CN114168646A - Multi-data fusion-based commercial vehicle transportation monitoring method and system - Google Patents
Multi-data fusion-based commercial vehicle transportation monitoring method and system Download PDFInfo
- Publication number
- CN114168646A CN114168646A CN202111275618.5A CN202111275618A CN114168646A CN 114168646 A CN114168646 A CN 114168646A CN 202111275618 A CN202111275618 A CN 202111275618A CN 114168646 A CN114168646 A CN 114168646A
- Authority
- CN
- China
- Prior art keywords
- data
- vehicle
- risk
- driving
- road
- 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 58
- 238000012544 monitoring process Methods 0.000 title claims abstract description 20
- 230000004927 fusion Effects 0.000 title claims abstract description 16
- 230000007613 environmental effect Effects 0.000 claims abstract description 27
- 238000012545 processing Methods 0.000 claims description 17
- 230000008569 process Effects 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000011156 evaluation Methods 0.000 claims description 13
- 230000009467 reduction Effects 0.000 claims description 10
- 206010039203 Road traffic accident Diseases 0.000 claims description 9
- 230000001133 acceleration Effects 0.000 claims description 8
- 238000007477 logistic regression Methods 0.000 claims description 8
- 230000006855 networking Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000013145 classification model Methods 0.000 claims description 5
- 238000012423 maintenance Methods 0.000 claims description 5
- 238000012847 principal component analysis method Methods 0.000 claims description 4
- 238000004140 cleaning Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000011160 research Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000013507 mapping Methods 0.000 claims description 2
- 238000005286 illumination Methods 0.000 claims 1
- 230000006399 behavior Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 8
- 238000004590 computer program Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 7
- 230000001186 cumulative effect Effects 0.000 description 6
- 238000012502 risk assessment Methods 0.000 description 6
- 238000004458 analytical method Methods 0.000 description 4
- 238000003860 storage Methods 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 238000007621 cluster analysis Methods 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000002265 prevention Effects 0.000 description 3
- 230000007547 defect Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 239000006185 dispersion Substances 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 238000012098 association analyses Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000036461 convulsion Effects 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000000265 homogenisation Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000006996 mental state Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Images
Classifications
-
- 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
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- 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
- G06Q10/08—Logistics, e.g. warehousing, loading or distribution; Inventory or stock management
- G06Q10/083—Shipping
-
- 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
- G06Q50/40—Business processes related to the transportation industry
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Human Resources & Organizations (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Development Economics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- Game Theory and Decision Science (AREA)
- Educational Administration (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method and a system for monitoring transportation of commercial vehicles based on multi-data fusion, which are used for determining the driving style and the vehicle state of a corresponding driver of each operation enterprise based on natural driving data of an internet of vehicles, acquiring the characteristics and the environmental state of a road to be driven and determining the road operation risk on the one hand, and comprehensively monitoring the transportation of the commercial vehicles from data in various aspects such as vehicle-person-road-environment-enterprise and the like by combining the credit risk of the enterprise to which the commercial vehicles belong, thereby ensuring the orderly and safe transportation.
Description
Technical Field
The invention belongs to the technical field of traffic transportation management and control, and particularly relates to a method and a system for monitoring transportation of a commercial vehicle based on multi-data fusion.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
Transportation is an important support and a strong guarantee for economic development, transportation safety concerns are reliable and stable development of transportation, the prevention and control of safety risks of operating vehicles are the central importance of the field of road traffic safety, once accidents happen to the operating vehicles, the accidents are often super-large road traffic accidents, and specific losses are brought to life safety and property safety of people.
Therefore, risk prevention, control and safety supervision are needed for the safety of the commercial vehicles. However, as far as the inventor knows, the current supervision measures are mainly focused on risk assessment of the driver, and the supervision is mainly focused on the mental state of the driver, such as whether fatigue driving exists or not, and the driving style is ignored. The driving style refers to the relatively stable behavior characteristic shown by a driver operating a vehicle, and a large amount of road traffic accident cause analysis shows that most accidents are related to the behavior operation of the driver, wherein strong correlation exists between the driving style and the accident occurrence rate. The National Highway Traffic Safety Administration (NHTSA) in the united states finds that aggressive driving behaviors account for about two thirds of all fatal traffic accidents, and the higher the driving aggressiveness, the more likely bad driving behaviors such as rapid speed change, frequent lane change, overspeed driving and the like occur in the driving process, thereby seriously affecting the traffic safety.
Meanwhile, in terms of road transportation risk and enterprise information, the transportation of operating vehicles is greatly influenced, but the existing monitoring system is rarely involved in hunting of the part of the content or adopts expert experience in the aspects, so that the subjectivity is high, actual data support is lacked, and reliable and accurate evaluation is difficult to obtain.
Disclosure of Invention
The invention aims to solve the problems and provides a method and a system for monitoring the transportation of commercial vehicles based on multi-data fusion.
According to some embodiments, the invention adopts the following technical scheme:
a method for monitoring transportation of commercial vehicles based on multi-data fusion comprises the following steps:
acquiring relevant historical driving data of commercial vehicles including speed, acceleration, yaw rate, travel and impact, dividing data of each vehicle according to continuous travel and vehicle ID, and respectively combining different driving data of the same vehicle and different driving data of drivers;
carrying out dimension reduction processing on different driving data of the same driver, calculating an information contribution value of each type of driving data to the driving style, giving a weight to each type of driving data according to the information contribution value, and classifying the driving style by using a classification model;
preprocessing different driving data of the same vehicle, and determining the vehicle state of the corresponding commercial vehicle according to the travel and the related driving data of other vehicle states;
acquiring road related information of a pre-driving route, acquiring environmental information of pre-driving time, preprocessing the driving road and the environmental information, determining the probability of accidents caused by corresponding roads and environmental risk sources and possible economic losses by using a calculation model, and quantifying the roads and the environmental risks according to calculated values;
and comprehensively analyzing the driving style, the vehicle state and the risks on roads and environments by using a logistic regression analysis method, determining the transportation risk of the operating vehicle, and performing networking early warning and supervision according to the transportation risk.
In an alternative embodiment, the relevant historical driving data includes vehicle speed extrema, mean and standard deviation, acceleration extrema and mean, jerk mean, distance traveled, yaw rate mean and standard deviation.
As an alternative embodiment, the specific process of performing the dimension reduction processing on different driving data of the same driver includes: the method comprises the steps of adopting a principal component analysis method to achieve dimension reduction processing of a driving style related data set, conducting standardization processing on acquired m-dimensional features, calculating a correlation coefficient matrix, a feature value and a feature vector of the m-dimensional features, calculating an information contribution rate and an accumulated contribution rate of the feature value, and mapping the features to a p dimension by utilizing orthogonal change according to the information contribution rate and the accumulated contribution rate, wherein p is less than m.
As an alternative embodiment, the specific process of determining the vehicle state of the corresponding service vehicle from the trip and other vehicle state related driving data includes: and determining the vehicle state according to the total travel of the commercial vehicle, the total time length of transportation and the vehicle maintenance record.
As an alternative embodiment, the specific process of preprocessing the driving road and environment information includes: and cleaning, screening and combining the data, and connecting the data tables according to accident numbers.
As an alternative embodiment, the risk source indicators of the traveling road and environment information include at least a part of parameters of whether to transport dangerous goods, road intersections, road alignment, road gradient, road sharp turns, road pavement state, presence or absence of traffic control equipment, time, weather conditions and light conditions.
As an alternative embodiment, the specific process of determining the probability of accidents caused by the corresponding road and environmental risk sources and the possible economic losses by using the calculation model comprises the following steps: the method comprises the steps of extracting casualty conditions and vehicle damage conditions of each accident by utilizing historical accident data under corresponding roads and environmental conditions, applying an incident loss consequence calculation model, and quantifying the severity of the traffic accident into economic loss by combining local social and economic conditions, relevant legal regulations and relevant research data.
As an alternative embodiment, the specific process of quantifying the road and environmental risks according to the calculated values includes: according to the probability of accidents caused by the risk source and the economic loss caused by the accidents, the possibility and the severity of the accidents caused by the risk source are divided into different grades, corresponding risk evaluation indexes are respectively given, the objective weight of each index is calculated by combining an entropy weight method, and the vehicle transportation risk grade is determined.
As an alternative embodiment, the specific process of comprehensively analyzing the driving style, the vehicle state and the risks on the road and the environment includes: respectively establishing statistical data reference pages according to the driving style, the vehicle state and the risks on the road and the environment, and displaying the statistical data reference pages on corresponding pages according to the risk order;
or giving a risk coefficient to each type of risk, comprehensively calculating the risk values in multiple directions to further obtain a comprehensive risk value, and displaying the transportation risk of the commercial vehicle according to the comprehensive risk value sequence.
An operating vehicle transportation monitoring system based on multidata fusion, comprising:
the transportation data acquisition module is configured to acquire relevant historical driving data of the commercial vehicle including speed, acceleration, yaw rate, travel and impact degree, divide the data of each vehicle according to continuous travel and vehicle ID, and respectively combine different driving data of the same vehicle and a driver;
the driving style classification module is configured to perform dimension reduction processing on different driving data of the same driver, calculate an information contribution value of each type of driving data to the driving style, give a weight to each driving data according to the information contribution value, and classify the driving style by using a classification model;
the vehicle state determination module is configured to preprocess different driving data of the same vehicle and determine the vehicle state of the corresponding commercial vehicle according to the travel and the driving data related to other vehicle states;
the driving risk calculation module is configured to acquire road related information of a pre-driving route, acquire environmental information of pre-driving time, preprocess driving road and environmental information, determine probability of accidents caused by corresponding road and environmental risk sources and possible economic loss by using a calculation model, and quantify road and environmental risks according to calculated values;
and the comprehensive monitoring module is configured to comprehensively analyze the driving style, the vehicle state and the risks on roads and environments by using a logistic regression analysis method, determine the transportation risk of the operating vehicle, and perform networking early warning and supervision according to the transportation risk.
Compared with the prior art, the invention has the beneficial effects that:
the invention comprehensively considers risk factors on driving style, vehicle state, road condition and environment condition, carries out whole-course closed-loop supervision on operating vehicles, effectively solves the problems of high requirement on personal quality of managers and large influence on organizational structures in traditional risk analysis, has theoretical and practical application value in aspects of road transportation risk assessment and accident prevention, and also provides technical support for networking supervision, accurate supervision, high-efficiency supervision and cooperative supervision of emergency, traffic, public security, environmental protection and other departments.
The method is based on the natural driving data of the Internet of vehicles, utilizes the driving style classification model to realize the evaluation of the style of the driver, and overcomes the defects of low precision caused by the random selection of the initial clustering center by the traditional clustering algorithm;
the invention considers the risk of the vehicle state, preprocesses different driving data of the same vehicle, determines the vehicle state of the corresponding commercial vehicle according to the travel and the driving data related to other vehicle states, and effectively ensures the vehicle safety.
The invention uses an entropy weight method and an incident loss consequence calculation model, combines the statistical data of the road traffic accidents to calculate the index weight, calculates the pre-driving road and the environmental risk, and overcomes the defect of over-strong subjectivity of the traditional risk evaluation method.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
FIG. 1 is a driving style principal component contribution ratio graph in accordance with at least one embodiment of the present disclosure;
FIGS. 2(a) and (b) are schematic views of a driver statistics and risk association analysis interface according to at least one embodiment of the present disclosure;
FIG. 3 is an operational enterprise statistics reference interface in accordance with at least one embodiment of the present disclosure;
FIG. 4 is an operational enterprise risk cluster analysis interface in accordance with at least one embodiment of the present disclosure;
FIG. 5 is a schematic flow chart of at least one embodiment of the present invention.
The specific implementation mode is as follows:
the invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. 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 invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
The invention aims to: extracting multidimensional data such as vehicle running states, driver behaviors and road environments generated in the running process of commercial vehicles based on massive natural driving data of the Internet of vehicles, determining space-time information related to vehicle illegal behaviors, driver dangerous behaviors and the like through map matching, and calculating characteristic indexes; performing dimensionality reduction treatment on the linear correlation indexes by using a principal component analysis method to obtain a comprehensive evaluation index set of risk evaluation of the commercial vehicle driver, and performing cluster analysis on the existing multidimensional heterogeneous space-time information according to a K-means + + clustering method based on Euclidean distance to obtain a risk index of the commercial vehicle driver; and establishing a risk quantitative grading model according to a risk management theory by combining the statistical data of the road traffic accidents, and researching the risk state of the accidents from the possibility and the severity of the accidents. And constructing a logistic regression score card model based on the risk assessment of the driver and the transport vehicle, calculating to obtain a transport enterprise risk comprehensive evaluation index, determining the risk of the operation enterprise, and making corresponding key risk supervision measures according to the risk and the transportation management department.
The following description is given in terms of an exemplary embodiment, as shown in fig. 5, including the following steps:
(1) driving style determination
Based on the vehicle networking test historical data, dividing data of each vehicle according to continuous travel and vehicle ID, merging different travels of the same driver, performing statistical processing on time point data of speed, acceleration and yaw rate, generating driving style quantitative indexes such as an average value, a standard deviation, a maximum value, a minimum value, travel distance and the like, and obtaining a driving style quantitative data set of the driver.
In other embodiments, vehicle driving parameters may be adjusted as the case may be.
TABLE 1 quantized index set of driving styles
In addition, the present embodiment considers the correlation of the above 18 driving style indices and the workload required for the subsequent driving style clusteringIn the embodiment, the dimension reduction processing of the driving style index set is realized by adopting a principal component analysis method, and the main idea is that m-dimensional features are mapped to p-dimension (p < m) by utilizing orthogonal change, wherein the m-dimension is mutually independent principal components containing original p-dimension information. For the driving style evaluation index selected in this embodiment, an 18-dimensional data set is imported, the raw data is firstly normalized in Python software, a correlation coefficient matrix, eigenvalues and eigenvectors of the raw data are calculated, and then, an eigenvalue λ is calculated according to formulas (1) and (2)j(j-1, 2, …, m) and an accumulated contribution rate.
Wherein, bjAs a principal component yiThe information contribution rate of (1).
Wherein alpha ispAs a principal component y1,y2,…,ypThe cumulative contribution rate of. When alpha ispWhen the value is close to 1, the first p index parameters y are selected1,y2,…,ypAs p principal components, the original m index parameters are replaced.
Fig. 1 shows the cumulative contribution ratio of 18 principal components in the present embodiment, the abscissa shows 18 principal component variables, the ordinate of the histogram shows the information contribution ratio of each principal component, the larger the value thereof, the more data information is contained, and the ordinate of the line graph shows the cumulative contribution ratio of each principal component. As shown in fig. 1 and table 2, the cumulative contribution rate of the first 6 principal components reaches 85%, and the cumulative contribution rate can be used to represent the original 18 evaluation indexes and serve as the input of the subsequent K-means + + driving risk evaluation model. The model divides drivers into a calm type, a general type and an aggressive type based on Euclidean distance, and different classification results are presented by different risk evaluation indexes.
Of course, in other embodiments, the parameters described above may be modified.
TABLE 2 information contribution ratio and cumulative contribution ratio of each principal component
(2) Risk of vehicle condition
And determining the vehicle state and demarcating the risk level according to the total travel of the commercial vehicle, the total transported time and the vehicle maintenance record.
(3) Vehicle operation, road and environmental risks
In order to improve the traffic safety management level of operating enterprises, risk factors in vehicle operation should be accurately identified and evaluated. By combining the 2019 U.S. traffic accident data counted by the National Highway Traffic Safety Administration (NHTSA), risk source indexes are screened to cover the time of accident occurrence, road alignment, weather and other influence factors, as shown in Table 3.
TABLE 3 Risk impact factor index set
And cleaning, screening and combining the data by using Python software according to the risk indexes, and connecting a plurality of data tables according to accident numbers. The casualty condition and the vehicle damage condition of each accident are extracted, an incident loss consequence calculation model is applied, the severity of the traffic accident is quantized into economic loss by combining the local social and economic condition, relevant legal regulations and relevant research data, and partial results are shown in table 4.
TABLE 4 post-processing fractional data
Based on the risk management theory, a risk quantitative grading model is established, and the risk state of the model is researched based on the probability and the severity of the accident. According to the probability of accidents caused by the risk source and the economic loss caused by the accidents, the possibility and the severity of the accidents caused by the risk source are divided into different grades, and corresponding risk evaluation indexes are respectively given. And calculating the objective weight of each index by combining an entropy weight method, and determining the vehicle transportation risk level.
According to the characteristics of entropy, the randomness and the disorder degree of an event can be judged by calculating the entropy, or the dispersion degree of a certain index can be judged by using the entropy, and the larger the dispersion degree of the index is, the larger the influence (weight) of the index on comprehensive evaluation is. The method comprises the following specific steps:
for n samples, h indexes, then xijThe value of the j index of the ith sample;
normalization processing of indexes: heterogeneous index homogenization
The forward direction index is as follows:
negative direction index:
calculating the proportion of the ith sample value in the jth index:
fourthly, calculating the entropy of the j index:
wherein k is 1/ln (n)>0, satisfies ej≥0；
Calculating information entropy redundancy (difference):
dj＝1-ej,j＝1,…,h (7)
sixthly, calculating the weight of each index:
and seventhly, calculating the comprehensive score of each sample:
wherein x isijIs normalized data.
(4) Risk portrait of operating enterprise
Logistic regression is a multivariate statistical analysis method for researching the relationship between expression variables and predictive variables of binary classification, and belongs to probability type nonlinear regression. And establishing a scoring card model on the basis of the logistic regression function, and establishing a transportation risk evaluation model of the transportation enterprise to realize enterprise risk portrait. The implementation principle of the logic scoring card is as follows: the grading card model selects u characteristics to grade the transportation enterprises, wherein the characteristic X is (X)1,X2,…,Xu) Sufficient information for judging whether a transportation enterprise is good or bad, such as driver behavior information of acceleration, speed and the like, driver state information of distraction driving, drunk driving and the like, vehicle transportation risk information of road gradient, alignment, cargo state and the like, is contained, the information is substituted into a formula (10) and a logistic regression function (11) for calculation, and a value between (0 and 1) is obtained, and q (z) is called a client risk score value.
z＝a+b1X1+b2X2+…+buXu (10)
On the basis of the analysis method, the embodiment also provides that the enterprise risk representation system for operation is divided into a driver personal module, an enterprise manager and a transportation management department door module, and the following modules are respectively arranged below the enterprise risk representation system: the system comprises modules of driving information maintenance, driver risk assessment, driving advice, enterprise risk representation, label management and the like.
The system consists of functional modules of information maintenance and the like of the traditional business type enterprise management system and an image functional module of a big data system. In a business type enterprise management system, the driving style and risk assessment aiming at a driver is realized. As shown in fig. 2(a) and (b), the driver statistical data interface shows the statistical reference results obtained by the individual driver based on the group data, including the proportion of each individual attribute of the driver in the whole, the risk coefficient, the risk score details, the risk trend, and the like. The driving data are processed and classified according to rules, then relevant risk factors are obtained through analysis, the risk coefficient of the operating vehicle is obtained through a machine learning relevant algorithm, and further the implicit association among typical risks is obtained through an intelligent algorithm.
The image function module and the service data of the management system share a MySQL database for storage. Fig. 3 shows a statistical data reference page at the administrator user side, which shows statistical reference results obtained based on group data, including the percentage of each attribute, the risk coefficient, the risk score details, the risk trend, and the like. The system can count out the typical risk that the driver suffered from the same illness, look over the proportional ranking, and every quarter has corresponding risk coefficient, finally forms the risk trend, supplies the administrator to have comparatively accurate assurance to the risk of enterprise. Fig. 4 shows a risk cluster analysis page at the administrator user side, where attributes to be clustered are selected in this column based on cross clustering of basic attributes of drivers such as gender, age, and violation times, so as to obtain corresponding analysis results.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Although the embodiments of the present invention have been described with reference to the accompanying drawings, it is not intended to limit the scope of the present invention, and it should be understood by those skilled in the art that various modifications and variations can be made without inventive efforts by those skilled in the art based on the technical solution of the present invention.
Claims (10)
1. A method for monitoring transportation of commercial vehicles based on multi-data fusion is characterized by comprising the following steps: the method comprises the following steps:
acquiring relevant historical driving data of commercial vehicles including speed, acceleration, yaw rate, travel and impact, dividing data of each vehicle according to continuous travel and vehicle ID, and respectively combining different driving data of the same vehicle and different driving data of drivers;
carrying out dimension reduction processing on different driving data of the same driver, calculating an information contribution value of each type of driving data to the driving style, giving a weight to each type of driving data according to the information contribution value, and classifying the driving style by using a classification model;
preprocessing different driving data of the same vehicle, and determining the vehicle state of the corresponding commercial vehicle according to the travel and the related driving data of other vehicle states;
acquiring road related information of a pre-driving route, acquiring environmental information of pre-driving time, preprocessing the driving road and the environmental information, determining the probability of accidents caused by corresponding roads and environmental risk sources and possible economic losses by using a calculation model, and quantifying the roads and the environmental risks according to calculated values;
and comprehensively analyzing the driving style, the vehicle state and the risks on roads and environments by using a logistic regression analysis method, determining the transportation risk of the operating vehicle, and performing networking early warning and supervision according to the transportation risk.
2. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the relevant historical driving data comprises an extreme value, a mean value and a standard deviation of the vehicle speed, an extreme value and a mean value of acceleration in all directions, an average value of impact in all directions, a travel distance, a mean value of yaw rate and a standard deviation.
3. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the specific process of performing the dimension reduction processing on different driving data of the same driver comprises the following steps: the method comprises the steps of adopting a principal component analysis method to achieve dimension reduction processing of a driving style related data set, conducting standardization processing on acquired m-dimensional features, calculating a correlation coefficient matrix, a feature value and a feature vector of the m-dimensional features, calculating an information contribution rate and an accumulated contribution rate of the feature value, and mapping the features to a p dimension by utilizing orthogonal change according to the information contribution rate and the accumulated contribution rate, wherein p is less than m.
4. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the specific process of determining the vehicle state of the corresponding commercial vehicle according to the travel and the driving data related to other vehicle states includes: and determining the vehicle state according to the total travel of the commercial vehicle, the total time length of transportation and the vehicle maintenance record.
5. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the specific process of preprocessing the driving road and environment information comprises the following steps: and cleaning, screening and combining the data, and connecting the data tables according to accident numbers.
6. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the risk source indexes of the running road and the environmental information comprise at least one part of parameters of whether dangerous goods are transported or not, road intersections, road line shapes, road gradients, road sharp turns, road pavement states, whether traffic control equipment exists or not, time, weather conditions and illumination conditions.
7. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the concrete process for determining the probability of accidents caused by the corresponding road and environmental risk sources and the possible economic loss by using the calculation model comprises the following steps: the method comprises the steps of extracting casualty conditions and vehicle damage conditions of each accident by utilizing historical accident data under corresponding roads and environmental conditions, applying an incident loss consequence calculation model, and quantifying the severity of the traffic accident into economic loss by combining local social and economic conditions, relevant legal regulations and relevant research data.
8. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the concrete process of quantifying the road and environmental risks according to the calculated values comprises the following steps: according to the probability of accidents caused by the risk source and the economic loss caused by the accidents, the possibility and the severity of the accidents caused by the risk source are divided into different grades, corresponding risk evaluation indexes are respectively given, the objective weight of each index is calculated by combining an entropy weight method, and the vehicle transportation risk grade is determined.
9. The method as claimed in claim 1, wherein the method for monitoring transportation of operating vehicles based on multi-data fusion comprises: the specific process of comprehensively analyzing the driving style, the vehicle state and the risks on the road and the environment comprises the following steps: respectively establishing statistical data reference pages according to the driving style, the vehicle state and the risks on the road and the environment, and displaying the statistical data reference pages on corresponding pages according to the risk order;
or giving a risk coefficient to each type of risk, comprehensively calculating the risk values in multiple directions to further obtain a comprehensive risk value, and displaying the transportation risk of the commercial vehicle according to the comprehensive risk value sequence.
10. The utility model provides an operation vehicle transportation monitored control system based on multidata fuses which characterized by: the method comprises the following steps:
the transportation data acquisition module is configured to acquire relevant historical driving data of the commercial vehicle including speed, acceleration, yaw rate, travel and impact degree, divide the data of each vehicle according to continuous travel and vehicle ID, and respectively combine different driving data of the same vehicle and a driver;
the driving style classification module is configured to perform dimension reduction processing on different driving data of the same driver, calculate an information contribution value of each type of driving data to the driving style, give a weight to each driving data according to the information contribution value, and classify the driving style by using a classification model;
the vehicle state determination module is configured to preprocess different driving data of the same vehicle and determine the vehicle state of the corresponding commercial vehicle according to the travel and the driving data related to other vehicle states;
the driving risk calculation module is configured to acquire road related information of a pre-driving route, acquire environmental information of pre-driving time, preprocess driving road and environmental information, determine probability of accidents caused by corresponding road and environmental risk sources and possible economic loss by using a calculation model, and quantify road and environmental risks according to calculated values;
and the comprehensive monitoring module is configured to comprehensively analyze the driving style, the vehicle state and the risks on roads and environments by using a logistic regression analysis method, determine the transportation risk of the operating vehicle, and perform networking early warning and supervision according to the transportation risk.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111275618.5A CN114168646A (en) | 2021-10-29 | 2021-10-29 | Multi-data fusion-based commercial vehicle transportation monitoring method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111275618.5A CN114168646A (en) | 2021-10-29 | 2021-10-29 | Multi-data fusion-based commercial vehicle transportation monitoring method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114168646A true CN114168646A (en) | 2022-03-11 |
Family
ID=80477820
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111275618.5A Pending CN114168646A (en) | 2021-10-29 | 2021-10-29 | Multi-data fusion-based commercial vehicle transportation monitoring method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114168646A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114612016A (en) * | 2022-05-10 | 2022-06-10 | 浪潮通信技术有限公司 | Method and system for supervising safety of commercial vehicle |
| CN115662143A (en) * | 2022-11-21 | 2023-01-31 | 吉林大学 | Dynamic prediction system and method for operation safety situation of public transport enterprise |
| CN116109145A (en) * | 2023-04-10 | 2023-05-12 | 天津所托瑞安汽车科技有限公司 | Risk assessment method, risk assessment device, risk assessment terminal and risk assessment storage medium for vehicle driving route |
| CN116911610A (en) * | 2023-07-20 | 2023-10-20 | 上海钢联物流股份有限公司 | Method and system for monitoring, evaluating and early warning of driving safety risk of transport vehicle |
| CN117549913A (en) * | 2024-01-11 | 2024-02-13 | 交通运输部水运科学研究所 | Safe driving early warning system for mixed flow of port and district tank truck |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105070097A (en) * | 2015-07-16 | 2015-11-18 | 山东交通学院 | Risk recognition method for operating vehicle road traffic accidents |
| US20160189303A1 (en) * | 2014-03-21 | 2016-06-30 | Gil Emanuel Fuchs | Risk Based Automotive Insurance Rating System |
| CN110120153A (en) * | 2019-05-24 | 2019-08-13 | 广州公交集团第三公共汽车有限公司 | A kind of public transport drives accident risk assessment system and its method |
| CN112419719A (en) * | 2020-11-18 | 2021-02-26 | 济南北方交通工程咨询监理有限公司 | Method and system for evaluating traffic operation safety of highway |
| CN113065804A (en) * | 2021-04-27 | 2021-07-02 | 山东交通学院 | Hazardous chemical substance road transportation risk assessment method and system |
-
2021
- 2021-10-29 CN CN202111275618.5A patent/CN114168646A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20160189303A1 (en) * | 2014-03-21 | 2016-06-30 | Gil Emanuel Fuchs | Risk Based Automotive Insurance Rating System |
| CN105070097A (en) * | 2015-07-16 | 2015-11-18 | 山东交通学院 | Risk recognition method for operating vehicle road traffic accidents |
| CN110120153A (en) * | 2019-05-24 | 2019-08-13 | 广州公交集团第三公共汽车有限公司 | A kind of public transport drives accident risk assessment system and its method |
| CN112419719A (en) * | 2020-11-18 | 2021-02-26 | 济南北方交通工程咨询监理有限公司 | Method and system for evaluating traffic operation safety of highway |
| CN113065804A (en) * | 2021-04-27 | 2021-07-02 | 山东交通学院 | Hazardous chemical substance road transportation risk assessment method and system |
Non-Patent Citations (1)
| Title |
|---|
| 李镇;张伟;李永建;: "高速公路主动交通安全驾驶辅助系统", 中国交通信息化, no. 1, 3 April 2018 (2018-04-03) * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114612016A (en) * | 2022-05-10 | 2022-06-10 | 浪潮通信技术有限公司 | Method and system for supervising safety of commercial vehicle |
| CN115662143A (en) * | 2022-11-21 | 2023-01-31 | 吉林大学 | Dynamic prediction system and method for operation safety situation of public transport enterprise |
| CN116109145A (en) * | 2023-04-10 | 2023-05-12 | 天津所托瑞安汽车科技有限公司 | Risk assessment method, risk assessment device, risk assessment terminal and risk assessment storage medium for vehicle driving route |
| CN116109145B (en) * | 2023-04-10 | 2023-06-20 | 天津所托瑞安汽车科技有限公司 | Risk assessment method, risk assessment device, risk assessment terminal and risk assessment storage medium for vehicle driving route |
| CN116911610A (en) * | 2023-07-20 | 2023-10-20 | 上海钢联物流股份有限公司 | Method and system for monitoring, evaluating and early warning of driving safety risk of transport vehicle |
| CN117549913A (en) * | 2024-01-11 | 2024-02-13 | 交通运输部水运科学研究所 | Safe driving early warning system for mixed flow of port and district tank truck |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114168646A (en) | Multi-data fusion-based commercial vehicle transportation monitoring method and system | |
| Ma et al. | Driving style recognition and comparisons among driving tasks based on driver behavior in the online car-hailing industry | |
| Arbabzadeh et al. | A data-driven approach for driving safety risk prediction using driver behavior and roadway information data | |
| CN112508392B (en) | Dynamic evaluation method for traffic conflict risk of hidden danger road section of mountain area double-lane highway | |
| Qu et al. | Feature recognition of urban road traffic accidents based on GA-XGBoost in the context of big data | |
| CN110796859A (en) | Real-time traffic state identification and accident risk early warning method based on traffic flow | |
| CN107918921A (en) | Criminal case court verdict measure and system | |
| CN109408557B (en) | Traffic accident cause analysis method based on multiple correspondences and K-means clustering | |
| Momeni et al. | Clustering stock market companies via k-means algorithm | |
| CN110826848A (en) | Driver risk assessment method based on analytic hierarchy process | |
| Zhang et al. | A proactive crash risk prediction framework for lane-changing behavior incorporating individual driving styles | |
| CN111563555A (en) | Driver driving behavior analysis method and system | |
| Wang et al. | Driving behavior clustering for hazardous material transportation based on genetic fuzzy C-means algorithm | |
| CN110570655A (en) | Vehicle feature evaluation method based on hierarchical clustering and decision tree | |
| CN114971009A (en) | Vehicle insurance risk prediction method and computer equipment | |
| Zhang et al. | A road traffic accidents prediction model for traffic service robot | |
| Zhang | Research on risk projection of urban road traffic safety based on RS-SVM combination model. | |
| CN110263074B (en) | Method for mining illegal accident corresponding relation based on LLE and K mean value method | |
| Gürbüz et al. | Classification rule discovery for the aviation incidents resulted in fatality | |
| Beshah et al. | Knowledge discovery from road traffic accident data in Ethiopia: Data quality, ensembling and trend analysis for improving road safety | |
| CN116432864A (en) | Prediction method and system for regional operation driver group security situation | |
| Chen et al. | The impact of truck proportion on traffic safety using surrogate safety measures in China | |
| Habibzadeh et al. | Presentation of machine learning approaches for predicting the severity of accidents to propose the safety solutions on rural roads | |
| Yokoyama et al. | Do drivers' behaviors reflect their past driving histories?-large scale examination of vehicle recorder data | |
| Shaon et al. | Crash data-based investigation into how injury severity is affected by driver errors |
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 |