Electric bicycle passing risk management and control method and device, equipment and storage medium

Abstract

The invention discloses an electric bicycle traffic risk management and control method and device, equipment and a storage medium, and the method comprises the steps: constructing a basic data set which comprises electric bicycle traffic accident data and road network topological structure data; determining a traffic accident matched with each road network object according to the basic data set, and counting a safety risk coefficient of each road network object according to the traffic accident matched with each road network object; screening out a high-risk road network object from the plurality of road network objects according to the safety risk coefficient of each road network object; association rule mining is carried out on the high-risk road network object to obtain an association rule of the high-risk road network object, and the association rule is a rule between an accident environment attribute and an accident collision type; and setting a management and control strategy of the high-risk road network object according to the association rule of the high-risk road network object.

Description

Technical Field

[0001] The present application relates to the field of electric bicycle traffic safety management, and in particular to an electric bicycle traffic risk management method and apparatus, equipment, and storage medium. Background Art

[0002] In the area of ​​urban road safety management, electric bicycles are the mode of transportation that demands the most attention. Among urban road traffic accidents, electric bicycle accidents account for over 70% of all non-motorized vehicle accidents, and the number of electric bicycle accidents continues to increase at a rapid annual rate. Electric bicycle safety is affected by both riders' traffic violations and risky riding behaviors, such as riding against traffic, running red lights, speeding, and illegally occupying lanes. Furthermore, it is affected by road infrastructure and the environment, with the probability of electric bicycle accidents increasing at night and in rainy and snowy weather.

[0003] However, risk management and control of e-bike traffic faces significant difficulties. On the one hand, e-bikes are widespread and widespread, and safety enforcement and control primarily rely on on-site management by road enforcement forces, requiring significant manpower and time. On the other hand, e-bike traffic safety management lacks precision. Currently, on-site enforcement and control are primarily conducted during peak hours, at intersections with high traffic volume, or on main roads. However, e-bike traffic safety risks are concentrated on some secondary roads, branches, or special sections. The e-bike control model lacks precise adaptation to the spatiotemporal distribution characteristics of safety risks, and the pressure to reduce e-bike traffic accidents remains significant. Summary of the Invention

[0004] In order to solve the above technical problems, the embodiments of the present application provide a method and device, equipment, and computer storage medium for electric bicycle traffic risk management and control.

[0005] The electric bicycle traffic risk management method provided in the embodiment of the present application includes:

[0006] Constructing a basic data set, wherein the basic data set includes electric bicycle traffic accident data and road network topology data, wherein the electric bicycle traffic accident data includes data of multiple traffic accidents, and the road network topology data includes data of multiple road network objects, wherein the multiple road network objects include multiple intersections and / or multiple road sections;

[0007] Determining traffic accidents matching each road network object according to the basic data set, and calculating a safety risk coefficient of each road network object according to the traffic accidents matching each road network object;

[0008] According to the safety risk coefficient of each road network object, first N road network objects with the highest safety risk coefficients are screened out from the plurality of road network objects as high-risk road network objects, where N is a positive integer;

[0009] Performing association rule mining on the high-risk road network object to obtain association rules for the high-risk road network object, wherein the association rules are rules between accident environment attributes and accident collision types;

[0010] According to the association rules of the high-risk road network objects, a management and control strategy for the high-risk road network objects is set.

[0011] The electric bicycle traffic risk control device provided in the embodiment of the present application includes:

[0012] A construction unit is used to construct a basic data set, wherein the basic data set includes electric bicycle traffic accident data and road network topology data, wherein the electric bicycle traffic accident data includes data of multiple traffic accidents, and the road network topology data includes multiple;

[0013] a matching unit, configured to determine a traffic accident matching each road network object based on the basic data set, and calculate a safety risk coefficient of each road network object based on the traffic accident matching each road network object;

[0014] a risk identification unit, configured to screen out top N road network objects with the highest safety risk coefficients from the plurality of road network objects according to the safety risk coefficient of each road network object, as high-risk road network objects, where N is a positive integer;

[0015] an association rule mining unit, configured to perform association rule mining on the high-risk road network object to obtain an association rule for the high-risk road network object, wherein the association rule is a rule between accident environment attributes and accident collision types;

[0016] The management and control unit is used to set a management and control strategy for the high-risk road network object according to the association rule of the high-risk road network object.

[0017] The electric bicycle traffic risk management device provided in the embodiment of the present application includes: a processor and a memory, the memory is used to store computer programs, and the processor is used to call and run the computer program stored in the memory to execute the above-mentioned electric bicycle traffic risk management method.

[0018] The computer-readable storage medium provided in the embodiment of the present application is used to store a computer program, and the computer program enables a computer to execute the above-mentioned electric bicycle traffic risk management method.

[0019] The technical solution of the embodiments of this application uses a large amount of historical data on electric bicycle traffic accidents, accurately matching the accident locations with the road network structure to identify high-risk intersections and road sections for electric bicycle traffic. By mining and analyzing the association rules between accidents and the road environment, high-risk factors in the electric bicycle traffic environment are identified. Based on the spatiotemporal characteristics of electric bicycle traffic risks, management and control strategies and measures are formulated and categorized to achieve precise risk management and accident prevention, thereby improving the safety of electric bicycle traffic on urban roads. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 This is a flow chart of the electric bicycle traffic risk management method provided in an embodiment of the present application;

[0021] Figure 2 This is a schematic diagram of the structure of the electric bicycle traffic risk control device provided in an embodiment of the present application;

[0022] Figure 3 This is a schematic structural diagram of an electric bicycle traffic risk management device provided in an embodiment of the present application;

[0023] Figure 4 It is a schematic structural diagram of the chip of an embodiment of the present application. DETAILED DESCRIPTION

[0024] The following will describe the technical solutions in the embodiments of this application in conjunction with the drawings in the embodiments of this application. Obviously, the described embodiments are part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0025] It should be noted that the term "and / or" in this article is only a description of the association relationship of associated objects, indicating that there may be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the objects associated with each other are in an "or" relationship. It should also be understood that the "corresponding" mentioned in the embodiments of the present application can indicate that there is a direct or indirect correspondence between the two, or it can indicate that there is an association relationship between the two. It should also be understood that the "first" and "second" mentioned in the embodiments of the present application are only used for the purpose of convenience of description, and cannot be understood as indicating or implying relative importance or implicitly indicating the number of technical features. The meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0026] In response to the practical problems that the number of electric bicycles in cities is growing rapidly but the road traffic order is chaotic, and there are many electric bicycle traffic accidents but the road law enforcement and control forces are extremely limited, the embodiment of the present application proposes an electric bicycle traffic risk control method related to the causes of accidents. Based on the spatiotemporal data of historical accidents, through risk clustering and grading, the road points with higher electric bicycle traffic risks on urban roads are identified. Combined with the road traffic conditions such as lighting conditions, weather conditions, and non-motor vehicle isolation facilities, risk warnings and on-site law enforcement for electric bicycle riders are carried out in a classified manner, and the risk management of electric bicycle traffic on key roads and key nodes is accurately strengthened, so as to significantly reduce electric bicycle traffic accidents and save road law enforcement and control forces.

[0027] Figure 1 This is a flow chart of the electric bicycle traffic risk management method provided in the embodiment of the present application. Figure 1 As shown, the electric bicycle traffic risk management method includes the following steps:

[0028] Step 101: Construct a basic data set, which includes electric bicycle traffic accident data and road network topology data. The electric bicycle traffic accident data includes data on multiple traffic accidents, and the road network topology data includes data on multiple road network objects. The multiple road network objects include multiple intersections and / or multiple road sections.

[0029] In this embodiment of the present application, a data set is constructed for electric bicycle traffic risk analysis. The data set includes the following two types of data: electric bicycle traffic accident data and road network topology data. Here, the electric bicycle traffic risk analysis refers to the content related to the following steps 102 to 104.

[0030] In some embodiments, the electric bicycle traffic accident data comes from the city's public security traffic management department. For example, the electric bicycle traffic accident data includes traffic accident data involving electric bicycles and resulting in casualties that occurred on roads in urban built-up areas in recent years (such as the past five years).

[0031] Electric bicycle traffic accident data includes data on multiple traffic accidents. This data includes one or more of the following fields: accident number ID_a, accident location latitude and longitude (lon_a, lat_a), accident date data_a, accident time time_a, accident fatality number death_a, and accident injury number injury_a.

[0032] In some embodiments, the road network topology data is derived from open source electronic maps, urban public security traffic management departments, urban natural resources departments, etc., including intersection and road section data of urban built-up area road networks, and optionally, corresponding traffic management facility setting information.

[0033] Road network topology data includes data on multiple road network objects, each of which includes multiple intersections and / or multiple road segments. For intersections, the data includes one or more of the following fields: intersection ID_node, intersection center latitude and longitude (lon_node, lat_node), and intersection type type_node. For segments, the data includes one or more of the following fields: segment ID_link, segment latitude and longitude [(lon_start, lat_start), ..., (lon_end, lat_end)], segment type type_link, segment length length_link, and separation_link, which indicates the separation between motor vehicles and non-motor vehicles.

[0034] Step 102: Determine the traffic accidents that match each road network object based on the basic data set, and calculate the safety risk coefficient of each road network object based on the traffic accidents that match each road network object.

[0035] In the embodiment of the present application, "determining the traffic accidents matching each road network object based on the basic data set" can be understood as performing spatiotemporal matching on the electric bicycle traffic accident data and the road network topology structure data, so as to determine the traffic accidents matching each road network object. Specifically, assuming that the electric bicycle traffic accident data includes data on V1 traffic accidents, the road network topology structure data includes data on W1 road network objects, and the W1 road network objects include H1 intersections and H2 road sections, based on this, the electric bicycle traffic accident data and the road network topology structure data are spatiotemporally matched in the following manner: first, the data on V1 traffic accidents and the data on H1 intersections are matched, and the matching intersections for each traffic accident are determined from the V1 traffic accidents. It is assumed that f1 (f1≤V1) traffic accidents are matched to the corresponding intersections, and the remaining V2 (V2=V1-f1) traffic accidents are not matched to the corresponding intersections; secondly, the data on V2 traffic accidents and the data on H2 road sections are matched, and the matching road sections for each traffic accident are determined from the V2 traffic accidents. It is assumed that f2 (f2≤V2) traffic accidents are matched to the corresponding road sections, and the remaining V3 (V3=V2-f2) traffic accidents are not matched to the corresponding road sections. Finally, the V3 traffic accidents that were not successfully matched are regarded as isolated accidents, and the data of the V3 traffic accidents can be excluded from the electric bicycle traffic accident data.

[0036] In some embodiments, when the road network object is an intersection, the distance between the accident site and the intersection is calculated based on the longitude and latitude of the accident site and the longitude and latitude of the intersection center. If the distance between the accident site and only one intersection is less than or equal to a first distance threshold, the accident is recorded as a traffic accident matching the intersection. If the distance between the accident site and multiple intersections is less than or equal to the first distance threshold, the accident is recorded as a traffic accident matching the closest intersection. For example, the first distance threshold is 100 meters. Of course, the first distance threshold can be flexibly set as needed.

[0037] In one example, an intersection range is created. Specifically, a circular area with the longitude and latitude of the intersection center point (lon_node, lat_node) as the center and a first distance threshold (such as 100m) as the radius is used as the intersection range. For a certain traffic accident, the distance between the longitude and latitude of the accident site and the longitude and latitude of the intersection center is calculated. When the distance is less than or equal to the first distance threshold (such as 100m), the traffic accident is recorded as an accident occurring within this intersection (that is, the traffic accident matches this intersection). In particular, when the distance between the longitude and latitude of the accident site and the longitude and latitude of the centers of two or more intersections is less than or equal to the first distance threshold (such as 100m), the traffic accident is recorded as an accident at the nearest intersection.

[0038] In some embodiments, the total number of traffic accidents K recorded at each intersection and the corresponding intersection safety risk coefficient ω are counted. _node Specifically, the intersection safety risk coefficient is calculated according to the following formula (1):

[0039]

[0040] Among them, ω _node Represents the intersection safety risk factor; death _i Represents the number of fatalities in the i-th traffic accident matching the intersection; injury _i represents the number of injured persons in the i-th traffic accident matching the intersection; K represents the total number of traffic accidents matching the intersection.

[0041] In some embodiments, when the road network object is a road segment, the projected distance between the accident site and the road segment is calculated based on the longitude and latitude of the accident site and the longitude and latitude of the road segment. If the projected distance between the accident site and only one road segment is less than or equal to a second distance threshold, the accident is recorded as a traffic accident matching the road segment. If the projected distance between the accident site and multiple road segments is less than or equal to the second distance threshold, the accident is recorded as a traffic accident matching the road segment with the closest projected distance. Exemplarily, the second distance threshold is 50 meters. Of course, the second distance threshold can be flexibly set as needed.

[0042] In one example, a road segment range is created. Specifically, a rectangular area with the longitude and latitude of the road segment [(lon_start, lat_start), ..., (lon_end, lat_end)] as the center line and a certain distance (such as 10m) extending on both sides is the road segment range. For a certain traffic accident (the traffic accident is the remaining traffic accident except for the traffic accidents included in the intersection), vector projection is used to calculate the shortest distance from the longitude and latitude of the accident location to the road segment (that is, the projection distance). When the distance is less than or equal to a second distance threshold (such as 50m), the traffic accident is recorded as an accident occurring within this road segment (that is, the traffic accident matches this road segment). In particular, when the shortest distance between the longitude and latitude of the traffic accident location and two or more road segments is less than or equal to the second distance threshold (such as 50m), the traffic accident is recorded as an accident at the nearest road segment.

[0043] In some embodiments, the total number of recorded accidents P and the corresponding road safety risk coefficient ω of each road section are counted. _link Specifically, the road section safety risk coefficient is calculated according to the following formula (2):

[0044]

[0045] Among them, ω _link Represents the road section safety risk factor; death _j Represents the number of deaths in the j-th traffic accident matching the road segment; injury _j represents the number of injured persons in the jth traffic accident that matches the road segment; P represents the total number of traffic accidents that match the road segment.

[0046] In some embodiments, when determining traffic accidents matching each road network object based on the basic dataset, the traffic accidents matching each intersection are first screened from multiple traffic accidents. Then, traffic accidents matching each road segment are screened from the remaining traffic accidents. Finally, data on traffic accidents not included in intersections and road segments are removed from the basic dataset.

[0047] Step 103: Based on the safety risk coefficient of each road network object, select the top N road network objects with the highest safety risk coefficients from the multiple road network objects as high-risk road network objects, where N is a positive integer.

[0048] In some embodiments, screening out top N road network objects with the highest safety risk coefficients from a plurality of road network objects as high-risk road network objects based on the safety risk coefficient of each road network object includes:

[0049] In the case where the road network object is an intersection, the intersection safety risk coefficients of multiple intersections are sorted from high to low, and the intersection with the highest number of intersections is regarded as a high-risk intersection;

[0050] When the road network object is a road section, the road safety risk coefficients of the multiple road sections are sorted from high to low, and the second highest number of road sections are taken as high-risk sections.

[0051] In some embodiments, the first number is determined based on the total number of traffic accidents matching the intersection and the first percentage. Assuming the total number of traffic accidents matching the intersection is K and the first percentage is S1 (e.g., S1 = 1%), then the first number is K*S1. For example, all intersections within a built-up area of ​​a city are ranked according to their intersection safety risk coefficients, and the top 1% of these intersections are designated as high-risk intersections (danger_node).

[0052] In some implementations, the second number is determined based on the total number of traffic accidents matching the road segment and the second percentage. Assuming the total number of traffic accidents matching the road segment is P, and the second percentage is S2 (e.g., S2 = 1%), then the second number is P*S2. For example, all road segments within a built-up area of ​​a city are ranked according to their safety risk factors, and the top 1% of the ranked road segments are designated as high-risk segments (danger_link).

[0053] Step 104: performing association rule mining on the high-risk road network objects to obtain association rules for the high-risk road network objects. The association rules are rules between accident environment attributes and accident collision types.

[0054] In the embodiment of the present application, based on association rule mining, a combination of environmental attributes with a higher probability of traffic accidents is calculated for the high-risk intersections and / or high-risk road sections screened out in step 103.

[0055] In some embodiments, an accident attribute set is established for a high-risk road network, and the accident attribute set includes the following multiple attribute items: time period, weather, average road travel speed, traffic light control method, road non-motor vehicle flow, road conditions and accident collision type; association rules are mined on the accident attribute set to obtain association rules for high-risk road network objects.

[0056] For example, for the time period attribute item, there may be the following options: morning peak period 7:00-9:00, noon period 11:00-13:00, evening peak period 17:00-19:00, and night period 22:00-6:00 the next day.

[0057] For example, for the weather attribute item, there may be the following options: rainy day, snowy day, foggy day, sunny day.

[0058] For example, for the average road travel speed (car) attribute item, there may be the following options: low speed (≤19km / h), medium speed (20-35km / h), relatively high speed (36-60km / h), and high speed (>60km / h).

[0059] For example, for the signal light control mode (referred to as the signal control mode), there may be the following options: setting a left-turn non-motor vehicle signal light, setting a non-motor vehicle signal light, and no non-motor vehicle signal light.

[0060] For example, for the attribute item of road non-motor vehicle flow, there may be the following options: small (≤1000 veh / h), medium (1001-2000 veh / h), large (>2000 veh / h).

[0061] For example, for the road condition attribute item, there may be the following options: there is a non-motorized vehicle lane with organic non-physical isolation, there is a non-motorized vehicle lane without organic non-physical isolation, and there is no non-motorized vehicle lane.

[0062] For example, for the accident collision type attribute item, there may be the following options: side collision with a motor vehicle, head-on collision with a motor vehicle, rear-end collision with a motor vehicle, single-vehicle accident, and collision with a pedestrian.

[0063] In some embodiments, the support of each attribute item in the accident attribute set is calculated, and M attribute items with support greater than or equal to a minimum support threshold are screened out from multiple attribute items based on the support of each attribute item, as frequent attribute items, where M is a positive integer; multiple candidate rules are generated based on the frequent attribute items, and the candidate rules are rules between accident environment attributes and accident collision types, and the accident environment attributes include one or more of the following: time period, weather, average road travel speed, traffic light control method, road non-motor vehicle flow, and road conditions; the confidence and minimum lift of each candidate rule are calculated, and based on the confidence of each candidate rule, candidate rules with confidence greater than or equal to the minimum confidence are screened out from multiple candidate rules, and if the minimum lift of the screened candidate rule is greater than the minimum lift, the screened candidate rule is determined to be a valid rule, wherein the valid rule is an association rule for a high-risk road network object.

[0064] In association rule mining, support is defined as follows: the support of an item set refers to the frequency of its occurrence in a data set. In the present embodiment, an item set refers to a combination of environmental attributes (i.e., a combination of time period, weather, average road travel speed, signal control mode, non-motor vehicle traffic volume, road conditions, and accident collision type), and a data set refers to the aforementioned accident attribute set (including various combinations of environmental attributes). The support of an item set X is calculated as follows:

[0065]

[0066] Among them, Support(X) represents the support of item set X.

[0067] The minimum support threshold can be set by the user to filter out "meaningful" frequent itemsets from the accident attribute set. The screening condition is: if the support of an item set is greater than or equal to the minimum support threshold, the item set is considered to be a frequent item set (corresponding to the frequent attribute items described above).

[0068] In association rule mining, confidence is a key indicator for measuring the reliability of a rule, and is used to determine the probability that "if item set X appears, then item set Y also appears." The rule is in the form of: X→Y, which means "if X appears, then Y also appears." In the embodiment of the present application, X represents the accident environment attributes (such as time period, weather, average road travel speed, traffic light control method, road non-motor vehicle traffic volume, road conditions), and Y represents the accident collision type. The calculation formula for the confidence corresponding to the rule X→Y is:

[0069]

[0070] Among them, Confidence(X→Y) represents the confidence corresponding to rule X→Y; Support(X∪Y) represents the support of item sets X and Y appearing at the same time; Support(X) represents the support of item set X.

[0071] In association rule mining, lift is an indicator to measure the correlation between item sets X and Y. The calculation formula for the lift corresponding to rule X→Y is:

[0072]

[0073] Among them, Lift(X→Y) represents the lift corresponding to rule X→Y, Support(X∪Y) represents the support of item sets X and Y appearing at the same time; Support(X) represents the support of item set X; Support(Y) represents the support of item set Y.

[0074] In one example, a minimum support threshold is set to 10%. Frequent attribute items (i.e., attribute items with support greater than or equal to 10%) are filtered from the accident attribute set based on the minimum support threshold, and candidate rules are generated from the frequent attribute items. Next, a minimum confidence level is set to 70% and a minimum lift level is set to 1.2. Valid rules are filtered from the candidate rules based on the minimum confidence level and minimum lift level. Valid rules meet the following requirements: the confidence level of the rule is greater than or equal to the minimum confidence level, and the lift level of the rule is greater than or equal to the minimum lift level. Examples of the valid rules that are filtered out include: at high-risk intersections {evening rush hour, high speed, no non-motor vehicle signal lights, low non-motor vehicle traffic volume} → {head-on collision with a motor vehicle}, and at high-risk road sections {morning rush hour, rainy days, medium speed, no non-motor vehicle lanes} → {sideways collision with a motor vehicle}. Finally, the association rules for each high-risk intersection / road section are determined by ranking by confidence level.

[0075] Step 105: Setting a management and control strategy for high-risk road network objects based on the association rules of high-risk road network objects.

[0076] In the embodiment of the present application, a targeted management and control strategy is formulated for the high-risk intersections / road sections based on the association rules of the high-risk intersections / road sections screened out in step 104.

[0077] In some implementations, for vehicles with a higher risk of side collisions with motor vehicles, traffic engineering measures such as installing separation facilities for vehicles and non-motorized vehicles, setting non-motorized vehicle lanes, and setting reasonable vehicle speed limits are implemented. Law enforcement and control measures include dispatching police on the road during peak hours, conducting video patrols at night, and increasing the crackdown on speeding violations. Roadside safety information such as speed reduction and accident-prone driving are also provided in rainy and snowy weather.

[0078] In some implementations, for areas with increased risk of head-on collisions with motor vehicles, traffic engineering measures such as establishing non-motorized vehicle crosswalks at intersections and on sections of roads are implemented; police patrols are deployed during peak hours and video patrols are conducted at night; road lighting conditions are improved at night; and roadside safety information such as speed reduction and accident-prone driving are provided on rainy and snowy days. At high-risk intersections, left-turn single-crossing or left-turn double-crossing traffic organization methods are implemented based on non-motorized vehicle traffic flow; non-motorized vehicle signal lights are installed, and the "early start and early stop" phases of non-motorized vehicles are optimized. At night, enforcement of red light running and speeding violations by both motor vehicles and non-motorized vehicles is increased.

[0079] In some implementations, the risk of rear-end collisions with motor vehicles is increased by improving road lighting conditions at night; providing roadside safety information such as slowing down and frequent accidents on rainy and snowy days; and strengthening enforcement of speeding violations during peak hours.

[0080] In some implementations, the risk of single-vehicle accidents is enhanced by improving road lighting conditions at night; providing roadside safety information such as slowing down and driving slowly during rainy and snowy days, and promoting the installation of vehicle and non-motorized vehicle separation facilities, non-motorized vehicle lanes, and reasonable vehicle speed limits.

[0081] In some embodiments, the risk of pedestrian collisions is enhanced by: improving road lighting conditions during nighttime hours; and installing isolation facilities on sidewalks.

[0082] The technical solution of the embodiments of this application, based on a large amount of historical data on electric bicycle traffic accidents, accurately matches the accident locations with the road network structure to identify high-risk intersections and road sections for electric bicycle traffic. By mining and analyzing the association rules between accidents and the road environment, high-risk factors in the electric bicycle traffic environment are identified. Based on the spatiotemporal characteristics of electric bicycle traffic risks, management and control strategies and measures are formulated and categorized to achieve precise risk management and accident prevention, thereby improving the safety of electric bicycle traffic on urban roads.

[0083] Figure 2 Schematic diagram of the structure of the electric bicycle traffic risk control device provided in the embodiment of the present application. Figure 2 As shown, the electric bicycle traffic risk control device includes:

[0084] A construction unit 201 is configured to construct a basic data set, wherein the basic data set includes electric bicycle traffic accident data and road network topology data, wherein the electric bicycle traffic accident data includes data of multiple traffic accidents, and the road network topology data includes multiple;

[0085] A matching unit 202 is configured to determine a traffic accident matching each road network object based on the basic data set, and calculate a safety risk coefficient of each road network object based on the traffic accident matching each road network object;

[0086] a risk identification unit 203 configured to screen out top N road network objects with the highest safety risk coefficients from the plurality of road network objects according to the safety risk coefficient of each road network object, as high-risk road network objects, where N is a positive integer;

[0087] An association rule mining unit 204 is configured to mine association rules for the high-risk road network object to obtain association rules for the high-risk road network object, wherein the association rules are rules between accident environment attributes and accident collision types;

[0088] The management and control unit 205 is configured to set a management and control strategy for the high-risk road network object according to the association rule of the high-risk road network object.

[0089] In some embodiments, the traffic accident data includes one or more of the following fields: accident number, longitude and latitude of the accident location, date of accident, time of accident, number of deaths in the accident, number of injuries in the accident;

[0090] In the case where the road network object is an intersection, the data of the road network object includes one or more of the following fields: intersection number, longitude and latitude of the intersection center point, and intersection type; in the case where the road network object is a road section, the data of the road network object includes one or more of the following fields: road section number, longitude and latitude of the road section, road section type, road section length, and the form of separation between motor vehicles and non-motor vehicles.

[0091] In some embodiments, the matching unit 202 is used to calculate the distance between the location of the traffic accident and the intersection based on the longitude and latitude of the accident location and the longitude and latitude of the intersection center of the intersection when the road network object is an intersection; if the distance between the location of the traffic accident and only one intersection is less than or equal to a first distance threshold, the traffic accident is recorded as a traffic accident matching the intersection; if the distance between the location of the traffic accident and multiple intersections is less than or equal to the first distance threshold, the traffic accident is recorded as a traffic accident matching the nearest intersection; for the case where the road network object is a road section, calculate the projected distance between the location of the traffic accident and the road section based on the longitude and latitude of the accident location and the longitude and latitude of the road section; if the projected distance between the location of the traffic accident and only one road section is less than or equal to a second distance threshold, the traffic accident is recorded as a traffic accident matching the road section; if the projected distance between the location of the traffic accident and multiple road sections is less than or equal to the second distance threshold, the traffic accident is recorded as a traffic accident matching the road section with the closest projected distance;

[0092] In the process of determining the traffic accidents matching each road network object according to the basic data set, the traffic accidents matching each intersection are first screened out from the multiple traffic accidents, and then the traffic accidents matching each road section are screened out from the remaining traffic accidents after screening.

[0093] In some implementations, the matching unit 202 is configured to calculate the intersection safety risk coefficient according to the following formula when the road network object is an intersection:

[0094]

[0095] Among them, ω _node Represents the intersection safety risk factor; death _i Represents the number of fatalities in the i-th traffic accident matching the intersection; injury _i represents the number of injured persons in the i-th traffic accident matching the intersection; K represents the total number of traffic accidents matching the intersection;

[0096] The matching unit 202 is configured to calculate the road section safety risk coefficient according to the following formula when the road network object is a road section:

[0097]

[0098] Among them, ω _link Represents the road section safety risk factor; death _j Represents the number of deaths in the j-th traffic accident matching the road segment; injury _jrepresents the number of injured persons in the jth traffic accident that matches the road segment; P represents the total number of traffic accidents that match the road segment.

[0099] In some embodiments, the risk identification unit 203 is used to, when the road network object is an intersection, sort the intersection safety risk coefficients of the multiple intersections from high to low, and select the first number of intersections with the highest order as high-risk intersections; and when the road network object is a road section, sort the section safety risk coefficients of the multiple road sections from high to low, and select the second number of road sections with the highest order as high-risk sections.

[0100] In some embodiments, the association rule mining unit 204 is used to establish an accident attribute set for the high-risk road network, where the accident attribute set includes the following multiple attribute items: time period, weather, average road travel speed, traffic light control method, road non-motor vehicle flow, road conditions, and accident collision type; and perform association rule mining on the accident attribute set to obtain association rules for the high-risk road network object.

[0101] In some embodiments, the association rule mining unit 204 is used to calculate the support of each attribute item in the accident attribute set, and screen out M attribute items with support greater than or equal to a minimum support threshold from the multiple attribute items based on the support of each attribute item, as frequent attribute items, where M is a positive integer; generate multiple candidate rules based on the frequent attribute items, and the candidate rules are rules between accident environment attributes and accident collision types, and the accident environment attributes include one or more of the following: time period, weather, average road travel speed, traffic light control method, road non-motor vehicle flow, and road conditions; calculate the confidence and minimum lift of each candidate rule, and screen out candidate rules with confidence greater than or equal to the minimum confidence from the multiple candidate rules based on the confidence of each candidate rule; if the minimum lift of the screened candidate rule is greater than the minimum lift, the screened candidate rule is determined to be a valid rule, wherein the valid rule is the association rule of the high-risk road network object.

[0102] It should be understood by those skilled in the art that Figure 2 The functions implemented by each unit in the electric bicycle traffic risk control device shown can be understood by referring to the relevant description of the aforementioned method. Figure 2 The functions of the various units in the electric bicycle traffic risk control device shown can be implemented by a program running on a processor, or by a specific logic circuit.

[0103] Figure 3 This is a schematic structural diagram of an electric bicycle traffic risk management device provided in an embodiment of the present application. Figure 3The electric bicycle traffic risk management and control device shown includes a processor 310, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0104] Alternatively, as Figure 3 As shown, the electric bicycle traffic risk management and control device may further include a memory 320. The processor 310 may call and run a computer program from the memory 320 to implement the method in the embodiment of the present application.

[0105] The memory 320 may be a separate device independent of the processor 310 , or may be integrated into the processor 310 .

[0106] The electric bicycle traffic risk control device can specifically be a server, and the electric bicycle traffic risk control device can implement the corresponding processes implemented by each method of the embodiment of the present application. For the sake of brevity, it will not be repeated here.

[0107] Figure 4 It is a schematic structural diagram of the chip of an embodiment of the present application. Figure 4 The chip shown includes a processor 410, which can call and run a computer program from a memory to implement the method in the embodiment of the present application.

[0108] Alternatively, as Figure 4 As shown, the chip may further include a memory 420. The processor 410 may call and run a computer program from the memory 420 to implement the method in the embodiment of the present application.

[0109] The memory 420 may be a separate device independent of the processor 410 , or may be integrated into the processor 410 .

[0110] Optionally, the chip may further include an input interface 430. The processor 410 may control the input interface 430 to communicate with other devices or chips, and specifically, may obtain information or data sent by other devices or chips.

[0111] Optionally, the chip may further include an output interface 440. The processor 410 may control the output interface 440 to communicate with other devices or chips, and specifically, may output information or data to other devices or chips.

[0112] This chip can implement the corresponding processes of each method implemented in the embodiments of this application. For the sake of brevity, they will not be described here.

[0113] The present application also provides a computer-readable storage medium for storing a computer program. This computer-readable storage medium can be applied to the electric bicycle traffic risk management device in the present application, and the computer program causes a computer to execute the corresponding processes implemented by the various methods in the present application. For the sake of brevity, these procedures are not further described here.

[0114] The present application also provides a computer program product, including computer program instructions. This computer program product can be applied to the electric bicycle traffic risk management device in the present application, and the computer program instructions cause a computer to execute the corresponding processes implemented by the various methods in the present application. For the sake of brevity, these instructions are not further described here.

[0115] Those skilled in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0116] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described devices and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0117] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the units is merely a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0118] The above description is merely a specific embodiment of the present application, but the scope of protection of the present application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in the present application should be included in the scope of protection of the present application. Therefore, the scope of protection of the present application should be based on the scope of protection of the claims.

Claims

1. A method for controlling the risk of electric bicycle traffic, characterized in that: The method comprises: Constructing a basic data set, wherein the basic data set includes electric bicycle traffic accident data and road network topology data, wherein the electric bicycle traffic accident data includes data of multiple traffic accidents, and the road network topology data includes data of multiple road network objects, wherein the multiple road network objects include multiple intersections and / or multiple road sections; Determining traffic accidents matching each road network object according to the basic data set, and calculating a safety risk coefficient of each road network object according to the traffic accidents matching each road network object; According to the safety risk coefficient of each road network object, first N road network objects with the highest safety risk coefficients are screened out from the plurality of road network objects as high-risk road network objects, where N is a positive integer; Performing association rule mining on the high-risk road network object to obtain association rules for the high-risk road network object, wherein the association rules are rules between accident environment attributes and accident collision types; According to the association rules of the high-risk road network objects, a management and control strategy for the high-risk road network objects is set.

2. The method according to claim 1, characterized in that The traffic accident data includes one or more of the following fields: accident number, latitude and longitude of the accident location, accident date, accident time, number of deaths in the accident, number of injuries in the accident; In the case where the road network object is an intersection, the data of the road network object includes one or more of the following fields: intersection number, longitude and latitude of the intersection center point, and intersection type; in the case where the road network object is a road section, the data of the road network object includes one or more of the following fields: road section number, longitude and latitude of the road section, road section type, road section length, and the form of separation between motor vehicles and non-motor vehicles.

3. The method according to claim 2, characterized in that Determining a traffic accident matching each road network object according to the basic data set includes: In the case where the road network object is an intersection, the distance between the location of the traffic accident and the intersection is calculated based on the longitude and latitude of the location of the traffic accident and the longitude and latitude of the intersection center; if the distance between the location of the traffic accident and only one intersection is less than or equal to a first distance threshold, the traffic accident is recorded as a traffic accident matching the intersection; if the distance between the location of the traffic accident and multiple intersections is less than or equal to the first distance threshold, the traffic accident is recorded as a traffic accident matching the nearest intersection; In the case where the road network object is a road segment, the projected distance between the traffic accident location and the road segment is calculated based on the latitude and longitude of the accident location and the latitude and longitude of the road segment; if the projected distance between the traffic accident location and only one road segment is less than or equal to a second distance threshold, the traffic accident is recorded as a traffic accident matching the road segment; if the projected distances between the traffic accident location and multiple road segments are all less than or equal to the second distance threshold, the traffic accident is recorded as a traffic accident matching the road segment with the closest projected distance; In the process of determining the traffic accidents matching each road network object according to the basic data set, the traffic accidents matching each intersection are first screened out from the multiple traffic accidents, and then the traffic accidents matching each road section are screened out from the remaining traffic accidents after screening.

4. The method according to claim 2, characterized in that The calculating of the safety risk coefficient of each road network object according to the traffic accidents matching each road network object includes: When the road network object is an intersection, the intersection safety risk coefficient is calculated according to the following formula: Among them, ω _node Represents the intersection safety risk factor; death _i Represents the number of fatalities in the i-th traffic accident matching the intersection; injury _i represents the number of injured persons in the i-th traffic accident matching the intersection; K represents the total number of traffic accidents matching the intersection; When the road network object is a road section, the road section safety risk coefficient is calculated according to the following formula: Among them, ω _link Represents the road section safety risk factor; death _j Represents the number of deaths in the j-th traffic accident matching the road segment; injury _j represents the number of injured persons in the jth traffic accident that matches the road segment; P represents the total number of traffic accidents that match the road segment.

5. The method according to claim 4, characterized in that The step of selecting top N road network objects with the highest safety risk coefficients from the plurality of road network objects according to the safety risk coefficient of each road network object as high-risk road network objects includes: In the case where the road network object is an intersection, the intersection safety risk coefficients of the plurality of intersections are sorted from high to low, and the first number of intersections ranked high are regarded as high-risk intersections; In the case where the road network object is a road section, the road section safety risk coefficients of the multiple road sections are sorted from high to low, and the second number of road sections with the highest sorting are regarded as high-risk road sections.

6. The method according to any one of claims 1 to 5, characterized in that The performing association rule mining on the high-risk road network object to obtain the association rule of the high-risk road network object includes: For the high-risk road network, an accident attribute set is established, wherein the accident attribute set includes the following attributes: time period, weather, average travel speed on the road, signal light control mode, non-motor vehicle flow on the road, road conditions, and accident collision type; Association rules are mined on the accident attribute set to obtain association rules of the high-risk road network objects.

7. The method according to claim 6, characterized in that The performing association rule mining on the accident attribute set to obtain the association rules of the high-risk road network object includes: Calculating the support of each attribute item in the accident attribute set, and selecting M attribute items whose support is greater than or equal to a minimum support threshold from the multiple attribute items according to the support of each attribute item, as frequent attribute items, where M is a positive integer; Generate multiple candidate rules based on the frequent attribute items, wherein the candidate rules are rules between accident environment attributes and accident collision types, and the accident environment attributes include one or more of the following: time period, weather, average road travel speed, signal light control method, road non-motor vehicle flow, and road conditions; The confidence and minimum lift of each candidate rule are calculated, and according to the confidence of each candidate rule, a candidate rule having a confidence greater than or equal to the minimum confidence is screened out from the multiple candidate rules; if the minimum lift of the screened candidate rule is greater than the minimum lift, the screened candidate rule is determined to be a valid rule, wherein the valid rule is the association rule of the high-risk road network object.

8. An electric bicycle traffic risk control device, characterized in that: The device comprises: A construction unit is used to construct a basic data set, wherein the basic data set includes electric bicycle traffic accident data and road network topology data, wherein the electric bicycle traffic accident data includes data of multiple traffic accidents, and the road network topology data includes multiple; a matching unit, configured to determine a traffic accident matching each road network object based on the basic data set, and calculate a safety risk coefficient of each road network object based on the traffic accident matching each road network object; a risk identification unit, configured to screen out top N road network objects with the highest safety risk coefficients from the plurality of road network objects according to the safety risk coefficient of each road network object, as high-risk road network objects, where N is a positive integer; an association rule mining unit, configured to perform association rule mining on the high-risk road network object to obtain an association rule for the high-risk road network object, wherein the association rule is a rule between accident environment attributes and accident collision types; The management and control unit is used to set a management and control strategy for the high-risk road network object according to the association rule of the high-risk road network object.

9. An electric bicycle traffic risk control device, characterized in that: include: A processor and a memory, the memory being used to store a computer program, the processor being used to call and run the computer program stored in the memory to execute the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that Used to store a computer program, wherein the computer program enables the electric bicycle traffic risk management device to execute the method as described in any one of claims 1 to 7.

Images