each group of coincident images;
it should be noted that, the relationship of relative importance is obtained by comparing based on analytic hierarchy process, and the discrimination matrix is obtained by normalization processing, as follows:
A=(a ij ) n×n
wherein: a is a discrimination matrix; a, a ij The importance ratio of the element i and the element j of the current level to the previous level is scaled; i and j are respectively different kinds of elements; n is the dimension of the hierarchical structure model, and the element is any element in the scheme layer.
Wherein, the weight calculation formula is as follows:
wherein, the weight coefficient of each element of W' W i For discriminating the geometric mean of each scale data of each row in the matrix.
S304, selecting the coincident intersection with the largest occupied proportion according to the proportion occupied by the same steering image information in each group of coincident images, wherein the coincident intersection is the intersection with the largest steering times, namely the uncertain information for measuring the traffic accident.
It should be noted that, according to the coincident intersection with the largest specific gravity, the intersection with the largest steering times is also used, so that a basis is provided for predicting traffic road conditions, the important factors for measuring traffic accidents are provided, and the accuracy of traffic road condition prediction is also improved.
S400, carrying out grey correlation analysis on the flow information and the historical track data to obtain a correlation value of each flow information and the historical track data.
It should be noted that, discrete behavior observation values of system factors are converted into piecewise continuous broken lines by a linear interpolation method, and then a model for measuring the association degree is constructed according to geometric features of the broken lines. The degree of correlation is essentially the degree of difference in geometry between curves. Therefore, the difference between curves can be used as a measure of the degree of association.
It is understood that S401, S402, S403, and S404 are included in step S400, in which:
s401, carrying out sequence analysis on the flow information and the historical track data to obtain first sequence data and second sequence data, wherein the historical track data is used as a parent sequence reflecting traffic road condition factors, and the flow information is used as a subsequence reflecting traffic road condition factors;
it can be understood that by analyzing the traffic information and the historical track data, traffic road condition factors reflecting the overall behavior development are taken as a parent sequence, and data sequences formed by factors influencing the system development are taken as child sequences.
S402, carrying out dimensionless quantification on the first sequence data and the second sequence data, and carrying out mean value calculation on the processed data to obtain first mean value data of the first sequence data and second mean value data of the second sequence data;
it should be noted that, because the physical meanings of the factors in the first sequence data and the second sequence data are different, the dimensions of the data are not necessarily the same, and comparison is inconvenient, so that dimensionless quantization processing is required to be performed, the first sequence data and the second sequence data are subjected to dimensionless quantization processing, and mean value calculation is performed, as follows:
Wherein x is ij The ith row and the jth row of data, n is n total data.
S403, performing association calculation based on the first sequence data, the second sequence data, the first average value data and the second average value data to obtain an association coefficient between the subsequence and the parent sequence;
it can be understood that the calculation formula of the association coefficient in the above steps is as follows:
wherein: gamma ray f (k) The correlation coefficient of the history accident data and the history operation parameter information after dimensionless treatment is provided; f is history accident data after dimensionless treatment; k, historical operation parameter information after dimensionless treatment; y (k) is a time series before the occurrence of a historical accident; x is x f (k) Is a time sequence after the occurrence of a historical accident; ρ is the resolution factor, taking 0-1.
S404, determining a relevance value of each flow information and the historical track data based on the relevance coefficient.
It can be understood that the association value calculation formula is as follows:
wherein: epsilon t The association degree corresponding to the independent variable t; t is the data type of the parent sequence; h is the data type of the subsequence; m is the total number of samples of the sub-sequence data; gamma ray f (h) Is a coefficient of relationship of the sub-sequence data f to the dependent variable h.
S500, processing the relevance value, the flow information and the historical track data according to a pre-trained road condition prediction model to obtain traffic road condition prediction information, wherein the road condition prediction model is obtained by training according to the traffic road conditions in the to-be-tested area in a historical period.
It will be appreciated that step S500 includes steps S501, S502, S503, S504 and S505, wherein:
s501, classifying the relevance value, the flow information and the historical track data to obtain a training set and a prediction set, and respectively carrying out standardized processing on the data of the training set and the data of the prediction set to obtain a first standardized processing result and a second standardized processing result;
s502, setting the number of layers and the number of neurons of each layer of an LSTM neural network model, and selecting an activation function and an optimizer of the LSTM neural network model which are suitable for being set, based on a deep learning library and a grid search parameter optimization method, wherein the activation function and the optimizer are used for updating parameters of the LSTM neural network model;
it should be noted that, setting the layer number of the DNN model network structure and the number of neurons at each layer, selecting an activation function and an optimizer suitable for the model through the sc i kit-l ean network searching function in the Keras library, and selecting a Mean Square Error (MSE) as a loss function to measure the output loss of a training sample, wherein the optimizer is Adam for updating model parameters, and optimizing the loss function to obtain a minimized extremum after each training period; the iteration step length and the training times are set, the model is trained, the road condition is predicted by the trained model, and the accuracy of traffic road condition prediction is improved.
S503, optimizing the updated LSTM neural network model according to the loss function to obtain an optimized LSTM neural network model;
it should be noted that, by optimizing the model parameter algorithm, the value of the loss function is gradually reduced, so that the error rate of the neural network for predicting the training data is continuously reduced. Let training set be t= (x 1 ,y 1 ),(x 2 ,y 2 ),…,(x n ,y n ) Wherein x is n A vector representing the nth input, each vector characterized by x n ,y n Is the correct classification for each datum. Assuming that the output of the neural network is a and gives the loss function, the calculation formula is as follows:
where w and b represent model parameters and n is the data of the samples in the training set, and in fact, the loss function describes the mean square error between the predictions and the sample labels of the optimized LSTM neural network model.
S504, sending a first standardized processing result to the optimized LSTM neural network model for processing, wherein data in the first standardized processing result is segmented by taking 30 minutes as a unit, and the first standardized processing result in different time periods is input to the LSTM neural network model for processing after being more optimized to obtain output data in different time periods, wherein the output data is flow information in different time periods;
It will be appreciated that by encoding each image using a self-encoder, a sequence of images for each image at different time periods is determined.
The present step S504 includes S5041, S5042, and S5043, wherein:
s5041, setting the time period to be measured corresponding to each time point to be measured in all the areas to be measured every day in a time period of 30 minutes according to the acquired data of the flow information, so as to obtain preprocessed data;
the setting is performed with 30 minutes as a time period, which is beneficial to avoiding redundancy and improving the processing efficiency.
S5042, carrying out data cleaning on the preprocessed data, wherein the data comprises analysis, duplication removal, omission, noise and exception processing on the preprocessed data;
specifically, the data is analyzed, de-duplicated, omitted, noise and abnormal processed, so that the judging precision can be improved, the accurate judgment of road conditions is facilitated, and the preparation is made for standardization.
S5043, performing linear transformation on the cleaned data to obtain traffic flow data, and recording the traffic flow data as the first standardized processing result.
It should be noted that, the traffic flow data is obtained by mapping the data into the range of [ -1,1] by linear transformation of the traffic flow data.
S505, comparing the second standardized processing result with the output data to obtain a comparison result; and if the comparison result is that the second standardized processing result is inconsistent with the output data, continuously adjusting parameters by adopting a grid search parameter optimization method until the comparison result is that the second standardized processing result is consistent with the output data, wherein the parameters are input feature dimension, hidden layer dimension and input layer data of the STM neural network model.
It can be understood that the LSTM neural network model is trained in the step, data results in different time periods are predicted, and the prediction accuracy is adjusted, so that the purpose of high efficiency and high speed is achieved.
Example 2:
as shown in fig. 2, the present embodiment provides a traffic condition prediction system based on internet of vehicles big data, and the system described with reference to fig. 2 includes a first acquisition module 701, a second acquisition module 702, a first processing module 703, an analysis module 704, and a second processing module 705, where:
the first acquisition module 701: the method comprises the steps of acquiring historical track data of the region to be detected in a preset time period before the current moment;
the second acquisition module 702: the method comprises the steps of respectively obtaining first track data and second track data of traffic road conditions in an area to be detected, wherein the first track data is the total number of vehicles in all vehicle tracks, the vehicles are not in the area to be detected at the previous moment and are in the area to be detected at the current moment; the second track data is the total number of vehicles in all the vehicle tracks, wherein the vehicles are in the region to be detected at the previous moment and are not in the region to be detected at the current moment;
The first processing module 703: the method comprises the steps of processing the first track data and the second track data based on three-dimensional vectors to obtain flow information of all vehicle tracks of each time point to be detected in all the areas to be detected, wherein the flow information comprises relative traffic flow among all vehicles, relative traffic flow change rate, uncertain information of traffic accidents and environmental factors of a current road;
analysis module 704: the gray correlation analysis is used for carrying out gray correlation analysis on the flow information and the historical track data to obtain a correlation value of each flow information and the historical track data;
the second processing module 705: and the traffic road condition prediction model is obtained by training the traffic road conditions in the to-be-tested area in a history period.
Specifically, the acquisition process of the uncertain information of the traffic accident in the first processing module 703 includes an acquisition unit 7021, an identification unit 7022, a first determination unit 7023, and a selection unit 7024, wherein:
Acquisition unit 7021: the image processing device is used for acquiring traffic road condition image information of each time point to be detected in the region to be detected by adopting a camera device;
identification unit 7022: the method comprises the steps of carrying out image preprocessing on traffic road condition image information, and identifying the preprocessed images based on a Yo l ov3 network to obtain a plurality of groups of coincident images, wherein the plurality of groups of coincident images are at least three groups, and the coincident images comprise at least two tracks with the same steering information and are divided into the same image track set;
first determination unit 7023: the method is used for carrying out analytic hierarchy process on all the coincident images and determining the proportion of the same steering image information in each group of coincident images;
selection unit 7024: the method is used for selecting the coincident intersection with the largest occupied proportion according to the proportion occupied by the same steering image information in each group of coincident images, wherein the coincident intersection is the intersection with the largest steering times, namely the uncertain information used for measuring the traffic accident.
Specifically, the analysis module 704 includes an analysis unit 7041, a first processing unit 7042, a calculation unit 7043, and a determination unit 7044, wherein:
analysis unit 7041: the method comprises the steps of carrying out sequence analysis on flow information and historical track data to obtain first sequence data and second sequence data, wherein the historical track data is used as a parent sequence reflecting traffic road condition factors, and the flow information is used as a subsequence reflecting the traffic road condition factors;
First processing unit 7042: the method comprises the steps of performing non-dimensionality processing on first sequence data and second sequence data, and performing average value calculation on the processed data to obtain first average value data of the first sequence data and second average value data of the second sequence data;
calculation unit 7043: the correlation calculation is used for carrying out correlation calculation based on the first sequence data, the second sequence data, the first average value data and the second average value data to obtain a correlation coefficient between the subsequence and the parent sequence;
determination unit 7044: and the correlation value is used for determining the correlation value of each flow information and the historical track data based on the correlation coefficient.
Specifically, the second processing module 705 includes a classification unit 7051, a first setting unit 7052, an optimization unit 7053, a second processing unit 7054, and a comparison unit 7055, wherein:
classification unit 7051: the method comprises the steps of classifying the relevance value, the flow information and the historical track data to obtain a training set and a prediction set, and respectively carrying out standardized processing on the data of the training set and the data of the prediction set to obtain a first standardized processing result and a second standardized processing result;
First setting unit 7052: the method comprises the steps of setting the number of layers and the number of neurons of each layer of an LSTM neural network model, and selecting an activation function and an optimizer of the LSTM neural network model, which are suitable for being set, based on a deep learning library and a grid search parameter optimization method, wherein the activation function and the optimizer are used for updating parameters of the LSTM neural network model;
optimization unit 7053: the method comprises the steps of optimizing the updated LSTM neural network model according to a loss function to obtain an optimized LSTM neural network model;
second processing unit 7054: the method comprises the steps of sending a first standardized processing result to an optimized LSTM neural network model for processing, wherein data in the first standardized processing result is segmented by taking 30 minutes as a unit, and the first standardized processing result in different time periods is input to the LSTM neural network model for processing after being more optimized to obtain output data in different time periods, wherein the output data is flow information in different time periods;
comparison unit 7055: the second normalization processing result is used for comparing the second normalization processing result with the output data to obtain a comparison result; and if the comparison result is that the second standardized processing result is inconsistent with the output data, continuously adjusting parameters by adopting a grid search parameter optimization method until the comparison result is that the second standardized processing result is consistent with the output data, wherein the parameters are input feature dimension, hidden layer dimension and input layer data of the STM neural network model.
Specifically, the classifying unit 7051 includes a second setting unit 70511, a cleaning unit 70512, and a converting unit 70513, wherein:
the second setting unit 70511: the method comprises the steps of setting the time period to be measured corresponding to each time point to be measured in all areas to be measured every day with 30 minutes as a time period according to the collected data of the flow information, and obtaining preprocessed data;
cleaning unit 70512: the data processing method comprises the steps of carrying out data cleaning on the preprocessed data, wherein the data comprises analysis, duplication removal, omission, noise and exception processing on the preprocessed data;
transform unit 70513: and the method is used for carrying out linear transformation on the cleaned data to obtain traffic flow data, and the traffic flow data is recorded as the first standardized processing result.
It should be noted that, regarding the system in the above embodiment, the specific manner in which the respective modules perform the operations has been described in detail in the embodiment regarding the method, and will not be described in detail herein.
Example 3:
corresponding to the above method embodiment, a traffic condition prediction device based on internet of vehicles big data is further provided in this embodiment, and a traffic condition prediction device based on internet of vehicles big data described below and a traffic condition prediction based on internet of vehicles big data described above may be referred to correspondingly with each other.
Fig. 3 is a block diagram illustrating a traffic condition prediction apparatus 800 based on internet of vehicles big data according to an exemplary embodiment. As shown in fig. 3, the traffic condition prediction device 800 based on internet of vehicles big data may include: a processor 801, a memory 802. The internet of vehicles big data based traffic condition prediction device 800 may further include one or more of a multimedia component 803, an i/O interface 804, and a communication component 805.
The processor 801 is configured to control the overall operation of the traffic condition prediction device 800 based on the internet of vehicles, so as to complete all or part of the steps in the traffic condition prediction method based on the internet of vehicles. The memory 802 is used to store various types of data to support operation at the internet of vehicles-based big data traffic road condition prediction device 800, which may include, for example, instructions for any application or method operating on the internet of vehicles-based big data traffic road condition prediction device 800, as well as application-related data such as contact data, messages, pictures, audio, video, and the like. The Memory 802 may be implemented by any type or combination of volatile or non-volatile Memory devices, such as static random access Memory (Stat i c Random Access Memory, SRAM for short), electrically erasable programmable Read-only Memory (E l ectr i ca l l y Erasab l e Programmab l e Read-On l y Memory, EEPROM for short), erasable programmable Read-only Memory (Erasab l e Programmab l e Read-On l y Memory, EPROM for short), programmable Read-only Memory (Programmab l e Read-On l y Memory, PROM for short), read-On l y Memory (ROM for short), magnetic Memory, flash Memory, magnetic disk, or optical disk. The multimedia component 803 may include a screen and an audio component. Wherein the screen may be, for example, a touch screen, the audio component being for outputting and/or inputting audio signals. For example, the audio component may include a microphone for receiving external audio signals. The received audio signals may be further stored in the memory 802 or transmitted through the communication component 805. The audio assembly further comprises at least one speaker for outputting audio signals. The I/O interface 804 provides an interface between the processor 801 and other interface modules, which may be a keyboard, mouse, buttons, etc. These buttons may be virtual buttons or physical buttons. The communication component 805 is configured to perform wired or wireless communication between the traffic condition prediction device 800 based on internet of vehicles big data and other devices. Wireless communication, such as Wi-F i, bluetooth, near field communication (Near F i e l dCommun i cat i on, NFC for short), 2G, 3G or 4G, or a combination of one or more thereof, the respective communication component 805 may thus comprise: wi-F i module, bluetooth module, NFC module.
In an exemplary embodiment, the traffic condition prediction device 800 based on the internet of vehicles big data may be implemented by one or more application specific integrated circuits (App l I cat I on Spec I f I C I ntegrated C I rcu I t, abbreviated AS ic), digital signal processors (D I g I ta l S I gna l Processor, abbreviated DSP), digital signal processing devices (D I g I ta l S I gna l Process I ng Dev I ce, abbreviated DSPD), programmable logic devices (Programmab l e Log I C Dev I ce, abbreviated PLD), field programmable gate arrays (F I e l d Programmab l e Gate Array, abbreviated FPGA), controllers, microcontrollers, microprocessors or other electronic components for executing the traffic condition prediction method based on the internet of vehicles big data.
In another exemplary embodiment, a computer readable storage medium is provided that includes program instructions that when executed by a processor implement the steps of the traffic condition prediction method based on internet of vehicles big data described above. For example, the computer readable storage medium may be the memory 802 including the program instructions described above, which may be executed by the processor 801 of the internet of vehicles big data based traffic condition prediction device 800 to perform the internet of vehicles big data based traffic condition prediction method described above.
Example 4:
corresponding to the above method embodiment, a readable storage medium is further provided in this embodiment, and a readable storage medium described below and a traffic condition prediction based on internet of vehicles big data described above may be referred to correspondingly.
A readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps of the traffic condition prediction method based on internet of vehicles big data in the above method embodiment.
The readable storage medium may be a usb disk, a removable hard disk, a Read-only Memory (ROM), a random access Memory (Random Access Memory, RAM), a magnetic disk, or an optical disk, and the like.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the present invention, but various modifications and variations can be made to the present invention by those skilled in the art. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
The foregoing is merely illustrative of the present invention, and the present invention is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present invention. Therefore, the protection scope of the invention is subject to the protection scope of the claims.
Claims (10)
1. The traffic road condition prediction method based on the internet of vehicles big data is characterized by comprising the following steps:
acquiring historical track data of the region to be detected in a preset time period before the current moment;
respectively acquiring first track data and second track data of traffic road conditions in an area to be detected, wherein the first track data is the total number of vehicles in all vehicle tracks, which are not in the area to be detected at the previous moment of the vehicles but are in the area to be detected at the current moment; the second track data is the total number of vehicles in all the vehicle tracks, wherein the vehicles are in the region to be detected at the previous moment and are not in the region to be detected at the current moment;
processing the first track data and the second track data based on three-dimensional vectors to obtain flow information of all vehicle tracks of each time point to be detected in all the areas to be detected, wherein the flow information comprises relative traffic flow among all vehicles, relative traffic flow change rate, uncertain information of traffic accidents and environmental factors of current roads;
carrying out gray correlation analysis on the flow information and the historical track data to obtain a correlation value of each flow information and the historical track data;
And processing the relevance value, the flow information and the historical track data according to a pre-trained road condition prediction model to obtain traffic road condition prediction information, wherein the road condition prediction model is obtained by training according to the traffic road conditions in the to-be-tested area in a historical period.
2. The traffic condition prediction method based on internet of vehicles big data according to claim 1, wherein the traffic information includes relative traffic flow between all vehicles, relative traffic flow change rate, uncertain information of traffic accidents and environmental factors of current roads, and the acquiring process of the uncertain information of traffic accidents includes:
acquiring traffic road condition image information of each time point to be detected in the region to be detected by adopting a camera device;
carrying out image preprocessing on the traffic road condition image information, and identifying the preprocessed images based on a Yolov3 network to obtain a plurality of groups of coincident images, wherein the plurality of groups of coincident images are at least three groups, and the coincident images comprise at least two tracks with the same steering information and are divided into the same image track set;
performing hierarchical analysis on all the coincident images to determine the proportion of the same steering image information in each group of coincident images;
And selecting the coincident intersection with the largest proportion according to the proportion of the same turning image information in each group of coincident images, wherein the coincident intersection is the intersection with the largest turning times, namely the uncertain information for measuring the traffic accident.
3. The traffic condition prediction method based on internet of vehicles big data according to claim 1, wherein the gray correlation analysis is performed on the flow information and the historical track data to obtain a correlation value of each flow information and the historical track data, and the method comprises the following steps:
performing sequence analysis on the flow information and the historical track data to obtain first sequence data and second sequence data, wherein the historical track data is used as a parent sequence reflecting traffic road condition factors, and the flow information is used as a subsequence reflecting traffic road condition factors;
performing dimensionless treatment on the first sequence data and the second sequence data, and performing average value calculation on the treated data to obtain first average value data of the first sequence data and second average value data of the second sequence data;
performing association calculation based on the first sequence data, the second sequence data, the first average value data and the second average value data to obtain an association coefficient between the subsequence and the parent sequence;
And determining a relevance value of each flow information and the historical track data based on the relevance coefficient.
4. The traffic condition prediction method based on internet of vehicles big data according to claim 1, wherein the processing the association value, the flow information and the historical track data according to a pre-trained condition prediction model to obtain traffic condition prediction information comprises:
classifying the association degree value, the flow information and the historical track data to obtain a training set and a prediction set, and respectively carrying out standardized processing on the data of the training set and the data of the prediction set to obtain a first standardized processing result and a second standardized processing result;
setting the number of layers and the number of neurons in each layer of an LSTM neural network model, and selecting an activation function and an optimizer of the LSTM neural network model, which are suitable for being set, based on a deep learning library and a grid search parameter optimization method, wherein the activation function and the optimizer are used for updating parameters of the LSTM neural network model;
optimizing the updated LSTM neural network model according to the loss function to obtain an optimized LSTM neural network model;
Transmitting a first standardized processing result to the optimized LSTM neural network model for processing, wherein data in the first standardized processing result is segmented by taking 30 minutes as a unit, and the first standardized processing result in different time periods is input to the more optimized LSTM neural network model for processing, so that output data in different time periods is obtained, and the output data is flow information in different time periods;
comparing the second standardized processing result with the output data to obtain a comparison result; and if the comparison result is that the second standardized processing result is inconsistent with the output data, continuously adjusting parameters by adopting a grid search parameter optimization method until the comparison result is that the second standardized processing result is consistent with the output data, wherein the parameters are input feature dimension, hidden layer dimension and input layer data of the STM neural network model.
5. The method for predicting traffic conditions based on internet of vehicles according to claim 4, wherein the obtaining the first standardized processing result comprises:
according to the acquired data of the flow information, setting each time point to be detected in all the areas to be detected in a time period of 30 minutes corresponding to the time period to be detected every day, and obtaining preprocessed data;
Carrying out data cleaning on the preprocessed data, wherein the data after preprocessing comprises analysis, duplication removal, omission, noise and exception processing;
and carrying out linear transformation on the cleaned data to obtain traffic flow data, and recording the traffic flow data as the first standardized processing result.
6. A traffic road condition prediction system based on Internet of vehicles big data is characterized by comprising:
a first acquisition module: the method comprises the steps of acquiring historical track data of the region to be detected in a preset time period before the current moment;
and a second acquisition module: the method comprises the steps of respectively obtaining first track data and second track data of traffic road conditions in an area to be detected, wherein the first track data is the total number of vehicles in all vehicle tracks, the vehicles are not in the area to be detected at the previous moment and are in the area to be detected at the current moment; the second track data is the total number of vehicles in all the vehicle tracks, wherein the vehicles are in the region to be detected at the previous moment and are not in the region to be detected at the current moment;
a first processing module: the method comprises the steps of processing the first track data and the second track data based on three-dimensional vectors to obtain flow information of all vehicle tracks of each time point to be detected in all the areas to be detected, wherein the flow information comprises relative traffic flow among all vehicles, relative traffic flow change rate, uncertain information of traffic accidents and environmental factors of a current road;
And an analysis module: the gray correlation analysis is used for carrying out gray correlation analysis on the flow information and the historical track data to obtain a correlation value of each flow information and the historical track data;
and a second processing module: and the traffic road condition prediction model is obtained by training the traffic road conditions in the to-be-tested area in a history period.
7. The traffic condition prediction system based on internet of vehicles according to claim 6, wherein the acquiring procedure of the uncertain information of the traffic accident in the first processing module comprises:
an acquisition unit: the image processing device is used for acquiring traffic road condition image information of each time point to be detected in the region to be detected by adopting a camera device;
an identification unit: the method comprises the steps of carrying out image preprocessing on traffic road condition image information, and identifying the preprocessed images based on a Yolov3 network to obtain a plurality of groups of coincident images, wherein the plurality of groups of coincident images are at least three groups, and the coincident images comprise at least two tracks with the same steering information and are divided into the same image track set;
A first determination unit: the method is used for carrying out analytic hierarchy process on all the coincident images and determining the proportion of the same steering image information in each group of coincident images;
the selecting unit: the method is used for selecting the coincident intersection with the largest occupied proportion according to the proportion occupied by the same steering image information in each group of coincident images, wherein the coincident intersection is the intersection with the largest steering times, namely the uncertain information used for measuring the traffic accident.
8. The internet of vehicles big data based traffic condition prediction system according to claim 6, wherein the analysis module comprises:
analysis unit: the method comprises the steps of carrying out sequence analysis on flow information and historical track data to obtain first sequence data and second sequence data, wherein the historical track data is used as a parent sequence reflecting traffic road condition factors, and the flow information is used as a subsequence reflecting the traffic road condition factors;
a first processing unit: the method comprises the steps of performing non-dimensionality processing on first sequence data and second sequence data, and performing average value calculation on the processed data to obtain first average value data of the first sequence data and second average value data of the second sequence data;
A calculation unit: the correlation calculation is used for carrying out correlation calculation based on the first sequence data, the second sequence data, the first average value data and the second average value data to obtain a correlation coefficient between the subsequence and the parent sequence;
a determination unit: and the correlation value is used for determining the correlation value of each flow information and the historical track data based on the correlation coefficient.
9. The internet of vehicles big data based traffic condition prediction system according to claim 6, wherein the second processing module comprises:
classification unit: the method comprises the steps of classifying the relevance value, the flow information and the historical track data to obtain a training set and a prediction set, and respectively carrying out standardized processing on the data of the training set and the data of the prediction set to obtain a first standardized processing result and a second standardized processing result;
a first setting unit: the method comprises the steps of setting the number of layers and the number of neurons of each layer of an LSTM neural network model, and selecting an activation function and an optimizer of the LSTM neural network model, which are suitable for being set, based on a deep learning library and a grid search parameter optimization method, wherein the activation function and the optimizer are used for updating parameters of the LSTM neural network model;
An optimizing unit: the method comprises the steps of optimizing the updated LSTM neural network model according to a loss function to obtain an optimized LSTM neural network model;
a second processing unit: the method comprises the steps of sending a first standardized processing result to an optimized LSTM neural network model for processing, wherein data in the first standardized processing result is segmented by taking 30 minutes as a unit, and the first standardized processing result in different time periods is input to the LSTM neural network model for processing after being more optimized to obtain output data in different time periods, wherein the output data is flow information in different time periods;
comparison unit: the second normalization processing result is used for comparing the second normalization processing result with the output data to obtain a comparison result; and if the comparison result is that the second standardized processing result is inconsistent with the output data, continuously adjusting parameters by adopting a grid search parameter optimization method until the comparison result is that the second standardized processing result is consistent with the output data, wherein the parameters are input feature dimension, hidden layer dimension and input layer data of the STM neural network model.
10. The traffic condition prediction system based on internet of vehicles according to claim 9, wherein the classification unit includes:
a second setting unit: the method comprises the steps of setting the time period to be measured corresponding to each time point to be measured in all areas to be measured every day with 30 minutes as a time period according to the collected data of the flow information, and obtaining preprocessed data;
and a cleaning unit: the data processing method comprises the steps of carrying out data cleaning on the preprocessed data, wherein the data comprises analysis, duplication removal, omission, noise and exception processing on the preprocessed data;
a conversion unit: and the method is used for carrying out linear transformation on the cleaned data to obtain traffic flow data, and the traffic flow data is recorded as the first standardized processing result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211738591.3A CN116189425A (en) | 2022-12-30 | 2022-12-30 | Traffic road condition prediction method and system based on Internet of vehicles big data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202211738591.3A CN116189425A (en) | 2022-12-30 | 2022-12-30 | Traffic road condition prediction method and system based on Internet of vehicles big data |
Publications (1)
Publication Number | Publication Date |
---|---|
CN116189425A true CN116189425A (en) | 2023-05-30 |
Family
ID=86445488
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202211738591.3A Pending CN116189425A (en) | 2022-12-30 | 2022-12-30 | Traffic road condition prediction method and system based on Internet of vehicles big data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116189425A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118015857A (en) * | 2024-04-08 | 2024-05-10 | 北京悦知未来科技有限公司 | Road traffic planning method |
-
2022
- 2022-12-30 CN CN202211738591.3A patent/CN116189425A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN118015857A (en) * | 2024-04-08 | 2024-05-10 | 北京悦知未来科技有限公司 | Road traffic planning method |
CN118015857B (en) * | 2024-04-08 | 2024-06-07 | 北京悦知未来科技有限公司 | Road traffic planning method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110889546B (en) | Attention mechanism-based traffic flow model training method | |
CN112085947B (en) | Traffic jam prediction method based on deep learning and fuzzy clustering | |
CN112470199A (en) | System and method for point-to-point traffic prediction | |
Ghanim et al. | Estimating turning movements at signalized intersections using artificial neural networks | |
CN110674858B (en) | Traffic public opinion detection method based on space-time correlation and big data mining | |
CN114664091A (en) | Early warning method and system based on holiday traffic prediction algorithm | |
CN111179591B (en) | Road network traffic time sequence characteristic data quality diagnosis and restoration method | |
CN114141385B (en) | Early warning method, system and readable storage medium for infectious diseases | |
CN112990530B (en) | Regional population quantity prediction method, regional population quantity prediction device, electronic equipment and storage medium | |
CN116189425A (en) | Traffic road condition prediction method and system based on Internet of vehicles big data | |
CN115331425A (en) | Traffic early warning method, device and system | |
CN113570867A (en) | Urban traffic state prediction method, device, equipment and readable storage medium | |
CN116010838A (en) | Vehicle track clustering method integrating density value and K-means algorithm | |
CN112541621B (en) | Movement prediction method, intelligent terminal and storage medium | |
Lei et al. | Prediction of PM2. 5 concentration considering temporal and spatial features: A case study of Fushun, Liaoning Province | |
Cao et al. | Cluster-based correlation of severe driving events with time and location | |
JP4123196B2 (en) | Traffic information prediction function learning device, traffic information prediction device, traffic information fluctuation law acquisition device and method | |
CN117349769A (en) | Garment logistics management-oriented space-time data anomaly detection method and system | |
Lushan et al. | Supervising vehicle using pattern recognition: Detecting unusual behavior using machine learning algorithms | |
US20230177959A1 (en) | Vehicle accident prediction system, vehicle accident prediction method, vehicle accident prediction program, and learned model creation system | |
CN111949840A (en) | Topological graph structure construction method and device based on Internet of things data | |
CN113688506B (en) | Potential atmospheric pollution source identification method based on multi-dimensional data such as micro-station and the like | |
Samal et al. | Speedpro: A predictive multi-model approach for urban traffic speed estimation | |
CN112651577B (en) | Tunnel deformation prediction method based on fusion spatio-temporal data | |
Huang | SVM‐Based Real‐Time Identification Model of Dangerous Traffic Stream State |
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 |