A traffic accident data integration and analysis method and system

Abstract

The application discloses a traffic accident data integration and analysis method and system, the method comprising: acquiring historical traffic accident data, and dividing the historical traffic accident data into multiple periods according to time; setting a traffic accident trend prediction model, a traffic accident frequency model and a traffic accident influence model respectively, and calculating accident data values, traffic accident frequencies and traffic accident influence values according to the historical traffic accident data; when the accident data values are greater than or equal to a preset accident occurrence threshold, issuing a traffic accident occurrence early warning information, and / or when the traffic accident frequencies are greater than or equal to a preset accident occurrence frequency threshold, issuing a traffic accident occurrence early warning information, and / or when the traffic accident influence values are greater than or equal to a preset accident occurrence influence threshold, issuing a traffic accident occurrence early warning information.

Description

Technical Field

[0001] This invention belongs to the field of traffic accident data integration technology, and more specifically, relates to a method and system for traffic accident data integration and analysis. Background Technology

[0002] The following is a general overview of highway traffic accident data integration:

[0003] Data sources are diverse: Highway traffic accident data typically comes from various sources, including traffic police records, insurance company data, medical records, government transportation department data, internet platforms, GPS data, etc. These data sources are inconsistent and may use different formats and standards.

[0004] Data integration challenges: Integrating data from different sources and formats is a complex challenge. Data may include information such as the date, time, location, participants, vehicle type, injuries, weather conditions, and road type of an accident. Integrating this data typically requires data cleaning, standardization, and transformation.

[0005] Data quality: Data quality is a critical issue. Data from different sources may contain errors, inconsistencies, and missing values. Ensuring the accuracy and completeness of data is of paramount importance.

[0006] Geographic Information System (GIS): GIS technology plays a crucial role in the integration of highway accident data. It helps correlate accident data with geographic locations to enable geospatial analysis, such as hotspot analysis and geographic visualization.

[0007] However, there is no existing technology that can effectively integrate traffic accident data and analyze the integrated data to provide early warning information about traffic accidents. Summary of the Invention

[0008] To address the above technical problems, this invention proposes a method for integrating and analyzing traffic accident data, comprising:

[0009] Acquire historical traffic accident data and divide the historical traffic accident data into multiple periods according to time;

[0010] A traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model are set up respectively, and the accident data value, traffic accident frequency, and traffic accident impact value are calculated respectively based on the historical traffic accident data.

[0011] When the accident data value is greater than or equal to a preset accident occurrence threshold, a traffic accident occurrence warning message is issued; and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, a traffic accident occurrence warning message is issued; and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold, a traffic accident occurrence warning message is issued.

[0012] Furthermore, the traffic accident trend prediction model includes:

[0013]

[0014] Among them, Y t Let be the accident data value at time t, μ be the mean of the time series, p be the number of autoregressive coefficients, and β″ be the mean of the time series. i Y is the i-th autoregressive coefficient. t-i Here, σ′ is the accident data value at time ti, B(H,t) is the volatility adjustment factor, s is the fractal Brownian motion with the Hurst exponent H at time t, and γ is the number of periods. j Let be the weight of the j-th period, T be the period length, q be the number of exogenous variables, and δ be the weight of the j-th period. k Let X be the weight of the k-th exogenous variable. k，t Let ε be the k-th exogenous variable at time t. t This represents the residual value at time t.

[0015] Furthermore, the traffic accident frequency model includes:

[0016]

[0017] Wherein, AF is the frequency of traffic accidents, λ is the basic accident rate of traffic accidents, α is the time weight, β1 is the time adjustment factor, T is the cycle length, γ is the distance weight, β2 is the distance adjustment factor, L is the distance to the nearest toll station when the accident occurs, δ is the road slipperiness weight, β3 is the road slipperiness adjustment factor, RT is the road slipperiness, φ is the visibility weight, β4 is the visibility adjustment factor, and W is the visibility.

[0018] Furthermore, the traffic accident impact model includes:

[0019]

[0020] Where Impact is the traffic accident impact value, α′ is the traffic accident impact moderating factor, and β′ is the impact factor. i Let x' be the weight of the i-th kernel function, and x′ be the feature vector of the current accident data. i Let θ be the i-th feature vector of the historical accident data, γ′ be the phase, and σ be the width of the kernel function.

[0021] Furthermore, at time t, the k-th exogenous variable X k，t This includes visibility, traffic flow, and road slipperiness.

[0022] This invention also proposes a traffic accident data integration and analysis system, comprising:

[0023] The data acquisition module is used to acquire historical traffic accident data and divide the historical traffic accident data into multiple periods according to time.

[0024] The calculation module is used to set up a traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model, and to calculate the accident data value, traffic accident frequency, and traffic accident impact value based on the historical traffic accident data.

[0025] The early warning module is used to issue a traffic accident early warning message when the accident data value is greater than or equal to a preset accident occurrence threshold, and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold.

[0026] Furthermore, the traffic accident trend prediction model includes:

[0027]

[0028] Among them, Y t Let be the accident data value at time t, μ be the mean of the time series, p be the number of autoregressive coefficients, and β″ be the mean of the time series. i Y is the i-th autoregressive coefficient. t-i Here, σ′ is the accident data value at time ti, B(H,t) is the volatility adjustment factor, s is the fractal Brownian motion with the Hurst exponent H at time t, and γ is the number of periods. j Let be the weight of the j-th period, T be the period length, q be the number of exogenous variables, and δ be the weight of the j-th period. k Let X be the weight of the k-th exogenous variable. k，t Let ε be the k-th exogenous variable at time t. t This represents the residual value at time t.

[0029] Furthermore, the traffic accident frequency model includes:

[0030]

[0031] Wherein, AF is the frequency of traffic accidents, λ is the basic accident rate of traffic accidents, α is the time weight, β1 is the time adjustment factor, T is the cycle length, γ is the distance weight, β2 is the distance adjustment factor, L is the distance to the nearest toll station when the accident occurs, δ is the road slipperiness weight, β3 is the road slipperiness adjustment factor, RT is the road slipperiness, φ is the visibility weight, β4 is the visibility adjustment factor, and W is the visibility.

[0032] Furthermore, the traffic accident impact model includes:

[0033]

[0034] Where Impct is the traffic accident impact value, α′ is the traffic accident impact adjustment factor, and β′ is the impact factor. i Let x' be the weight of the i-th kernel function, and x′ be the feature vector of the current accident data. i Let θ be the i-th feature vector of the historical accident data, γ′ be the phase, and σ be the width of the kernel function.

[0035] Furthermore, at time t, the k-th exogenous variable X k，t This includes visibility, traffic flow, and road slipperiness.

[0036] Compared with the prior art, the above-described technical solutions conceived in this invention have the following beneficial effects:

[0037] This invention acquires historical traffic accident data and divides it into multiple periods based on time. It then sets up a traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model, respectively, and calculates the accident data value, traffic accident frequency, and traffic accident impact value based on the historical traffic accident data. When the accident data value is greater than or equal to a preset accident occurrence threshold, a traffic accident warning is issued; and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, a traffic accident warning is issued; and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold, a traffic accident warning is issued. Through the above technical solutions, this invention can accurately predict potential traffic accidents on highways by setting up relevant models based on historical traffic accident data. Attached Figure Description

[0038] Figure 1 This is a flowchart of Example 1;

[0039] Figure 2 This is a system structure diagram of Example 2; Detailed Implementation

[0040] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0041] The method provided by this invention can be implemented in a terminal environment that may include one or more of the following components: a processor, a storage medium, and a display screen. The storage medium stores at least one instruction, which is loaded and executed by the processor to implement the method described in the following embodiments.

[0042] A processor may include one or more processing cores. The processor uses various interfaces and lines to connect various parts of the terminal, and performs various functions and processes data by running or executing instructions, programs, code sets or instruction sets stored in the storage medium, and by calling data stored in the storage medium.

[0043] Storage media can include random access memory (RAM) or read-only memory (ROM). Storage media can be used to store instructions, programs, code, code sets, or instructions.

[0044] The display screen is used to show the user interface of each application.

[0045] In the formula of this invention, all subscripts are only used to distinguish parameters and have no actual meaning.

[0046] In addition, those skilled in the art will understand that the structure of the terminal described above does not constitute a limitation on the terminal. The terminal may include more or fewer components, or combine certain components, or have different component arrangements. For example, the terminal may also include radio frequency circuits, input units, sensors, audio circuits, power supplies, and other components, which will not be described in detail here.

[0047] Example 1

[0048] like Figure 1 As shown, this invention proposes a method for integrating and analyzing traffic accident data, including:

[0049] Step 101: Obtain historical traffic accident data and divide the historical traffic accident data into multiple periods according to time.

[0050] Step 102: Set up a traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model respectively, and calculate the accident data value, traffic accident frequency, and traffic accident impact value respectively based on the historical traffic accident data.

[0051] Specifically, the traffic accident trend prediction model includes:

[0052]

[0053] Among them, Y t Let be the accident data value at time t, μ be the mean of the time series, p be the number of autoregressive coefficients, and β″ be the mean of the time series. i Y is the i-th autoregressive coefficient. t-i Here, σ′ is the accident data value at time ti, B(H,t) is the volatility adjustment factor, s is the fractal Brownian motion with the Hurst exponent H at time t, and γ is the number of periods. j Let be the weight of the j-th period, T be the period length, q be the number of exogenous variables, and δ be the weight of the j-th period. k Let X be the weight of the k-th exogenous variable. k，t Let ε be the k-th exogenous variable at time t. t This represents the residual value at time t.

[0054] Specifically, the traffic accident frequency model includes:

[0055]

[0056] Wherein, AF is the frequency of traffic accidents, λ is the basic accident rate of traffic accidents, α is the time weight, β1 is the time adjustment factor, T is the cycle length, γ is the distance weight, β2 is the distance adjustment factor, L is the distance to the nearest toll station when the accident occurs, δ is the road slipperiness weight, β3 is the road slipperiness adjustment factor, RT is the road slipperiness, φ is the visibility weight, β4 is the visibility adjustment factor, and W is the visibility.

[0057] Specifically, the traffic accident impact model includes:

[0058]

[0059] Where Impact is the traffic accident impact value, α′ is the traffic accident impact moderating factor, and β′ is the impact factor. i Let x' be the weight of the i-th kernel function, and x′ be the feature vector of the current accident data. i Let θ be the i-th feature vector of the historical accident data, γ′ be the phase, and σ be the width of the kernel function.

[0060] Specifically, at time t, the k-th exogenous variable X k，t This includes visibility, traffic flow, and road slipperiness.

[0061] Step 103: When the accident data value is greater than or equal to a preset accident occurrence threshold, issue a traffic accident occurrence warning message, and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, issue a traffic accident occurrence warning message, and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold, issue a traffic accident occurrence warning message.

[0062] Example 2

[0063] like Figure 2 As shown, the present invention also proposes a traffic accident data integration and analysis system, comprising:

[0064] The data acquisition module is used to acquire historical traffic accident data and divide the historical traffic accident data into multiple periods according to time.

[0065] The calculation module is used to set up a traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model, and to calculate the accident data value, traffic accident frequency, and traffic accident impact value based on the historical traffic accident data.

[0066] Specifically, the traffic accident trend prediction model includes:

[0067]

[0068] Among them, Y t Let be the accident data value at time t, μ be the mean of the time series, p be the number of autoregressive coefficients, and β″ be the mean of the time series. i Y is the i-th autoregressive coefficient. t-i Here, σ′ is the accident data value at time ti, B(H,t) is the volatility adjustment factor, s is the fractal Brownian motion with the Hurst exponent H at time t, and γ is the number of periods. j Let be the weight of the j-th period, T be the period length, q be the number of exogenous variables, and δ be the weight of the j-th period. k Let X be the weight of the k-th exogenous variable. k，t Let ε be the k-th exogenous variable at time t. t This represents the residual value at time t.

[0069] Specifically, the traffic accident frequency model includes:

[0070]

[0071] Wherein, AF is the frequency of traffic accidents, λ is the base accident rate, α is the time weight, β1 is the time adjustment factor, T is the period length, γ is the distance weight, β2 is the distance adjustment factor, L is the distance to the nearest toll station at the time of the accident, δ is the road slipperiness weight, β3 is the road slipperiness adjustment factor, RT is the road slipperiness, and φ is the visibility weight. β 4 is the visibility adjustment factor, and W is the visibility.

[0072] Specifically, the traffic accident impact model includes:

[0073]

[0074] Where Impact is the traffic accident impact value, α′ is the traffic accident impact moderating factor, and β′ is the impact factor. i Let x' be the weight of the i-th kernel function, and x′ be the feature vector of the current accident data. i Let θ be the i-th feature vector of the historical accident data, γ′ be the phase, and σ be the width of the kernel function.

[0075] Specifically, at time t, the k-th exogenous variable X k，t This includes visibility, traffic flow, and road slipperiness.

[0076] The early warning module is used to issue a traffic accident early warning message when the accident data value is greater than or equal to a preset accident occurrence threshold, and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold.

[0077] Example 3

[0078] This invention also proposes a storage medium storing multiple instructions for implementing the aforementioned traffic accident data integration and analysis method.

[0079] Optionally, in this embodiment, the storage medium may be located in any computer terminal in a group of computer terminals in a computer network, or in any mobile terminal in a group of mobile terminals.

[0080] Optionally, in this embodiment, the storage medium is configured to store program code for performing the following steps: Step 101, acquiring historical traffic accident data and dividing the historical traffic accident data into multiple periods according to time;

[0081] Step 102: Set up a traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model respectively, and calculate the accident data value, traffic accident frequency, and traffic accident impact value respectively based on the historical traffic accident data.

[0082] Specifically, the traffic accident trend prediction model includes:

[0083]

[0084] Among them, Y t Let be the accident data value at time t, μ be the mean of the time series, p be the number of autoregressive coefficients, and β″ be the mean of the time series. i Y is the i-th autoregressive coefficient. t-i Here, σ′ is the accident data value at time ti, B(H,t) is the volatility adjustment factor, s is the fractal Brownian motion with the Hurst exponent H at time t, and γ is the number of periods. j Let be the weight of the j-th period, T be the period length, q be the number of exogenous variables, and δ be the weight of the j-th period. k Let X be the weight of the k-th exogenous variable. k，t Let ε be the k-th exogenous variable at time t. t This represents the residual value at time t.

[0085] Specifically, the traffic accident frequency model includes:

[0086]

[0087] Wherein, AF is the frequency of traffic accidents, λ is the basic accident rate of traffic accidents, α is the time weight, β1 is the time adjustment factor, T is the cycle length, γ is the distance weight, β2 is the distance adjustment factor, L is the distance to the nearest toll station when the accident occurs, δ is the road slipperiness weight, β3 is the road slipperiness adjustment factor, RT is the road slipperiness, φ is the visibility weight, β4 is the visibility adjustment factor, and W is the visibility.

[0088] Specifically, the traffic accident impact model includes:

[0089]

[0090] Where Impact is the traffic accident impact value, α′ is the traffic accident impact moderating factor, and β′ is the impact factor. i Let x' be the weight of the i-th kernel function, and x′ be the feature vector of the current accident data. i Let θ be the i-th feature vector of the historical accident data, γ′ be the phase, and σ be the width of the kernel function.

[0091] Specifically, at time t, the k-th exogenous variable X k，tThis includes visibility, traffic flow, and road slipperiness.

[0092] Step 103: When the accident data value is greater than or equal to a preset accident occurrence threshold, issue a traffic accident occurrence warning message, and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, issue a traffic accident occurrence warning message, and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold, issue a traffic accident occurrence warning message.

[0093] Example 4

[0094] This invention also proposes an electronic device, including a processor and a storage medium connected to the processor. The storage medium stores multiple instructions, which can be loaded and executed by the processor to enable the processor to perform a traffic accident data integration and analysis method.

[0095] Specifically, the electronic device in this embodiment can be a computer terminal, which may include one or more processors and a storage medium.

[0096] The storage medium can be used to store software programs and modules, such as the traffic accident data integration and analysis method in this embodiment of the invention. The corresponding program instructions / modules allow the processor to execute various functional applications and data processing by running the software programs and modules stored in the storage medium, thus realizing the aforementioned traffic accident data integration and analysis method. The storage medium may include high-speed random access storage media, and may also include non-volatile storage media, such as one or more magnetic storage systems, flash memory, or other non-volatile solid-state storage media. In some instances, the storage medium may further include storage media remotely configured relative to the processor, which can be connected to the terminal via a network. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0097] The processor can call the information and application stored in the storage medium through the transmission system to perform the following steps: Step 101, acquire historical traffic accident data and divide the historical traffic accident data into multiple periods according to time;

[0098] Step 102: Set up a traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model respectively, and calculate the accident data value, traffic accident frequency, and traffic accident impact value respectively based on the historical traffic accident data.

[0099] Specifically, the traffic accident trend prediction model includes:

[0100]

[0101] Among them, Y t Let be the accident data value at time t, μ be the mean of the time series, p be the number of autoregressive coefficients, and β″ be the mean of the time series. i Y is the i-th autoregressive coefficient. t-i Here, σ′ is the accident data value at time ti, B(H,t) is the volatility adjustment factor, s is the fractal Brownian motion with the Hurst exponent H at time t, and γ is the number of periods. j Let be the weight of the j-th period, T be the period length, q be the number of exogenous variables, and δ be the weight of the j-th period. k Let X be the weight of the k-th exogenous variable. k，t Let ε be the k-th exogenous variable at time t. t This represents the residual value at time t.

[0102] Specifically, the traffic accident frequency model includes:

[0103]

[0104] Wherein, AF is the frequency of traffic accidents, λ is the basic accident rate of traffic accidents, α is the time weight, β1 is the time adjustment factor, T is the cycle length, γ is the distance weight, β2 is the distance adjustment factor, L is the distance to the nearest toll station when the accident occurs, δ is the road slipperiness weight, β3 is the road slipperiness adjustment factor, RT is the road slipperiness, φ is the visibility weight, β4 is the visibility adjustment factor, and W is the visibility.

[0105] Specifically, the traffic accident impact model includes:

[0106]

[0107] Where Impct is the traffic accident impact value, α′ is the traffic accident impact adjustment factor, and β′ is the impact factor. i Let x' be the weight of the i-th kernel function, and x′ be the feature vector of the current accident data. i Let θ be the i-th feature vector of the historical accident data, γ′ be the phase, and σ be the width of the kernel function.

[0108] Specifically, at time t, the k-th exogenous variable X k，t This includes visibility, traffic flow, and road slipperiness.

[0109] Step 103: When the accident data value is greater than or equal to a preset accident occurrence threshold, issue a traffic accident occurrence warning message, and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, issue a traffic accident occurrence warning message, and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold, issue a traffic accident occurrence warning message.

[0110] The sequence numbers of the above embodiments of the present invention are for descriptive purposes only and do not represent the superiority or inferiority of the embodiments.

[0111] In the above embodiments of the present invention, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions of other embodiments.

[0112] In the several embodiments provided by this invention, it should be understood that the disclosed technical content can be implemented in other ways. The system embodiments described above are merely illustrative; for example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces, or indirect coupling or communication connection between units or modules, and may be electrical or other forms.

[0113] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0114] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0115] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: USB flash drives, read-only storage media (ROM), random access storage media (RAM), portable hard drives, magnetic disks, optical disks, and other media capable of storing program code.

[0116] Obviously, the above embodiments are merely illustrative examples for clear explanation and are not intended to limit the implementation. Those skilled in the art will recognize that other variations or modifications can be made based on the above description. It is neither necessary nor possible to exhaustively list all possible implementations here. However, obvious variations or modifications derived therefrom are still within the scope of protection of this invention.

Claims

1. A method for integrating and analyzing traffic accident data, characterized in that, include: Acquire historical traffic accident data and divide the historical traffic accident data into multiple periods according to time; A traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model are set up respectively, and the accident data value, traffic accident frequency, and traffic accident impact value are calculated respectively based on the historical traffic accident data. The traffic accident trend prediction model includes: ， in, For time Accident data values ​​at that time, The mean of the time series. The number of autoregressive coefficients. For the first One autoregressive coefficient, For time Accident data values ​​at that time, As a volatility adjustment factor, For time When it has the Hearst index fractal Brownian motion, For the number of cycles, For the first Weights for each period, The period length, The number of exogenous variables, For the first The weights of each exogenous variable, For time Time One exogenous variable, For time The residual value at that time; The traffic accident frequency model includes: ， in, For traffic accident frequency, The baseline accident rate for traffic accidents. As time weight, For time adjustment factor, The period length, Distance weights Distance adjustment factor The distance to the nearest toll station at the time of the accident. As a weight for road slipperiness, This is a road slipperiness adjustment factor. For road slipperiness, For visibility weight, This is the visibility adjustment factor. Visibility; The traffic accident impact model includes: ， in, This represents the impact value of traffic accidents. As a moderating factor for the impact of traffic accidents, For the first The weights of each kernel function, This is the feature vector of the current accident data. The first of the historical accident data 1 eigenvector For phase, For amplitude, The width of the kernel function; When the accident data value is greater than or equal to a preset accident occurrence threshold, a traffic accident occurrence warning message is issued; and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, a traffic accident occurrence warning message is issued; and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold, a traffic accident occurrence warning message is issued.

2. The method for integrating and analyzing traffic accident data as described in claim 1, characterized in that, The time Time exogenous variables This includes visibility, traffic flow, and road slipperiness.

3. A traffic accident data integration and analysis system, characterized in that, include: The data acquisition module is used to acquire historical traffic accident data and divide the historical traffic accident data into multiple periods according to time. The calculation module is used to set up a traffic accident trend prediction model, a traffic accident frequency model, and a traffic accident impact model, and to calculate the accident data value, traffic accident frequency, and traffic accident impact value based on the historical traffic accident data. The traffic accident trend prediction model includes: ， in, For time Accident data values ​​at that time, The mean of the time series. The number of autoregressive coefficients. For the first One autoregressive coefficient, For time Accident data values ​​at that time, As a volatility adjustment factor, For time When it has the Hearst index fractal Brownian motion, For the number of cycles, For the first Weights for each period, The period length, The number of exogenous variables, For the first The weights of each exogenous variable, For time Time One exogenous variable, For time The residual value at that time; The traffic accident frequency model includes: ， in, For traffic accident frequency, The baseline accident rate for traffic accidents. As time weight, For time adjustment factor, The period length, Distance weights Distance adjustment factor The distance to the nearest toll station at the time of the accident. As a weight for road slipperiness, This is a road slipperiness adjustment factor. For road slipperiness, For visibility weight, This is the visibility adjustment factor. Visibility; The traffic accident impact model includes: ， in, This represents the impact value of traffic accidents. As a moderating factor for the impact of traffic accidents, For the first The weights of each kernel function, This is the feature vector of the current accident data. The first of the historical accident data 1 eigenvector For phase, For amplitude, The width of the kernel function; The early warning module is used to issue a traffic accident early warning message when the accident data value is greater than or equal to a preset accident occurrence threshold, and / or when the traffic accident frequency is greater than or equal to a preset accident occurrence frequency threshold, and / or when the traffic accident impact value is greater than or equal to a preset accident occurrence impact threshold.

4. The traffic accident data integration and analysis system as described in claim 3, characterized in that, The time Time exogenous variables This includes visibility, traffic flow, and road slipperiness.

Images