A data-driven traffic safety risk assessment and variable speed limit control algorithm and system

Abstract

The present application is a data-driven traffic safety risk assessment and variable speed limit control algorithm and system, which relates to the field of highway management. The algorithm includes obtaining first data related to traffic safety and second data related to traffic accidents; based on the first data and the second data, constructing a traffic accident prediction model, the traffic accident prediction model outputs prediction data related to traffic accidents; based on the prediction data and the traffic accident prediction model, constructing a traffic safety risk assessment model, the traffic safety risk assessment model outputs a risk assessment value related to traffic safety; generating a variable speed limit control algorithm; according to the variable speed limit control algorithm, if the risk assessment value is greater than a preset threshold, the speed limit control measures are activated; if the risk assessment value is not greater than the preset threshold, the speed limit control measures are not activated. Based on the traffic safety risk assessment and variable speed limit control algorithm, the present application performs variable speed limit control by lane to ensure highway safety.

Description

Technical Field

[0001] The present application relates to the field of highway management, and in particular to data-driven traffic safety risk assessment and variable speed limit control algorithms and systems. Background Art

[0002] At present, highway traffic safety risk assessment models generally use historical highway traffic accident statistics and traffic flow detection data to construct a mathematical function relationship between traffic accidents and the average headway time of traffic flow, that is, a model-driven highway traffic safety risk assessment model. However, the model-driven traffic safety risk assessment model requires a long series of historical traffic accident data as a data source, which is more suitable for macro-level judgment of highway traffic safety. It is difficult to support dynamic assessment of lane-level highway traffic safety risks, and it is impossible to comprehensively consider the influencing factors such as different vehicle types, different weather conditions, and different road geometric characteristics. The refined safety risk level assessment at the lane level. In addition, if the above-mentioned influencing factors are taken into account, the model will be complicated, and there will be problems such as difficulty in fitting model parameters.

[0003] Therefore, it is hoped to provide a data-driven traffic safety risk assessment and variable speed limit control algorithm and system. Based on the real-time collected lane-by-lane and vehicle-type traffic flow data, dynamic weather data, and road traffic event data, a lane-level traffic safety risk assessment model can be constructed to support dynamic speed limit control of smart highway lanes under different vehicle type compositions, different weather conditions, and different road geometry characteristics, effectively improving the safety level of highway sections and ensuring highway safety. Summary of the invention

[0004] According to a first aspect of some embodiments of the present application, a data-driven traffic safety risk assessment and variable speed limit control algorithm is provided, which is applied to a terminal (for example, a control system, etc.), and the algorithm may include obtaining first data related to traffic safety and second data related to traffic accidents; constructing a traffic accident prediction model based on the first data and the second data, and the traffic accident prediction model outputs predicted data related to traffic accidents; constructing a traffic safety risk assessment model based on the predicted data and the traffic accident prediction model, and the traffic safety risk assessment model outputs a risk assessment value related to traffic safety; generating a variable speed limit control algorithm; according to the variable speed limit control algorithm, if the risk assessment value is greater than a preset threshold, speed limit control measures are initiated; if the risk assessment value is not greater than the preset threshold, speed limit control measures are not initiated.

[0005] In some embodiments, constructing the traffic accident prediction model specifically includes inputting the first data, wherein the first data includes the independent variable x of the traffic accident prediction model; inputting the second data, wherein the second data includes the dependent variable y of the traffic accident prediction model; and constructing the traffic accident prediction model y=f(x).

[0006] In some embodiments, the constructing the traffic accident prediction model y=f(x) specifically includes using a generalized linear regression model to construct the traffic accident prediction model y=f(x), Among them, y i The dependent variable for sample i, x i The independent variable of sample i, x i,d is the d-th dimension independent variable of sample i, 1≤d≤7, ω0, ω1…ω7 are weight coefficients, ε i is a distribution error term; and the traffic accident prediction model y=f(x) is fitted using the second data associated with the traffic accident.

[0007] In some embodiments, the construction of the traffic safety risk assessment model specifically includes setting y as the number of traffic accidents, the probability p(y=y) as the probability of the occurrence of the number of traffic accidents y, and using the negative binomial model to construct the distribution function of y:

[0008]

[0009] Wherein, parameter θ is a random variable assumed to obey the gamma distribution, λ is the mean of y λ=E(y); determine the optimal estimate of parameter θ.

[0010] In some embodiments, determining the optimal estimate of the parameter θ specifically includes:

[0011] Step 1: According to Bayesian theory, set sample y i The posterior probability of parameter θ (i=1,…,n) is:

[0012]

[0013] Among them, P(θ|y i ) is the posterior probability of parameter θ, P(θ|y i )∝P(y=y i |θ)π(θ);

[0014] Step 2: Determine the likelihood function L(θ), let y1,y2,…,y n Samples from the population y, y1,y2,…,y n Assuming independent and identical distribution, the likelihood function of parameter θ is

[0015] Step 3, determine the prior probability π(θ):

[0016]

[0017] Among them, α and β are the hyperparameters of the prior probability π(θ);

[0018] Step 4: Let y1,y2,…,y n For a sample from the population y, the posterior probability P(θ|y1,y2,…,y n )∝L(θ)π(θ), let

[0019] P(θ|y1,y2,…,y n )=k×L(θ)×π(θ)

[0020] Where k is a constant, k = 1 / ∫ Θ P(y=y i |θ)π(θ)dθ;

[0021] Step 5: Determine the optimal parameter estimates set up is the estimated value of parameter θ, the optimal parameter estimate is the posterior probability P(θ|y1,y2,…,y n ), that is,

[0022]

[0023] In some embodiments, determining the likelihood function L(θ) specifically includes:

[0024]

[0025] Among them, n is the number of samples, and the number of traffic accidents y is i is the dependent variable of sample i, i∈[1,n]; λ i for y i The mean value λ i =E(y i ), λ i =exp{x i ω},x′ i =(x i1 ,x i2 ,…,x ip ) is the independent variable of sample i, and the independent variables include traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature and weather visibility, p = 7, ω is a (p+1)×1 parameter vector, and when there is no prior information, uniform distribution is used as the prior distribution of ω.

[0026] In some embodiments, the algorithm for generating a variable speed limit control specifically includes determining the traffic state of the first lane according to the risk assessment value of the first lane if the risk assessment value is greater than a preset threshold; determining the variable speed limit interval and the first speed limit value of the first lane according to the traffic state; determining the spatial range of the upstream speed limit section of the first lane according to the traffic state; and determining the variable speed limit value of the first lane according to the spatial range.

[0027] In some embodiments, the traffic status includes very safe, safe, normal, dangerous, and very dangerous; the determination of the spatial scope of the upstream speed limit section of the first lane specifically includes: if the traffic status is very dangerous, the control range of the speed limit control measure is the upstream first distance section of the first lane; if the traffic status is dangerous, the control range of the speed limit control measure is the upstream second distance section of the first lane, and the first distance is greater than the second distance; if the traffic status is normal, safe, or very safe, the speed limit control measure is not activated.

[0028] In some embodiments, determining the variable speed limit value of the first lane specifically includes inputting a first speed limit value v0 of the first lane and an average vehicle speed v of a first upstream distance section. u , calculate the speed difference Δv=v u -v0; determine the number m of information board gantries in the first upstream distance section, set the information board 1 at the closest upstream distance to correspond to gantry 1, and set the information board m at the farthest upstream distance to correspond to gantry m; set the variable speed limit value of the upstream speed limit section to gradually decrease from far to near, determine the speed limit values ​​of m information boards; determine the speed limit value of the first information board Speed ​​limit on the second information board The speed limit value of the mth information board That is v u .

[0029] According to a second aspect of some embodiments of the present application, a data-driven traffic safety risk assessment and variable speed limit control system is provided, the system comprising: an acquisition module, configured to acquire data of a first lane, the data comprising traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature, and weather visibility; an assessment module, configured to predict the number of traffic accidents in the first lane based on a traffic accident prediction model, and to assess the risk assessment value of the first lane based on a traffic safety risk assessment model; a control module, configured to perform lane-by-lane variable speed limit control according to the risk assessment value; a memory, configured to store data and instructions; and a A processor, wherein, when executing instructions in a memory, the processor is configured to: obtain first data related to traffic safety and second data related to traffic accidents; construct a traffic accident prediction model based on the first data and the second data, the traffic accident prediction model outputting prediction data related to traffic accidents; construct a traffic safety risk assessment model based on the prediction data and the traffic accident prediction model, the traffic safety risk assessment model outputting a risk assessment value related to traffic safety; generate a variable speed limit control algorithm; according to the variable speed limit control algorithm, if the risk assessment value is greater than a preset threshold, start speed limit control measures; if the risk assessment value is not greater than the preset threshold, do not start speed limit control measures.

[0030] Therefore, according to the data-driven traffic safety risk assessment and variable speed limit control algorithm and system of some embodiments of the present application, a lane-level traffic safety risk assessment model is constructed based on real-time collected lane-by-lane and vehicle type traffic flow data, dynamic weather data, and road traffic event data. It supports dynamic speed limit control of smart highway lanes under different vehicle type compositions, different weather conditions, and different road geometry characteristics, effectively improving the safety level of highway sections and ensuring highway safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] In order to better understand and explain some embodiments of the present application, the following description of the embodiments will be made with reference to the accompanying drawings, in which the same reference numerals indicate corresponding parts in the drawings.

[0032] Figure 1 It is an exemplary schematic diagram of a data-driven traffic safety risk assessment and variable speed limit control system provided according to some embodiments of the present application.

[0033] Figure 2 It is an exemplary flow chart of a data-driven traffic safety risk assessment and variable speed limit control algorithm provided according to some embodiments of the present application. DETAILED DESCRIPTION

[0034] The following description with reference to the accompanying drawings is intended to facilitate a comprehensive understanding of the various embodiments of the present application as defined by the claims and their equivalents. These embodiments include various specific details for ease of understanding, but these are considered to be exemplary only. Therefore, it will be appreciated by those skilled in the art that various changes and modifications to the various embodiments described herein will not depart from the scope and spirit of the present application. In addition, in order to briefly and clearly describe the present application, the present application will omit the description of known functions and structures.

[0035] The terms and phrases used in the following specification and claims are not limited to the literal meanings, but are only to enable a clear and consistent understanding of the present application. Therefore, it will be appreciated by those skilled in the art that the description of various embodiments of the present application is provided only for the purpose of illustration, rather than to limit the present application of the appended claims and their equivalent definitions.

[0036] The following will be combined with the drawings in some embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0037] It should be noted that the terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms of "one", "one", "a kind of", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings. It should also be understood that the term "and / or" used in the present application refers to and includes any or all possible combinations of one or more bound listed items. The expressions "first", "second", "the first" and "the second" are used to modify the corresponding elements without considering the order or importance, and are only used to distinguish one element from another element, without limiting the corresponding elements.

[0038] According to some embodiments of the present application, the terminal may be an intelligent terminal, a platform, equipment and / or an electronic device, etc.; the intelligent terminal may include a management and control system, etc. The platform may include a cloud control platform, etc., and the platform may include a system platform composed of one or more electronic devices; the equipment may include an intelligent connected vehicle (ICV); the electronic device may include a personal computer (PC, such as a tablet computer, a desktop computer, a notebook, a netbook, a handheld computer PDA), a client device, a virtual reality device (VR), an augmented reality device (AR), a mixed reality device (MR), an XR device, a rendering machine, a smart phone, a mobile phone, an e-book reader, a portable multimedia player (PMP), an audio / video player (MP3 / MP4), a camera, and a wearable device, etc. One or a combination of several. According to some embodiments of the present application, the wearable device may include an accessory type (such as a watch, a ring, a bracelet, glasses, or a head-mounted device (HMD)), an integrated type (such as electronic clothing), a decorative type (such as a skin pad, a tattoo, or a built-in electronic device), etc., or a combination of several. In some embodiments of the present application, the electronic device may be flexible, not limited to the above-mentioned devices, or may be a combination of one or several of the above-mentioned various devices. In this application, the term "user" may refer to a person using an electronic device or a device (eg, an artificial intelligence electronic device) using an electronic device.

[0039] The embodiment of the present application provides a data-driven traffic safety risk assessment and variable speed limit control algorithm and system. In order to facilitate the understanding of the embodiment of the present application, the embodiment of the present application will be described in detail with reference to the accompanying drawings.

[0040] Figure 1 is an exemplary schematic diagram of a data-driven traffic safety risk assessment and variable speed limit control system provided according to some embodiments of the present application. Figure 1The data-driven traffic safety risk assessment and variable speed limit control system 100 may include a network 110, a control terminal 120 (for example, a data-driven traffic safety risk assessment and variable speed limit control system), a user terminal 130, and a server 140. The data-driven traffic safety risk assessment and variable speed limit control system may include an acquisition module, an evaluation module, a control module, a memory, a processor that establishes communication with the memory, and the like. Specifically, the control terminal 120 and the user terminal 130 establish communication through the network. For example, the control terminal 120 and the user terminal 130 can communicate in the same local area network (for example, the network environment of the same router, etc.). Further, the control terminal 120 can be connected to the network 110 by wired (for example, a network cable, etc.) or wireless (for example, a cloud server, etc.), and the user terminal 130 can establish a communication connection with the network 110 by wired or wireless (for example, WIFI, etc.). In some embodiments, the user terminal 130 can send vehicle speed information to the control terminal 120 and the server 140. Furthermore, the control terminal 120 and the server 140 may provide feedback of variable speed limit control measures to the user terminal 130. Based on the feedback information, the user terminal 130 may perform speed change operations based on the variable speed limit control measures. As an example, the server 140 and / or the control terminal 120 may construct a lane-level traffic safety risk assessment model based on real-time collected lane-by-lane and vehicle-type traffic flow data, dynamic weather data, and road traffic event data. For example, the data-driven traffic safety risk assessment and variable speed limit control system may support dynamic speed limit control of smart highway lanes under different vehicle types, different weather conditions, and different road geometry characteristics.

[0041] According to some embodiments of the present application, the control terminal 120 and the user terminal 130 may be the same or different terminal devices, etc. The terminal devices may include but are not limited to a control system, a cloud control platform, an intelligent terminal, a mobile terminal, a computer, etc. In the intelligent transportation scenario, the control terminal 120 may include a control system, etc., and the user terminal 130 may include a display device, etc. In some embodiments, the control terminal 120 and the user terminal 130 may be integrated into one device, for example, a control system, etc. In some embodiments, the server 140 is a type of computer, which has advantages such as faster operation and higher load than ordinary computers, and the corresponding price is higher. In a network environment, the server can provide computing or application services for other clients (for example, PCs, smart phones, ATMs and other terminals, as well as large equipment such as transportation systems). The server has high-speed CPU computing power, long-term reliable operation, powerful I / O external data throughput and better scalability. The services that the server can provide include but are not limited to the ability to respond to service requests, undertake services, and guarantee services. As an electronic device, the server has an extremely complex internal structure, including an internal structure similar to that of an ordinary computer. As an example, the internal structure of the server may include a central processing unit (CPU), a hard disk, a memory, a system, a system bus, etc.

[0042] In some embodiments of the present application, the data-driven traffic safety risk assessment and variable speed limit control system 100 may omit one or more elements, or may further include one or more other elements. As an example, the data-driven traffic safety risk assessment and variable speed limit control system 100 may include multiple user terminals 130, such as multiple intelligent equipment, etc. For another example, the data-driven traffic safety risk assessment and variable speed limit control system 100 may include one or more control terminals 120. For another example, the data-driven traffic safety risk assessment and variable speed limit control system 100 may include multiple servers 140, etc. In some embodiments, the data-driven traffic safety risk assessment and variable speed limit control system 100 may include but is not limited to a system for issuing control measures based on urban intelligent traffic scenarios. The network 110 may be any type of communication network, and the communication network may include a computer network (for example, a local area network (LAN) or a wide area network (WAN), the Internet and / or a telephone network, etc., or a combination of several. In some embodiments, the network 110 may be other types of wireless communication networks. The wireless communication may include microwave communication and / or satellite communication, etc. The wireless communication may include cellular communication, for example, Global System for Mobile Communications (GSM), Code Division Multiple Access (CDMA), third generation mobile communication (3G), fourth generation mobile communication (4G), fifth generation mobile communication (5G), sixth generation mobile communication (6G), Long Term Evolution (LTE), LTE-A (LTE-Advanced), Wideband Code Division Multiple Access (WCDMA), Universal Mobile Telecommunications System (UMTS), wireless broadband (WiBro), etc., or a combination of several thereof.In some embodiments, the user terminal 130 may be other equipment and / or electronic devices with equivalent functional modules, and the equipment and / or electronic devices may include one or a combination of intelligent connected vehicles (ICV), virtual reality equipment (VR), rendering machines, personal computers (PCs, such as tablet computers, desktop computers, notebooks, netbooks, handheld computers (PDAs), smart phones, mobile phones, e-book readers, portable multimedia players (PMPs), audio / video players (MP3 / MP4s), cameras, and wearable devices.

[0043] In some embodiments, the WIFI may be other types of wireless communication technologies. According to some embodiments of the present application, the wireless communication may include wireless LAN (WiFi, Wireless Fidelity), Bluetooth, Bluetooth Low Energy (BLE, Bluetooth Low Energy), ZigBee, Near Field Communication (NFC, Near Field Communication), magnetic security transmission, radio frequency and body area network (BAN, Body Area Network), etc., or a combination of several. According to some embodiments of the present application, the wired communication may include a global navigation satellite system (Glonass / GNSS, Global Navigation Satellite System), a global positioning system (GPS, Global Position System), a Beidou navigation satellite system or Galileo (European Global Satellite Navigation System), etc. The wired communication may include a universal serial bus (USB, Universal Serial Bus), a high-definition multimedia interface (HDMI, High-Definition Multimedia Interface), a recommended standard 232 (RS-232, Recommend Standard 232), and / or a simple old telephone service (POTS, Plain Old Telephone Service), etc., or a combination of several.

[0044] It should be noted that the above description of the data-driven traffic safety risk assessment and variable speed limit control system 100 is only for convenience of description and cannot limit the present application to the scope of the embodiments. It can be understood that for those skilled in the art, based on the principle of the present system, it is possible to arbitrarily combine the various components, or form a subsystem connected with other components without deviating from the principle, and make various corrections and changes in form and details to the application field of the above method and system. For example, the server 140 and / or the control terminal 120 can obtain lane-by-lane traffic flow data, meteorological monitoring data, and traffic event data through roadside equipment (e.g., millimeter wave radar, meteorological detection station, visibility detector, traffic event detector, etc.). For another example, the control terminal 120 / user terminal 130 can be integrated in the control system, etc. Such variations are all within the scope of protection of the present application.

[0045] Figure 2 is an exemplary flow chart of a data-driven traffic safety risk assessment and variable speed limit control algorithm provided according to some embodiments of the present application. Figure 2 The process 200 may be implemented by a data-driven traffic safety risk assessment and variable speed limit control system 100. In some embodiments, the data-driven traffic safety risk assessment and variable speed limit control algorithm 200 may be automatically started or started by an instruction. The instruction may include a system instruction, a device instruction, a user instruction, an action instruction, etc., or a combination of several.

[0046] At 201, first data related to traffic safety and second data related to traffic accidents are obtained. Operation 201 can be implemented by the control terminal 120 and the server 140 of the data-driven traffic safety risk assessment and variable speed limit control system 100. In some embodiments, the control terminal 120 and / or the server 140 can obtain the first data related to traffic safety and the second data related to traffic accidents. The first data and the second data can be obtained by deploying various types of detection equipment along the roadside of the highway, and the detection equipment can include but is not limited to millimeter wave radar (for example, over-the-horizon millimeter wave radar), meteorological detection station, visibility detector, traffic event detector, etc. As an example, the over-the-horizon millimeter wave radar can sense lane-by-lane traffic flow data, etc. The first data related to traffic safety can include but is not limited to traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature, weather visibility, etc. in different lanes at different times. The second data related to traffic accidents may include the number of traffic accidents, etc. As an example, the visibility detector can detect visibility data; for another example, other detection equipment can obtain highway line data, the number of highway traffic accidents, etc.

[0047] At 202, a traffic accident prediction model is constructed based on the first data and the second data, and the traffic accident prediction model outputs prediction data associated with the traffic accident. Operation 202 can be implemented by the control terminal 120 and the server 140 of the data-driven traffic safety risk assessment and variable speed limit control system 100. In some embodiments, the control terminal 120 and / or the server 140 can construct a traffic accident prediction model based on the first data and the second data, and the traffic accident prediction model can output prediction data associated with the traffic accident.

[0048] In some embodiments, the construction of the traffic accident prediction model specifically includes: inputting the first data, the first data includes the independent variable x of the traffic accident prediction model; inputting the second data, the second data includes the dependent variable y of the traffic accident prediction model; and constructing the traffic accident prediction model y=f(x). The independent variable x is the independent variable of the traffic accident prediction model, including traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature, and weather visibility.

[0049] As an example, the construction of the traffic accident prediction model y=f(x) specifically includes: using a generalized linear regression model to construct the traffic accident prediction model y=f(x), and the predicted number of traffic accidents y is a function of seven independent variables x, namely, traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature, and weather visibility; specifically as follows:

[0050]

[0051] Among them, y i The dependent variable for sample i, x i The independent variable of sample i, x i,d is the d-th dimension independent variable of sample i, 1≤d≤7, ω0, ω1…ω7 are weight coefficients, ε i is a distribution error term; the traffic accident prediction model y=f(x) is fitted using the second data associated with the traffic accident. As an example, the traffic accident prediction model fitting can be performed using lane-divided traffic accident related data collected on the highway to fit the generalized linear regression model y=f(x) to obtain a traffic accident prediction function.

[0052] At 203, a traffic safety risk assessment model is constructed based on the prediction data and the traffic accident prediction model, and the traffic safety risk assessment model outputs a risk assessment value associated with traffic safety. Operation 203 can be implemented by the control terminal 120 and the server 140 of the data-driven traffic safety risk assessment and variable speed limit control system 100. In some embodiments, the control terminal 120 and / or the server 140 can construct a traffic safety risk assessment model based on the prediction data and the traffic accident prediction model, and the traffic safety risk assessment model outputs a risk assessment value associated with traffic safety.

[0053] In some embodiments, the construction of the traffic safety risk assessment model specifically includes setting y as the number of traffic accidents, the probability p(y=y) as the probability of the occurrence of the number of traffic accidents y, and using the negative binomial model to construct the distribution function of y:

[0054]

[0055] Wherein, parameter θ is a random variable assumed to obey the gamma distribution, λ is the mean of y λ=E(y); determine the optimal estimate of parameter θ.

[0056] In some embodiments, determining the optimal estimate of the parameter θ specifically includes:

[0057] Step 1: According to Bayesian theory, set sample y i The posterior probability of parameter θ (i=1,…,n) is:

[0058]

[0059] Among them, P(θ|y i ) is the posterior probability of parameter θ, P(θ|y i )∝P(y=y i |θ)π(θ);

[0060] Step 2: Determine the likelihood function L(θ), let y1,y2,…,y n Samples from the population y, y1,y2,…,y n Assuming independent and identical distribution, the likelihood function of parameter θ is As an example, determining the likelihood function L(θ) specifically includes:

[0061]

[0062] Among them, n is the number of samples, and the number of traffic accidents y is i is the dependent variable of sample i, i∈[1,n]; λ i for y i The mean value λ i =E(y i), λ i =exp{x i ω},x′ i =(x i1 ,x i2 ,…,x ip ) is the independent variable of sample i, and the independent variables include traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature and weather visibility, p = 7, ω is a (p+1)×1 parameter vector, and when there is no prior information, uniform distribution is used as the prior distribution of ω.

[0063] Step 3, determine the prior probability π(θ):

[0064]

[0065] Among them, α and β are the hyperparameters of the prior probability π(θ);

[0066] Step 4: Let y1,y2,…,y n For a sample from the population y, the posterior probability P(θ|y1,y2,…,y n )∝L(θ)π(θ), let

[0067] P(θ|y1,y2,…,y n )=k×L(θ)×π(θ)

[0068] Where k is a constant, k = 1 / ∫ Θ P(y=y i |θ)π(θ)dθ;

[0069] Step 5: Determine the optimal parameter estimates set up is the estimated value of parameter θ, the optimal parameter estimate is the posterior probability P(θ|y1,y2,…,y n ), that is,

[0070] As an example, the MCMC method can be used to estimate the optimal parameters using massive data to obtain In order to obtain the distribution function of the predicted number of traffic accidents y.

[0071] At 204, a variable speed limit control algorithm is generated. Operation 204 may be implemented by the server 140 and / or the control end 120 of the data-driven traffic safety risk assessment and variable speed limit control system 100. In some embodiments, the server 140 and / or the control end 120 may generate a variable speed limit control algorithm.

[0072] According to some embodiments of the present application, the algorithm for generating a variable speed limit control specifically includes: if the risk assessment value is greater than a preset threshold, determining the traffic state of the first lane according to the risk assessment value of the first lane; determining the variable speed limit interval and the first speed limit value of the first lane according to the traffic state; determining the spatial range of the upstream speed limit section of the first lane according to the traffic state; and determining the variable speed limit value of the first lane according to the spatial range. In some embodiments, the first lane may include each lane of a monitored section of a highway, and the monitored section may include accident-prone sections, sections with high traffic volume, etc. As an example, the traffic state may include very safe, safe, normal, dangerous, very dangerous, etc. As an example, the variable speed limit value of the lane may be determined according to the traffic state, and each level of variable speed limit value may be classified and determined in combination with the corresponding traffic state level, as shown in the following table:

[0073] Traffic status Very safe Safety normal Danger Very dangerous Average speed ≥90 [70,90) [50,70) [30,50) <30 Speed ​​limit / 70 50 30 20

[0074] As an example, by setting the five levels of traffic status as shown in the table above, the average vehicle speed and the vehicle speed limit corresponding to each level of traffic status are determined. For example, when the traffic status is "very safe", the average vehicle speed is greater than or equal to 90km / h, and the speed limit is not used; when the traffic status is "very dangerous", the average vehicle speed is less than 30km / h, and the speed limit is 20km / h. Specifically, the average speed v u The difference Δv from the speed limit value v0 can determine the variable speed limit value of the upstream section from far to near. That is v u , gradually decreasing to

[0075] At 205, according to the variable speed limit control algorithm, if the risk assessment value is greater than a preset threshold, the speed limit control measure is activated. Operation 205 may be implemented by the server 140 and / or the control end 120 of the data-driven traffic safety risk assessment and variable speed limit control system 100. In some embodiments, the server 140 and / or the control end 120 may, according to the variable speed limit control algorithm, activate the speed limit control measure if the risk assessment value is greater than a preset threshold.

[0076] In some embodiments, the determining of the spatial scope of the upstream speed limit section of the first lane specifically includes: if the traffic state is very dangerous, the control scope of the speed limit control measure is the upstream first distance section of the first lane; if the traffic state is dangerous, the control scope of the speed limit control measure is the upstream second distance section of the first lane, and the first distance is greater than the second distance.

[0077] As an example, if the traffic status of the lane is very dangerous, the controlled spatial range is 2000m upstream of the lane; if the traffic safety status of the lane is dangerous, the controlled spatial range is 1000m upstream of the lane; if the traffic safety status of the lane is normal, safe, or very safe, no speed limit is imposed. It should be noted that the above 2000m and 1000m are for example only, and the specific values ​​can be evaluated and confirmed based on the actual traffic safety status of the expressway.

[0078] At 206, if the risk assessment value is not greater than the preset threshold, the speed limit control measure is not activated. Operation 206 can be implemented by the server 140 and / or the control terminal 120 of the data-driven traffic safety risk assessment and variable speed limit control system 100. In some embodiments, the server 140 and / or the control terminal 120 can not activate the speed limit control measure based on the risk assessment value being not greater than the preset threshold. In some embodiments, the determining of the spatial scope of the upstream speed limit section of the first lane specifically includes not activating the speed limit control measure if the traffic state is normal, safe, or very safe.

[0079] According to some embodiments of the present application, determining the variable speed limit value of the first lane specifically includes inputting a first speed limit value v0 of the first lane and an average vehicle speed v of a first upstream distance section. u , calculate the speed difference Δv=v u -v0; determine the number m of information board gantries in the first upstream distance section, set the information board 1 at the closest upstream distance to correspond to gantry 1, that is, gantry 1 is the gantry closest to the current event, and set the speed limit value of gantry 1 to the minimum speed limit value of the current section (such as ); the upstream information board m at the farthest distance upstream corresponds to the gantry m, that is, the gantry m is the farthest gantry in the first distance section upstream (for example, a 2000-meter speed limit control section), and the speed limit value of the gantry m is set to the maximum speed limit value of the speed limit control section (such as v u As an example, the variable speed limit value of the upstream speed limit section is set to gradually decrease from far to near, and the speed limit values ​​of m information boards are determined; the speed limit value of the first information board is determined Speed ​​limit on the second information board The speed limit value of the mth information board That is v u .

[0080] According to some embodiments of the present application, the variable speed limit control measures information can be displayed in the user interface (UI) of the user terminal 130, and the display scene of the variable speed limit control measures information can include but is not limited to scene display through any form or combination of VR, AR, MR, and XR.

[0081] According to some embodiments of the present application, a data-driven traffic safety risk assessment and variable speed limit control system is provided, the system comprising: an acquisition module, configured to acquire data of a first lane, the data comprising traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature, and weather visibility; an assessment module, configured to predict the number of traffic accidents in the first lane based on a traffic accident prediction model, and to assess the risk assessment value of the first lane based on a traffic safety risk assessment model; a control module, configured to perform lane-by-lane variable speed limit control according to the risk assessment value; a memory, configured to store data and instructions; and a processor that establishes communication with the memory. Among them, when executing instructions in the memory, the processor is configured to: obtain first data related to traffic safety and second data related to traffic accidents; construct a traffic accident prediction model based on the first data and the second data, and the traffic accident prediction model outputs prediction data related to traffic accidents; construct a traffic safety risk assessment model based on the prediction data and the traffic accident prediction model, and the traffic safety risk assessment model outputs a risk assessment value related to traffic safety; generate a variable speed limit control algorithm; according to the variable speed limit control algorithm, if the risk assessment value is greater than a preset threshold, start the speed limit control measures; if the risk assessment value is not greater than the preset threshold, do not start the speed limit control measures.

[0082] It should be noted that the above description of process 200 is only for the convenience of description and does not limit the present application to the scope of the embodiments. It is understandable that for those skilled in the art, based on the principle of the present system, it is possible to arbitrarily combine the various operations, or constitute a sub-process and other operation combination without deviating from the principle, and make various corrections and changes in form and details to the functions of implementing the above-mentioned processes and operations. For example, process 200 may further include operations such as feedback to the control system based on a lane-level traffic safety risk assessment model, and issuing variable speed limit control measures. Such variations are within the scope of protection of the present application.

[0083] To summarize, according to the data-driven traffic safety risk assessment and variable speed limit control algorithm and system of the embodiment of the present application, a lane-level traffic safety risk assessment model is constructed based on real-time collected lane-by-lane and vehicle type traffic flow data, dynamic weather data, and road traffic event data. It supports dynamic speed limit control of smart highway lanes under different vehicle type compositions, different weather conditions, and different road geometry characteristics, effectively improving the safety level of highway sections and ensuring highway safety.

[0084] It should be noted that the above-mentioned embodiments are merely used as examples, and the present application is not limited to such examples, but various changes can be made.

[0085] It should be noted that, in this specification, the terms "include", "comprises" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or device including the element.

[0086] Finally, it should be noted that the above series of processing includes not only processing executed in time series in the order described here, but also processing executed in parallel or separately rather than in time series.

[0087] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by hardware related to computer program instructions, and the program can be stored in a computer-readable storage medium, which, when executed, can include the processes in the embodiments of the above-mentioned methods. The storage medium can be a disk, an optical disk, a read-only memory (ROM) or a random access memory (RAM), etc.

[0088] The above disclosures are only some preferred embodiments of the present application, which cannot be used to limit the scope of rights of the present application. Ordinary technicians in this field can understand that all or part of the processes of implementing the above embodiments and equivalent changes made according to the claims of the present application are still within the scope of the invention.

Claims

1. A data-driven traffic safety risk assessment and variable speed limit control method, characterized in that: include: Acquire first data related to traffic safety and second data related to traffic accidents; Based on the first data and the second data, construct a traffic accident prediction model, wherein the traffic accident prediction model outputs prediction data associated with the traffic accident; Based on the prediction data and the traffic accident prediction model, a traffic safety risk assessment model is constructed, and the traffic safety risk assessment model outputs a risk assessment value associated with traffic safety; Generate variable speed limit control algorithm; According to the variable speed limit control algorithm, if the risk assessment value is greater than a preset threshold, a speed limit control measure is initiated; If the risk assessment value is not greater than the preset threshold, the speed limit control measure is not initiated; The construction of the traffic accident prediction model specifically includes: Inputting the first data, wherein the first data includes an independent variable x of a traffic accident prediction model; Inputting the second data, wherein the second data includes a dependent variable y of a traffic accident prediction model; Constructing the traffic accident prediction model y=f(x); The construction of the traffic accident prediction model y=f(x) specifically includes: The traffic accident prediction model y=f(x) is constructed using a generalized linear regression model. Among them, y i The dependent variable for sample i, x i The independent variable of sample i, x i,d is the d-th dimension independent variable of sample i, 1≤d≤7, ω0, ω1…ω7 are weight coefficients, ε i is the distribution error term; Using the second data associated with the traffic accident to fit the traffic accident prediction model y=f(x); The construction of the traffic safety risk assessment model specifically includes: Let y be the number of traffic accidents, and probability p(y=y) be the probability of y number of traffic accidents. The negative binomial model is used to construct the distribution function of y: Where, parameter θ is a random variable assumed to follow a gamma distribution, λ is the mean of y λ = E(y); Determine the optimal estimate of the parameter θ; The algorithm for generating a variable speed limit control specifically includes: If the risk assessment value is greater than a preset threshold, determining the traffic state of the first lane according to the risk assessment value of the first lane; Determining a variable speed limit interval and a first speed limit value of the first lane according to the traffic state; Determining, according to the traffic state, a spatial range of an upstream speed limit section of the first lane; Determining a variable speed limit value of the first lane according to the spatial range; The traffic status includes very safe, safe, normal, dangerous, and very dangerous; and determining the spatial range of the upstream speed limit section of the first lane specifically includes: If the traffic condition is extremely dangerous, the speed limit control measure is activated for the first distance upstream of the first lane; If the traffic state is dangerous, the control range of the speed limit control measure is the upstream section of the first lane at a second distance, and the first distance is greater than the second distance; If the traffic status is normal, safe, or very safe, speed limit control measures will not be activated; The determining of the variable speed limit value of the first lane specifically includes: Input the first speed limit value v0 of the first lane and the average speed v of the first upstream distance section u , calculate the speed difference Δv=v u -v0; Determine the number m of information board gantries of the first upstream distance section, set the information board 1 at the closest upstream distance to correspond to gantry 1, and set the information board m at the farthest upstream distance to correspond to gantry m; Set the variable speed limit value of the upstream speed limit section to gradually decrease from far to near, and determine the speed limit values ​​of m information boards; Determine the speed limit value of the first information board Speed ​​limit on the second information board The speed limit value of the mth information board That is v u .

2. The data-driven traffic safety risk assessment and variable speed limit control method according to claim 1 is characterized in that: The determining of the optimal estimate of the parameter θ specifically includes: Step 1: According to Bayesian theory, the posterior probability of parameter θ of sample i (i=1,…,n) is set as: Among them, P(θ|y i ) is the posterior probability of parameter θ, P(θ|y i )∝P(y=y i |θ)π(θ); Step 2: Determine the likelihood function L(θ), let y1,y2,…,y n Samples from the population y, y1,y2,…,y n Assuming independent and identical distribution, the likelihood function of parameter θ is Step 3, determine the prior probability π(θ): Among them, α and β are the hyperparameters of the prior probability π(θ); Step 4: Let y1,y2,…,y n For a sample from the population y, the posterior probability P(θ|y1,y2,…,y n )∝L(θ)π(θ), let P(θ|y1,y2,…,y n ) = k×L(θ)×π(θ) Where k is a constant, k = 1 / ∫ Θ P(y=y i |θ)π(θ)dθ; Step 5: Determine the optimal parameter estimates set up is the estimated value of parameter θ, the optimal parameter estimate is the posterior probability P(θ|y1,y2,…,y n ), that is, 3. The data-driven traffic safety risk assessment and variable speed limit control method according to claim 2 is characterized in that: The determining of the likelihood function L(θ) specifically includes: Among them, n is the number of samples, and the number of traffic accidents y is i is the dependent variable of sample i, i∈[1,n]; λ i for y i The mean λ i =E(y i ), λ i =exp{x i ω},x′ i =(x i1 ,x i2 ,…,x ip ) is the independent variable of sample i, and the independent variables include traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature and weather visibility, p = 7, ω is a (p+1)×1 parameter vector, and when there is no prior information, uniform distribution is used as the prior distribution of ω.

4. A data-driven traffic safety risk assessment and variable speed limit control system, characterized in that: include: an acquisition module configured to acquire data of the first lane, the data including traffic volume, average speed, average headway, truck ratio, horizontal curve curvature, vertical curve curvature, and weather visibility; an evaluation module configured to predict the number of traffic accidents in the first lane based on a traffic accident prediction model, and to evaluate a risk evaluation value of the first lane based on a traffic safety risk evaluation model; A control module is configured to perform lane-by-lane variable speed limit control according to the risk assessment value; a memory configured to store data and instructions; A processor in communication with a memory, wherein when executing instructions in the memory, the processor is configured to: Acquire first data related to traffic safety and second data related to traffic accidents; Based on the first data and the second data, construct a traffic accident prediction model, wherein the traffic accident prediction model outputs prediction data associated with the traffic accident; Based on the prediction data and the traffic accident prediction model, a traffic safety risk assessment model is constructed, and the traffic safety risk assessment model outputs a risk assessment value associated with traffic safety; Generate variable speed limit control algorithm; According to the variable speed limit control algorithm, if the risk assessment value is greater than a preset threshold, a speed limit control measure is initiated; If the risk assessment value is not greater than the preset threshold, the speed limit control measure is not initiated; The construction of the traffic accident prediction model specifically includes: Inputting the first data, wherein the first data includes an independent variable x of a traffic accident prediction model; Inputting the second data, wherein the second data includes a dependent variable y of a traffic accident prediction model; Constructing the traffic accident prediction model y=f(x); The construction of the traffic accident prediction model y=f(x) specifically includes: The traffic accident prediction model y=f(x) is constructed using a generalized linear regression model. Among them, y i The dependent variable for sample i, x i The independent variable of sample i, x i,d is the d-th dimension independent variable of sample i, 1≤d≤7, ω0, ω1…ω7 are weight coefficients, ε i is the distribution error term; Using the second data associated with the traffic accident to fit the traffic accident prediction model y=f(x); The construction of the traffic safety risk assessment model specifically includes: Let y be the number of traffic accidents, and probability p(y=y) be the probability of y number of traffic accidents. The negative binomial model is used to construct the distribution function of y: Where, parameter θ is a random variable assumed to follow a gamma distribution, λ is the mean of y λ = E(y); Determine the optimal estimate of the parameter θ; The algorithm for generating a variable speed limit control specifically includes: If the risk assessment value is greater than a preset threshold, determining the traffic state of the first lane according to the risk assessment value of the first lane; Determining a variable speed limit interval and a first speed limit value of the first lane according to the traffic state; Determining, according to the traffic state, a spatial range of an upstream speed limit section of the first lane; Determining a variable speed limit value of the first lane according to the spatial range; The traffic status includes very safe, safe, normal, dangerous, and very dangerous; and determining the spatial range of the upstream speed limit section of the first lane specifically includes: If the traffic condition is extremely dangerous, the speed limit control measure is activated for the first distance upstream of the first lane; If the traffic state is dangerous, the control range of the speed limit control measure is the upstream section of the first lane at a second distance, and the first distance is greater than the second distance; If the traffic status is normal, safe, or very safe, speed limit control measures will not be activated; The determining of the variable speed limit value of the first lane specifically includes: Input the first speed limit value v0 of the first lane and the average speed v of the first upstream distance section u , calculate the speed difference Δv=v u -v0; Determine the number m of information board gantries of the first upstream distance section, set the information board 1 at the closest upstream distance to correspond to gantry 1, and set the information board m at the farthest upstream distance to correspond to gantry m; Set the variable speed limit value of the upstream speed limit section to gradually decrease from far to near, and determine the speed limit values ​​of m information boards; Determine the speed limit value of the first information board Speed ​​limit on the second information board The speed limit value of the mth information board That is v u .

Images