Traffic accident analysis method and system based on multivariate data

Abstract

The invention relates to the technical field of traffic accident analysis, in particular to a traffic accident analysis method and system based on multivariate data, and the method comprises the steps: determining influence factors of historical traffic accidents according to a correlation analysis result, and forming an influence factor set; determining an actual influence factor set according to a principal component analysis method; the characterization tendency of the current traffic accident is determined according to the actual influence factor set so as to control the acquisition unmanned aerial vehicle to acquire the traffic video of the corresponding highway section, and the driving data set of each driving vehicle is determined so as to determine the driving characterization tendency of any driving vehicle; locking the position of the driving vehicle on the congested road section according to the driving data of the driving vehicle with the recessive stable trend, and controlling the flight preset position of the communication unmanned aerial vehicle to collect a congestion video in combination with the position relationship of the congested road section so as to determine the congestion reason; the accident influence factors are analyzed according to the historical traffic accidents, and the accident tendency is predicted in combination with the real-time traffic characteristics, so that the timeliness of the traffic accidents is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic accident analysis, and in particular to a traffic accident analysis method and system based on multivariate data. Background Art

[0002] With the increase in traffic volume on highways, the frequency of traffic accidents has also increased, posing a huge challenge to traffic safety and traffic management; traditional traffic accident analysis methods are often based on a single data source or simple statistical analysis, and have the following limitations: relying solely on limited data sources such as accident site reports and traffic police records, it is impossible to fully reflect the complex environment and multiple influencing factors of traffic accidents. For example, factors such as weather conditions, road facilities, and vehicle driving conditions may not be fully considered; it is difficult to obtain traffic information in real time and analyze potential accident risks in a timely manner. Usually, investigations and analyses are conducted after the accident occurs, and effective preventive measures cannot be taken before the accident occurs, resulting in the inability to avoid accidents or mitigate the impact of accidents in a timely manner; the analysis method used is relatively simple and cannot handle complex multivariate data. It is difficult to accurately identify the degree of influence of different factors on traffic accidents, and it is also difficult to accurately predict and evaluate traffic conditions, which affects the traffic management department's formulation of scientific and effective traffic management strategies and emergency measures.

[0003] Chinese patent announcement number CN108417033B discloses a high-speed traffic accident analysis and prediction method based on multi-dimensional factors, which includes the following steps: establishing a database based on historical traffic accident data and historical daily record data; selecting traffic accident types and corresponding daily record data from the database to obtain multi-dimensional influencing factor data of traffic accidents; establishing a Bayesian network for the multi-dimensional influencing factor data to obtain the probability of each factor affecting the traffic accident, and use it as a prediction model; predicting high-speed traffic accidents based on the prediction model and real-time data. The invention can pre-process and convert historical traffic accident data, analyze and use the multi-dimensional influencing factors of traffic accidents to establish a corresponding Bayesian network to form a prediction model for traffic accidents, use data mining technology to find out the probability relationship between the multi-dimensional factors that affect traffic accidents, and use real-time observation data based on the results of the analysis to predict whether an accident will occur. It can be seen that the prior art has the following problems: Existing technologies are unable to analyze accident influencing factors based on historical traffic accidents and are unable to predict accident tendencies based on real-time traffic characteristics, which leads to the problem of untimely handling after a traffic accident occurs. Summary of the invention

[0004] To this end, the present invention provides a traffic accident analysis method and system based on multivariate data to overcome the problem in the prior art that it is impossible to analyze accident influencing factors based on historical traffic accidents and to predict accident tendencies based on real-time traffic characteristics, thereby leading to untimely handling of traffic accidents.

[0005] To achieve the above object, on the one hand, the present invention provides a traffic accident analysis method based on multivariate data, comprising: Obtaining the historical traffic accident congestion rate of the expressway section and its corresponding traffic accident characteristics, and determining the influencing factors of the historical traffic accident according to the correlation analysis results of each of the traffic accident characteristics and the corresponding historical traffic accident congestion rate, and forming an influencing factor set; Determine the contribution rate and principal component characteristics of each influencing factor in the influencing factor set according to the principal component analysis method, so as to determine the influencing factor contribution set and principal component characteristic set corresponding to the historical traffic accidents; The actual influencing factors affecting the traffic accidents on the expressway section are determined according to the intersection of the principal component feature sets of each historical traffic accident to determine the actual influencing factor set; Obtain the specific value of each influencing factor in the influencing factor set in real time to determine the real-time contribution rate of each influencing factor, and determine the characterization tendency of the current traffic accident according to the real-time cumulative contribution rate of the actual influencing factor set; According to the determination result of the characterization tendency, a plurality of collecting drones are controlled to take off in sequence and collect traffic videos of corresponding highway sections respectively; Determine a driving data group of each driving vehicle based on a single traffic video to determine a driving characteristic trend of any driving vehicle; In response to the existence of a congested road section, the position of the vehicle with an implicit stable trend in the congested road section is locked according to the driving data of the vehicle with an implicit stable trend; According to the position relationship between the driving vehicle position of the implicit stable trend and the congested road section, the communication drone is controlled to fly to a preset position to collect congestion video to determine whether the cause of the congestion is a traffic accident; The driving data group includes the driving speed, the driving speed difference with the preceding vehicle during driving, and whether the vehicle is overtaking / changing lanes; The driving characterization trend includes an explicit stable trend and an implicit stable trend.

[0006] Furthermore, the traffic accident characteristics include traffic accident environment characteristics and traffic accident types; The traffic accident environment characteristics include weather, visibility, time period, road section, road condition, lighting, whether it is a holiday, vehicle speed and traffic volume; The types of traffic accidents include rear-end collisions, lane change / overtaking accidents, single-vehicle accidents and multi-vehicle chain accidents.

[0007] Further, determining characteristic variables related to the traffic accident according to the Pearson correlation coefficient between the historical traffic accident and each of the traffic accident characteristics, determining the related characteristic variables as a set of influencing factors of the traffic accident and recording the data corresponding to each influencing factor as influencing factor data of the traffic accident; Among them, if the absolute value of the Pearson correlation coefficient between a single traffic accident feature and the traffic accident is greater than a preset value, it is determined that the traffic accident feature is related to the traffic accident and is recorded as an influencing factor.

[0008] Furthermore, the contribution rate of each influencing factor in the influencing factor set is determined according to the principal component analysis method, and each influencing factor whose cumulative contribution rate is greater than or equal to the preset contribution rate is determined as the principal component feature.

[0009] Furthermore, the specific value of each influencing factor in the influencing factor set is obtained in real time to determine the real-time contribution rate of each influencing factor according to the principal component analysis method, and the characterization tendency of the current traffic accident is determined according to the real-time cumulative contribution rate of the actual influencing factor set, wherein, If the real-time cumulative contribution rate is greater than or equal to the preset cumulative contribution rate, it is determined that the current traffic accident representation tendency is an occurrence tendency; If the real-time cumulative contribution rate is less than the preset cumulative contribution rate, it is determined that the current traffic accident characterization tendency is a non-occurrence tendency.

[0010] Further, according to the determination result that the tendency is characterized as an occurrence tendency, a plurality of collecting drones are controlled to take off in sequence and collect traffic videos of corresponding highway sections respectively; The number of the collection drones is at least 3, and the take-off time intervals of the collection drones are equal and greater than a preset time length.

[0011] Furthermore, the flight direction of the collection drone is opposite to the travel direction of the moving vehicle.

[0012] Further, the driving data of each driving vehicle is determined based on the single traffic video to determine the driving characteristic trend of any driving vehicle, including: Using artificial intelligence software to determine the driving data group of each driving vehicle based on the single traffic video; Determine the difference between each driving data in a plurality of driving data groups determined by a single driving vehicle according to each traffic video; The driving characterization trend of the corresponding vehicle is determined according to the difference between each driving data, where: If the differences of the driving data are all less than or equal to the preset differences, it is determined that the driving characteristic trend of the driving vehicle is a dominant stable trend; If there is any driving data whose difference is greater than a preset difference, it is determined that the driving characteristic trend of the driving vehicle is a hidden stable trend.

[0013] Further, according to the position relationship between the driving vehicle position of the implicit stable trend and the congested road section, the communication drone is controlled to fly to a preset position and a congestion video is collected at the preset position, including: If the position of the moving vehicle with an implicit stable trend is before the target position of the congested road section, the flight preset position of the control communication drone is above the position of the moving vehicle; If the position of the driving vehicle with an implicit stable trend is not before the target position of the congested road section, the preset flight position of the control communication drone is the target position of the congested road section; The target location is located at one quarter of the congested road section.

[0014] On the other hand, the present invention also provides a traffic accident analysis system based on multivariate data, comprising: The data collection module includes a retrieval unit for obtaining the historical traffic accident congestion rate of the expressway section and its corresponding traffic accident characteristics, a collection unit for obtaining the specific values ​​of each influencing factor in the influencing factor set in real time, and a networking unit for determining whether there is a congested section; A data analysis module, which is connected to the data acquisition module, is used to determine the influencing factors of the historical traffic accident and form an influencing factor set according to the correlation analysis results of each of the traffic accident characteristics and the corresponding historical traffic accident congestion rate, determine the contribution rate and principal component characteristics of each influencing factor in the influencing factor set according to the principal component analysis method to determine the influencing factor contribution set and principal component characteristic set of the corresponding historical traffic accident, and determine the actual influencing factors that affect the traffic accident on the expressway section according to the intersection of the principal component characteristic sets of each historical traffic accident to determine the actual influencing factor set; A real-time analysis module, which is connected to the data acquisition module and the data analysis module respectively, and is used to determine the real-time contribution rate of each influencing factor according to the specific value of each real-time influencing factor, determine the characterization tendency of the current traffic accident according to the real-time cumulative contribution rate of the actual influencing factor set, control a number of collection drones to take off in sequence and collect traffic videos of corresponding highway sections respectively according to the determination result of the characterization tendency, and determine the driving data group of each driving vehicle according to a single traffic video to determine the driving characterization trend of any driving vehicle; The analysis and determination module is respectively connected to the real-time analysis module and the data acquisition module, and is used to respond to the existence of a congested road section and lock the position of the vehicle with an implicit stable trend in the congested road section according to the driving data of the vehicle with an implicit stable trend, and control the communication drone to fly at a preset position to collect congestion video according to the positional relationship between the position of the vehicle with the implicit stable trend and the congested road section, so as to determine whether the cause of the congestion is a traffic accident.

[0015] Compared with the prior art, the beneficial effect of the present invention lies in that the traffic accident analysis method based on multivariate data provided by the present invention comprehensively uses multivariate data and advanced technologies, first determines the influencing factors and contribution sets through correlation analysis and principal component analysis, then judges the accident characterization tendency in combination with real-time data, and then uses drones to collect videos to obtain vehicle driving data, thereby predicting the vehicle position, locking the specific vehicle position in the congested section, and finally collecting congestion videos to analyze the cause of the accident; the method can accurately identify the factors affecting traffic accidents, monitor the accident tendency in real time, and efficiently obtain traffic information, providing a comprehensive and effective solution for the prevention and handling of traffic accidents, and improving the scientificity, accuracy and timeliness of traffic management; Furthermore, by obtaining the specific values ​​of influencing factors in real time, using principal component analysis to determine the real-time contribution rate, and then comparing the real-time cumulative contribution rate of the actual influencing factor set with the preset cumulative contribution rate, the characterization tendency of the current traffic accident can be determined. Based on historical data and real-time dynamic information, the risk of traffic accidents can be accurately and timely assessed, providing strong data support for traffic management decisions, and effectively improving the foresight and scientific nature of traffic management; Furthermore, based on the result of the determination of the tendency of traffic accidents, at least three collecting drones are controlled to take off in sequence at equal time intervals greater than a preset time length to collect traffic videos of the corresponding expressway section; at the same time, multiple parking points with at least two drones are reasonably distributed along the expressway section, and the distance between the parking points is adjusted according to the frequency of accidents on the road section; this arrangement can make use of the monitoring of multiple drones at different time points, use advanced models to predict and analyze traffic conditions, so as to more accurately grasp the current traffic situation, make predictions and responses to traffic accidents in a timely manner, and improve the timeliness and effectiveness of traffic management; Furthermore, artificial intelligence software is used to determine the vehicle driving data group from a single traffic video, calculate the difference between each driving data, and determine the vehicle driving performance trend based on the difference and the speed difference with the preceding vehicle. This process can clearly distinguish the vehicle driving status and accurately identify vehicles with potential traffic impact risks, providing a refined vehicle behavior analysis basis for traffic management, helping to predict traffic congestion and accident risks in advance, and improving the accuracy and effectiveness of traffic management. Furthermore, based on the positional relationship between vehicles with an implicit stable trend and the target position of the congested section, the communication drone can be flexibly controlled to fly at a preset position to collect congestion videos and transmit them to the traffic management center in real time. This measure can quickly provide traffic management personnel with clear and targeted congestion site information, helping them to accurately grasp the traffic conditions, so as to formulate response strategies in a timely and effective manner and improve the efficiency of traffic congestion management. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 A step diagram of a traffic accident analysis method and system based on multivariate data according to an embodiment of the present invention; Figure 2 A flow chart for determining an actual influencing factor set for an embodiment of the present invention; Figure 3 A flow chart of determining a driving characterization trend of a moving vehicle according to an embodiment of the present invention; Figure 4 It is a connection diagram of the traffic accident analysis system based on multivariate data according to an embodiment of the present invention. DETAILED DESCRIPTION

[0017] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0018] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0019] It should be noted that, in the description of the present invention, terms such as "up", "down", "left", "right", "inside" and "outside" indicating directions or positional relationships are based on the directions or positional relationships shown in the drawings. This is merely for the convenience of description and does not indicate or imply that the device or element must have a specific orientation, be constructed and operated in a specific orientation. Therefore, it cannot be understood as a limitation on the present invention.

[0020] In addition, it should be noted that in the description of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", and "connected" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For those skilled in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0021] See also Figure 1As shown, it is a step diagram of a traffic accident analysis method and system based on multivariate data in an embodiment of the present invention. An embodiment of the present invention provides a traffic accident analysis method based on multivariate data, comprising: Step S1, obtaining the historical traffic accident congestion rate of the expressway section and several corresponding traffic accident features, and determining the influencing factors of the historical traffic accident according to the correlation analysis results between each of the traffic accident features and the corresponding historical traffic accident congestion rate, and forming an influencing factor set; it can be understood that, according to the conceivable traffic accident features, the correlation between each feature and the traffic accident is determined, and the relevant features and irrelevant features can be determined, and the relevant features are recorded as influencing factors, and the corresponding data can be collected in real time for subsequent analysis of the occurrence tendency of traffic accidents; Step S2, determining the contribution rate and principal component characteristics of each influencing factor in the influencing factor set according to the principal component analysis method (determining the principal component characteristics according to the contribution rate of each influencing factor) to determine the influencing factor contribution set and the principal component characteristic set corresponding to the historical traffic accident; it can be understood that by determining the contribution rate of each influencing factor according to the principal component analysis method, the contribution rate of each influencing factor can be determined; in implementation, the principal component analysis method is an existing technology, so how to calculate it will not be described in detail; Step S3, determining the actual influencing factors affecting the traffic accidents on the expressway section according to the intersection of the principal component feature sets of each historical traffic accident as the actual influencing factors to determine the actual influencing factor set; it can be understood that several principal component features with lower contribution rates in the principal component feature sets of each historical traffic accident may have slight differences, indicating that several principal component features have relatively weak actual impacts on each traffic accident, therefore, the intersection of the principal component feature sets is determined as the actual influencing factor set; Step S4, obtaining in real time the specific value of each influencing factor in the influencing factor set (recorded as real-time influencing factor data) to determine the real-time contribution rate of each influencing factor, and determining the characterization tendency of the current traffic accident according to the real-time cumulative contribution rate of the actual influencing factor set; Step S5, controlling a plurality of collecting drones to take off in sequence and collect traffic videos of corresponding highway sections respectively according to the determination result of the characterization tendency; Step S6, determining a driving data group of each driving vehicle based on the single traffic video to determine a driving characteristic trend of any driving vehicle; Step S7, in response to the existence of a congested road section (in implementation, whether it is congested can be determined according to any navigation software), the position of the vehicle with an implicit stable trend in the congested road section is locked according to the driving data of the vehicle with an implicit stable trend; it can be understood that according to the video taken by each drone and the position and speed of a single vehicle when shooting, the position of the vehicle at a future time point can be predicted by AI, GPT, and a trained machine learning model; this is a prior art, so it will not be repeated; Step S8, controlling the communication drone to fly to a preset position to collect congestion video according to the position relationship between the position of the traveling vehicle with the implicit stable trend and the congested road section, so as to determine whether the cause of the congestion is a traffic accident; The driving data group includes driving speed, driving speed difference with the preceding vehicle during driving, and whether overtaking / lane changing is continuous; it is understood that the driving speed difference with the preceding vehicle = the driving speed of the preceding vehicle - the driving speed of the vehicle, it is understood that the driving speed difference with the preceding vehicle can be positive or negative, a positive value represents that the driving speed of the preceding vehicle is greater than the driving speed of the vehicle, and a negative value represents that the driving speed of the preceding vehicle is less than the driving speed of the vehicle; it is understood that if the driving speed of the vehicle is too slow, it is easy to cause the lane change of the vehicle behind, and it is easy to cause congestion; The driving characterization trend includes an explicit stable trend and an implicit stable trend.

[0022] It can be understood that (1) by conducting a correlation analysis on the historical traffic accident congestion rate of the expressway section and multiple traffic accident characteristics, the factors that really affect the traffic accidents can be effectively screened out to form an influencing factor set, and then the principal component analysis is used to determine the contribution rate and principal component characteristics of each influencing factor, and further find out the actual influencing factor set to avoid the interference of irrelevant factors, making the analysis results more targeted and accurate, and helping to gain a deeper understanding of the causes of traffic accidents; (2) by obtaining the specific values ​​of each influencing factor in the influencing factor set in real time, calculating the real-time contribution rate, and determining the characterization tendency of the current traffic accident based on the real-time cumulative contribution rate of the actual influencing factor set, this enables the traffic management department to promptly grasp the possibility of an accident, take preventive measures in advance, and reduce the probability of traffic accidents. ; (3) Use drones to collect traffic videos of highway sections, and determine the driving data group and driving characterization trend of the vehicles based on the videos. This method can quickly and comprehensively obtain traffic information, avoid the limitations of traditional manual monitoring methods, and improve the efficiency and accuracy of information collection; (4) After discovering a congested section, it can predict its future position based on the driving data of the vehicles, and lock the position of the vehicles with hidden stable trends in the congested section, which helps to quickly find the source vehicles that may cause congestion and provide strong support for subsequent traffic diversion and accident handling; (5) Through the communication drone to collect congestion videos at a preset location, combined with vehicle driving data and driving characterization trends, it can accurately determine whether the cause of congestion is a traffic accident, and deeply analyze the cause of the accident. This provides a basis for formulating targeted traffic management strategies and accident handling plans, and improves the scientificity and effectiveness of traffic management.

[0023] Specifically, in step S1, the traffic accident characteristics include traffic accident environment characteristics and traffic accident type; The traffic accident environment characteristics include weather, visibility, time period, road section, road condition, lighting, whether it is a holiday, vehicle speed and traffic volume; The types of traffic accidents include rear-end collisions, lane change / overtaking accidents, single-vehicle accidents and multi-vehicle chain accidents.

[0024] See also Figure 2 As shown, it is a flow chart of determining the actual influencing factor set according to an embodiment of the present invention. Specifically, in step S1, it includes: step S11, determining the characteristic variables related to the traffic accident according to the Pearson correlation coefficient between the historical traffic accident and each of the traffic accident characteristics; step S12, determining the relevant characteristic variables as the influencing factor set of the traffic accident and recording the data corresponding to each influencing factor as the influencing factor data of the traffic accident; Among them, if the absolute value of the Pearson correlation coefficient between a single traffic accident feature and the traffic accident is greater than a preset value, it is determined that the traffic accident feature is related to the traffic accident and is recorded as an influencing factor.

[0025] It is understandable that the calculation method of the Pearson correlation coefficient is a prior art, so it will not be described in detail.

[0026] In implementation, the preset value is ≥ 0.5; it is understandable that when the preset value is around 0.3, it is generally considered to be a low correlation, indicating that there is a certain linear relationship between the variables, but the relationship is relatively weak; if the research does not have very high requirements for correlation, or is just a preliminary exploratory analysis, 0.3 may be used as the judgment threshold; around 0.5 is usually regarded as a moderate correlation, at which time the linear relationship between the variables is more obvious. In some studies with slightly higher requirements, 0.5 will be used as the boundary, and only when it is greater than 0.5 will the traffic accident feature be considered an influencing factor, so that factors with a stronger correlation with the accident can be screened out; 0.7 and above are considered to be highly correlated, indicating that there is a strong linear relationship between the variables; taking 0.7 as the preset value, only when the Pearson correlation coefficient reaches this level will it be determined that the feature is significantly correlated with the traffic accident and recorded as an influencing factor.

[0027] It is understandable that the larger the preset value is, the stronger the correlation between the determined influencing factors and the congestion rate is. However, the principal component analysis method is required to determine the contribution rate of each influencing factor in the future, and a secondary determination will be performed. Therefore, the preset value here does not need to be too large; preferably, the preset value = 0.6. Specifically, in step S2, the contribution rate of each influencing factor in the influencing factor set is determined according to the principal component analysis method, and each influencing factor whose cumulative contribution rate is greater than or equal to the preset contribution rate is determined as the principal component feature.

[0028] In practice, the preset contribution rate is ≥ 80%; (1) When the cumulative contribution rate is 80%, it means that the extracted principal components can explain 80% of the information of the original data. This value is relatively loose and is suitable for those who want to reduce the number of principal components as much as possible while retaining most of the data information to simplify data analysis and interpretation. In some preliminary exploratory studies, the requirements for data dimensionality reduction are not particularly strict. An 80% cumulative contribution rate can help quickly find the main influencing factors and provide direction for subsequent in-depth research. (2) 85% is a relatively moderate choice, which strikes a good balance between retaining data information and reducing the number of principal components. In most practical applications, this value can ensure that the extracted principal components can fully reflect the original data. The main features of the data will not be too many principal components, which makes it easier to analyze and understand the data. In the fields of market research data analysis, traffic flow characteristics analysis, etc., an 85% cumulative contribution rate can usually meet research needs and help researchers identify key influencing factors or features. (3) A 90% cumulative contribution rate is more stringent, requiring that the extracted principal components can explain 90% of the information of the original data. This value is suitable for situations where high requirements for data information retention are required, such as in some high-precision scientific research, engineering data analysis, or fields with strict requirements on the accuracy of the results, such as aerospace, medical imaging analysis, etc. It is necessary to retain the information of the original data as comprehensively as possible to ensure the reliability and accuracy of the analysis results. Therefore, preferably, the preset contribution rate = 85%.

[0029] Specifically, in step S4, the specific value of each influencing factor in the influencing factor set is obtained in real time to determine the real-time contribution rate of each influencing factor according to the principal component analysis method, and the characterization tendency of the current traffic accident is determined according to the real-time cumulative contribution rate of the actual influencing factor set, wherein: If the real-time cumulative contribution rate is greater than or equal to the preset cumulative contribution rate, it is determined that the current traffic accident representation tendency is an occurrence tendency; If the real-time cumulative contribution rate is less than the preset cumulative contribution rate, it is determined that the current traffic accident characterization tendency is a non-occurrence tendency.

[0030] It is understandable that each historical traffic accident will have its own actual cumulative contribution rate (all greater than the preset contribution rate) when conducting principal component analysis. The value of the preset cumulative contribution rate is determined based on the average value and standard deviation of the cumulative contribution rate of each traffic accident. The difference between the average value and the standard deviation of the cumulative contribution rate of each traffic accident ≤ the preset cumulative contribution rate ≤ the sum of the average value and the standard deviation of the cumulative contribution rate of each traffic accident. Generally, the preset cumulative contribution rate = the average value of the cumulative contribution rate of each traffic accident.

[0031] It can be understood that (1) real-time acquisition of the specific values ​​of each influencing factor in the influencing factor set can keep up with the dynamic changes of traffic conditions. Compared with relying solely on historical data, this method can timely capture the real-time status of various factors affecting traffic accidents in the current traffic environment, provide the latest information for real-time assessment of traffic accident risks, and make the assessment results more in line with actual traffic scenarios; (2) principal component analysis is a scientific and effective data dimensionality reduction and analysis method. It can extract key information from complex multivariate data and quantify the impact of various factors on traffic accidents, so that the judgment of the characterization tendency of traffic accidents has a scientific and quantitative basis and avoids the bias of subjective judgment; (3) the preset cumulative contribution rate is determined according to the average value and standard deviation of the cumulative contribution rate of each historical traffic accident, and the preset cumulative contribution rate is usually set as the average value of the cumulative contribution rate of each traffic accident. This setting method not only refers to the overall characteristics of the historical data, but also takes into account the discrete degree of the data (reflected by the standard deviation), so that the preset cumulative contribution rate is reasonable and representative; the preset value set based on historical data provides a reliable reference standard for the comparison of real-time cumulative contribution rate, which can more accurately determine the characterization tendency of the current traffic accident.

[0032] Specifically, in step S5, according to the determination result that the characteristic tendency is an occurrence tendency, a plurality of collecting drones are controlled to take off in sequence and collect traffic videos of corresponding highway sections respectively; The number of the collection drones is at least 3, and the take-off time intervals of the collection drones are equal and greater than a preset time. In implementation, 5 min ≤ preset time ≤ 10 min. It is understandable that each drone can record the corresponding traffic driving video during the flight. Multiple drones taking off at the same time interval can predict and analyze the traffic process during this period based on AI, machine learning, GPT and other models, which can provide a clearer understanding of the current traffic conditions and timely prediction and response to traffic accidents.

[0033] During the implementation, several drone parking points for data collection are distributed along the corresponding expressway sections, and each parking point has at least two drones; the distance between any two drone parking points in sections with low traffic accident incidence is greater than 2km, and the distance between any two drone parking points in sections with high traffic accident incidence is greater than 1km.

[0034] It can be understood that (1) multiple drones take off in sequence at time intervals that are equal and greater than the preset time length, and can collect traffic videos of highway sections at different time points; this makes it possible to obtain dynamic information on traffic conditions over a period of time. Compared with monitoring at a single time point, it can provide a more comprehensive and in-depth understanding of the operation of traffic flow, including changes in vehicle speed, lane change frequency, traffic flow changes, etc., providing a rich data foundation for accurate analysis of traffic conditions; (2) Using advanced models such as AI, machine learning, and GPT to analyze traffic videos collected by multiple drones at different time points can more accurately predict traffic development trends: for example, by analyzing the vehicle's driving trajectory and speed changes over a period of time, it is possible to discover potential traffic congestion points or accident hazards in advance, thereby And take corresponding measures in time to effectively prevent the occurrence of traffic accidents and improve the safety and efficiency of traffic operation; (3) Distribute multiple parking points with at least two drones along the expressway, and adjust the distance between the parking points according to the frequency of accidents on the road section. Reduce the distance between the parking points in sections with high traffic accident incidence, which can ensure more intensive monitoring coverage in these areas and capture accidents in time; and appropriately increase the distance between the parking points in sections with low traffic accident incidence, which can not only meet basic monitoring needs, but also reasonably allocate resources, avoid excessive waste of resources, and achieve optimal utilization of resources; (4) Each parking point is equipped with at least two drones. When one of the drones fails or runs out of power, the other can take over the task in time, ensuring the continuity and stability of monitoring work. This greatly improves the reliability of traffic management, ensures that traffic information can be continuously obtained under any circumstances, and provides strong support for traffic management decisions.

[0035] Specifically, in step S5, the flight direction of the data collection drone is opposite to the driving direction of the moving vehicle. It can be understood that the two highway sections in opposite directions (location a→location b, location b→location a) are two sets of identical analysis processes, and this application only considers the highway section in one direction; the traffic accident analysis process in the other direction is the same, but the historical traffic accidents determined in step S1 and their corresponding historical traffic accident congestion rates and traffic accident characteristics are different.

[0036] See also Figure 3 As shown, it is a flow chart of determining the driving characterization trend of a moving vehicle according to an embodiment of the present invention. Specifically, in step S6, the driving data of each moving vehicle is determined according to a single traffic video to determine the driving characterization trend of any moving vehicle, including: Step S61, using artificial intelligence software to determine the driving data group of each driving vehicle based on the single traffic video; it can be understood that three collection drones can obtain three traffic videos, that is, three driving data groups of each driving vehicle can be determined; in practice, each drone is equipped with a wide-angle camera, so that when the drone is flying and the vehicle is driving, it can also capture a continuous video segment of a vehicle; Step S62, determining the difference of each driving data in a plurality of driving data groups determined by a single driving vehicle according to each traffic video; it can be understood that three driving data groups mean that any one driving data of each driving vehicle has three, and then the difference of any corresponding driving data should be two; it can be understood that if there is continuous overtaking / lane change (i.e., lane change / overtaking more than 3 times within 200m), it is determined that the difference of the driving data (whether it is continuous overtaking / lane change) is greater than the preset difference; Step S63, determining the driving characteristic trend of the corresponding vehicle according to the difference between the driving data and the driving speed difference with the preceding vehicle, wherein: If the difference between each driving data is less than or equal to the preset difference and the driving speed difference with the preceding vehicle is less than or equal to the preset speed difference, it is determined that the driving characteristic trend of the driving vehicle is a dominant stable trend; If the difference of any driving data is greater than a preset difference and / or the driving speed difference of the preceding vehicle is greater than a preset speed difference, it is determined that the driving characteristic trend of the driving vehicle is a hidden stable trend; In implementation, the difference is expressed as a percentage, the difference of driving speed = (adjacent and rear driving speed - adjacent and front driving speed) ÷ adjacent and front driving speed × 100%, the difference of driving speed difference = (adjacent and rear driving speed difference - adjacent and front driving speed difference) ÷ adjacent and front driving speed difference × 100%; generally, the preset difference ∈ [10%, 20%], preferably set to 15%; In practice, if the vehicle travels too slowly, it is easy to cause the vehicle behind to change lanes and cause congestion. If the difference with the vehicle in front is too large, it means that the congestion may start from this vehicle. The preset speed difference is 10 km / h to 20 km / h; preferably, it is set to 15 km / h.

[0037] It can be understood that (1) with the help of artificial intelligence software to process and collect traffic videos taken by drones, the driving data group of each moving vehicle can be quickly and accurately determined, especially the continuous video segments obtained by multiple drones equipped with wide-angle cameras, which can ensure the comprehensive capture of vehicle driving data, greatly improve the efficiency of data collection, and provide a rich and accurate data basis for subsequent analysis. Compared with traditional manual collection methods, it greatly saves manpower and time costs; (2) by calculating the difference between each driving data, the change of vehicle driving state is quantified, and a reasonable preset difference range is set, which can be used as a quantitative standard for judging whether the vehicle driving state is stable, providing a scientific basis for accurately judging the driving characterization trend; (3) according to the difference between each driving data and the driving state of the preceding vehicle, the driving state of the preceding vehicle can be accurately determined. The speed difference is based on the driving data, and a clear driving trend judgment rule is formulated. When the difference between the driving data is small and the speed difference with the preceding vehicle is small, it is judged as an explicit stable trend, indicating that the vehicle is in a stable driving state; when the data difference is large or the speed difference is large, it is judged as a hidden stable trend, which means that there are unstable factors in vehicle driving, which may affect traffic. This accurate judgment method helps to timely discover potential traffic risk sources; (4) Predict traffic congestion and accident risks in advance based on the driving trend of vehicles. When a large number of vehicles show a hidden stable trend, especially when the vehicle is driving too slowly or the speed difference with the preceding vehicle is too large, it can be inferred that it may cause the following vehicles to change lanes frequently, leading to traffic congestion or even accidents. Traffic management departments can take measures in advance based on this.

[0038] Specifically, in step S8, the communication drone is controlled to fly to a preset position and collect congestion video at the preset position according to the position relationship between the driving vehicle position with an implicit stable trend and the congested road section, including: If the position of the driving vehicle with an implicit stable trend is before the target position of the congested road section (i.e., between the starting position of the congestion and the target position), the flight preset position of the control communication drone is above the position of the driving vehicle; If the position of the driving vehicle with an implicit stable trend is not before the target position of the congested road section (i.e., after the target position), the preset flight position of the control communication drone is the target position of the congested road section; Among them, the target position is located at one quarter of the congested road section; that is, the distance between the starting position of the congested road section and the target position is recorded as the first distance, and the distance between the ending position of the congested road section and the target position is recorded as the second distance, and the first distance: the second distance = 1:3.

[0039] It is understandable that communication drones collect congestion videos on site and transmit them to the traffic management center in real time. Connecting with any traffic management personnel, they can enable traffic management personnel to quickly understand current traffic problems and respond.

[0040] During implementation, each drone parking point also includes at least two communication drones, and the communication drones that take off are also determined based on the principle of proximity.

[0041] It can be understood that (1) by setting the target position at one quarter of the congested road section, and determining the preset flight position of the communication drone based on the front-to-back relationship between the vehicle with the implicit stable trend and the target position: if the vehicle is before the target position, the drone is positioned above the vehicle, focusing on the key vehicle that may cause congestion, capturing its driving status and the impact on the surrounding traffic flow; if the vehicle is after the target position, the drone is positioned at the target position of the congested road section, and the core area of ​​the congested road section is fully photographed to ensure that the most valuable congestion information is collected, thereby improving the pertinence and accuracy of video collection; (2) The communication drone collects congestion videos in real time and transmits them to the traffic management center, directly connecting with traffic management personnel, greatly shortening the time. (3) After obtaining real-time and accurate congestion videos, traffic management personnel can clearly and intuitively observe the actual situation of the congested road sections, such as vehicle density, driving direction, road conditions and other details. Based on these detailed information, they can quickly and accurately determine the cause of the congestion and then formulate more targeted response measures, such as arranging police force to guide traffic, adjusting traffic light timing, issuing traffic guidance information, etc., effectively improving the efficiency and effectiveness of traffic congestion management and ensuring smooth traffic on the roads.

[0042] See also Figure 4 As shown, it is a connection diagram of a traffic accident analysis system based on multivariate data according to an embodiment of the present invention. On the other hand, the present invention also provides a traffic accident analysis system based on multivariate data, comprising: The data collection module includes a retrieval unit for obtaining the historical traffic accident congestion rate of the expressway section and its corresponding traffic accident characteristics, a collection unit for obtaining the specific values ​​of each influencing factor in the influencing factor set in real time, and a networking unit for determining whether there is a congested section; A data analysis module, which is connected to the data acquisition module, is used to determine the influencing factors of the historical traffic accident and form an influencing factor set according to the correlation analysis results of each of the traffic accident characteristics and the corresponding historical traffic accident congestion rate, determine the contribution rate and principal component characteristics of each influencing factor in the influencing factor set according to the principal component analysis method to determine the influencing factor contribution set and principal component characteristic set of the corresponding historical traffic accident, and determine the actual influencing factors that affect the traffic accident on the expressway section according to the intersection of the principal component characteristic sets of each historical traffic accident to determine the actual influencing factor set; A real-time analysis module, which is connected to the data acquisition module and the data analysis module respectively, and is used to determine the real-time contribution rate of each influencing factor according to the specific value of each real-time influencing factor, determine the characterization tendency of the current traffic accident according to the real-time cumulative contribution rate of the actual influencing factor set, control a number of collection drones to take off in sequence and collect traffic videos of corresponding highway sections respectively according to the determination result of the characterization tendency, and determine the driving data group of each driving vehicle according to a single traffic video to determine the driving characterization trend of any driving vehicle; The analysis and determination module is respectively connected to the real-time analysis module and the data acquisition module, and is used to respond to the existence of a congested road section and lock the position of the vehicle with an implicit stable trend in the congested road section according to the driving data of the vehicle with an implicit stable trend, and control the communication drone to fly at a preset position to collect congestion video according to the positional relationship between the position of the vehicle with the implicit stable trend and the congested road section, so as to determine whether the cause of the congestion is a traffic accident.

[0043] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0044] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A traffic accident analysis method based on multivariate data, characterized in that: include: Obtaining the historical traffic accident congestion rate of the expressway section and its corresponding traffic accident characteristics, and determining the influencing factors of the historical traffic accident according to the correlation analysis results of each of the traffic accident characteristics and the corresponding historical traffic accident congestion rate, and forming an influencing factor set; Determine the contribution rate and principal component characteristics of each influencing factor in the influencing factor set according to the principal component analysis method, so as to determine the influencing factor contribution set and principal component characteristic set corresponding to the historical traffic accidents; The actual influencing factors affecting the traffic accidents on the expressway section are determined according to the intersection of the principal component feature sets of each historical traffic accident to determine the actual influencing factor set; Obtain the specific value of each influencing factor in the influencing factor set in real time to determine the real-time contribution rate of each influencing factor, and determine the characterization tendency of the current traffic accident according to the real-time cumulative contribution rate of the actual influencing factor set; According to the determination result of the characterization tendency, a plurality of collecting drones are controlled to take off in sequence and collect traffic videos of corresponding highway sections respectively; Determine a driving data group of each driving vehicle based on a single traffic video to determine a driving characteristic trend of any driving vehicle; In response to the existence of a congested road section, the position of the vehicle with an implicit stable trend in the congested road section is locked according to the driving data of the vehicle with an implicit stable trend; According to the position relationship between the driving vehicle position of the implicit stable trend and the congested road section, the communication drone is controlled to fly to a preset position to collect congestion video to determine whether the cause of the congestion is a traffic accident; The driving data group includes the driving speed, the driving speed difference with the preceding vehicle during driving, and whether the vehicle is overtaking / changing lanes; The driving characterization trend includes an explicit stable trend and an implicit stable trend.

2. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: The traffic accident characteristics include traffic accident environment characteristics and traffic accident types; The traffic accident environment characteristics include weather, visibility, time period, road section, road condition, lighting, whether it is a holiday, vehicle speed and traffic volume; The types of traffic accidents include rear-end collisions, lane change / overtaking accidents, single-vehicle accidents and multi-vehicle chain accidents.

3. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: Determine characteristic variables related to the traffic accident according to the Pearson correlation coefficient between the historical traffic accident and each of the traffic accident characteristics, determine the relevant characteristic variables as a set of influencing factors of the traffic accident and record the data corresponding to each influencing factor as influencing factor data of the traffic accident; Among them, if the absolute value of the Pearson correlation coefficient between a single traffic accident feature and the traffic accident is greater than a preset value, it is determined that the traffic accident feature is related to the traffic accident and is recorded as an influencing factor.

4. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: The contribution rate of each influencing factor in the influencing factor set is determined according to the principal component analysis method, and each influencing factor whose cumulative contribution rate is greater than or equal to the preset contribution rate is determined as the principal component feature.

5. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: The specific value of each influencing factor in the influencing factor set is obtained in real time to determine the real-time contribution rate of each influencing factor according to the principal component analysis method, and the characterization tendency of the current traffic accident is determined according to the real-time cumulative contribution rate of the actual influencing factor set, where: If the real-time cumulative contribution rate is greater than or equal to the preset cumulative contribution rate, it is determined that the current traffic accident representation tendency is an occurrence tendency; If the real-time cumulative contribution rate is less than the preset cumulative contribution rate, it is determined that the current traffic accident characterization tendency is a non-occurrence tendency.

6. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: According to the determination result that the characteristic tendency is an occurrence tendency, a plurality of collecting drones are controlled to take off in sequence and collect traffic videos of corresponding highway sections respectively; The number of the collection drones is at least 3, and the take-off time intervals of the collection drones are equal and greater than a preset time length.

7. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: The flying direction of the collection drone is opposite to the driving direction of the moving vehicle.

8. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: Determining the driving data of each driving vehicle based on the single traffic video to determine the driving characteristic trend of any driving vehicle, including: Using artificial intelligence software to determine the driving data group of each driving vehicle based on the single traffic video; Determine the difference between each driving data in a plurality of driving data groups determined by a single driving vehicle according to each traffic video; The driving characterization trend of the corresponding vehicle is determined according to the difference between each driving data, where: If the differences of the driving data are all less than or equal to the preset differences, it is determined that the driving characteristic trend of the driving vehicle is a dominant stable trend; If there is any driving data whose difference is greater than a preset difference, it is determined that the driving characteristic trend of the driving vehicle is a hidden stable trend.

9. The traffic accident analysis method based on multivariate data according to claim 1, characterized in that: According to the position relationship between the driving vehicle position of the implicit stable trend and the congested road section, the communication drone is controlled to fly to a preset position and collect congestion video at the preset position, including: If the position of the moving vehicle with an implicit stable trend is before the target position of the congested road section, the preset flight position of the control communication drone is above the position of the moving vehicle; If the position of the driving vehicle with an implicit stable trend is not before the target position of the congested road section, the preset flight position of the control communication drone is the target position of the congested road section; The target location is located at one quarter of the congested road section.

10. A traffic accident analysis system based on multivariate data using the traffic accident analysis method based on multivariate data according to any one of claims 1 to 9, characterized in that: include, The data collection module includes a retrieval unit for obtaining the historical traffic accident congestion rate of the expressway section and its corresponding traffic accident characteristics, a collection unit for obtaining the specific values ​​of each influencing factor in the influencing factor set in real time, and a networking unit for determining whether there is a congested section; A data analysis module, which is connected to the data acquisition module, is used to determine the influencing factors of the historical traffic accident and form an influencing factor set according to the correlation analysis results of each of the traffic accident characteristics and the corresponding historical traffic accident congestion rate, determine the contribution rate and principal component characteristics of each influencing factor in the influencing factor set according to the principal component analysis method to determine the influencing factor contribution set and principal component characteristic set of the corresponding historical traffic accident, and determine the actual influencing factors that affect the traffic accident on the expressway section according to the intersection of the principal component characteristic sets of each historical traffic accident to determine the actual influencing factor set; A real-time analysis module, which is connected to the data acquisition module and the data analysis module respectively, and is used to determine the real-time contribution rate of each influencing factor according to the specific value of each real-time influencing factor, determine the characterization tendency of the current traffic accident according to the real-time cumulative contribution rate of the actual influencing factor set, control a number of collection drones to take off in sequence and collect traffic videos of corresponding highway sections respectively according to the determination result of the characterization tendency, and determine the driving data group of each driving vehicle according to a single traffic video to determine the driving characterization trend of any driving vehicle; The analysis and determination module is respectively connected to the real-time analysis module and the data acquisition module, and is used to respond to the existence of a congested road section and lock the position of the vehicle with an implicit stable trend in the congested road section according to the driving data of the vehicle with an implicit stable trend, and control the communication drone to fly at a preset position to collect congestion video according to the positional relationship between the position of the vehicle with the implicit stable trend and the congested road section, so as to determine whether the cause of the congestion is a traffic accident.

Images