Traffic network vehicle carbon emission prediction system, method, equipment and medium

Abstract

The invention provides a traffic road network vehicle carbon emission prediction system, method and device and a medium, carbon emission coefficients in different road sections are determined through carbon emission characteristics of different vehicle types and traffic flow information, and then a reference topological link of carbon emission in a traffic road network is constructed through combination of a spatial topological relation and all the carbon emission coefficients; determining a vehicle speed attenuation rate, and performing coupling correction on a carbon emission coefficient corresponding to the event road section according to the vehicle speed attenuation rate; performing dynamic adaptive adjustment on the reference topological link according to the corrected carbon emission coefficient in combination with traffic flow conduction characteristics of emergencies, and further generating a dynamic carbon emission topological matrix of the traffic road network according to an adjustment result; and generating a carbon emission prediction report of each road section in the target traffic road network by combining the dynamic carbon emission topological matrix with the traffic flow evolution trend of the target traffic road network. By adopting the scheme of the invention, deep coupling of the static prediction model and the road network dynamic traffic state can be realized.

Description

Technical Field

[0001] This application relates to the field of carbon emission prediction technology, and more specifically, to a system, method, device and medium for predicting carbon emissions from vehicles in a transportation network. Background Technology

[0002] Carbon emission forecasting refers to the process of quantitatively estimating and qualitatively analyzing the carbon emissions, emission structure, and changing trends of a specific region, industry, enterprise, or even globally by integrating theories from multiple disciplines such as environmental science, statistics, and computer science, and combining key elements such as historical carbon emission data, energy consumption patterns, industrial structure characteristics, policy planning guidance, and climate change trends, and by using tools such as mathematical statistical models (such as regression analysis and time series analysis), machine learning algorithms (such as neural networks and random forests), or system dynamics models.

[0003] Traffic network vehicle carbon emission prediction refers to a technical method that integrates theories from multiple fields such as traffic engineering, environmental science, and data science, combines real-time operational data of the traffic network, and uses tools such as traffic flow simulation models, mathematical statistics methods, or intelligent algorithms to quantitatively calculate and analyze the carbon emissions, emission hotspots, and changing patterns of a specific traffic network in a specific future period. In traditional traffic network vehicle carbon emission prediction processes, there is a reliance on static parameter modeling of fixed carbon emission factors or isolated road segments (such as pre-setting emission coefficients for single vehicle types and ignoring the spatial correlation of the road network). The inability to effectively address dynamic changes in traffic flow leads to multi-dimensional adaptation discrepancies between static prediction models and the dynamic traffic conditions of the road network. For example, traditional predictions may exclude sudden drops in vehicle speed caused by unexpected events (such as traffic accidents) from the scope of automatic model correction. They fail to adjust the carbon emission coefficient of the affected road segment in real time based on the correlation between vehicle speed and carbon emission characteristics and the vehicle speed decay rate, resulting in a significant deviation between the predicted carbon emission value of the road segment and the actual increase in emissions caused by the sudden drop in vehicle speed. Therefore, how to achieve deep coupling between static prediction models and the dynamic traffic conditions of the road network has become a challenge for the industry. Summary of the Invention

[0004] This application provides a traffic network vehicle carbon emission prediction system, method, device and medium, which can realize deep coupling between static prediction model and dynamic traffic state of the road network.

[0005] In a first aspect, this application provides a method for predicting vehicle carbon emissions in a transportation network, comprising the following steps: Obtain traffic flow information for different vehicle types on various road segments within the target traffic network; Based on the carbon emission characteristics of different vehicle types and the traffic flow information, the carbon emission coefficients in different road segments are determined, and then the baseline topology link of carbon emission in the traffic network is constructed by combining all carbon emission coefficients through the spatial topology relationship of different road segments in the target traffic network. When a sudden event occurs in the target traffic network, the vehicle speed decay rate of the event segment within a preset time window is determined, and then the carbon emission coefficient corresponding to the event segment is coupled and corrected based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate. The baseline topology links are dynamically adapted and adjusted based on the modified carbon emission coefficient and the traffic flow transmission characteristics of sudden events, and then a dynamic carbon emission topology matrix of the traffic network is generated based on the adjustment results. The carbon emission prediction report for each segment of the target traffic network is generated by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network.

[0006] Optionally, determining the carbon emission coefficient for different road segments based on the carbon emission characteristics of different vehicle types and the traffic flow information specifically includes: The traffic flow information is used to determine the traffic flow percentage of each vehicle type on different road sections; The carbon emission coefficients for different road sections are determined based on the carbon emission characteristics of different vehicle types and the traffic flow ratio of each vehicle type on different road sections.

[0007] Optionally, constructing a baseline topological link for carbon emissions in the transportation network by combining the spatial topological relationships of different road segments within the target transportation network with all carbon emission coefficients specifically includes: Determine the topological connection edges between different road segments by using the spatial topological relationships of the target traffic network; Determine the basic connection strength of each topological connection edge; The baseline correlation strength of each topological connection edge is obtained by associating each topological connection edge with the carbon emission coefficient of its corresponding adjacent road segment. A baseline topology link for carbon emissions in the transportation network is constructed based on all baseline correlation strengths.

[0008] Optionally, the coupling correction of the carbon emission coefficient corresponding to the event road segment based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed attenuation rate specifically includes: Determine the correlation characteristics between vehicle speed and carbon emission characteristics; The carbon emission correction factor for the event segment is determined by the correlation features and the vehicle speed decay rate. The carbon emission correction factor is used to couple and correct the carbon emission coefficient corresponding to the event road segment.

[0009] Optionally, dynamically adapting and adjusting the baseline topology link based on the corrected carbon emission coefficient and the traffic flow transmission characteristics of sudden events specifically includes: All affected topological connections of the event segment are determined by the traffic flow transmission characteristics of the sudden event; The conduction correlation strength of each affected topology connection edge is determined based on the corrected carbon emission coefficient; The baseline topology links are dynamically adjusted based on the strength of all conduction correlations.

[0010] Optionally, generating a dynamic carbon emission topology matrix for the transportation network based on the adjustment results specifically includes: Use all road segments in the target traffic network as the row and column indices of the matrix; The results are adjusted to serve as the matrix edge weights between the corresponding row and column indices of the road segments. A dynamic carbon emission topology matrix for the transportation network is generated based on the matrix dimension and the matrix edge weights.

[0011] Optionally, generating a carbon emission prediction report for each segment of the target traffic network by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network specifically includes: Emission trend characteristics when determining carbon emissions based on traffic flow evolution trends of the target transportation network; The predicted carbon emission information for each segment of the target traffic network is output through the emission trend characteristics and the dynamic carbon emission topology matrix. Based on the predicted carbon emission information, a carbon emission prediction report for each segment of the target transportation network is generated.

[0012] Secondly, this application provides a vehicle carbon emission prediction system for a transportation network, comprising: The acquisition module is used to acquire traffic flow information for different vehicle types on various road segments within the target traffic network; The processing module is used to determine the carbon emission coefficients in different road segments based on the carbon emission characteristics of different vehicle types and the traffic flow information, and then construct the benchmark topology link of carbon emissions in the traffic network by combining all carbon emission coefficients through the spatial topology relationship of different road segments in the target traffic network. The processing module is also used to determine the vehicle speed decay rate of the event segment within a preset time window when a sudden event occurs in the target traffic network, and then to couple and correct the carbon emission coefficient corresponding to the event segment based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate. The processing module is also used to dynamically adapt and adjust the baseline topology link based on the corrected carbon emission coefficient and the traffic flow transmission characteristics of the sudden event, and then generate a dynamic carbon emission topology matrix of the traffic network based on the adjustment result. The execution module is used to generate carbon emission prediction reports for each segment of the target traffic network by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network.

[0013] Thirdly, this application provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the steps of the above-described method for predicting carbon emissions from vehicles in a traffic network.

[0014] Fourthly, this application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the steps of the above-described method for predicting vehicle carbon emissions from a traffic network.

[0015] The technical solutions provided by the embodiments disclosed in this application have the following beneficial effects: The traffic network vehicle carbon emission prediction system, method, device, and medium provided in this application acquire traffic flow information of different vehicle types in each segment of the target traffic network; determine the carbon emission coefficient in different segments based on the carbon emission characteristics of different vehicle types and the traffic flow information; then construct a baseline topology link for carbon emissions in the traffic network by combining the spatial topology relationship of different segments in the target traffic network with all carbon emission coefficients; when a sudden event occurs in the target traffic network, determine the vehicle speed decay rate of the event segment within a preset time window; then couple and correct the carbon emission coefficient corresponding to the event segment based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate; dynamically adapt and adjust the baseline topology link based on the corrected carbon emission coefficient and the traffic flow transmission characteristics of the sudden event; then generate a dynamic carbon emission topology matrix of the traffic network based on the adjustment results; and generate a carbon emission prediction report for each segment of the target traffic network by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network.

[0016] Therefore, this solution first determines the segment-specific carbon emission coefficient by combining the carbon emission characteristics of different vehicle types with the traffic flow information of each segment of the target road network. Then, it constructs a carbon emission baseline topology link by combining the spatial topological relationships of different road segments. This baseline topology link breaks away from the problem of traditional static models that only preset fixed coefficients for single road segments and ignore the traffic flow correlation between road segments. It transforms isolated road segment carbon emission coefficients into a road network-level emission link with spatial correlation, quantifying the differences in emission characteristics of different vehicle types and establishing the basis for carbon emission transmission between road segments. This avoids the coupling discontinuity of traditional models and provides a predictive framework that fits the actual road network structure for subsequent dynamic adaptation. Then, when a sudden event occurs in the target road network, a preset time window is used to... The system uses the vehicle speed decay rate as a reference, combined with the correlation characteristics between vehicle speed and carbon emissions, to couple and correct the coefficients of the event road segment. Then, it dynamically adapts and adjusts the baseline topology links based on the traffic flow transmission characteristics of the sudden event, ultimately generating a dynamic carbon emission topology matrix. This dynamic topology matrix can accurately respond to real-time fluctuations in traffic flow. By correcting local coefficients through the vehicle speed decay rate and adjusting global links based on traffic flow transmission characteristics, it ensures that the carbon emission coefficients of the event road segment are dynamically updated with vehicle speed, and that the emission predictions of related road segments are synchronously adapted to the traffic flow transmission effect. This allows the model parameters to be linked in real time with the dynamic changes in traffic flow (vehicle speed, traffic flow distribution), avoiding the problem of prediction lag in traditional models. In summary, this scheme can achieve deep coupling between the static prediction model and the dynamic traffic state of the road network. Attached Figure Description

[0017] Figure 1 This is a flowchart illustrating a method for predicting vehicle carbon emissions from a transportation network, according to some embodiments of this application. Figure 2 This is a flowchart illustrating the implementation of coupling correction according to some embodiments of this application; Figure 3 This is a schematic diagram of the process for generating a dynamic carbon emission topology matrix according to some embodiments of this application; Figure 4 This is a schematic diagram of the structure of a traffic network vehicle carbon emission prediction system according to some embodiments of this application; Figure 5 This is an internal structural diagram of a computer device for implementing a method for predicting vehicle carbon emissions from a traffic network, according to some embodiments of this application. Detailed Implementation

[0018] To better understand the technical solutions in this embodiment, the technical solutions in this embodiment will be described in detail below with reference to the accompanying drawings and specific implementation methods.

[0019] refer to Figure 1The figure is a flowchart illustrating a method for predicting vehicle carbon emissions in a transportation network according to some embodiments of this application. This method mainly includes the following steps: In step 101, traffic flow information for different vehicle types is obtained for each segment of the target traffic network.

[0020] In practice, dynamic data collection data of each road segment of the target road network can be obtained through a traffic data collection system. Preferably, the number and frequency of different vehicle types (such as small cars, medium-sized buses, large trucks, small trucks, and buses) in each time period and road segment can be extracted from the image recognition records of video surveillance cameras. The traffic flow statistics results can be verified from the detection data of microwave radar sensors and supplemented with vehicle speed correlation information. The vehicle passing frequency can be extracted from the sensing records of loop detectors to assist in correcting the traffic flow data. The basic time information of the corresponding collection period can be extracted from the operation log of the traffic management platform and integrated to form the traffic flow information of different vehicle types in each road segment.

[0021] It should be noted that the traffic flow information of different vehicle types mentioned in this application refers to a set of parameters reflecting the traffic characteristics of each road segment of the target traffic network. Physically, it refers to the number of different types of vehicles passing through a designated detection section of a certain road segment within a unit of time (e.g., 5 minutes, 15 minutes, 1 hour). The vehicle type classification is based on the national motor vehicle classification standard, and is classified according to vehicle wheelbase, gross vehicle weight, body length, and purpose. The traffic data acquisition system refers to the collective term for integrated equipment and systems used to collect traffic operation data in real time. It usually includes front-end sensing equipment (e.g., video surveillance cameras, microwave radar sensors, coil detectors, infrared detectors, etc.), data transmission modules (e.g., fiber optic transmission links), and preliminary data processing units. The road segment refers to a road section in the target traffic network divided according to the actual function and physical nodes of the road. It is usually bounded by two adjacent traffic intersections (e.g., crossroads, T-junctions) and road signs (e.g., bridge endpoints, tunnel entrances and exits, road name change points), and is the basic spatial unit for traffic flow statistics and road network management.

[0022] In step 102, carbon emission coefficients in different road segments are determined based on the carbon emission characteristics of different vehicle types and the traffic flow information. Then, a baseline topology link for carbon emissions in the traffic network is constructed by combining the spatial topology relationships of different road segments in the target traffic network with all carbon emission coefficients.

[0023] In some embodiments, determining the carbon emission coefficient for different road segments based on the carbon emission characteristics of different vehicle models and the traffic flow information can be achieved using the following steps: The traffic flow information is used to determine the traffic flow percentage of each vehicle type on different road sections; The carbon emission coefficients for different road sections are determined based on the carbon emission characteristics of different vehicle types and the traffic flow ratio of each vehicle type on different road sections.

[0024] In specific implementation, determining the traffic flow ratio of each vehicle type in different road segments based on the traffic flow information can be achieved in the following way: First, obtain the total number of vehicles passing through each road segment within a preset time window and the number of vehicles of each vehicle type passing through the traffic flow information; then, calculate the ratio of the number of vehicles of each vehicle type passing through the corresponding road segment to the total number of vehicles passing through that road segment to obtain the traffic flow ratio of each vehicle type in the corresponding road segment; preferably, a time weighting coefficient can be introduced before the ratio calculation to differentiate the traffic flow data between peak and off-peak periods, so as to improve the accuracy of traffic flow ratio calculation in traffic fluctuation scenarios; in other embodiments, the number of vehicles passing through can also be smoothed by moving average, exponential smoothing or Bayesian estimation to eliminate the interference of sudden abnormal traffic flow on the traffic flow ratio calculation, which is not limited in this application.

[0025] It should be noted that the traffic flow ratio mentioned in this application refers to the ratio of the number of vehicles of various types passing through each road segment in the target traffic network to the total number of vehicles passing through that road segment, in order to reflect the traffic characteristics of different vehicle types in each road segment and their distribution in the traffic flow structure.

[0026] In practice, determining the carbon emission coefficient for different road segments based on the carbon emission characteristics of different vehicle models and the traffic flow ratio of each model in different road segments can be achieved in the following way: First, obtain the carbon emission characteristic parameters corresponding to each vehicle model. These parameters reflect the amount of carbon dioxide emitted per unit mileage and can be referenced from authoritative emission models or national annual statistical reports (such as the China Motor Vehicle Emission Annual Report). Then, for each road segment, multiply the traffic flow ratio of each vehicle model in that segment with the corresponding vehicle model's carbon emission characteristic parameters to obtain the contribution value of each vehicle model to the carbon emission coefficient of the road segment. Finally, sum up the contribution values ​​of all vehicle models and use the resulting value as the carbon emission coefficient for the corresponding road segment, thus obtaining the carbon emission coefficient for different road segments.

[0027] It should be noted that the carbon emission coefficient mentioned in this application refers to a parameter value used to characterize the amount of carbon dioxide emissions generated per unit mileage or unit time in each road segment of the target traffic network. The carbon emission coefficient is obtained by multiplying and summing the traffic flow ratio of each vehicle type in the corresponding road segment with its carbon emission characteristic parameter, and is used to reflect the overall carbon emission level of different road segments under the traffic flow structure.

[0028] In some embodiments, constructing a baseline topological link for carbon emissions in a transportation network by combining the spatial topological relationships of different road segments in the target transportation network with all carbon emission coefficients can be achieved through the following steps: Determine the topological connection edges between different road segments by using the spatial topological relationships of the target traffic network; Determine the basic connection strength of each topological connection edge; The baseline correlation strength of each topological connection edge is obtained by associating each topological connection edge with the carbon emission coefficient of its corresponding adjacent road segment. A baseline topology link for carbon emissions in the transportation network is constructed based on all baseline correlation strengths.

[0029] It should be noted that the spatial topology of the target traffic network described in this application refers to the connection relationship and node connection structure between road segments in the target traffic network in terms of space and traffic direction. The topology relationship can be extracted from digital road maps, Geographic Information System (GIS) road network data or open source road network data, and modeled by combining road geometric information (such as the coordinates of the starting and ending points of road segments), road segment attributes (such as the number of lanes, road grade, and traffic direction), and traffic rule constraints (such as restrictions on left turns, right turns, and U-turns). The spatial topology relationship includes the connection node information between road segments, the connecting edges of adjacent road segments and their directionality, and the initial connection weights that can be used to describe the traffic possibility between road segments. In other embodiments, a topology graph construction algorithm can also be used to form a topology graph of the target traffic network by treating all road segments as nodes and the connection relationship between road segments as edges, for subsequent carbon emission coefficient association and topology link calculation. This application does not limit this.

[0030] In specific implementation, determining the topological connection edges between different road segments based on the spatial topology of the target traffic network can be achieved in the following way: First, obtain the connection nodes and adjacent road segment connection information of all road segments based on the spatial topology of the target traffic network; then, filter the connection relationships between each road segment according to spatial location and travel direction, calculate the spatial distance between the end point of the selected road segment and the starting point of the corresponding road segment of another connection node, and compare it with a preset tolerance. The preset tolerance can be based on road measurement accuracy and the Global Positioning System (GPS). The positioning error of the GPS system is determined based on traffic planning requirements. For example, it can be set to within 50 meters, or it can be adjusted to a range of 30 to 100 meters according to the road network density and road grade. When the spatial distance is less than or equal to the preset tolerance, the connection relationship is used as a candidate topological connection edge. Then, the candidate connection edge is verified according to the road segment traffic direction information and traffic rule constraints recorded in the spatial topological relationship. Specifically, this includes: checking whether the allowed traffic direction of the starting road segment allows vehicles to enter the ending road segment; checking whether there are restrictions such as prohibition of left turn, right turn or U-turn; checking the restrictions of one-way streets, lane separation and intersection signal control; when the candidate connection edge violates any of the above traffic conditions, it is removed. Subsequently, the remaining candidate connection edges are used as topological connection edges. In other embodiments, topological connection edges can also be automatically extracted and generated by combining topology graph construction tools. This application does not limit this.

[0031] It should be noted that the topological connection edge mentioned in this application refers to the edge structure used to characterize the passable connection relationship between two adjacent road segments based on the spatial topological relationship of the target traffic road network. The topological connection edge is determined by analyzing the road segment connection nodes, spatial location, travel direction and traffic rule constraints, and is used to reflect the feasible path and passability of a vehicle traveling from the starting road segment to the ending road segment in the road network.

[0032] In practice, the basic connection strength of each topological connection edge can be determined in the following way: First, obtain the road attribute information of the starting and ending road segments corresponding to each topological connection edge, including the number of lanes, road grade, road segment length, and turning matching type; Subsequently, weights are assigned to the basic connectivity strength based on each attribute factor. The contribution ratio of each factor in the basic connectivity strength can be determined by using the analytic hierarchy process or expert experience assignment. For example, the weight of the number of lanes is 0.4, the weight of steering matching degree is 0.3, and the weight of road grade is 0.3. Next, each factor was quantified into numerical indicators, such as the number of lanes: 2 lanes = 0.5, 4 lanes = 0.8, 6 lanes and above = 1.0; steering matching degree: straight = 1.0, right turn = 0.7, left turn = 0.5, U-turn = 0.3; road grade: expressway = 1.0, main road = 0.8, secondary road = 0.6, local road = 0.4; Then, the quantified values ​​of each factor are linearly weighted and summed with their corresponding weights to obtain the basic connection strength of the topological connection edge. In other embodiments, the basic connection strength can also be dynamically adjusted based on actual traffic flow or simulation data, which is not limited in this application.

[0033] In specific implementation, associating each topological connection edge with the carbon emission coefficient of its corresponding adjacent road segment to obtain the baseline association strength of each topological connection edge can be achieved in the following way: First, calculate the arithmetic mean of the carbon emission coefficients of the starting road segment and the ending road segment to obtain the average carbon emission value of the connection edge; then, multiply the baseline connection strength of the connection edge with the average carbon emission value to calculate the baseline association strength of the corresponding topological connection edge; preferably, the carbon emission coefficients of the starting and ending road segments can be allocated according to a certain weight before being multiplied with the baseline connection strength to reflect the relative influence of different road segments on the connection edge; in other embodiments, the coupling of the carbon emission coefficients of the starting and ending road segments with the baseline connection strength can also be achieved through geometric mean, weighted harmonic mean, or multiplication based on normalization coefficients to obtain the baseline association strength, and this application does not limit this.

[0034] It should be noted that the basic connectivity strength mentioned in this application refers to an initial quantitative index used to characterize the traffic flow capacity of each topological connection edge in the target traffic network; it is used to reflect the smoothness of traffic flow and potential carrying capacity of the topological connection edge without considering external disturbances.

[0035] In specific implementation, the construction of the benchmark topology links for carbon emissions in the transportation network based on all benchmark association strengths can be achieved in the following way: First, the starting road segment node, ending road segment node, and corresponding benchmark association strength of each topological connection edge are organized into an edge weight information table. The rows of the table represent the starting road segment nodes, the columns represent the ending road segment nodes, and the cell values ​​are the benchmark association strengths of the connection edges. Then, based on the edge weight information table, each connection edge is sequentially established in the topology graph, connecting the starting node and the ending node, and the corresponding benchmark association strength is assigned as the weight of the edge, completing the construction of the directed weighted graph. Next, the above operation is repeated for all topological connection edges until the benchmark association strengths of all nodes and connection edges in the entire transportation network are mapped to the topology graph. Finally, the resulting weighted topology graph is used as the benchmark topology links for carbon emissions in the transportation network. In other embodiments, the identifiers of nodes and edges and the edge weights can also be entered one by one through a graph database or network analysis tool to achieve the construction of complete benchmark topology links. This application does not limit this.

[0036] It should be noted that the reference topology link mentioned in this application refers to a directed weighted topology graph constructed based on the starting and ending nodes of each topology connection edge in the transportation network and the corresponding reference association strength, which is used to characterize the initial network structure of the carbon emission association relationship between each road segment in the transportation network without considering the dynamic changes of traffic flow and external disturbances.

[0037] In step 103, when a sudden event occurs in the target traffic network, the vehicle speed decay rate of the event segment within a preset time window is determined, and then the carbon emission coefficient corresponding to the event segment is coupled and corrected based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate.

[0038] In specific implementation, determining the speed decay rate of the event segment within a preset time window can be achieved in the following way: First, determine the preset time window for the event segment, including a reference time period before the event and a target time period during the event. For example, the morning rush hour from 7:00 to 8:00 a week before the event can be set as the reference time period, and 7:30 to 8:30 on the day of the event can be set as the target time period. Then, collect vehicle driving data for the event segment within each time period. Preferably, the time information of vehicles passing through the segment can be obtained through floating car GPS, road segment traffic detectors, or vehicle navigation data. Next, calculate the average speed within the reference time period, that is, divide the segment length by the average passage time of all vehicles within that time period to obtain the normal speed. Similarly, calculate the average speed within the target time period to obtain the event speed. Then, calculate the speed decay rate based on the event speed and the normal speed, specifically including: dividing the difference between the normal speed and the event speed by the normal speed as the speed decay rate of the event segment within the preset time window.

[0039] It should be noted that the vehicle speed attenuation rate mentioned in this application refers to a proportional value used to characterize the degree to which the vehicle speed on the event road segment decreases relative to the normal reference speed within a preset time window, in order to reflect the intensity and magnitude of the impact of the traffic event on the road segment's traffic speed.

[0040] In some embodiments, reference Figure 2 As shown in the figure, this is a schematic diagram of the process for implementing coupling correction according to some embodiments of this application. The coupling correction of the carbon emission coefficient corresponding to the event road segment based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed attenuation rate can be achieved by the following steps: First, in step 1031, the correlation characteristics between vehicle speed and carbon emission characteristics are determined; Then, in step 1032, the carbon emission correction factor for the event segment is determined by the associated features and the vehicle speed decay rate; Finally, in step 1033, the carbon emission coefficient corresponding to the event road segment is coupled and corrected based on the carbon emission correction factor.

[0041] In practice, determining the correlation between vehicle speed and carbon emission characteristics can be achieved as follows: First, acquire carbon emission data per unit mileage for each vehicle type at different speeds on the event road segment, and organize the carbon emission data corresponding to each speed into a data table or matrix, ensuring that each speed point corresponds to a carbon emission measurement value; then, use a polynomial regression method to fit the organized data. The specific steps include: constructing a polynomial function model for each vehicle type, selecting the polynomial order (e.g., second or third order), using each vehicle speed as the independent variable and carbon emission data as the dependent variable; then, using the least squares method to determine the regression coefficients of the polynomial model. The process involves solving for each coefficient by minimizing the squared error between the actual carbon emission value and the model's predicted value. During the solution process, matrix operations can be used to form a coefficient matrix from the carbon emission data and vehicle speed data, and regression coefficients can be calculated using normal equations or pseudo-inverse methods. Subsequently, residual analysis and goodness-of-fit evaluation are performed on the fitting results to verify whether the fitted curve can accurately describe the carbon emission change trend under different vehicle speeds. Finally, the fitted polynomial model is recorded as the correlation feature between vehicle speed and carbon emissions. In other embodiments, the fitting effect can also be optimized by selecting different polynomial orders or adding regularization methods; this application does not limit this.

[0042] It should be noted that the vehicle speed and carbon emission correlation characteristics mentioned in this application refer to a mathematical model used to characterize the carbon emission variation pattern of each vehicle type per unit mileage under different vehicle speed conditions, in order to reflect the trend and sensitivity of the influence of vehicle speed on carbon emission levels.

[0043] In specific implementation, the carbon emission correction factor for the event road segment can be determined by the correlation feature and the vehicle speed attenuation rate in the following manner: First, the normal vehicle speed and the event vehicle speed of the event road segment are respectively input as independent variables into the polynomial model corresponding to the correlation feature to obtain the carbon emission coefficient corresponding to the normal vehicle speed and the carbon emission coefficient corresponding to the event vehicle speed; then, the carbon emission coefficient under the event vehicle speed is divided by the carbon emission coefficient under the normal vehicle speed to obtain the carbon emission correction factor for the event road segment; preferably, weights can be set for different vehicle types, and the correction factors of each vehicle type can be weighted and synthesized according to the actual traffic flow ratio or other traffic distribution characteristics of each vehicle type in the event road segment to obtain a more accurate carbon emission correction factor for the event road segment; in other embodiments, the input of the polynomial model can also be divided into intervals, and the correction factors of different intervals can be calculated separately and then weighted and synthesized to optimize the correction accuracy. This application does not limit this.

[0044] It should be noted that the carbon emission correction factor mentioned in this application refers to an adjustment coefficient used to characterize the impact of changes in vehicle speed on carbon emission levels during the event, and is used to reflect the increase or decrease in carbon emissions when the actual vehicle speed deviates from the normal vehicle speed.

[0045] In specific implementation, the carbon emission coefficient corresponding to the event road segment can be coupled and corrected based on the carbon emission correction factor in the following manner: the carbon emission coefficient corresponding to the event road segment is multiplied by the carbon emission correction factor of the event road segment to obtain the coupled and corrected carbon emission coefficient of the event road segment as the correction result. Preferably, the carbon emission correction factors of different vehicle types in the event road segment can be weighted and summed according to the actual traffic flow ratio of each vehicle type in the road segment to obtain a weighted average carbon emission correction factor of the event road segment, and then multiplied by the carbon emission coefficient of the event road segment to obtain the coupled and corrected carbon emission coefficient. This application does not limit this.

[0046] It should be noted that the coupled modified carbon emission coefficient mentioned in this application refers to the value after adjusting the original carbon emission coefficient based on the changes in vehicle speed on the event road segment and the traffic flow ratio of each vehicle type, in order to reflect the changes in the actual carbon emission level of the road segment under the influence of the event.

[0047] In step 104, the baseline topology links are dynamically adapted and adjusted based on the corrected carbon emission coefficient and the traffic flow transmission characteristics of the sudden event, and then a dynamic carbon emission topology matrix of the traffic network is generated based on the adjustment results.

[0048] In some embodiments, the dynamic adaptation and adjustment of the baseline topology link based on the modified carbon emission coefficient and the traffic flow transmission characteristics of sudden events can be achieved by the following steps: All affected topological connections of the event segment are determined by the traffic flow transmission characteristics of the sudden event; The conduction correlation strength of each affected topology connection edge is determined based on the corrected carbon emission coefficient; The baseline topology links are dynamically adjusted based on the strength of all conduction correlations.

[0049] It should be noted that the traffic flow transmission characteristics of the sudden event described in this application refer to the diffusion and propagation patterns of traffic flow, vehicle speed, and congestion caused by the sudden event in the spatial topological relationship within the target traffic network. This includes changes in vehicle density on the event segment, vehicle speed attenuation, and the transmission path and intensity of the event's impact along upstream, downstream, and adjacent road segments. Specifically, the traffic flow transmission characteristics can be obtained through traffic flow diffusion simulation based on the Cell Transmission Model (CTM). The traffic density of the event segment is used as input, and the spatial topological relationship of the road and traffic rules are combined to simulate the transmission process of the event's impact along the topological connecting edges to upstream, downstream, and adjacent road segments. During the simulation, indicators such as vehicle speed attenuation rate, traffic density change gradient, or congestion wave propagation speed can be used to characterize the transmission intensity and ripple range. In other embodiments, historical event data or actual traffic flow observation data can also be combined to calibrate the traffic flow transmission characteristics to more accurately reflect the ripple patterns of the event in the traffic network. This application does not limit this approach.

[0050] In practical implementation, determining all affected topological connecting edges of an event road segment based on the traffic flow transmission characteristics of a sudden event can be achieved in the following way: First, obtain all topological connecting edges of the event road segment, including upstream connecting edges, downstream connecting edges, and adjacent branch road connecting edges intersecting with the event road segment; then, use the traffic flow density of the event road segment as an input parameter and input it into a traffic flow transmission model based on a unit transmission model. Combined with the spatial topological relationship and traffic rules of the target traffic network, simulate the transmission process of the event's impact on each topological connecting edge; finally, calculate each topological connecting edge based on the simulation results. The transmission traffic density increment of an edge is calculated as follows: the difference between the baseline traffic density before the event and the traffic density during the event is used as the transmission increment; then, each transmission traffic density increment is compared with a preset transmission determination threshold. When the transmission increment is greater than or equal to the threshold, the edge is determined to be affected by the event and marked as a affected edge; when the transmission increment is less than the threshold, the edge is determined not to be significantly affected and is not included in the affected area; finally, all edges determined to be affected by the event are grouped together as all affected edges of the event segment. As a preferred embodiment, the preset... The transmission threshold can be set based on historical traffic event samples or simulation results. For example, it can be set as the average traffic flow density under normal traffic conditions plus a standard deviation. Furthermore, the simulation process (simulating the transmission process of the event's impact on various topological connecting edges) specifically includes: First, based on the traffic flow transmission model, the event segment is divided into several continuous cell units, each cell having vehicle stock parameters, capacity parameters, and outflow constraint parameters. Then, at a preset time step, the traffic flow transfer volume of each cell is iteratively calculated. Specifically, the traffic flow density of the event segment is used as the initial input, combined with the capacity of the cell... Based on the remaining capacity of adjacent cells, determine the outflow and inflow traffic flow within each time step; then, transfer the traffic flow of each cell to the topological connection edge connected to the event segment, updating the cells of upstream and downstream segments and adjacent branch segments; next, constrain the transfer results in conjunction with traffic rules, including: if the topological connection edge has a one-way restriction or a no-turn constraint, then block the traffic flow transmission in the corresponding direction; if there is a traffic light timing constraint, then reduce the transmitted traffic flow according to the green light ratio; finally, iterate to the set simulation duration, and output the dynamic change sequence of traffic flow density of each topological connection edge under the influence of the event as the simulation result.

[0051] It should be noted that the affected topological connecting edges mentioned in this application refer to the set of topological connecting edges that are determined to be affected by the event and have a significant change in traffic density after the occurrence of a sudden event, based on the traffic flow transmission characteristics of the event road segment and the traffic flow simulation results. This set is used to characterize the specific road segment range and transmission path that the event's impact may affect in the traffic network.

[0052] In practice, determining the transmission correlation strength of each affected topology connection edge based on the corrected carbon emission coefficient can be achieved in the following way: First, obtain the dynamic change sequence of traffic flow density for all affected topology connection edges (simulation results); then, couple the dynamic change sequence of traffic flow density with the corresponding corrected carbon emission coefficient to obtain the carbon emission increment value of each affected topology connection edge. Specifically, multiply the traffic flow density increment during the event by the corrected carbon emission coefficient to obtain the carbon emission correction increment per unit time; then, accumulate the carbon emission correction increment over a preset simulation period to obtain the cumulative carbon emission correction value of each affected topology connection edge. Next, the cumulative carbon emission correction value is compared with the baseline carbon emission value of the corresponding affected topology connection edge, and the relative change ratio is calculated as the transmission correlation strength of the affected topology connection edge. As a preferred embodiment, the baseline carbon emission value can be calculated from historical traffic data under no-event conditions, for example, based on the product of the average traffic flow density during normal operation and the corrected carbon emission coefficient as the baseline value. In other embodiments, the calculation of the transmission correlation strength can further introduce traffic state classification parameters, such as traffic flow levels during peak, off-peak, and low-peak periods, and use a classified baseline value to improve the accuracy of adaptation and adjustment. This application does not limit this.

[0053] It should be noted that the transmission correlation strength mentioned in this application refers to the parameter value that reflects the degree of transmission influence on carbon emissions of each affected topological connecting edge during the event, based on the coupling calculation results of the traffic flow density change and the corrected carbon emission coefficient of the event-affected topological connecting edge during the event, and characterizes the relative strength of the event's transmission to carbon emissions along the topological connecting edge in the traffic network.

[0054] In specific implementation, the dynamic adjustment of the baseline topology link based on all conducted correlation strengths can be achieved in the following way: First, obtain the conducted correlation strength of all affected topology connection edges; then, map each affected topology connection edge to the corresponding edge segment in the baseline topology link, wherein upstream connection edges are mapped to the upstream adjacent edge segment position of the baseline topology link, downstream connection edges are mapped to the downstream adjacent edge segment position of the baseline topology link, and adjacent branch connection edges intersecting with event road segments are mapped to the fork nodes of the baseline topology link; subsequently, after completing the mapping, the edge segment or node parameters at the corresponding position in the baseline topology link are adapted and corrected, specifically: when the conducted correlation strength of the selected affected topology connection edge is greater than a preset adjustment threshold, reduce the effective traffic capacity parameter of the edge segment corresponding to its mapped position, and simultaneously increase the efficiency of that edge. The carbon emission weighting coefficient of the segment is used to reflect the impact of the event on the traffic status and carbon emissions of the segment. When the transmission correlation strength is less than the adjustment threshold, the parameters of the mapping position remain unchanged. Then, based on all the corrected segment and node parameters, the path weight of the entire baseline topology link is recalculated to obtain the dynamically adjusted topology link as the adjustment result of the baseline topology link. As a preferred embodiment, the corresponding mapping can be implemented through an adjacency matrix, that is, taking the baseline topology link as the backbone, the row and column positions of each affected topology connection edge in the adjacency matrix are mapped to the node index of the backbone link. In addition, the preset adjustment threshold can be set according to the carbon emission impact distribution of historical events, for example, it can be set as the average transmission correlation strength under normal conditions plus a variance coefficient. This application does not limit this.

[0055] It should be noted that the dynamically adjusted baseline topology link mentioned in this application refers to the traffic network link structure after adapting and correcting the parameters of the corresponding edge segments or nodes in the baseline topology link based on the transmission correlation strength of the event segment and the topology connection edge, in order to reflect the dynamic change characteristics of the traffic capacity and carbon emission weight of each segment after the event occurs.

[0056] In some embodiments, generating a dynamic carbon emission topology matrix of the transportation network based on the adjustment results can be achieved through the following steps: Use all road segments in the target traffic network as the row and column indices of the matrix; The results are adjusted to serve as the matrix edge weights between the corresponding row and column indices of the road segments. A dynamic carbon emission topology matrix for the transportation network is generated based on the matrix dimension and the matrix edge weights.

[0057] In specific implementation, using all road segments in the target traffic network as the row and column indices of the matrix can be achieved in the following way: First, obtain the unique identifier information of all road segments in the target traffic network. The unique identifier can be the road segment name or road segment number, used to uniquely represent each road segment. Then, count the total number of road segments n in the target traffic network, and determine the dimension of the dynamic carbon emission topology matrix as n×n accordingly. Then, arrange the unique identifiers of the road segments sequentially as the row and column indices of the matrix, where the row index is used to represent the starting road segment, and the column index is used to represent the ending road segment. The element characterizes the carbon emission correlation between the starting and ending road segments; finally, a matrix index structure containing n row indices and n column indices is formed; as a preferred embodiment, the unique identifier of the road segment can be obtained from the digital map database of the traffic network, and can be arranged according to the spatial topology numbering order of the road or the traffic jurisdiction division order to ensure the consistency and traceability of the index; in other embodiments, the index order can also be flexibly set according to the actual application needs, such as sorting according to the road segment length, traffic flow level or carbon emission intensity, which is not limited in this application.

[0058] In specific implementation, the adjustment results can be used as the matrix edge weights between road segments corresponding to the row and column indices, which can be achieved in the following way: First, based on the topological connection relationship of the traffic network, the carbon emission correction value of each affected topological connection edge in the adjustment results is assigned to the corresponding row and column index positions in the dynamic carbon emission topology matrix to represent the carbon emission transmission intensity from the starting road segment to the ending road segment; for edges that have topological connections but are not affected, the baseline carbon emission value is assigned to the corresponding position in the matrix; for road segment pairs that do not have a direct connection relationship, the value is assigned to zero in the corresponding position in the matrix to indicate that there is no carbon emission transmission relationship between the two road segments; finally, the assignment of all off-diagonal elements in the matrix is ​​completed, thereby obtaining the matrix edge weights between road segments corresponding to the row and column indices; in other embodiments, the edge weights can also be dynamically corrected in combination with time period information to reflect the differences in carbon emission transmission during different peak and off-peak periods, which is not limited in this application.

[0059] It should be noted that the matrix edge weights mentioned in this application refer to the values ​​used in the dynamic carbon emission topology matrix to characterize the intensity of carbon emission transmission from the starting road segment to the ending road segment, in order to reflect the degree and direction of the mutual influence of carbon emissions among different road segments in the transportation network.

[0060] For specific implementation, refer to Figure 3As shown in the figure, this is a schematic diagram of the process for generating a dynamic carbon emission topology matrix according to some embodiments of this application. The dynamic carbon emission topology matrix of the traffic network generated based on the matrix dimension and the matrix edge weights can be implemented in the following way: First, an initial matrix of size n×n (total number of road segments n) is constructed, with the row index and column index corresponding to the unique identifier of each road segment in the target traffic network; then, the matrix edge weights are filled into the off-diagonal elements of the matrix one by one according to the index position to ensure that the carbon emission value of each topological connection edge is correctly mapped to the corresponding starting and ending road segment positions; next, the diagonal elements of the matrix are assigned the carbon emission characteristics of each road segment, where the event road segment uses the corrected carbon emission coefficient and the non-event road segment uses the baseline carbon emission value, forming a complete dynamic carbon emission topology matrix; in other embodiments, a three-dimensional matrix or tensor structure can also be generated by combining time series to dynamically reflect the carbon emission topology changes in different time periods, which is not limited in this application.

[0061] It should be noted that the dynamic carbon emission topology matrix mentioned in this application refers to a two-dimensional matrix constructed based on the topological connection relationship between each road segment in the transportation network and the matrix edge weights. This matrix is ​​used to characterize the carbon emission transmission intensity between road segments and their own carbon emission characteristics, and to reflect the dynamic interaction relationship and changing trend of carbon emissions of each road segment in the transportation network under different conditions.

[0062] In step 105, a carbon emission prediction report for each segment of the target traffic network is generated by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network.

[0063] In some embodiments, generating a carbon emission prediction report for each segment of the target traffic network by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network can be achieved through the following steps: Emission trend characteristics when determining carbon emissions based on traffic flow evolution trends of the target transportation network; The predicted carbon emission information for each segment of the target traffic network is output through the emission trend characteristics and the dynamic carbon emission topology matrix. Based on the predicted carbon emission information, a carbon emission prediction report for each segment of the target transportation network is generated.

[0064] In specific implementation, the emission trend characteristics for determining carbon emissions based on the traffic flow evolution trend of the target traffic network can be achieved in the following way: First, acquire historical traffic observation data for each road segment in the target traffic network; then, input the time series data into a long short-term memory neural network for training. During training, the historical traffic flow and speed sequences of each road segment are used as input features, and the traffic flow and speed for the corresponding future time period are used as output targets. The network captures the dynamic changes in traffic flow over time and the influence of external conditions through memory units, and uses the backpropagation algorithm to iteratively optimize the network parameters to minimize the prediction error; after training, input the historical data for the most recent period to gradually predict the traffic flow and speed for each road segment in the future for several time periods, obtaining the traffic flow evolution trend data for each road segment; then, based on the historical traffic data, statistically analyze the carbon emission level per unit traffic flow in different speed ranges, specifically by analyzing the data for each road segment. The average traffic flow in each time period is paired with the carbon emissions measured or calculated at the corresponding vehicle speed. After accumulating data from multiple time periods, the average carbon emission coefficient for each speed range is calculated, and a mapping table between vehicle speed and carbon emission coefficient is formed. Then, the traffic flow of each road segment in the predicted time period is multiplied by the carbon emission coefficient corresponding to the predicted vehicle speed, and the basic carbon emissions of each road segment in each predicted time period are obtained by combining the road segment length and time step. The carbon emission influence coefficient of adjacent road segments on the current road segment is obtained according to the dynamic carbon emission topology matrix. The basic carbon emissions of adjacent road segments are multiplied by the corresponding influence coefficient and then accumulated to obtain the correction increment of carbon emissions of each road segment in each predicted time period. Finally, the basic carbon emissions and the correction increment are added to obtain the total carbon emissions of each road segment in each predicted time period, and the total carbon emissions are used as the emission trend characteristics when carbon emissions occur. In other embodiments, other methods can also be used to determine the carbon emissions, which are not limited here.

[0065] It should be noted that the carbon emission trend characteristics mentioned in this application refer to a set of parameters used to characterize the dynamic changes in carbon emissions of each road segment in the target traffic network during the prediction period as traffic flow evolves, in order to reflect the temporal evolution trend of carbon emissions between road segments and their mutual influence.

[0066] In specific implementation, the predicted carbon emission information of each road segment in the target traffic network can be output through the emission trend characteristics and the dynamic carbon emission topology matrix in the following manner: First, obtain the emission trend characteristic data of each road segment in the prediction period, including the total carbon emission of each road segment in each period, and arrange them in the order of road segments to form a preliminary carbon emission data table; then, combine the dynamic carbon emission topology matrix, and use the carbon emission correlation strength between each road segment and its adjacent topological connection edge as a correction coefficient to perform weighted adjustment on the preliminary carbon emission data. Specifically, multiply the basic carbon emission of each road segment and the basic carbon emission of its adjacent road segments by the corresponding topology matrix edge weights and sum them to obtain the comprehensive carbon emission value of each road segment in each prediction period as the predicted carbon emission information of each road segment in the target traffic network.

[0067] In practice, generating carbon emission prediction reports for each road segment in the target traffic network based on the predicted carbon emission information can be achieved in the following way: First, the predicted carbon emission information is organized into a structured data table according to road segment identification and time sequence, recording the basic carbon emission, associated correction increment, and total carbon emission for each road segment; then, the total carbon emission of each road segment is statistically analyzed to determine high-emission road segments and high-emission time periods. Specifically, the distribution of predicted carbon emission values ​​for all road segments is calculated, and road segments or time periods exceeding a preset percentile (e.g., 80%) are marked as high-emission, and corresponding warning labels are generated; next, visualization charts are generated based on the organized data, including a time series chart showing the 24-hour carbon emission change trend of each road segment, a spatial heat map reflecting the carbon emission distribution in the road network, and a bar chart or stacked chart showing the contribution ratio of basic emissions and associated correction emissions; finally, the organized tabular data, visualization charts, and high-emission warning information are integrated, and a complete report is generated according to road segment grouping and prediction time period sequence as the carbon emission prediction report for each road segment in the target traffic network.

[0068] In another aspect, in some embodiments, this application provides a vehicle carbon emission prediction system for transportation networks, with reference to... Figure 4 The figure is a schematic diagram of the structure of a traffic network vehicle carbon emission prediction system according to some embodiments of this application. The traffic network vehicle carbon emission prediction system 200 includes: an acquisition module 201, a processing module 202, and an execution module 203, which are described below: The acquisition module 201 in this application is mainly used to acquire traffic flow information of different vehicle types in each segment of the target traffic network; Processing module 202, in this application, is mainly used to determine the carbon emission coefficient in different road segments based on the carbon emission characteristics of different vehicle types and the traffic flow information, and then construct the benchmark topology link of carbon emission in the traffic network by combining all carbon emission coefficients through the spatial topology relationship of different road segments in the target traffic network. In addition, the processing module 202 in this application is also used to determine the vehicle speed decay rate of the event segment in a preset time window when a sudden event occurs in the target traffic network, and then to couple and correct the carbon emission coefficient corresponding to the event segment based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate. In addition, the processing module 202 in this application is also used to dynamically adapt and adjust the reference topology link according to the modified carbon emission coefficient and the traffic flow transmission characteristics of the sudden event, and then generate a dynamic carbon emission topology matrix of the traffic network based on the adjustment result. The execution module 203 in this application is mainly used to generate carbon emission prediction reports for each segment of the target traffic network by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network.

[0069] In addition, this application also provides a computer device, the computer device including a memory and a processor, the memory storing code, and the processor being configured to acquire the code and execute the above-described method for predicting vehicle carbon emissions from a traffic network.

[0070] In some embodiments, reference Figure 5 This figure is an internal structural diagram of a computer device for implementing a method for predicting vehicle carbon emissions from a traffic network, according to some embodiments of this application. The traffic network vehicle carbon emission prediction method in the above embodiments can be implemented through... Figure 5 The computer device shown is used to implement this, and the computer device 300 includes at least one processor 301, a communication bus 302, a memory 303, and at least one communication interface 304.

[0071] The processor 301 may be a general-purpose central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more devices used to control the execution of the traffic network vehicle carbon emission prediction method in this application.

[0072] The communication bus 302 is used to transmit information between the aforementioned components.

[0073] Memory 303 may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital versatile optical discs, Blu-ray discs, etc.), magnetic disks or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. Memory 303 may exist independently and be connected to processor 301 via communication bus 302. Memory 303 may also be integrated with processor 301.

[0074] The memory 303 stores program code for executing the scheme of this application, and its execution is controlled by the processor 301. The processor 301 executes the program code stored in the memory 303. The program code may include one or more software modules. In the above embodiment, the traffic network vehicle carbon emission prediction method can be implemented by the processor 301 and one or more software modules in the program code in the memory 303.

[0075] Communication interface 304 uses any transceiver-like device to communicate with other devices or communication networks, such as Ethernet, radio access network (RAN), wireless local area networks (WLAN), etc.

[0076] In a specific implementation, as one example, a computer device may include multiple processors, each of which may be a single-core (single-CPU) processor or a multi-core (multi-CPU) processor. Here, a processor may refer to one or more devices, circuits, and / or processing cores for processing data (e.g., computer program instructions).

[0077] The aforementioned computer device can be a general-purpose computer device or a special-purpose computer device. In specific implementations, the computer device may be a desktop computer, a portable computer, a network server, a handheld digital assistant (PDA), a mobile phone, a tablet computer, a wireless terminal device, a communication device, or an embedded device. This application does not limit the type of computer device.

[0078] In addition, this application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for predicting vehicle carbon emissions from a traffic network.

[0079] In summary, the traffic network vehicle carbon emission prediction system, method, device, and medium disclosed in this application obtains traffic flow information of different vehicle types in each segment of the target traffic network; determines carbon emission coefficients in different segments based on the carbon emission characteristics of different vehicle types and the traffic flow information; and then constructs a baseline topology link for carbon emissions in the traffic network by combining the spatial topology relationship of different segments in the target traffic network with all carbon emission coefficients. When a sudden event occurs in the target traffic network, the vehicle speed decay rate of the event segment within a preset time window is determined, and the carbon emission coefficient corresponding to the event segment is coupled and corrected according to the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate. The baseline topology link is dynamically adapted and adjusted according to the corrected carbon emission coefficient and the traffic flow transmission characteristics of the sudden event, and a dynamic carbon emission topology matrix of the traffic network is generated based on the adjustment results. A carbon emission prediction report for each segment of the target traffic network is generated by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network. This enables deep coupling between the static prediction model and the dynamic traffic state of the road network.

[0080] Although preferred embodiments of this application have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of this application.

[0081] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. A method for predicting vehicle carbon emissions from a transportation network, characterized in that, Includes the following steps: Obtain traffic flow information for different vehicle types on various road segments within the target traffic network; Based on the carbon emission characteristics of different vehicle types and the traffic flow information, the carbon emission coefficients in different road segments are determined, and then the baseline topology link of carbon emission in the traffic network is constructed by combining all carbon emission coefficients through the spatial topology relationship of different road segments in the target traffic network. When a sudden event occurs in the target traffic network, the vehicle speed decay rate of the event segment within a preset time window is determined, and then the carbon emission coefficient corresponding to the event segment is coupled and corrected based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate. The baseline topology links are dynamically adapted and adjusted based on the modified carbon emission coefficient and the traffic flow transmission characteristics of sudden events, and then a dynamic carbon emission topology matrix of the traffic network is generated based on the adjustment results. The carbon emission prediction report for each segment of the target traffic network is generated by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network.

2. The method as described in claim 1, characterized in that, Determining the carbon emission coefficient for different road sections based on the carbon emission characteristics of different vehicle types and the traffic flow information specifically includes: The traffic flow information is used to determine the traffic flow percentage of each vehicle type on different road sections; The carbon emission coefficients for different road sections are determined based on the carbon emission characteristics of different vehicle types and the traffic flow ratio of each vehicle type on different road sections.

3. The method as described in claim 1, characterized in that, By combining the spatial topological relationships of different road segments in the target transportation network with all carbon emission coefficients, a baseline topological link for carbon emissions in the transportation network is constructed, specifically including: Determine the topological connection edges between different road segments by using the spatial topological relationships of the target traffic network; Determine the basic connection strength of each topological connection edge; The baseline correlation strength of each topological connection edge is obtained by associating each topological connection edge with the carbon emission coefficient of its corresponding adjacent road segment. A baseline topology link for carbon emissions in the transportation network is constructed based on all baseline correlation strengths.

4. The method as described in claim 1, characterized in that, The coupling correction of the carbon emission coefficient corresponding to the event road segment based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed attenuation rate specifically includes: Determine the correlation characteristics between vehicle speed and carbon emission characteristics; The carbon emission correction factor for the event segment is determined by the correlation features and the vehicle speed decay rate. The carbon emission correction factor is used to couple and correct the carbon emission coefficient corresponding to the event road segment.

5. The method as described in claim 1, characterized in that, The dynamic adaptation and adjustment of the baseline topology link based on the corrected carbon emission coefficient and the traffic flow transmission characteristics of sudden events specifically includes: All affected topological connections of the event segment are determined by the traffic flow transmission characteristics of the sudden event; The conduction correlation strength of each affected topology connection edge is determined based on the corrected carbon emission coefficient; The baseline topology links are dynamically adjusted based on the strength of all conduction correlations.

6. The method as described in claim 1, characterized in that, The dynamic carbon emission topology matrix of the transportation network generated based on the adjustment results specifically includes: Use all road segments in the target traffic network as the row and column indices of the matrix; The results are adjusted to serve as the matrix edge weights between the corresponding row and column indices of the road segments. A dynamic carbon emission topology matrix for the transportation network is generated based on the matrix dimension and the matrix edge weights.

7. The method as described in claim 1, characterized in that, The carbon emission prediction report for each segment of the target traffic network is generated by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network. Specifically, it includes: Emission trend characteristics when determining carbon emissions based on traffic flow evolution trends of the target transportation network; The predicted carbon emission information for each segment of the target traffic network is output through the emission trend characteristics and the dynamic carbon emission topology matrix. Based on the predicted carbon emission information, a carbon emission prediction report for each segment of the target transportation network is generated.

8. A vehicle carbon emission prediction system for a transportation network, characterized in that, include: The acquisition module is used to acquire traffic flow information for different vehicle types on various road segments within the target traffic network; The processing module is used to determine the carbon emission coefficients in different road segments based on the carbon emission characteristics of different vehicle types and the traffic flow information, and then construct the benchmark topology link of carbon emissions in the traffic network by combining all carbon emission coefficients through the spatial topology relationship of different road segments in the target traffic network. The processing module is also used to determine the vehicle speed decay rate of the event segment within a preset time window when a sudden event occurs in the target traffic network, and then to couple and correct the carbon emission coefficient corresponding to the event segment based on the correlation characteristics between vehicle speed and carbon emission characteristics and the vehicle speed decay rate. The processing module is also used to dynamically adapt and adjust the baseline topology link based on the corrected carbon emission coefficient and the traffic flow transmission characteristics of the sudden event, and then generate a dynamic carbon emission topology matrix of the traffic network based on the adjustment result. The execution module is used to generate carbon emission prediction reports for each segment of the target traffic network by combining the dynamic carbon emission topology matrix with the traffic flow evolution trend of the target traffic network.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method for predicting vehicle carbon emissions from a transportation network as described in any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it implements the steps of the method for predicting vehicle carbon emissions from a transportation network as described in any one of claims 1 to 7.

Images