A method and system for risk identification of an e-bike rider

Abstract

The application provides a method and system for identifying the risk of an electric bicycle rider, which is based on a preset road traffic violation information to establish a risk data set, and then based on the risk data set, a fuzzy clustering algorithm is used to analyze the traffic safety risk of the electric bicycle rider to divide it according to a preset risk level. Finally, according to the attribute information of the rider and the electric bicycle vehicle characteristic information, the electric bicycle rider groups of each risk level are divided into different risk categories again. The method can accurately locate the electric bicycle groups with different safety risk levels, so as to formulate different management strategies for the electric bicycle riders of each safety risk level, to carry out differentiated management of the electric bicycle rider groups, and to provide a basis for formulating electric bicycle management measures.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of vehicle illegal behavior monitoring, in particular to a risk identification method and system for electric bicycle riders. BACKGROUND

[0002] Electric bicycles have become an important means of transportation for urban travel, and the rider group is large and widely distributed, including both private vehicle riders and delivery industry vehicle riders, both regular commuters and occasional travelers. However, traffic violations by electric bicycle riders occur frequently, especially risk riding behaviors such as red light running, reverse driving, and speeding, which not only seriously affect the urban traffic order, but also lead to a large number of traffic accidents and injuries. Therefore, how to accurately identify the risk behaviors of electric bicycle riders and classify them according to different traffic safety risk levels for differentiated management of the electric bicycle rider group is particularly important for reducing the traffic risk behaviors of electric bicycle riders. SUMMARY

[0003] Therefore, in order to differentiate the management of electric bicycle riders, the present application provides a risk identification method and system for electric bicycle riders.

[0004] In a first aspect, the present application provides a risk identification method for electric bicycle riders, comprising:

[0005] In a sampling period, collect vehicle characteristic information of electric bicycles, pre-set road traffic violation information of riders, and attribute information of riders, and establish a risk data set based on the pre-set road traffic violation information;

[0006] Based on the risk data set, use a fuzzy clustering algorithm to analyze the traffic safety risk of electric bicycle riders and classify them according to pre-set risk levels;

[0007] According to the attribute information of the riders and the vehicle characteristic information of the electric bicycles, the electric bicycle rider groups of each risk level are again divided into different risk categories.

[0008] Optionally, based on the risk data set, using a fuzzy clustering algorithm to analyze the traffic safety risk of electric bicycle riders and classifying them according to pre-set risk levels, comprises:

[0009] Determining a risk factor set of electric bicycle riders according to the risk data set;

[0010] Setting a cluster center set according to the pre-set risk levels, obtaining the membership degree of the cluster center set according to the cluster center set and the risk factor set, and obtaining the rider traffic risk membership degree matrix according to the membership degree.

[0011] Iteratively calculating clustering analysis results of the e-bike rider risk level until the rider traffic risk membership matrix meets the preset condition, and obtaining the preset risk level of the e-bike rider.

[0012] Optionally, the cluster center set is set according to the preset risk level, the membership of the cluster center set is obtained according to the cluster center set and the risk factor set, and the rider traffic risk membership matrix is obtained according to the membership, comprising:

[0013] The cluster center set V = {v ωt} is set; wherein v ωt represents the cluster center of the ωth risk level and the tth iteration, ω ∈ [1, M], and M is the number of preset risk levels.

[0014] The membership of the cluster center set is obtained according to the cluster center set and the risk factor set

[0015] Wherein, d ωi represents the Euclidean distance from the ith rider to the cluster center of the ωth risk category, q is the fuzzy index; S ωi is the risk factor set of the ωth risk level and the ith rider, and N is the total number of e-bike riders; V ωi represents the cluster center set of the ωth risk level and the ith rider.

[0016] Meanwhile, μ ωi should satisfy the following constraint condition:

[0017]

[0018] The rider traffic risk membership matrix U = {μ 1i , …, μ ωi} is obtained according to the membership of the cluster center set; wherein ω ∈ [1, M], M is the number of preset risk levels, i ∈ [1, N], and N is the total number of e-bike riders.

[0019] Optionally, the rider traffic risk membership matrix meets the preset condition, comprising:

[0020] The absolute value of the difference between the rider traffic risk membership matrices calculated by adjacent two iterations reaches a preset stop threshold or reaches a preset iteration number.

[0021] Optionally, the vehicle characteristic information includes: vehicle license plate type and vehicle license plate number;

[0022] The preset road traffic violation information includes: a traffic violation behavior occurrence time, a location, and a frequency.

[0023] The attribute information of the rider includes: a rider age.

[0024] Optionally, the risk factor set of the electric bicycle rider is determined according to the risk data set, including:

[0025] The risk factor set is determined according to the frequency of the traffic violation behavior of the electric bicycle, the frequency of the traffic violation behavior in a preset time period, and the frequency of the traffic violation behavior at a preset location.

[0026] Optionally, the electric bicycle riders of each risk level are re-divided according to the preset information and the electric bicycle vehicle characteristics, including:

[0027] The electric bicycle riders of each risk level are cross-classified according to the rider age, the vehicle license plate type of the electric bicycle, and the vehicle license plate number.

[0028] In a second aspect, the present application provides a risk identification system for electric bicycle riders, including:

[0029] The collection unit is configured to collect, in a sampling period, vehicle characteristic information of an electric bicycle, preset road traffic violation information of a rider, and attribute information of the rider, and establish a risk data set based on the preset road traffic violation information.

[0030] The risk level division unit is configured to receive the risk data set sent by the collection unit, and analyze the traffic safety risk of the electric bicycle rider based on the risk data set by using a fuzzy clustering algorithm, and divide the electric bicycle rider into different risk levels according to a preset risk level.

[0031] The rider group division unit is configured to re-divide the electric bicycle rider groups of each risk level into different risk categories according to the attribute information of the rider and the vehicle characteristic information of the electric bicycle.

[0032] In a third aspect, the present application provides a computer device, including: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the steps of the risk identification method for electric bicycle riders according to the first aspect or any optional implementation manner of the first aspect.

[0033] In a fourth aspect, the present application provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the risk identification method for electric bicycle riders according to the first aspect or any optional implementation manner of the first aspect.

[0034] The technical scheme of the present application has the following advantages:

[0035] The method provided by the present application can focus on the cyclist group with high traffic safety risk, and then develop different management strategies for the electric bicycle cyclists of different risk levels, that is, carry out targeted management on each electric bicycle cyclist. Finally, according to the attribute information of the cyclist and the vehicle characteristic information of the electric bicycle, the electric bicycle cyclist group of each risk level is divided into different risk categories again, which can accurately locate the electric bicycle group with safety risks and manage the electric bicycle cyclist group differently, and also provides a basis for developing electric bicycle management measures. BRIEF DESCRIPTION OF DRAWINGS

[0036] In order to more clearly illustrate the technical scheme in the specific embodiments or prior art of the present application, the drawings needed in the description of the specific embodiments or prior art will be briefly introduced as follows. Obviously, the drawings in the following description are some embodiments of the present application, and those skilled in the art can also obtain other drawings according to these drawings without creative labor.

[0037] Figure 1 The flow chart of the risk identification method of the electric bicycle cyclist provided by the embodiment of the present application is shown in the figure.

[0038] Figure 2 The structural schematic diagram of the risk identification system of the electric bicycle cyclist provided by the embodiment of the present application is shown in the figure.

[0039] Figure 3 The structural schematic diagram of the computer device provided by the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0040] The technical scheme of the present application will be described in detail below with reference to the drawings. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0041] In addition, the technical features involved in the different embodiments of the application described below can be combined with each other as long as they do not conflict with each other.

[0042] The risk identification method for the e-bike rider provided by the embodiment of the application has a flowchart as shown in the figure Figure 1 The risk identification method for the e-bike rider provided by the embodiment of the application has a flowchart as shown in the figure

[0043] Step S1, in a sampling period, collect the vehicle characteristic information of the e-bike, the preset road traffic violation information of the rider and the attribute information of the rider, and establish a risk data set based on the preset road traffic violation information.

[0044] In actual application, the above information can be collected in various ways, for example, the vehicle characteristic information of the e-bike can be captured in real time through a video monitoring device, the preset road traffic violation information of the rider can be collected through a Beidou positioning system or a global positioning system, and the attribute information of the rider can be obtained by matching with an online database, but it is not limited thereto as long as the collection of the above information can be realized.

[0045] According to the actual application requirement, different sampling periods are set, for example, in a period of D days, the vehicle characteristic information of the e-bike and the corresponding information of the rider are collected; the specific value of the number of days D can be flexibly adjusted and is not fixed to a certain value. It should be noted that the method for dividing the e-bike riders according to the preset risk level is the same in different sampling periods, and the specific method can be referred to the following content.

[0046] Step S2, based on the risk data set, analyze the traffic safety risk of the e-bike rider by using a fuzzy clustering algorithm, and divide the e-bike rider according to the preset risk level.

[0047] Specifically, the risk data set is established based on the preset road traffic violation information of the rider, which can include the time, location and frequency of the traffic violation behavior, and then the fuzzy clustering algorithm is used to iteratively calculate the above information to obtain the traffic safety risk of the e-bike rider, so as to divide the e-bike riders according to the preset risk level, wherein the number of the preset risk levels is determined according to the specific situation, and the embodiment of the application takes four preset risk levels as an example for illustration, i.e., the preset risk levels include low risk, general risk, high risk and major risk; at the same time, in order to facilitate the distinction, different preset risk levels can be marked by color, for example, the low-risk e-bike rider is marked as green, the general-risk e-bike rider is marked as yellow, the high-risk e-bike rider is marked as orange, and the major-risk e-bike rider is marked as red. The specific division process is described in the following embodiment, and the division process of other number of preset risk levels is the same as this, and will not be repeated here.

[0048] Step S3, according to the attribute information of the riders and the characteristic information of the electric bicycle vehicles, the electric bicycle rider groups of each risk level are divided into different risk categories again.

[0049] After step S2 is performed, the electric bicycle riders are preliminarily divided according to different preset risk levels, and then the electric bicycle riders of each different preset risk level are divided again according to the attribute information of the riders and the characteristic information of the electric bicycle vehicles. The attribute information of the riders can include the age of the riders, etc., at this time, the electric bicycle riders of each different preset risk level can be divided again according to the age of the riders, for example, divided into: [16 years old, 30 years old], [31 years old, 40 years old], [41 years old, 50 years old], [51 years old, 60 years old], [61 years old, ∞], not limited to this; the characteristic information of the electric bicycle vehicles can include the vehicle license plate type, the vehicle license plate number, etc., the type can be divided into: private electric bicycles, delivery industry vehicles, etc., not limited to this. That is, the process of re-dividing the electric bicycle riders of different preset risk levels is to cross-classify the electric bicycle riders of each preset risk level according to the age of the riders, the vehicle license plate type of the electric bicycle, and the vehicle license plate number; therefore, based on the above cross-classification results, different age groups of riders can be managed differently, for example, safety education or traffic management measures can be developed for the elderly and young people; targeted management measures can also be developed for electric bicycles of different vehicle license plate types, for example, for delivery riders with high traffic safety risks, after identifying the traffic risk behaviors of the riders, the enterprise platform is pushed to make them pay attention to and strengthen the traffic safety management of the riders, not limited to this. That is, the electric bicycle riders with safety risks can be accurately positioned, and the differential management of the electric bicycle riders can be realized.

[0050] The risk identification method for electric bicycle riders provided in the embodiment adopts a fuzzy clustering analysis method to divide the electric bicycle riders into different preset risk levels, and then divides the electric bicycle riders of each preset risk level again according to the age of the riders and the vehicle license plate type of the electric bicycle, which can accurately locate the riders with different safety risk levels, provides a basis for developing electric bicycle management measures, so as to develop corresponding management measures for riders of different risk levels and realize the differential management of the electric bicycle rider groups.

[0051] In one specific embodiment, step S2 of the above-mentioned risk identification method for electric bicycle riders includes the following steps.

[0052] Step S21, determining a risk factor set of the electric bicycle riders according to a risk data set.

[0053] Specifically, when the preset road traffic violation information includes the time, location and frequency of the traffic violation behavior, the risk factor set can be determined according to the frequency of the traffic violation behavior of the electric bicycle, the frequency of the traffic violation behavior in a preset time period, and the frequency of the traffic violation behavior at a preset location. It should be noted that the traffic violation behavior, the preset time period and the preset location can be set according to actual application conditions, and are not limited specifically. For example, when the traffic violation behavior includes reverse driving, violation of traffic signals and illegal lane occupation, the frequencies of the electric bicycle rider i to commit the three types of traffic violation behaviors, i.e., reverse driving, violation of traffic signals and illegal lane occupation, are respectively denoted as α i1 , α i2 , and α i3 ; the preset time period is the morning peak period 7:00-9:00 and the evening peak period 17:00-19:00, and the frequencies of the electric bicycle rider i to commit the three types of traffic violation behaviors in the two time periods are respectively denoted as α i4 , α i5 ; the preset location is an intersection and a preset road section, and the frequencies of the electric bicycle rider i to commit the three types of traffic violation behaviors in the above two locations are respectively denoted as α i6 , α i7 ; at this time, the risk factor set S i of the electric bicycle rider i is obtained as S i1 ={α i2 , α i3 , α i4 , α i5 , α i6 , α i7}, where i∈[1, N] and N is the total number of electric bicycle riders.

[0054] In step S22, a cluster center set is set according to a preset risk level, a membership degree of the cluster center set is obtained according to the cluster center set and the risk factor set, and a rider traffic risk membership degree matrix is obtained according to the membership degree.

[0055] In practice, the cluster center set V={v ωt} can be set according to the preset risk level, where v ωt represents the cluster center of the rider of the ωth risk level in the tth iteration, ω∈[1, M], M is the number of preset risk levels, and the four preset risk levels in the above embodiment are taken as an example for description, so ω∈[1, 4]. Specifically, the cluster center of the rider of the ωth risk level is v After t iterations, v ωt is obtained, and then the cluster center set V is obtained; where μ ωi is the membership degree of the cluster center set, and q is a fuzzy index. The membership degree of the cluster center set is obtained Where, d ωi This represents the Euclidean distance from the i-th cyclist to the ω-th preset risk level cluster center. S ωi V represents the set of risk factors for the ω-th risk level and the i-th cyclist during the iterative calculation process. ωi Let ω represent the cluster center set of the ω-th risk level and the ith cyclist. The fuzzy index q can be set according to the actual situation without specific limitations.

[0056] In this embodiment of the invention, if the number of preset security levels is four, then the membership degree μ out The following constraints should be met:

[0057]

[0058] Therefore, based on this membership degree, the traffic risk membership matrix U={μ 1i , ..., μ ωi}, where i∈[1,N], and N is the total number of electric bicycle riders.

[0059] Step S23: Iteratively calculate the cluster analysis results of the risk level of electric bicycle riders until the rider's traffic risk membership matrix meets the preset conditions, and obtain the preset risk level of electric bicycle riders.

[0060] After obtaining the traffic risk membership matrix of electric bicycle riders, iterative calculations are performed on this matrix. In practical applications, preset conditions for stopping the iteration calculation can be set according to specific circumstances. For example, if the absolute value of the difference between the rider traffic risk membership matrices calculated in two consecutive iterations reaches a preset stopping threshold, i.e., |U(t)-U(t-1)|<ε, where ε is the preset stopping threshold, and U(t) and U(t-1) are the rider traffic risk membership matrices calculated in two consecutive iterations; or, if a preset number of iterations is reached, the iteration calculation stops. It should be noted that the specific values ​​of the preset stopping threshold and the preset number of iterations can be flexibly adjusted and are not specifically limited. After stopping the iteration calculation, the cluster analysis results of the electric bicycle rider risk levels are output to obtain the preset risk levels of electric bicycles.

[0061] like Figure 2 As shown, based on the same inventive concept as the risk identification method for electric bicycle riders, one or more embodiments of the present invention can also provide a risk identification system for electric bicycle riders.

[0062] The electric bicycle rider risk identification system comprises: a collection unit 1, which is used to collect vehicle characteristic information of the electric bicycle, preset road traffic violation information of the rider and attribute information of the rider within a sampling period, and establish a risk data set based on the preset road traffic violation information; a risk level division unit 2, which is used to receive the risk data set sent by the collection unit, analyze the traffic safety risk of the electric bicycle rider based on the risk data set by using a fuzzy clustering algorithm, and divide according to a preset risk level; and a riding group division unit 3, which is used to divide the electric bicycle rider groups of each risk level into different risk categories according to the attribute information of the rider and the vehicle characteristic information of the electric bicycle.

[0063] As shown in Figure 3 the same as the illegal identification method of the electric bicycle based on the same inventive concept, one or more embodiments of the present application can also provide a computer device, comprising: at least one processor; and a memory in communication connection with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to make the at least one processor execute the illegal identification method of the electric bicycle provided by at least one embodiment of the present application. The detailed implementation process of the illegal identification method of the electric bicycle has been described in detail in the specification, and will not be repeated here.

[0064] As shown in Figure 3 the same as the illegal identification method of the electric bicycle based on the same inventive concept, one or more embodiments of the present application can also provide a computer readable storage medium for non-transiently storing computer executable instructions, which implement the illegal identification method of the electric bicycle provided by at least one embodiment of the present application when executed by a processor. The detailed implementation process of the illegal identification method of the electric bicycle has been described in detail in the specification, and will not be repeated here.

[0065] The logic and / or steps represented in flow diagrams or otherwise described herein, for example, can be considered as a sequence of executable instructions, and can be embodied in any computer-readable storage medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For purposes of this specification, a "computer-readable storage medium" can be any apparatus that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. The computer-readable storage medium can specifically include the following: electrical connection (electrical) having one or more wires, a portable computer diskette (magnetic), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable storage medium can even be the paper or other suitable medium upon which the program can be printed, since the program can be electronically obtained, for example, by optically scanning the paper or other medium, then

[0066] It should be understood that portions of the present disclosure can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, and as in another embodiment, any of the following technologies known in the art or their combinations can be used: discrete logic circuitry having logic gates for implementing logic functions on data signals, application specific integrated circuits having appropriate combinational logic gates, programmable gate arrays (PGA), field programmable gate arrays (FPGA), etc.

[0067] Obviously, the above embodiments are merely example for clearly illustrating but not limitation to the embodiments. Based on the above description, other different forms of changes or variations can be made by those skilled in the art. Here, all the embodiments need not and can not be enumerated. The obvious changes or variations derived from the above description are still within the protection scope of the present application.

Claims

1. A method of risk identification of an e-bike rider, characterized in that, The method comprises the following steps: In a sampling period, vehicle characteristic information of an electric bicycle, preset road traffic violation information of a rider and attribute information of the rider are collected, a risk data set is established based on the preset road traffic violation information, the vehicle characteristic information comprises a vehicle license plate type and a vehicle license plate number, the preset road traffic violation information comprises a traffic violation behavior occurrence time, a traffic violation behavior occurrence location and a traffic violation behavior frequency, and the attribute information of the rider comprises a rider age, wherein the vehicle license plate type is classified into a private electric bicycle and a delivery industry vehicle, and the rider age is classified into 16-30 years old, 31-40 years old, 41-50 years old, 51-60 years old and over 61 years old; Based on the risk data set, a fuzzy clustering algorithm is used to analyze the traffic safety risk of the electric bicycle rider, and the electric bicycle rider is divided into different risk levels according to a preset risk level, which comprises the following steps: A risk factor set of the electric bicycle rider is determined according to the risk data set, which comprises the following steps: the risk factor set is determined according to a traffic violation behavior frequency of the electric bicycle, a traffic violation behavior frequency in a preset time period and a traffic violation behavior frequency at a preset location, wherein the traffic violation behavior comprises reverse driving, traffic signal violation and illegal road occupation, and the preset time period is an early morning peak and an early evening peak; A clustering center set is set according to a preset risk level, a membership degree of the clustering center set is obtained according to the clustering center set and the risk factor set, and a rider traffic risk membership degree matrix is obtained according to the membership degree; The clustering analysis result of the electric bicycle rider risk level is iteratively calculated until the rider traffic risk membership degree matrix meets a preset condition, and a preset risk level of the electric bicycle rider is obtained; According to the attribute information of the rider and the vehicle characteristic information of the electric bicycle, the electric bicycle rider groups of different preset risk levels are divided into different risk categories again, which comprises the following steps: the electric bicycle riders of different preset risk levels are cross-classified according to the rider age, the vehicle license plate type of the electric bicycle and the vehicle license plate number. The clustering center set is set according to a preset risk level, a membership degree of the clustering center set is obtained according to the clustering center set and the risk factor set, and a rider traffic risk membership degree matrix is obtained according to the membership degree, which comprises the following steps: Setting the cluster center set V = {v ωt}; wherein v ωt represents the cluster center of the ωth risk level, the tth iteration, ω ∈ [1, M], and M is the number of preset risk levels; obtaining membership of the cluster center set according to the cluster center set and the risk factor set wherein, d ωi represents the Euclidean distance from the ith rider to the ωth risk category cluster center, q is the fuzzy index; S ωi is the risk factor set of the ith rider in the ωth risk level, and N is the total number of electric bicycle riders; V ωi represents the cluster center set of the ith rider in the ωth risk level. At the same time, μ ωi The following constraints should be met: According to the membership degrees of the cluster center set, a rider traffic risk membership degree matrix U = {μ 1i , …, μ ωi} is obtained; wherein ω ∈ [1, M], M is a preset number of risk levels, i ∈ [1, N], N is a total number of electric bicycle riders.

2. The method of claim 1, wherein, The rider traffic risk membership degree matrix meets a preset condition, which comprises the following steps: An absolute value of a difference value of the rider traffic risk membership degree matrix obtained by adjacent two times of iteration calculation reaches a preset stop threshold value or reaches a preset iteration number.

3. A risk identification system for e-bike riders based on the method of claim 1, characterized by, The method comprises the following steps: A collection unit is configured to collect, in a sampling period, vehicle characteristic information of an electric bicycle, preset road traffic violation information of a rider and attribute information of the rider, and establish a risk data set based on the preset road traffic violation information; A risk level division unit is configured to receive the risk data set sent by the collection unit, analyze the traffic safety risk of the electric bicycle rider based on the risk data set by using a fuzzy clustering algorithm, and divide the electric bicycle rider into different risk levels according to a preset risk level. The cycling group dividing unit is used for dividing the electric bicycle rider groups of each risk level into different risk categories according to the attribute information of the riders and the electric bicycle vehicle characteristic information.

4. A computer device, comprising: Comprise: at least one processor; and a memory connected in communication with the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to cause the at least one processor to perform the steps of the electric bicycle rider risk identification method according to any one of claims 1-2.

5. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the electric bicycle rider risk identification method according to any one of claims 1-2.

Images