Multi-dimensional Road Network Data Integrated Supervision System and Method Based on Traffic Business Data

Abstract

The present invention discloses a multi-dimensional road network data integrated supervision system and method based on traffic service data, which relates to the technical field of multi-dimensional road network data supervision. It includes constructing a road network supervision cloud platform, obtaining historical vehicle passing records of road sections, obtaining historical vehicle passing speed data from the historical vehicle passing records, and conducting traffic abnormality assessment on road sections within the city; analyzing the degree of abnormal influence of traffic flow on the traffic of characteristic road sections to obtain characteristic vehicle passing data; obtaining historical passing data of historical public transport vehicles within the city, and combining with the historical vehicle passing data of characteristic road sections to construct a vehicle passing prediction model to predict the vehicle passing conditions of characteristic road sections in the current period; obtaining the passing data of public transport vehicles within the city in the current period, and combining with the characteristic vehicle passing data of characteristic road sections to conduct intelligent supervision on the traffic of characteristic road sections.

Description

Technical Field

[0001] The present invention relates to the technical field of multi-dimensional road network data supervision, and specifically to an integrated supervision system and method for multi-dimensional road network data based on traffic service data. Background Art

[0002] Traffic service data refers to various types of data related to the transportation system, which can be used for analyzing, managing, and optimizing transportation. The road network refers to a network system composed of various traffic roads connected to each other, and is an important part of transportation. Based on traffic service data, road network data can be better supervised.

[0003] The urban traffic network is composed of different roads connected to each other. The widths, road conditions, and vehicle passing requirements of different roads are all different. Both public transportation vehicles and private cars need to pass through the urban traffic network, and the passing requirements of these vehicles are different. For example, public transportation vehicles basically travel according to pre-set passing routes within a fixed time, while private cars do not have this characteristic in terms of passing time and passing routes. However, in actual traffic data supervision, the urban traffic is often simply supervised based on vehicle flow, rarely considering the impact of different roads and vehicles on traffic. This makes the prediction and analysis of the urban traffic situation inaccurate, not only causing traffic congestion, but also possibly leading to traffic safety accidents. Summary of the Invention

[0004] The purpose of the present invention is to provide an integrated supervision system and method for multi-dimensional road network data based on traffic service data to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: An integrated supervision method for multi-dimensional road network data based on traffic service data, the method comprising:

[0006] Step S100: Construct a road network supervision cloud platform, obtain the historical traffic accident records of sections in the city, obtain the historical vehicle passing records of the sections, obtain the historical vehicle passing speed data from the historical vehicle passing records, and evaluate the traffic abnormality of the sections in the city to obtain characteristic sections;

[0007] Step S200: Obtain the historical vehicle passing records within the characteristic sections, obtain the historical vehicle passing data from the historical vehicle passing records, analyze the abnormal influence degree of the traffic flow on the traffic of the characteristic sections, and obtain characteristic vehicle passing data;

[0008] Step S300: Obtain the historical traffic data of the characteristic road section, obtain the historical passing data of the historical public transportation vehicles in the city, and combine the historical vehicle passing data of the characteristic road section to construct a vehicle passing prediction model to predict the vehicle passing condition of the characteristic road section in the current cycle, and obtain the vehicle passing prediction data;

[0009] Step S400: Obtain the vehicle passing prediction data of the characteristic road section in the current cycle, obtain the passing data of the public transportation vehicles in the city in the current cycle, and combine the characteristic vehicle passing data of the characteristic road section to conduct intelligent supervision on the traffic of the characteristic road section.

[0010] Further, step S100 includes:

[0011] Step S101: Obtain the historical traffic accident records of the road sections in the city, extract the historical traffic accident data from the historical traffic accident records, and the historical traffic accident data includes the total number of vehicles involved in traffic accidents in the historical traffic accident records;

[0012] Step S102: Aggregate the vehicles passing through the road section every historical cycle to obtain the historical vehicle passing records of the road section, and extract the historical vehicle passing speed data from the historical vehicle passing records. The historical vehicle passing speed data includes the average speed of the passing vehicles on the road section in the historical cycle;

[0013] Step S103: Conduct a traffic abnormality assessment on each road section in the city. Among them, the specific assessment process for the traffic abnormality of the a-th road section in the city includes:

[0014] Obtain a number of historical traffic accident records of the a-th road section in each historical cycle, and calculate the traffic accident characteristic value of the a-th road section in each historical cycle. Among them, the traffic accident characteristic value P of the a-th road section in the b-th historical cycle a,b :

[0015] ,

[0016] Among them, j represents the total number of historical traffic accident records of the a-th road section in the b-th historical cycle; M a b,x represents the total number of vehicles involved in the x-th historical traffic accident record of the a-th road section in the b-th historical cycle;

[0017] Obtain the maximum value P of the traffic accident characteristic values of each road section in each historical cycle max ,the minimum value P min ;

[0018] Step S104: Obtain the preset maximum vehicle speed limit v of the a-th road section a, calculate the traffic anomaly score E of the a-th section a :

[0019] ,

[0020] where P a,i represents the traffic accident eigenvalue of the a-th section in the i-th historical period; v a,i represents the average speed of the passing vehicles on the a-th section in the i-th historical period; n represents the total number of each historical period; β1 represents the preset first characteristic proportionality coefficient; β2 represents the preset second characteristic proportionality coefficient; β1 + β2 = 1;

[0021] Step S105: When the traffic anomaly score E a is greater than the preset traffic anomaly score threshold, it is determined that the a-th section has traffic anomalies, and the a-th section is recorded as a characteristic section.

[0022] Furthermore, Step S200 includes:

[0023] Step S201: Obtain the historical vehicle passing records of the characteristic section, and calculate the characteristic passing congestion value of several historical vehicle passing records. Among them, the characteristic passing congestion value F of the c-th historical vehicle passing record of the characteristic section c :

[0024] ,

[0025] where v’ represents the maximum speed limit of the vehicles on the characteristic section; v’ c represents the average speed of the passing vehicles in the c-th historical vehicle passing record;

[0026] Step S202: When the characteristic passing congestion value F c is greater than the preset characteristic passing congestion threshold, it is determined that there is vehicle congestion in the historical characteristic section in the c-th historical vehicle passing record, and the c-th historical vehicle passing record is recorded as the characteristic historical vehicle passing record of the characteristic section;

[0027] Step S203: Obtain the historical vehicle passing data from the historical vehicle passing records. The historical vehicle passing data is the total number of passing vehicles in the historical vehicle passing records. Obtain several characteristic historical vehicle passing records in the characteristic section, and obtain the minimum value M of the total number of passing vehicles in the characteristic section in several characteristic historical vehicle passing records min , obtain the maximum value M’ of the total number of passing vehicles in several historical vehicle passing records in the characteristic section max , when the maximum value M’ max is greater than the minimum value M min , take the maximum value M’ maxThe characteristic vehicle threshold M' of the characteristic road section;

[0028] Conversely, when the maximum value M' max is less than or equal to the minimum value M min , take the minimum value M min as the characteristic vehicle threshold M' of the characteristic road section, and obtain the characteristic vehicle passing data of the characteristic road section.

[0029] Further, step S300 includes:

[0030] Step S301: Obtain the historical traffic data of the characteristic road section in each historical period. The historical traffic data includes the data corresponding to several traffic characteristic indicators of the characteristic road section;

[0031] Step S302: Obtain the historical passing data of the historical public transport vehicles in the city. The historical passing data includes the passing routes of the historical public transport vehicles in the historical period. Obtain the historical vehicle passing data of the characteristic road section. When the passing route of the historical public transport vehicle includes the characteristic road section, record the historical public transport vehicle as the marked historical public transport vehicle of the characteristic road section;

[0032] Step S303: Obtain the historical vehicle passing data of the characteristic road section. Obtain the total number of passing vehicles of the characteristic road section in each historical period from the historical vehicle passing data, and calculate the characteristic value of the passing vehicles of the characteristic road section in each historical period. Among them, the characteristic value K of the passing vehicles of the characteristic road section in the g-th historical period g =M g -γ g , M g represents the total number of passing vehicles of the characteristic road section in the g-th historical period, and γ g represents the total number of historical public transport vehicles passing through the characteristic road section in the g-th historical period;

[0033] Step S304: Construct a vehicle passing prediction model. Use several traffic characteristic indicators of the characteristic road section as the input data of the vehicle passing prediction model, use the characteristic value of the passing vehicles of the characteristic road section as the target data, and divide the historical traffic data and the characteristic value of the passing vehicles of the characteristic road section in each historical period into a training set and a test set, and train and test the vehicle passing prediction model;

[0034] Step S305: Obtain the average value Y of the characteristic values of the passing vehicles of the characteristic road section in each historical period △ , obtain the vehicle passing prediction model, and calculate the predicted values of the characteristic values of the passing vehicles of the characteristic road section in several historical periods. Calculate the model prediction score R of the vehicle passing prediction model:

[0035] ,

[0036] where Y z represents the characteristic value of the passing vehicles on the characteristic road section in the z-th historical period among a number of historical periods; Y △,z represents the predicted value of the characteristic value of the passing vehicles on the characteristic road section in the z-th historical period by the vehicle passing prediction model; q represents the total number of a number of historical periods;

[0037] Step S306: When the model prediction score of the vehicle passing prediction model is greater than the preset model prediction score, it is determined that the vehicle passing prediction model has prediction ability, obtain the data corresponding to several traffic characteristic indicators of the characteristic road section in the current period, and use the vehicle passing prediction model to predict the vehicle passing condition of the characteristic road section in the current period to obtain vehicle passing prediction data;

[0038] When constructing the vehicle passing prediction model, the target data of the set model is processed, that is, public transport vehicles are removed from the vehicles passing through the characteristic road section, because in real life, public transport vehicles have fixed passing times and passing routes and generally do not change due to road section conditions. Therefore, using the characteristic values of the passing vehicles on the road section as the target data can more accurately predict the traffic conditions of the road section, thereby making the formulated management strategies more scientific and effective.

[0039] Further, step S400 includes:

[0040] Step S401: Obtain the vehicle passing prediction data of the characteristic road section in the current period, and obtain the predicted value of the characteristic value of the passing vehicles on the characteristic road section in the current period from the vehicle passing prediction data;

[0041] Step S402: Obtain the passing data of the public transport vehicles in the current period. The passing data includes the passing time and passing route of the public transport vehicles. When the passing route of the public transport vehicles includes the characteristic road section and the passing time of the public transport vehicles within the characteristic road section is within the current period, record the public transport vehicles as several characteristic public transport vehicles on the characteristic road section in the current period;

[0042] Step S403: Obtain the total number of each characteristic public transport vehicle on the characteristic road section in the current period. When the sum of the predicted value of the characteristic value of the passing vehicles on the characteristic road section in the current period and the total number of several characteristic public transport vehicles is less than the characteristic vehicle threshold in the characteristic vehicle passing data on the characteristic road section, it is determined that the traffic on the characteristic road section in the current period is normal;

[0043] Step S404: When the sum of the total number of characteristic road sections in the current cycle is greater than the characteristic vehicle threshold, it is determined that there is traffic abnormality in the characteristic road sections in the current cycle. Obtain the vehicles with characteristic road sections in the navigation routes within the city in the current cycle, send a prompt to the users of the vehicles through the navigation system, and perform navigation route update recommendations to intelligently supervise the traffic of the characteristic road sections.

[0044] In order to better implement the above steps, a multi-dimensional road network data integrated supervision system based on traffic business data is also proposed. The system includes a characteristic road section module, a characteristic vehicle passing data module, a vehicle passing prediction data module, and an intelligent supervision module;

[0045] The characteristic road section module is used to evaluate the traffic abnormality of the road sections within the city to obtain characteristic road sections;

[0046] The characteristic vehicle passing data module is used to analyze the abnormal influence degree of traffic flow on the traffic of characteristic road sections to obtain characteristic vehicle passing data;

[0047] The vehicle passing prediction data module is used to obtain the historical traffic data of characteristic road sections, obtain the historical passing data of historical public transport vehicles within the city, construct a vehicle passing prediction model, and predict the vehicle passing condition of characteristic road sections in the current cycle to obtain vehicle passing prediction data;

[0048] The intelligent supervision module is used to obtain the passing data of public transport vehicles within the city, and combine the characteristic vehicle passing data of characteristic road sections to intelligently supervise the traffic of characteristic road sections.

[0049] Furthermore, the characteristic road section module includes a traffic abnormality scoring unit and a characteristic road section unit;

[0050] The traffic abnormality scoring unit is used to calculate the traffic accident characteristic values of road sections in each historical cycle, and calculate the traffic abnormality score of road sections according to the traffic accident characteristic values;

[0051] The characteristic road section unit is used to determine the traffic abnormality of road sections according to the traffic abnormality score to obtain characteristic road sections.

[0052] Furthermore, the characteristic vehicle passing data module includes a characteristic passing congestion value unit and a characteristic vehicle passing data unit;

[0053] The characteristic passing congestion value unit is used to obtain the historical vehicle passing records of characteristic road sections and calculate the characteristic passing congestion values of the historical vehicle passing records;

[0054] A characteristic vehicle passing data unit is used to determine historical vehicle passing records according to characteristic passing congestion values, and obtain characteristic vehicle thresholds for characteristic road sections, so as to obtain characteristic vehicle passing data for characteristic road sections.

[0055] Furthermore, the vehicle passing prediction data module includes a model construction unit and a vehicle passing prediction data unit;

[0056] The model construction unit is used to obtain historical traffic data of characteristic road sections, obtain historical passing data of historical public transport vehicles in the city, and combine the historical vehicle passing data of characteristic road sections to construct a vehicle passing prediction model;

[0057] The vehicle passing prediction data unit is used to obtain data corresponding to several traffic characteristic indicators of a characteristic road section in the current period, and use the vehicle passing prediction model to predict the vehicle passing conditions of the characteristic road section in the current period, so as to obtain vehicle passing prediction data.

[0058] Furthermore, the intelligent supervision module includes an intelligent supervision unit;

[0059] The intelligent supervision unit is used to determine traffic anomalies of characteristic road sections, obtain vehicles on navigation routes in the city that contain characteristic road sections in the current period, send prompts to the users of the vehicles through the navigation system, recommend updated navigation routes, and conduct intelligent supervision of the traffic of characteristic road sections.

[0060] Compared with the prior art, the beneficial effects of the present invention are as follows: The present invention realizes the integrated supervision of multi-dimensional road network data. Firstly, traffic anomalies of each road section are determined from the vehicle congestion conditions and traffic accident occurrence conditions of each road section in the historical period, and the road sections with frequent accidents and congestion are obtained. Also, considering that the actual situations of different road sections are different, the accommodation capacity of different road sections for passing vehicles is analyzed. At the same time, a prediction model is constructed to predict the passing vehicles of road sections in the current period, and the influence of public transport vehicles on the traffic conditions of road sections is considered. Then, the passing vehicles of different road sections in the city are managed, thereby greatly reducing the occurrence of traffic congestion phenomena on urban roads and also reducing the risk of traffic accidents to a certain extent. Brief Description of the Drawings

[0061] Figure 1 is the method flowchart of the integrated supervision system and method of multi-dimensional road network data based on traffic service data of the present invention;

[0062] Figure 2 is the module schematic diagram of the integrated supervision system and method of multi-dimensional road network data based on traffic service data of the present invention. Detailed Embodiments

[0063] The following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0064] Embodiment: As Figure 1 - Figure 2 shown, the present invention provides a technical solution, a multi-dimensional road network data integrated supervision method based on traffic service data. The method includes:

[0065] Step S100: Construct a road network supervision cloud platform, obtain the historical traffic accident records of the road sections in the city, obtain the historical vehicle passing records of the road sections, obtain the historical vehicle passing speed data from the historical vehicle passing records, and conduct a traffic anomaly assessment on the road sections in the city to obtain characteristic road sections;

[0066] Among them, step S100 includes:

[0067] Step S101: Obtain the historical traffic accident records of the road sections in the city, extract the historical traffic accident data from the historical traffic accident records. The historical traffic accident data includes the total number of vehicles involved in traffic accidents in the historical traffic accident records;

[0068] Step S102: Aggregate the vehicles passing through the road sections at each historical period to obtain the historical vehicle passing records of the road sections, extract the historical vehicle passing speed data from the historical vehicle passing records. The historical vehicle passing speed data includes the average speed of the passing vehicles on the road sections within the historical period;

[0069] Step S103: Conduct a traffic anomaly assessment on each road section in the city. Among them, the specific assessment process of the traffic anomaly of the a-th road section in the city includes:

[0070] Obtain a number of historical traffic accident records of the a-th road section in each historical period, and calculate the traffic accident characteristic value of the a-th road section in each historical period. Among them, the traffic accident characteristic value P of the a-th road section in the b-th historical period a,b :

[0071] ,

[0072] where j represents the total number of historical traffic accident records of the a-th road section in the b-th historical period; M a b,x represents the total number of vehicles involved in the x-th historical traffic accident record of the a-th road section in the b-th historical period;

[0073] For example, for the first road segment, the total number j of historical traffic accident records in the third historical period is represented as 3; for the first road segment, the total number M of vehicles involved in traffic accidents in the first historical traffic accident record in the third historical period 1 3,1 is 4; for the first road segment, the total number M of vehicles involved in traffic accidents in the second historical traffic accident record in the third historical period 1 3,2 is 5; for the first road segment, the total number M of vehicles involved in traffic accidents in the third historical traffic accident record in the third historical period 1 3,3 is 7;

[0074] Calculate the traffic accident eigenvalue P of the first road segment in the third historical period 1,3 :

[0075] ,

[0076] Obtain the maximum value P and minimum value P of the traffic accident eigenvalues of each road segment in each historical period max ; min ;

[0077] Step S104: Obtain the preset maximum speed limit v of vehicles on the a-th road segment a , and calculate the traffic anomaly score E of the a-th road segment a :

[0078] ,

[0079] where P a,i represents the traffic accident eigenvalue of the a-th road segment in the i-th historical period; v a,i represents the average speed of passing vehicles on the a-th road segment in the i-th historical period; n represents the total number of historical periods; β1 represents a preset first characteristic proportionality coefficient; β2 represents a preset second characteristic proportionality coefficient; β1 + β2 = 1;

[0080] Step S105: When the traffic anomaly score E a is greater than the preset traffic anomaly score threshold, determine that the a-th road segment is traffic abnormal, and mark the a-th road segment as a characteristic road segment;

[0081] Step S200: Obtain the historical vehicle passing records within the characteristic road segment, obtain the historical vehicle passing data from the historical vehicle passing records, and analyze the abnormal influence degree of the traffic flow on the traffic of the characteristic road segment to obtain the characteristic vehicle passing data;

[0082] Among them, step S200 includes:

[0083] Step S201: Obtain the historical vehicle passing records of the characteristic road section, and calculate the characteristic passing congestion values of several historical vehicle passing records. Among them, the characteristic passing congestion value F of the c-th historical vehicle passing record of the characteristic road section c :

[0084] ,

[0085] where v’ represents the maximum speed limit of vehicles on the characteristic road section; v’ c represents the average speed of the passing vehicles in the c-th historical vehicle passing record;

[0086] For example, the maximum speed limit v’ of vehicles on the characteristic road section is 60 km / h; the average speed v’2 of the passing vehicles in the 2nd historical vehicle passing record is 20 km / h;

[0087] Calculate the characteristic passing congestion value F2 of the 2nd historical vehicle passing record of the characteristic road section:

[0088] ,

[0089] Step S202: When the characteristic passing congestion value F c is greater than the preset characteristic passing congestion threshold, it is determined that there is vehicle congestion in the historical characteristic road section in the c-th historical vehicle passing record, and the c-th historical vehicle passing record is recorded as the characteristic historical vehicle passing record of the characteristic road section;

[0090] Step S203: Obtain the historical vehicle passing data from the historical vehicle passing records. The historical vehicle passing data is the total number of passing vehicles in the historical vehicle passing records. Obtain several characteristic historical vehicle passing records in the characteristic road section, and obtain the minimum value M of the total number of passing vehicles in the characteristic road section among several characteristic historical vehicle passing records min , and obtain the maximum value M’ of the total number of passing vehicles in several historical vehicle passing records in the characteristic road section max , when the maximum value M’ max is greater than the minimum value M min , take the maximum value M’ max as the characteristic vehicle threshold M’ of the characteristic road section;

[0091] On the contrary, when the maximum value M’ max is less than or equal to the minimum value M min , take the minimum value M min as the characteristic vehicle threshold M’ of the characteristic road section, and obtain the characteristic vehicle passing data of the characteristic road section;

[0092] Step S300: Obtain the historical traffic data of the characteristic section, obtain the historical passing data of the historical public transport vehicles in the city, and combine the historical vehicle passing data of the characteristic section to construct a vehicle passing prediction model to predict the vehicle passing condition of the characteristic section in the current cycle and obtain the vehicle passing prediction data;

[0093] Among them, step S300 includes:

[0094] Step S301: Obtain the historical traffic data of the characteristic section in each historical cycle. The historical traffic data includes the data corresponding to several traffic characteristic indicators of the characteristic section;

[0095] For example, several traffic characteristic indicators include time, temperature, weather, precipitation, etc.;

[0096] Step S302: Obtain the historical passing data of the historical public transport vehicles in the city. The historical passing data includes the passing routes of the historical public transport vehicles in the historical cycle. Obtain the historical vehicle passing data of the characteristic section. When the passing route of the historical public transport vehicle includes the characteristic section, record the historical public transport vehicle as the marked historical public transport vehicle of the characteristic section;

[0097] Step S303: Obtain the historical vehicle passing data of the characteristic section, obtain the total number of passing vehicles of the characteristic section in each historical cycle from the historical vehicle passing data, and calculate the characteristic value of the passing vehicles of the characteristic section in each historical cycle. Among them, the characteristic value K of the passing vehicles of the characteristic section in the g-th historical cycle g =M g -γ g ,M g represents the total number of passing vehicles of the characteristic section in the g-th historical cycle, and γ g represents the total number of historical public transport vehicles passing through the characteristic section in the g-th historical cycle;

[0098] Step S304: Construct a vehicle passing prediction model. Use several traffic characteristic indicators of the characteristic section as the input data of the vehicle passing prediction model, use the characteristic value of the passing vehicles of the characteristic section as the target data, and divide the historical traffic data and the characteristic value of the passing vehicles of the characteristic section in each historical cycle of the characteristic section into a training set and a test set, and train and test the vehicle passing prediction model;

[0099] Step S305: Obtain the average value Y of the characteristic values of the passing vehicles of the characteristic section in each historical cycle △ , obtain the vehicle passing prediction model, obtain the predicted values of the characteristic values of the passing vehicles of the characteristic section in several historical cycles, and calculate the model prediction score R of the vehicle passing prediction model:

[0100] ,

[0101] where Y z represents the characteristic value of the passing vehicles on the characteristic road section in the z-th historical cycle among a number of historical cycles; Y △,z represents the predicted value of the characteristic value of the passing vehicles on the characteristic road section in the z-th historical cycle by the vehicle passing prediction model; q represents the total number of a number of historical cycles;

[0102] Step S306: When the model prediction score of the vehicle passing prediction model is greater than the preset model prediction score, it is determined that the vehicle passing prediction model has prediction ability, obtain the data corresponding to several traffic characteristic indicators of the characteristic road section in the current cycle, and use the vehicle passing prediction model to predict the vehicle passing condition of the characteristic road section in the current cycle to obtain vehicle passing prediction data;

[0103] Step S400: Obtain the vehicle passing prediction data of the characteristic road section in the current cycle, obtain the passing data of the public transport vehicles in the city in the current cycle, and combine the characteristic vehicle passing data of the characteristic road section to conduct intelligent supervision on the traffic of the characteristic road section;

[0104] Among them, Step S400 includes:

[0105] Step S401: Obtain the vehicle passing prediction data of the characteristic road section in the current cycle, and obtain the predicted value of the characteristic value of the passing vehicles on the characteristic road section in the current cycle from the vehicle passing prediction data;

[0106] Step S402: Obtain the passing data of the public transport vehicles in the current cycle. The passing data includes the passing time and passing route of the public transport vehicles. When the passing route of the public transport vehicle includes the characteristic road section and the passing time of the public transport vehicle within the characteristic road section is within the current cycle, the public transport vehicle is recorded as several characteristic public transport vehicles on the characteristic road section in the current cycle;

[0107] Step S403: Obtain the total number of each characteristic public transport vehicle on the characteristic road section in the current cycle. When the predicted value of the characteristic value of the passing vehicles on the characteristic road section in the current cycle and the sum of the total number of several characteristic public transport vehicles are less than the characteristic vehicle threshold in the characteristic vehicle passing data of the characteristic road section, it is determined that the traffic on the characteristic road section in the current cycle is normal;

[0108] Step S404: When the sum of the total number of characteristic road segments in the current cycle is greater than the characteristic vehicle threshold, it is determined that there is traffic anomaly in the characteristic road segments in the current cycle. Obtain the vehicles with characteristic road segments in the navigation routes within the city in the current cycle, send a prompt to the users of the vehicles through the navigation system, and perform an updated recommendation for the navigation routes, and conduct intelligent supervision on the traffic of the characteristic road segments;

[0109] To better implement the above steps, a multi-dimensional road network data integrated supervision system based on traffic service data is also proposed. The system includes a characteristic road segment module, a characteristic vehicle passing data module, a vehicle passing prediction data module, and an intelligent supervision module;

[0110] The characteristic road segment module is used to evaluate the traffic anomaly of the road segments within the city to obtain characteristic road segments;

[0111] The characteristic vehicle passing data module is used to analyze the abnormal influence degree of the traffic flow on the traffic of the characteristic road segments to obtain characteristic vehicle passing data;

[0112] The vehicle passing prediction data module is used to obtain the historical traffic data of the characteristic road segments, obtain the historical passing data of the historical public transport vehicles within the city, construct a vehicle passing prediction model, and predict the vehicle passing condition of the characteristic road segments in the current cycle to obtain vehicle passing prediction data;

[0113] The intelligent supervision module is used to obtain the passing data of the public transport vehicles within the city, and combine the characteristic vehicle passing data of the characteristic road segments to conduct intelligent supervision on the traffic of the characteristic road segments;

[0114] Among them, the characteristic road segment module includes a traffic anomaly scoring unit and a characteristic road segment unit;

[0115] The traffic anomaly scoring unit is used to calculate the traffic accident characteristic values of the road segments in each historical cycle, and calculate the traffic anomaly score of the road segments according to the traffic accident characteristic values;

[0116] The characteristic road segment unit is used to determine the traffic anomaly of the road segments according to the traffic anomaly score to obtain characteristic road segments;

[0117] Among them, the characteristic vehicle passing data module includes a characteristic passing congestion value unit and a characteristic vehicle passing data unit;

[0118] The characteristic passing congestion value unit is used to obtain the historical vehicle passing records of the characteristic road segments and calculate the characteristic passing congestion values of the historical vehicle passing records;

[0119] A characteristic vehicle passing data unit is used to determine historical vehicle passing records according to characteristic passing congestion values, and obtain the characteristic vehicle thresholds of characteristic road sections, so as to obtain the characteristic vehicle passing data of characteristic road sections;

[0120] Among them, the vehicle passing prediction data module includes a model construction unit and a vehicle passing prediction data unit;

[0121] The model construction unit is used to obtain the historical traffic data of characteristic road sections, obtain the historical passing data of historical public transport vehicles in the city, and combine the historical vehicle passing data of characteristic road sections to construct a vehicle passing prediction model;

[0122] The vehicle passing prediction data unit is used to obtain the data corresponding to several traffic characteristic indicators of a characteristic road section in the current period, and use the vehicle passing prediction model to predict the vehicle passing conditions of the characteristic road section in the current period to obtain vehicle passing prediction data;

[0123] Among them, the intelligent supervision module includes an intelligent supervision unit;

[0124] The intelligent supervision unit is used to determine traffic anomalies of characteristic road sections, obtain the vehicles on the navigation routes in the city that contain characteristic road sections in the current period, send prompts to the users of the vehicles through the navigation system, recommend navigation route updates, and conduct intelligent supervision of the traffic of characteristic road sections.

[0125] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claims involved.

Claims

1. An integrated supervision method for multi-dimensional road network data based on traffic service data, characterized in that The method includes: Step S100: Construct a road network supervision cloud platform, obtain historical traffic accident records of road segments in the city, obtain historical vehicle passing records of the road segments, obtain historical vehicle passing speed data from the historical vehicle passing records, and conduct a traffic abnormality assessment on the road segments in the city to obtain characteristic road segments, where the characteristic road segments are road segments with traffic abnormalities; Step S200: Obtain historical vehicle passing records within the characteristic road segments, obtain historical vehicle passing data from the historical vehicle passing records, analyze the degree of abnormal impact of traffic flow on the traffic of the characteristic road segments, and obtain characteristic vehicle passing data, where the characteristic vehicle passing data is the threshold of the total number of passing vehicles in the characteristic road segments; Step S300: Obtain historical traffic data of the characteristic road segments, obtain historical passing data of historical public transport vehicles in the city, and combine with the historical vehicle passing data of the characteristic road segments to construct a vehicle passing prediction model, and predict the vehicle passing conditions of the characteristic road segments in the current period to obtain vehicle passing prediction data; Step S301: Obtain historical traffic data of the characteristic road segments in each historical period, where the historical traffic data includes data corresponding to several traffic characteristic indicators of the characteristic road segments; Step S303: Obtain the historical vehicle passing data of the characteristic road section, obtain the total number of passing vehicles on the characteristic road section in each historical period from the historical vehicle passing data, and calculate the characteristic value of the passing vehicles on the characteristic road section in each historical period. Among them, the characteristic value K of the passing vehicles on the characteristic road section in the g-th historical period g = M g - γ g , M g represents the total number of passing vehicles on the characteristic road section in the g-th historical period, and γ g represents the total number of historical public transportation vehicles passing on the characteristic road section in the g-th historical period; Step S304: Construct a vehicle passing prediction model, use several traffic characteristic indicators of the characteristic road segments as input data of the vehicle passing prediction model, use the characteristic values of the passing vehicles in the characteristic road segments as target data, divide the historical traffic data and the characteristic values of the passing vehicles in each historical period of the characteristic road segments into a training set and a test set, and train and test the vehicle passing prediction model; Step S400: Obtain vehicle passing prediction data of the characteristic road segments in the current period, obtain passing data of public transport vehicles in the city in the current period, and combine with the characteristic vehicle passing data of the characteristic road segments to conduct intelligent supervision on the traffic of the characteristic road segments.

2. The integrated supervision method for multi-dimensional road network data based on traffic service data according to claim 1, characterized in that, The step S100 includes: Step S101: Obtain historical traffic accident records of road segments in the city, extract historical traffic accident data from the historical traffic accident records, where the historical traffic accident data includes the total number of vehicles involved in traffic accidents in the historical traffic accident records; Step S102: Aggregate the vehicles passing through the road segments every historical period to obtain historical vehicle passing records of the road segments, extract historical vehicle passing speed data from the historical vehicle passing records, where the historical vehicle passing speed data includes the average speed of the passing vehicles on the road segments in the historical period; Step S103: Conduct a traffic abnormality assessment on each road segment in the city. Among them, the specific assessment process of the traffic abnormality of the a-th road segment in the city includes: Obtain a number of historical traffic accident records of the a-th section in each historical period, and calculate the traffic accident characteristic value of the a-th section in each historical period. Among them, the traffic accident characteristic value P of the a-th section in the b-th historical period a,b : ， where j represents the total number of historical traffic accident records of the a-th road section in the b-th historical period; M a b,x represents the total number of vehicles involved in traffic accidents in the x-th historical traffic accident record of the a-th road section in the b-th historical period; Obtain the maximum value P of the traffic accident characteristic values of each section in each historical period max , the minimum value P min ; Step S104: Obtain the preset maximum vehicle speed limit v of the a-th section, and calculate the traffic anomaly score E of the a-th section a , and calculate the traffic anomaly score E of the a-th section a : ， Among them, P a,i represents the traffic accident eigenvalue of the a-th section in the i-th historical period; v a,i represents the average speed of the passing vehicles on the a-th section in the i-th historical period; n represents the total number of the respective historical periods; β1 represents a preset first characteristic proportionality coefficient; β2 represents a preset second characteristic proportionality coefficient; β1 + β2 = 1; Step S105: When the traffic anomaly score E a is greater than a preset traffic anomaly score threshold, it is determined that the a-th section has a traffic anomaly, and the a-th section is recorded as a characteristic section.

3. The integrated supervision method for multi-dimensional road network data based on traffic service data according to claim 2, characterized in that, The step S200 includes: Step S201: Obtain the historical vehicle passing records of the feature road section, and calculate the characteristic passing congestion value of the several historical vehicle passing records. Among them, the characteristic passing congestion value F of the c-th historical vehicle passing record of the feature road section c : ， where v’ represents the maximum speed limit of vehicles on the feature road section; v’ c represents the average speed of the passing vehicles in the c-th historical vehicle passing record; Step S202: When the characteristic traffic congestion value F c is greater than a preset characteristic traffic congestion threshold, it is determined that there is vehicle congestion in the historical characteristic road section in the c-th historical vehicle passing record, and the c-th historical vehicle passing record is recorded as the characteristic historical vehicle passing record of the characteristic road section; Step S203: Obtain historical vehicle passing data from the historical vehicle passing records. The historical vehicle passing data is the total number of passing vehicles in the historical vehicle passing records. Obtain several characteristic historical vehicle passing records in the characteristic section, and obtain the minimum value M of the total number of passing vehicles in the characteristic section within the several characteristic historical vehicle passing records min , and obtain the maximum value M' of the total number of passing vehicles in several historical vehicle passing records in the characteristic section max , when the maximum value M' max is greater than the minimum value M min , take the maximum value M' max as the characteristic vehicle threshold M' of the characteristic section; Conversely, when the maximum value M' max is less than or equal to the minimum value M min , take the minimum value M min as the characteristic vehicle threshold M' of the characteristic road section, and obtain the characteristic vehicle passing data of the characteristic road section.

4. The integrated supervision method for multi-dimensional road network data based on traffic service data according to claim 3, characterized in that, The step S300 further includes: Step S302: Obtain the historical passing data of historical public transportation vehicles in the city. The historical passing data includes the passing routes of the historical public transportation vehicles within a historical period. Obtain the historical vehicle passing data of the characteristic section. When the passing route of the historical public transportation vehicle includes the characteristic section, record the historical public transportation vehicle as the marked historical public transportation vehicle of the characteristic section; Step S305: Obtain the average value Y of the characteristic values of the passing vehicles in each historical period of the characteristic road section △ , obtain a vehicle passing prediction model, calculate the predicted values of the characteristic values of the passing vehicles in several historical periods of the characteristic road section, and calculate the model prediction score R of the vehicle passing prediction model: ， Among them, Y z represents the eigenvalue of the passing vehicles in the z-th historical period of the characteristic road section in the several historical periods; Y △,z represents the predicted value of the eigenvalue of the passing vehicles in the z-th historical period of the characteristic road section by the vehicle passing prediction model; q represents the total number of the several historical periods; Step S306: When the model prediction score of the vehicle passing prediction model is greater than the preset model prediction score, determine that the vehicle passing prediction model has prediction ability. Obtain the data corresponding to several traffic characteristic indicators of the characteristic section within the current period. Use the vehicle passing prediction model to predict the vehicle passing condition of the characteristic section within the current period to obtain vehicle passing prediction data.

5. The integrated supervision method for multi-dimensional road network data based on traffic service data according to claim 4, characterized in that, The said step S400 includes: Step S401: Obtain the vehicle passing prediction data of the characteristic section within the current period. From the vehicle passing prediction data, obtain the predicted value of the characteristic value of the passing vehicles of the characteristic section within the current period; Step S402: Obtain the passing data of public transportation vehicles within the current period. The passing data includes the passing time and passing route of the public transportation vehicle. When the passing route of the public transportation vehicle includes the characteristic section and the passing time of the public transportation vehicle within the characteristic section is within the current period, record the public transportation vehicle as several characteristic public transportation vehicles of the characteristic section within the current period; Step S403: Obtain the total number of each characteristic public transportation vehicle of the characteristic section within the current period. When the sum of the predicted value of the characteristic value of the passing vehicles of the characteristic section within the current period and the total number of the several characteristic public transportation vehicles is less than the characteristic vehicle threshold in the characteristic vehicle passing data of the characteristic section, determine that the traffic of the characteristic section is normal within the current period; Step S404: When the sum of the total number of the characteristic section within the current period is greater than the characteristic vehicle threshold, determine that the traffic of the characteristic section is abnormal within the current period. Obtain the vehicles in the navigation routes in the city within the current period that contain the characteristic section, send a prompt to the users of the vehicles through the navigation system, and perform an updated recommendation for the navigation route to conduct intelligent supervision on the traffic of the characteristic section.

6. A multi-dimensional road network data integrated supervision system based on traffic service data, which is used to execute the multi-dimensional road network data integrated supervision method according to any one of claims 1-5, and is characterized in that, The system includes a characteristic section module, a characteristic vehicle passing data module, a vehicle passing prediction data module, and an intelligent supervision module; The characteristic section module is used to evaluate the traffic abnormality of the sections in the city to obtain characteristic sections; The characteristic vehicle passing data module is used to analyze the abnormal influence degree of the traffic flow on the traffic of the characteristic section to obtain characteristic vehicle passing data; The vehicle traffic prediction data module is used to obtain the historical traffic data of the feature section, obtain the historical traffic data of historical public transport vehicles in the city, construct a vehicle traffic prediction model, predict the vehicle traffic conditions of the feature section in the current period, and obtain vehicle traffic prediction data; The intelligent supervision module is used to obtain the traffic data of public transport vehicles in the city, and combine the characteristic vehicle traffic data of the feature section to intelligently supervise the traffic of the feature section.

7. The integrated supervision system for multi-dimensional road network data based on traffic service data according to claim 6, characterized in that, The feature section module includes a traffic anomaly scoring unit and a feature section unit; The traffic anomaly scoring unit is used to calculate the traffic accident characteristic values of the section in each historical period, and calculate the traffic anomaly score of the section according to the traffic accident characteristic values; The feature section unit is used to make a traffic anomaly determination on the section according to the traffic anomaly score to obtain a feature section.

8. The multi-dimensional road network data integrated supervision system based on traffic service data according to claim 6, wherein The characteristic vehicle traffic data module includes a characteristic traffic congestion value unit and a characteristic vehicle traffic data unit; The characteristic traffic congestion value unit is used to obtain the historical vehicle traffic records of the feature section and calculate the characteristic traffic congestion value of the historical vehicle traffic records; The characteristic vehicle traffic data unit is used to determine the historical vehicle traffic records according to the characteristic traffic congestion value, obtain the characteristic vehicle threshold of the feature section, and obtain the characteristic vehicle traffic data of the feature section.

9. The integrated supervision system for multi-dimensional road network data based on traffic service data according to claim 6, wherein The vehicle traffic prediction data module includes a model construction unit and a vehicle traffic prediction data unit; The model construction unit is used to obtain the historical traffic data of the feature section, obtain the historical traffic data of historical public transport vehicles in the city, and combine the historical vehicle traffic data of the feature section to construct a vehicle traffic prediction model; The vehicle traffic prediction data unit is used to obtain the data corresponding to several traffic characteristic indicators of the feature section in the current period, use the vehicle traffic prediction model to predict the vehicle traffic conditions of the feature section in the current period, and obtain vehicle traffic prediction data.

10. The multi-dimensional road network data integrated supervision system based on traffic service data according to claim 6, characterized in that, The intelligent supervision module includes an intelligent supervision unit; The intelligent supervision unit is used to make a traffic anomaly determination on the feature section, obtain the vehicles in the navigation routes in the city that contain the feature section in the current period, send a prompt to the users of the vehicles through the navigation system, make a recommendation for updating the navigation route, and intelligently supervise the traffic of the feature section.

Images