A method for constructing a knowledge graph of individual vehicle travel emissions

Abstract

This invention provides a method for constructing a knowledge graph of individual vehicle travel emissions, relating to the field of urban transportation system data mining technology. It includes: S1, acquiring basic vehicle travel data within a region; S2, obtaining a multi-dimensional travel emission association dataset through data association; S3, constructing a knowledge graph structure for the entity association of "vehicle-road-travel-emission"; and S4, generating a vehicle travel emission knowledge graph within the region using the knowledge graph structure. Based on the multi-dimensional travel emission association dataset and the "vehicle-road-travel-emission" graph structure, this invention generates an individual vehicle travel emission knowledge graph, realizing the knowledge representation of individual-level vehicle travel emissions. It can accurately describe the potential associations between multi-dimensional traffic travel emission data and the dynamic evolution and knowledge representation of individual vehicle travel emission patterns, achieving high accuracy in traffic emission assessment.

Description

Technical Field

[0001] The present invention relates to the technical field of urban traffic system data mining, and more specifically, to a method for constructing a knowledge graph of individual vehicle travel emissions. Background Art

[0002] High-precision traffic emission assessment can realize the recognition of the dynamic characteristics of individual vehicle travel emissions, provide support for the precise control of traffic travel emissions, and is an indispensable technical research for the control of air pollution. However, in previous studies, most of them established macro-scale and meso-scale motor vehicle emission relational databases to evaluate the emission status of regions or roads. Due to the individual differences and strong time-varying nature of vehicle travel, relational databases are often difficult to accurately describe the potential connections between multi-dimensional travel emission data and the dynamic evolution of individual vehicle travel emission laws, resulting in low precision in emission assessment. Faced with the large volume and multiple categories of multi-dimensional travel emission data, a method is needed to deeply explore the coupling relationship between vehicle-road-travel-emission data and realize rapid retrieval and cognition of individual-level travel emissions.

[0003] The prior art document relates to a motor vehicle exhaust emission data fusion system, including a roadside air pollutant concentration estimation module, a roadside air pollutant concentration forecast module, an urban global atmospheric environment forecast module, a motor vehicle exhaust emission factor estimation module and a motor vehicle exhaust emission characteristic analysis module; the five modules respectively realize different data analysis functions, and different functions can be realized by selecting different modules; they can be used alone or in combination of two or more to realize the storage, analysis and fusion of motor vehicle exhaust telemetry data and motor vehicle attributes, driving conditions, detection time, and meteorological conditions data, and analyze and process motor vehicle exhaust telemetry data in combination with the on-board diagnostic system database, the portable emission test system database, the vehicle inspection institute offline database, the traffic information database and the geographic information database to obtain the most discernible key indicators and statistical data; but the motor vehicle emission relational database is used to evaluate the emission status of the region or road. Due to the individual differences and strong time-varying nature of vehicle travel, relational databases are often difficult to accurately express the potential connections between multi-dimensional travel emission data and the dynamic evolution of individual vehicle travel emission laws, resulting in low precision of emission evaluation. Summary of the invention

[0004] In order to overcome the above-mentioned technical problems, the present invention provides a method for constructing an individual vehicle travel emission knowledge graph with high emission assessment precision.

[0005] The technical solution of the present invention is as follows:

[0006] A method for constructing a knowledge graph of individual vehicle travel emissions, comprising the steps of:

[0007] S1. Obtain basic vehicle travel data within a preset area;

[0008] S2. Perform data association on basic vehicle travel data to obtain a multi-dimensional travel emission association data set;

[0009] S3, build knowledge graph structure;

[0010] S4. Generate a knowledge graph of vehicle travel emissions in the region using basic vehicle travel data, multi-dimensional travel emission association data sets and knowledge graph structures.

[0011] This technical solution proposes a method for constructing a knowledge graph of individual vehicle travel emissions. The basic data of the knowledge graph is determined according to the needs of traffic emission assessment. Secondly, the acquired data is used to complete the construction of a multi-dimensional travel emission association data set. Then, with the emission information that characterizes the travel process of individual vehicles as the main line, a knowledge graph structure of the "vehicle-road-travel-emission" entity association is designed to effectively support the recognition and precise control of vehicle travel emission relationships down to the individual level, and accurately and finely express the potential relationship between vehicle emissions and the technical performance and travel of the vehicle itself; finally, based on the multi-dimensional travel emission association data set and the "vehicle-road-travel-emission" graph structure, an individual vehicle travel emission knowledge graph is generated to realize the knowledge expression of vehicle travel emissions at the individual level; it can accurately express the potential relationship between multi-dimensional traffic travel emission data and the dynamic evolution and knowledge expression of individual vehicle travel emission laws, and obtain a higher accuracy of traffic emission assessment.

[0012] Further, the vehicle travel basic data in step S1 includes vehicle technical information data and individual vehicle travel data, the vehicle technical information data is collected and obtained through motor vehicle registration information data and public network vehicle technical parameter data, the vehicle technical information data includes: deprived license plate number, license plate type, registration date, vehicle type, emission standard, fuel type, gross weight, vehicle age, brand and displacement, the individual vehicle travel data is obtained through the urban traffic travel monitoring data source, the individual vehicle travel data includes: deprived license plate number, license plate type, travel section, travel starting point, starting time, travel end point, end time, trip duration, vehicle speed and driving direction;

[0013] The multi-dimensional travel emission correlation data set in step S2 includes a travel-vehicle data correlation data set, and the travel-vehicle data correlation data set is obtained by correlating vehicle technical information data with individual vehicle travel data.

[0014] Furthermore, the method for obtaining individual vehicle travel data is as follows: based on the urban traffic travel monitoring data source, the checkpoint vehicle passing record data of all vehicles in the area is obtained, the checkpoint vehicle passing record data of individual vehicles is screened based on individual vehicles, the checkpoint vehicle passing record data of individual vehicles is sorted by time to obtain the travel itinerary of individual vehicles, and the travel duration, mileage and speed of the travel itinerary are calculated; and the travel itinerary of all individual vehicles in the area is constructed according to the above steps as the individual vehicle travel data.

[0015] Furthermore, the method for associating vehicle technical information data and individual vehicle travel data is: using the license plate number and license plate type of individual vehicles in the vehicle technical information data and individual vehicle travel data, the vehicle technical information data is matched to the vehicle travel trajectory data of all individual vehicles in the area to obtain a travel-vehicle data association data set.

[0016] Furthermore, the vehicle travel basic data in step S1 also includes individual vehicle emission data, and the individual vehicle emission data is calculated using vehicle technical information data and individual vehicle travel data of the individual vehicle;

[0017] The multidimensional travel emission association data set described in step S2 also includes a travel-vehicle-emission data association data set, which is obtained by associating vehicle technical information data, individual vehicle travel data of all individual vehicles in the area, and individual vehicle emission data of each travel trajectory of all individual vehicles in the area.

[0018] Furthermore, individual vehicle emission data includes emission volume and emission intensity, and the calculation method of emission volume and emission intensity is as follows:

[0019]

[0020] in, Q r,w,t,n For driving on the road Vehicles on In time period The amount of pollutants emitted within For driving on the road Vehicles on In time period The emission intensity of pollutants in is the average speed based on the scenario, For driving on the road Vehicles on In time period The average travel speed within is the basic emission factor, is the operating condition correction factor, is the degradation correction factor, is the fuel quality correction factor, For road section Length, is the vehicle type, It is the emission standard. is the type of fuel, It’s the age of the car.

[0021] Furthermore, the vehicle travel basic data in step S1 also includes road information data, and the road information data is extracted using urban road network geographic information data;

[0022] In step S2, the multidimensional travel emission correlation data set also includes a road-travel data correlation data set. The road section ID is used as the unique identifier of the individual vehicle travel process, the road information data is matched with the individual vehicle travel data, and the road information data and the individual vehicle travel data are correlated to obtain the road-travel data correlation data set.

[0023] Furthermore, the knowledge graph structure in step S3 includes: a vehicle information node knowledge graph, a travel information node knowledge graph, an emission information node knowledge graph, and a road information node knowledge graph;

[0024] The knowledge graph of vehicle information nodes is constructed using the vehicle information nodes, which include: vehicle information, vehicle type, emission standard, fuel type, total mass, vehicle age, brand and displacement; with vehicle information as the center, the vehicle type, emission standard, fuel type, total mass, vehicle age, brand and displacement are connected respectively, so as to construct the knowledge graph of vehicle information nodes;

[0025] The knowledge graph of travel information nodes is constructed using travel information nodes, which include travel information, date, hour, road section and speed level. With travel information as the center, the date, hour, road section and speed level are connected respectively to construct the knowledge graph of travel information nodes, and the travel information is connected to the vehicle information.

[0026] The knowledge graph of emission information nodes is constructed using emission information nodes, which include emission information, travel emission level, travel emission intensity level and road section emission intensity level. With emission information as the center, the travel emission level, travel emission intensity level and road section emission intensity level are connected respectively, thereby constructing a knowledge graph of emission information, and connecting emission information with travel information.

[0027] The road information node knowledge graph is constructed using the road information node, which includes: road information and road level; road information is connected to road level, thereby constructing a road information knowledge graph and connecting road information to travel information.

[0028] Furthermore, step S4 generates a knowledge graph of vehicle travel emissions in the region based on the knowledge graph structure constructed in step S3, and uses the multi-dimensional travel emission association data set established in step S2 to generate a knowledge graph of vehicle travel emissions in the region.

[0029] Furthermore, the specific method for generating the knowledge graph of vehicle travel emissions in the region is as follows:

[0030] The vehicle technical information data is used to construct a vehicle information node knowledge graph; the individual vehicle travel data is used to establish a travel information node knowledge graph; the individual vehicle emission data is used to establish an emission information node knowledge graph; the road information data is used to establish a road information node knowledge graph; then, based on the travel-vehicle data association data set, the travel-vehicle-emission data association data set and the road-travel data association data set, the basic vehicle travel data in the vehicle information node knowledge graph, the travel information node knowledge graph, the emission information node knowledge graph and the road information node knowledge graph are stored and associated in the form of a graph database to obtain a vehicle travel emission knowledge graph in the region.

[0031] The present technical solution proposes a method for constructing a knowledge graph of individual vehicle travel emissions. Compared with the prior art, the beneficial effects of the present technical solution are: determining the basic data of the knowledge graph according to the needs of traffic emission assessment, and secondly, using the acquired data to complete the construction of a multi-dimensional travel emission association data set; then, taking the emission information that characterizes the travel process of individual vehicles as the main line, designing a knowledge graph structure of the "vehicle-road-travel-emission" entity association, effectively supporting the recognition and precise control of vehicle travel emission relationships down to the individual level, and accurately and finely expressing the potential association between vehicle emissions and the vehicle's own technical performance and travel; finally, based on the multi-dimensional travel emission association data set and the "vehicle-road-travel-emission" graph structure, generating an individual vehicle travel emission knowledge graph, realizing the knowledge expression of vehicle travel emissions at the individual level; being able to accurately express the potential association between multi-dimensional traffic travel emission data and the dynamic evolution and knowledge expression of individual vehicle travel emission laws, and obtaining a higher accuracy of traffic emission assessment. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 A schematic diagram of the steps for constructing a knowledge graph of individual vehicle travel emissions;

[0033] Figure 2 This is a schematic diagram of the knowledge graph structure;

[0034] Figure 3 This is a schematic diagram of the results of using the knowledge graph to retrieve individual vehicle emission characteristics;

[0035] Figure 4 This is a schematic diagram of the results of using the knowledge graph to perform vehicle type-age-emission standard association retrieval. DETAILED DESCRIPTION

[0036] The user information obtained in this embodiment has been obtained with the user's consent and complies with the provisions of relevant laws and policies.

[0037] The specific implementation of the present invention is further described in detail below in conjunction with the accompanying drawings and examples. The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention.

[0038] Example 1

[0039] A method for constructing a knowledge graph of individual vehicle travel emissions Figure 1 As shown, the steps include:

[0040] S1. Obtain basic vehicle travel data within a preset area;

[0041] S2. Perform data association on basic vehicle travel data to obtain a multi-dimensional travel emission association data set;

[0042] S3, build knowledge graph structure;

[0043] S4. Generate a knowledge graph of vehicle travel emissions in the region using basic vehicle travel data, multi-dimensional travel emission association data sets and knowledge graph structures.

[0044] This embodiment determines the basic data of the knowledge graph according to the needs of traffic emission assessment. Secondly, the obtained data is used to complete the construction of a multi-dimensional travel emission association data set; then, with the emission information that characterizes the travel process of individual vehicles as the main line, a knowledge graph structure of the "vehicle-road-travel-emission" entity association is designed to effectively support the recognition and precise control of vehicle travel emission relationships down to the individual level, and accurately and finely express the potential relationship between vehicle emissions and the technical performance and travel of the vehicle itself; finally, based on the multi-dimensional travel emission association data set and the "vehicle-road-travel-emission" graph structure, an individual vehicle travel emission knowledge graph is generated to achieve knowledge expression of vehicle travel emissions at the individual level; it can accurately express the potential relationship between multi-dimensional traffic travel emission data and the dynamic evolution and knowledge expression of individual vehicle travel emission laws, and obtain a higher accuracy of traffic emission assessment.

[0045] Example 2

[0046] This embodiment provides a method for constructing an individual vehicle travel emission knowledge graph. Based on Embodiment 1, in this embodiment, the vehicle travel basic data described in step S1 includes vehicle technical information data and individual vehicle travel data. The vehicle technical information data is collected and obtained through motor vehicle registration information data and public network vehicle technical parameter data. The vehicle technical information data includes: deprived license plate number, license plate type, registration date, vehicle type, emission standard, fuel type, gross weight, vehicle age, brand and displacement. The individual vehicle travel data is obtained through the urban traffic travel monitoring data source. The individual vehicle travel data includes: deprived license plate number, license plate type, travel section, travel starting point, starting time, travel end point, end time, trip duration, vehicle speed and driving direction;

[0047] The multi-dimensional travel emission correlation data set in step S2 includes a travel-vehicle data correlation data set, and the travel-vehicle data correlation data set is obtained by correlating vehicle technical information data with individual vehicle travel data.

[0048] The method for obtaining individual vehicle travel data is as follows: based on the urban traffic travel monitoring data source, obtain the checkpoint vehicle record data of all vehicles in the area, screen the checkpoint vehicle record data of individual vehicles based on individual vehicles, sort the checkpoint vehicle record data of individual vehicles by time, obtain the travel itinerary of individual vehicles, calculate the travel time, mileage and speed of the travel itinerary; construct the vehicle travel trajectory of all individual vehicles in the vehicle technical information data as individual vehicle travel data according to the above steps. The individual vehicle travel data includes: the de-privacy license plate number, license plate type, travel section, travel starting point, starting time, travel end point, end time, travel time, vehicle speed and driving direction;

[0049] The method for associating vehicle technical information data with individual vehicle travel data is as follows: using the vehicle technical information data and the license plate number and license plate type of individual vehicles in the individual vehicle travel data, the vehicle technical information data is matched to the vehicle travel trajectory data of all individual vehicles in the area, and a travel-vehicle data association data set is obtained.

[0050] The vehicle travel basic data in step S1 also includes individual vehicle emission data, which is calculated using vehicle technical information data and individual vehicle travel data of the individual vehicle;

[0051] Individual vehicle emission data includes emission volume and emission intensity. The calculation methods of emission volume and emission intensity are as follows:

[0052]

[0053] in,Q r,w,t,n For driving on the road Vehicles on In time period The amount of pollutants emitted within For driving on the road Vehicles on In time period The emission intensity of pollutants in is the average speed based on the scenario, For driving on the road Vehicles on In time period The average travel speed within is the basic emission factor, is the operating condition correction factor, is the degradation correction factor, is the fuel quality correction factor, For road section Length, is the vehicle type, It is the emission standard. is the type of fuel, It’s the age of the car.

[0054] Among them, the pollutant emission data and the pollutant emission intensity data are divided into emission level intervals according to the 33% and 66% quantiles; the method for dividing the emission level intervals of the pollutant emission data is as follows: obtain the pollutant emission level parameter data; the values ​​below the 33% quantile are defined as the low emission level interval, the values ​​above the 66% quantile are defined as the high emission level interval, and the values ​​between the two are defined as the medium emission level interval;

[0055] The method for dividing the pollutant emission intensity data into emission intensity level intervals is as follows: obtain the pollutant emission intensity level parameter data; the values ​​below the 33% quantile are defined as the low emission intensity level interval, the values ​​above the 66% quantile are defined as the high emission intensity level interval, and the values ​​between the two are defined as the medium emission intensity level interval.

[0056] The multidimensional travel emission association data set described in step S2 also includes a travel-vehicle-emission data association data set, which is obtained by associating vehicle technical information data, individual vehicle travel data of all individual vehicles in the area, and individual vehicle emission data of each travel trajectory of all individual vehicles in the area.

[0057] The method for obtaining the travel-vehicle-emission data association data set is as follows: using the vehicle travel trajectory data and vehicle technical information data of individual vehicles, the gaseous pollutant emissions and emission intensity of each travel trajectory of the motor vehicle are calculated, so as to complete the acquisition of the emission data of each travel trajectory of all individual vehicles in the area; the vehicle technical information data, the vehicle travel trajectory data of all individual vehicles in the area, and the emission data of each travel trajectory of all individual vehicles in the area are associated to obtain the travel-vehicle-emission data association data set;

[0058] The vehicle travel basic data in step S1 also includes road information data, which is extracted using urban road network geographic information data; the road information data includes: road name, road type, road section ID, location and road section length.

[0059] The multi-dimensional travel emission correlation data set in step S2 also includes a road-travel data correlation data set, and the road information data and the individual vehicle travel data are correlated to obtain the road-travel data correlation data set.

[0060] The method for obtaining the road-travel data association data set is: using the road segment ID as the unique identifier of the individual vehicle travel process, matching the road information data with the individual vehicle travel data, and obtaining the road-travel data association data set;

[0061] The knowledge graph structure in step S3 includes: a vehicle information node knowledge graph, a travel information node knowledge graph, an emission information node knowledge graph, and a road information node knowledge graph;

[0062] The knowledge graph of vehicle information nodes is constructed using the vehicle information nodes, which include: vehicle information, vehicle type, emission standard, fuel type, total mass, vehicle age, brand and displacement; with vehicle information as the center, the vehicle type, emission standard, fuel type, total mass, vehicle age, brand and displacement are connected respectively, so as to construct the knowledge graph of vehicle information nodes;

[0063] The knowledge graph of travel information nodes is constructed using travel information nodes, which include travel information, date, hour, road section and speed level. With travel information as the center, the date, hour, road section and speed level are connected respectively to construct the knowledge graph of travel information nodes, and the travel information is connected to the vehicle information.

[0064] The knowledge graph of emission information nodes is constructed using emission information nodes, which include emission information, travel emission level, travel emission intensity level and road section emission intensity level. With emission information as the center, the travel emission level, travel emission intensity level and road section emission intensity level are connected respectively, thereby constructing a knowledge graph of emission information, and connecting emission information with travel information.

[0065] The road information node knowledge graph is constructed using the road information node, which includes: road information and road level; road information is connected to road level, thereby constructing a road information knowledge graph and connecting road information to travel information.

[0066] Step S4 generates a knowledge graph of vehicle travel emissions in the region. Based on the knowledge graph structure constructed in step S3, the multi-dimensional travel emission association data set established in step S2 is used to generate a knowledge graph of vehicle travel emissions in the region.

[0067] Specifically: the vehicle technical information data in step S22 is used to construct a knowledge graph of vehicle information nodes; the vehicle travel trajectory data in step S22 is used to establish a knowledge graph of travel information nodes; the vehicle emission trajectory data in step S23 is used to establish an emission information node knowledge graph; the road information data in step S21 is used to establish a road information node knowledge graph; at the same time, the basic vehicle travel data is stored and associated in the form of a graph database to obtain a knowledge graph of vehicle travel emissions in the region.

[0068] Example 3

[0069] This embodiment provides a method for constructing a knowledge graph of individual vehicle travel emissions in combination with a specific data example, including the following steps:

[0070] S1: Determine and obtain the basic data required for the knowledge graph, including vehicle technical information data, road information data, individual vehicle travel data, and individual vehicle emission data.

[0071] More specifically, in step S1, the specific process of obtaining vehicle travel basic data is as follows:

[0072] S11: Vehicle technical information data includes: de-privacy license plate number, license plate type, registration date, vehicle type, emission standard, fuel type, gross weight, vehicle age, brand and displacement. The vehicle technical information data is directly obtained by using the multi-source heterogeneous data collection capability of motor vehicle registration information. The obtained vehicle technical information data de-privacy license plate number, license plate type, registration date, vehicle type, emission standard, fuel type, gross weight, vehicle age, brand and displacement. With reference to national standard documents, the standard classification system of vehicle type, emission standard and fuel type is determined. Vehicle types are divided into: K1 large passenger car, K2 medium-sized passenger car, K3 small passenger car, K1 heavy truck, etc. Emission standards are divided into: pre-National I, National I, National II, National III, National IV and National V. Fuel types are divided into: A gasoline, B diesel, C electricity, E natural gas, N solar energy, etc. Examples of vehicle technical information data are shown in Table 1.

[0073] Table 1 Example of vehicle technical information data

[0074]

[0075] The vehicle age is obtained by combining the vehicle travel date with the registration date and calculating the vehicle age in years. The vehicle age calculation can be performed using formula (1):

[0076] (1)

[0077] in, Indicates vehicle The age of the car, Indicates the vehicle travel date, Indicates the vehicle registration date.

[0078] S12: The individual vehicle travel data includes: the de-privacy license plate number, license plate type, travel route, travel starting point, starting time, travel end point, end time, travel duration, vehicle speed and travel direction;

[0079] The method for obtaining individual vehicle travel data is as follows: based on the urban traffic travel monitoring data source and all the checkpoint vehicle record data in the study area, the checkpoint vehicle records are connected in ascending time order, and individual vehicles are taken as the object to reconstruct any short trip of the vehicle, calculate the trip duration, trip mileage, and vehicle speed, and form the vehicle travel trajectory of all individuals in the area to obtain the required individual vehicle travel data. The individual vehicle travel data specifically includes the de-privacy license plate number, license plate type, travel section, travel starting point, starting time, travel end point, end time, trip duration, vehicle speed, driving direction and other parameter information. An example of individual vehicle travel data is shown in Table 2.

[0080] Table 2 Example of individual vehicle travel data

[0081]

[0082] In order to address the problem that some checkpoint data have concentrated temporal and spatial distribution and vehicle trajectories are difficult to determine, the straight-line distance between the vehicle checkpoint coordinates at the previous moment and each adjacent monitoring point is calculated, and the checkpoint point with the smallest Euclidean distance value is selected as the vehicle's coordinate information at the next moment to accurately restore the vehicle's travel trajectory.

[0083] Among them, the vehicle speed information is the average travel speed, which is calculated using formula (2):

[0084] (2)

[0085] in, For vehicles After The average speed of the trajectory unit, For road section Length; For vehicles After The starting and ending time of each trajectory unit.

[0086] S13: Based on the urban road network geographic information data, extract the road information data of the required road section, including road name, road type, section number, location, and section length parameter information. An example of the road information data is shown in Table 2.

[0087] Table 3 Road information data example

[0088]

[0089] S2: Establish a travel emission correlation dataset, including the correlation of multi-source heterogeneous data and emission calculation.

[0090] The data association process consists of three parts: road-travel data association, travel-vehicle data association, and travel-vehicle-emission data association. The specific process is as follows:

[0091] S21: Road-travel data association: Using the "road segment ID" parameter information as the unique identifier of the individual vehicle travel process, the road information data in step S13 is matched with the individual vehicle travel data in step S12.

[0092] S22: Travel-vehicle data association. Using "license plate number + license plate type" as the vehicle identification tag solves the dilemma of multiple motor vehicles with the same license plate number but unable to be uniquely identified. Using the vehicle identity, the processed vehicle technical information data is matched to each vehicle travel trajectory unit to complete the spatiotemporal association of individual vehicle travel data and technical information.

[0093] S23: Travel-vehicle-emission data association. Using the single travel trajectory of the individual vehicle in step S12 as the activity level parameter and the technical parameters of the individual vehicle in step S11 as the calculation index, the gaseous pollutant emissions and emission intensity of each travel trajectory of the motor vehicle are calculated, thereby completing the extraction of emission data of each travel trajectory of all individual vehicles in the region and the association of travel-vehicle-emission data.

[0094] The emission data of individual vehicle travel trajectories are calculated using equations (3) and (4) respectively:

[0095] (3)

[0096] (4)

[0097] in, For driving on the road Vehicles on In time period The amount of pollutants discharged in For driving on the road Vehicles on In time period The pollutant emission intensity within is the average speed based on the scenario, For driving on the road Vehicles on In time period The average travel speed within is the basic emission factor, is the operating condition correction factor, is the degradation correction factor, is the fuel quality correction factor, For road section Length, is the vehicle type, It is the emission standard. is the type of fuel, is the age of the vehicle; S3: Design the knowledge graph structure of the “vehicle-road-travel-emission” entity association.

[0098] S3: Construct the knowledge graph structure of “car-road-travel-emission” entity association;

[0099] The knowledge graph structure includes: vehicle information node knowledge graph, travel information node knowledge graph, emission information node knowledge graph and road information node knowledge graph; a total of 19 entity nodes and 18 connection relationships. The vehicle information node knowledge graph is constructed using vehicle information nodes. Vehicle information nodes include: vehicle information, vehicle type, emission standards, fuel type, total mass, vehicle age, brand and displacement; with vehicle information as the center, vehicle type, emission standards, fuel type, total mass, vehicle age, brand and displacement are connected respectively to construct a knowledge graph of vehicle information nodes;

[0100] The knowledge graph of travel information nodes is constructed using travel information nodes, which include travel information, date, hour, road section and speed level. With travel information as the center, the date, hour, road section and speed level are connected respectively to construct the knowledge graph of travel information nodes.

[0101] The knowledge graph of emission information nodes is constructed using emission information nodes, which include emission information, travel emission level, travel emission intensity level and road section emission intensity level. With emission information as the center, the travel emission level, travel emission intensity level and road section emission intensity level are connected respectively, so as to construct the knowledge graph of emission information.

[0102] The road information node knowledge graph is constructed using the road information node, and the road information node includes: road information and road level; the road information is connected to the road level, thereby constructing the road information knowledge graph.

[0103] The entity nodes and attributes in the knowledge graph structure of the “car-road-travel-emission” entity association are shown in Table IV.

[0104] Table 4 Entity node names and attributes

[0105]

[0106] The specific knowledge graph structure is as follows: Figure 2 shown.

[0107] In the construction of the travel information graph, the speed grade entity needs to classify the vehicle speed in advance. The vehicle speed grade adopts the traffic operation status classification method based on the road section evaluation trip speed in the "Urban Traffic Operation Status Evaluation Specification", and divides the vehicle speed into five categories: high speed, high speed, medium speed, low speed and low speed. The specific classification standards are shown in Table 4.

[0108] Table 5 Speed ​​level classification method

[0109]

[0110] in, Indicates the average travel speed of the road section. Indicates the free flow speed of the road section.

[0111] The connection relationship between entity nodes is shown in Table VI.

[0112] Table 6 Connection relationship between entity nodes

[0113]

[0114] S4: Based on the knowledge graph structure designed in step S3, the multi-dimensional travel emission association data set established in step S2 is used to generate the individual vehicle travel emission knowledge graph. The vehicle technical information data is used to construct the vehicle information graph part; the vehicle travel trajectory data is used to establish the travel information graph part; the vehicle emission trajectory data is used to establish the emission information graph part; and the road information data is used to establish the road information graph part.

[0115] More specifically, the data import uses the Neo4j graph database as the data storage platform, and the Neo4j-import method is used to import multi-dimensional traffic emission related data. Figure 3 Part of the content of the knowledge graph that was finally established is displayed, realizing the graphical knowledge expression of vehicle travel emissions at the individual level.

[0116] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for constructing a knowledge graph of individual vehicle travel emissions, characterized in that: Includes steps: S1. Obtain basic vehicle travel data within a preset area; the basic vehicle travel data includes vehicle technical information data, individual vehicle travel data and individual vehicle emission data; the individual vehicle emission data includes emission volume and emission intensity, which are calculated using the vehicle technical information data and individual vehicle travel data of the individual vehicle; the calculation method is: in, For driving on the road Vehicles on In time period The amount of pollutants emitted within For driving on the road Vehicles on In time period The emission intensity of pollutants in is the average speed based on the scenario, For driving on the road Vehicles on In time period The average travel speed within is the basic emission factor, is the operating condition correction factor, is the degradation correction factor, is the fuel quality correction factor, For road section Length, is the vehicle type, It is the emission standard. is the type of fuel, It is the age of the vehicle; S2. Data association is performed on vehicle travel basic data to obtain a multi-dimensional travel emission association data set; the multi-dimensional travel emission association data set includes a travel-vehicle data association data set and a travel-vehicle-emission data association data set; the travel-vehicle data association data set is obtained by associating vehicle technical information data and individual vehicle travel data; the travel-vehicle-emission data association data set is obtained by associating vehicle technical information data, individual vehicle travel data of all individual vehicles in the area, and individual vehicle emission data of each travel trajectory of all individual vehicles in the area; S3, build knowledge graph structure; S4. Generate a knowledge graph of vehicle travel emissions in the region using basic vehicle travel data, multi-dimensional travel emission association data sets and knowledge graph structures.

2. The method for constructing a knowledge graph of individual vehicle travel emissions according to claim 1, characterized in that: The vehicle technical information data is collected through motor vehicle registration information data and public network vehicle technical parameter data. The vehicle technical information data includes: de-privacy license plate number, license plate type, registration date, vehicle type, emission standard, fuel type, gross weight, vehicle age, brand and displacement. The individual vehicle travel data is obtained through the urban traffic travel monitoring data source. The individual vehicle travel data includes: de-privacy license plate number, license plate type, travel route, travel starting point, starting time, travel end point, end time, trip duration, vehicle speed and driving direction.

3. The method for constructing a knowledge graph of individual vehicle travel emissions according to claim 2, characterized in that: The method for obtaining individual vehicle travel data is as follows: based on the urban traffic travel monitoring data source, the checkpoint vehicle passing record data of all vehicles in the area are obtained, the checkpoint vehicle passing record data of individual vehicles are screened based on individual vehicles, the checkpoint vehicle passing record data of individual vehicles are sorted by time to obtain the travel itinerary of individual vehicles, and the travel duration, mileage and speed of the travel itinerary are calculated; according to the above steps, the vehicle travel trajectory of all individual vehicles in the vehicle technical information data is constructed as the individual vehicle travel data.

4. The method for constructing a knowledge graph of individual vehicle travel emissions according to claim 2, characterized in that: The method for associating vehicle technical information data with individual vehicle travel data is as follows: using the vehicle technical information data and the license plate number and license plate type of individual vehicles in the individual vehicle travel data, the vehicle technical information data is matched to the vehicle travel trajectory data of all individual vehicles in the area, and a travel-vehicle data association data set is obtained.

5. The method for constructing a knowledge graph of individual vehicle travel emissions according to claim 1, characterized in that: The vehicle travel basic data in step S1 also includes road information data, which is extracted using urban road network geographic information data; In step S2, the multidimensional travel emission correlation data set also includes a road-travel data correlation data set. The road section ID is used as the unique identifier of the individual vehicle travel process, the road information data is matched with the individual vehicle travel data, and the road information data and the individual vehicle travel data are correlated to obtain the road-travel data correlation data set.

6. The method for constructing a knowledge graph of individual vehicle travel emissions according to claim 5, characterized in that: The knowledge graph structure in step S3 includes: a vehicle information node knowledge graph, a travel information node knowledge graph, an emission information node knowledge graph, and a road information node knowledge graph; The knowledge graph of vehicle information nodes is constructed using the vehicle information nodes, which include: vehicle information, vehicle type, emission standard, fuel type, total mass, vehicle age, brand and displacement; with vehicle information as the center, the vehicle type, emission standard, fuel type, total mass, vehicle age, brand and displacement are connected respectively, so as to construct the knowledge graph of vehicle information nodes; The knowledge graph of travel information nodes is constructed using travel information nodes, which include travel information, date, hour, road section and speed level. With travel information as the center, the date, hour, road section and speed level are connected respectively to construct the knowledge graph of travel information nodes, and the travel information is connected to the vehicle information. The knowledge graph of emission information nodes is constructed using emission information nodes, which include emission information, travel emission level, travel emission intensity level and road section emission intensity level. With emission information as the center, the travel emission level, travel emission intensity level and road section emission intensity level are connected respectively, thereby constructing a knowledge graph of emission information, and connecting emission information with travel information. The road information node knowledge graph is constructed using the road information node, which includes: road information and road level; road information is connected to road level, thereby constructing a road information knowledge graph and connecting road information to travel information.

7. The method for constructing a knowledge graph of individual vehicle travel emissions according to claim 6, characterized in that: Step S4 generates a knowledge graph of vehicle travel emissions in the region based on the knowledge graph structure constructed in step S3, and uses the multi-dimensional travel emission association data set established in step S2 to generate a knowledge graph of vehicle travel emissions in the region.

8. The method for constructing a knowledge graph of individual vehicle travel emissions according to claim 7, characterized in that: The specific method for generating the knowledge graph of vehicle travel emissions in a region is: The vehicle technical information data is used to construct a vehicle information node knowledge graph; the individual vehicle travel data is used to establish a travel information node knowledge graph; the individual vehicle emission data is used to establish an emission information node knowledge graph; the road information data is used to establish a road information node knowledge graph; then, based on the travel-vehicle data association data set, the travel-vehicle-emission data association data set and the road-travel data association data set, the basic vehicle travel data in the vehicle information node knowledge graph, the travel information node knowledge graph, the emission information node knowledge graph and the road information node knowledge graph are stored and associated in the form of a graph database to obtain a vehicle travel emission knowledge graph in the region.

Images