Digital data processing method for dual carbon, energy conservation and emission reduction and intermediate station

Abstract

The invention discloses a digital data processing method for dual carbon and energy conservation and emission reduction and a central station, and relates to the technical field of intelligent transportation, and the method comprises the steps: obtaining a vehicle model and a feature set, clustering to generate a vehicle threshold, and analyzing carbon emission to construct a mapping table. And the predicted traffic flow is obtained by inputting multi-source monitoring acquisition information into the predictor. And generating a regional signal control scheme based on the road network topology and the parameters. And calculating the total carbon emission based on the predicted traffic flow and the scheme simulation idling duration in the simulation space, setting the scheme of the minimum total carbon emission to be optimal, and controlling the signal lamp according to the scheme. The technical problems of poor traffic management efficiency, serious road vehicle idling and high regional vehicle idling carbon emission caused by the fact that an existing traffic signal lamp control mode cannot be accurately, flexibly and timely adjusted according to traffic flow changes are solved, and the purposes of improving the traffic management efficiency, reducing regional vehicle idling carbon emission and reducing the traffic flow change are achieved. And the technical effects of energy conservation, emission reduction and traffic environment improvement are promoted.

Description

Technical Field

[0001] The present application relates to the field of intelligent transportation technology, and in particular to a digital data processing method and a middle platform for dual carbon and energy conservation and emission reduction. Background Art

[0002] In the field of traffic management, with the development of cities and the continuous growth of the number of cars, traffic congestion has become increasingly severe, and the need to optimize traffic light control has become extremely urgent. The traditional traffic light control method has significant defects and is difficult to adapt to the complex and changing traffic situation. Efficiently controlling traffic lights to reduce carbon emissions and optimize traffic flow has become a key issue that needs to be solved in traffic management. Traditional traffic light control often presents a fixed periodicity, cannot be flexibly adjusted according to actual traffic flow, and has poor adaptability to traffic conditions. At the same time, its post-adjustment method based on monitoring data has obvious lag, making it difficult to predict traffic flow changes in advance and make corresponding adjustments. In addition, the traditional control method is seriously insufficient in the precision of prediction and cannot achieve precise control, resulting in unreasonable allocation of traffic resources, affecting traffic operation efficiency and energy conservation and emission reduction effects.

[0003] At the current stage, there is a technical problem in the relevant technologies that the traffic light control method cannot be accurately, flexibly and timely adjusted according to changes in traffic flow, resulting in poor traffic management efficiency and serious idling of road vehicles, causing high carbon emissions from regional vehicle idling. Summary of the invention

[0004] This application provides a digital data processing method and a middle platform for dual carbon and energy conservation and emission reduction. It uses the method of calling the vehicle monitoring log in the target area to obtain the vehicle model and feature set, clustering to generate vehicle thresholds, and analyzing carbon emissions to build a mapping table. The information collected through multi-source monitoring is input into the predictor to obtain the predicted traffic flow. The regional signal control scheme is generated based on the road network topology and parameters. In the simulation space, based on the predicted traffic flow and the scheme, the idling time is simulated, the total carbon emissions are calculated, and the scheme with the minimum total carbon emissions is set as the optimal. The traffic lights are controlled accordingly, achieving the technical effect of reducing vehicle idling, improving traffic management efficiency, reducing regional vehicle idling carbon emissions, and promoting energy conservation and emission reduction and traffic environment improvement through accurate, flexible and timely regulation of traffic lights.

[0005] This application provides a digital data processing method for dual carbon and energy conservation and emission reduction, including:

[0006] The vehicle monitoring log of the target area is called, and multiple vehicle models and multiple vehicle feature sets are queried and obtained. Based on the multiple vehicle feature sets, the multiple vehicle models are clustered to generate multiple vehicle thresholds, and vehicle idling carbon emissions are analyzed for the multiple vehicle thresholds respectively to determine multiple unit idling carbon emissions and construct a vehicle threshold-unit idling carbon emissions mapping table; real-time vehicle information and real-time environmental information of multiple roads in the target area are collected through a multi-source monitoring array, and the current time node, the real-time vehicle information and the real-time environmental information are input into a road flow predictor to predict the traffic flow within a predetermined future period, and output multiple predicted traffic flows; multiple signal lights and A plurality of signal control parameters are provided, and a plurality of regional signal control schemes are generated according to the plurality of signal lights and the plurality of signal control parameters at a predetermined interval step; in a regional traffic simulation space, vehicle idle simulation is performed respectively based on the plurality of predicted vehicle flows and the plurality of regional signal control schemes, a plurality of simulated idle durations are determined, and overall idle carbon emissions are calculated according to the vehicle threshold-unit idle carbon emission mapping table and the plurality of simulated idle durations to obtain a plurality of total carbon emissions; the regional signal control scheme corresponding to the minimum value of the plurality of total carbon emissions is set as the optimal signal control scheme, and within the predetermined future period, the plurality of signal lights in the target area are controlled according to the optimal signal control scheme.

[0007] This application also provides a digital data processing platform for dual carbon and energy conservation and emission reduction, including:

[0008] An idle carbon emission analysis module, the idle carbon emission analysis module is used to call the vehicle monitoring log of the target area, query and obtain multiple vehicle models and multiple vehicle feature sets, cluster the multiple vehicle models based on the multiple vehicle feature sets, generate multiple vehicle thresholds, perform vehicle idle carbon emission analysis on the multiple vehicle thresholds respectively, determine multiple unit idle carbon emissions, and construct a vehicle threshold-unit idle carbon emission mapping table; a vehicle flow prediction module, the vehicle flow prediction module is used to collect real-time vehicle information and real-time environmental information of multiple roads in the target area through a multi-source monitoring array, input the current time node, the real-time vehicle information and the real-time environmental information into a road flow predictor, perform vehicle flow prediction within a predetermined future period, and output multiple predicted vehicle flows; a control scheme generation module, the control scheme generation module is used to generate a vehicle idle carbon emission analysis based on the roads in the target area The network topology determines multiple traffic lights and multiple signal control parameters, and generates multiple regional signal control schemes according to the multiple traffic lights and multiple signal control parameters at a predetermined interval step; a total carbon emission calculation module, which is used to perform vehicle idle simulation in a regional traffic simulation space based on the multiple predicted vehicle flows and the multiple regional signal control schemes, determine multiple simulated idle time periods, and perform overall idle carbon emission calculations according to the vehicle threshold-unit idle carbon emission mapping table and the multiple simulated idle time periods to obtain multiple total carbon emissions; a traffic light control module, which is used to set the regional signal control scheme corresponding to the minimum value of the multiple total carbon emissions as the optimal signal control scheme, and control the multiple traffic lights in the target area according to the optimal signal control scheme within the predetermined future period.

[0009] The digital data processing method and middle platform for dual carbon and energy conservation and emission reduction proposed in this application are proposed. First, the vehicle monitoring log of the target area is called to obtain the vehicle model and feature set, clustering generates vehicle thresholds, and carbon emissions are analyzed to build a mapping table. Information collected through multi-source monitoring is input into the predictor to obtain the predicted traffic flow. The regional signal control scheme is generated based on the road network topology and parameters. In the simulation space, the idling time is simulated based on the predicted traffic flow and the scheme, the total carbon emissions are calculated, and the scheme with the minimum total carbon emissions is set as the optimal. The traffic lights are controlled in this way, achieving the technical effect of reducing vehicle idling, improving traffic management efficiency, reducing regional vehicle idling carbon emissions, and promoting energy conservation and emission reduction and traffic environment improvement by realizing accurate, flexible and timely regulation of traffic lights. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the drawings of the embodiment of the present invention are briefly introduced below. A flowchart is used in this application to illustrate the operations performed by the middle station according to the embodiment of the present application. It should be understood that the previous or following operations are not necessarily performed precisely in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0011] Figure 1 A flow chart of a digital data processing method for dual carbon and energy conservation and emission reduction provided in an embodiment of the present application;

[0012] Figure 2 A schematic diagram of the structure of a digital data processing platform for dual carbon and energy conservation and emission reduction provided in an embodiment of the present application.

[0013] Explanation of the accompanying drawings: idle carbon emission analysis module 10, vehicle flow prediction module 20, control scheme generation module 30, total carbon emission calculation module 40, traffic light control module 50. DETAILED DESCRIPTION

[0014] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0015] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0016] In the following description, reference is made to “some embodiments”, which describe a subset of all possible embodiments, but it is understood that “some embodiments” may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms “first\second” involved are merely to distinguish similar objects and do not represent a specific ordering of the objects. The terms “including” and “having” and any variations are intended to cover non-exclusive inclusions. For example, a process, method, middle platform, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field to which this application belongs. The terms used herein are for the purpose of describing the embodiments of this application only.

[0017] The present application embodiment provides a digital data processing method for dual carbon and energy conservation and emission reduction, such as Figure 1 As shown, the method includes:

[0018] Step S100, call the vehicle monitoring log of the target area, query and obtain multiple vehicle models and multiple vehicle feature sets, cluster the multiple vehicle models based on the multiple vehicle feature sets, generate multiple vehicle thresholds, analyze the vehicle idling carbon emissions for the multiple vehicle thresholds respectively, determine multiple unit idling carbon emissions, and construct a vehicle threshold-unit idling carbon emission mapping table. Specifically, call the vehicle monitoring log of the target area, the log contains vehicle data, and through the query operation, obtain multiple vehicle models and corresponding multiple vehicle feature sets. The feature set covers a lot of key information, such as the displacement, model, age, weight, fuel efficiency, etc. of the vehicle. Based on the vehicle feature set, use the clustering algorithm to classify the multiple vehicle models. By calculating the similarity or distance of different vehicle models in features, the vehicle models with similar features are classified into one category, thereby generating multiple vehicle thresholds. Each vehicle threshold represents a group of vehicles with similar features. For the generated multiple vehicle thresholds, analyze the vehicle idling carbon emissions respectively, and comprehensively consider factors such as the vehicle's engine performance, fuel type, and idling time to accurately evaluate each vehicle threshold. The idling carbon emissions of vehicles within each vehicle threshold are analyzed. After completing the carbon emission analysis of each vehicle threshold, the unit idling carbon emissions corresponding to each vehicle threshold are determined. The unit idling carbon emissions are a quantitative representation of the average idling carbon emission level of vehicles within the vehicle threshold. A vehicle threshold-unit idling carbon emission mapping table is constructed. The mapping table establishes a one-to-one correspondence between each vehicle threshold and its corresponding unit idling carbon emissions. Through the mapping table, a refined analysis of vehicle idling carbon emissions is achieved. For example, when it is necessary to understand the idling carbon emission level of a specific type of vehicle, it is only necessary to find the corresponding vehicle threshold to quickly obtain its unit idling carbon emission data, which is of great significance for accurately assessing the carbon emission status in the transportation field, formulating targeted emission reduction strategies, and optimizing traffic management measures.

[0019] In one possible implementation, the vehicle monitoring log of the target area is called, and multiple vehicle models and multiple vehicle feature sets are queried and obtained. Based on the multiple vehicle feature sets, the multiple vehicle models are clustered to generate multiple vehicle thresholds, and vehicle idle carbon emissions are analyzed for the multiple vehicle thresholds respectively to determine multiple unit idle carbon emissions, and a vehicle threshold-unit idle carbon emissions mapping table is constructed. Step S100 further includes step S110, constructing a vehicle feature space, wherein the vehicle feature space includes at least vehicle type, body size, body weight, engine displacement, fuel efficiency and vehicle age. Specifically, a comprehensive space for describing vehicle characteristics is created, in which several key factors that have a significant impact on vehicle performance and emissions are clearly defined and included. For example, vehicle types can be divided into sedans, SUVs, MPVs, etc., reflecting the basic purpose and design features of the vehicle; body dimensions include length, width, and height, which affect air resistance and interior space; body weight is measured by weighing equipment, which is related to energy consumption and power requirements; engine displacement is measured in liters, which determines power output and fuel consumption; fuel efficiency is calculated by fuel consumption per unit mileage, which is directly related to fuel economy; the vehicle age is determined based on the vehicle registration time and usage time, reflecting the aging of vehicle components and performance degradation. The elements together constitute the basic framework for describing vehicle characteristics.

[0020] Step S120, sequentially analyzing the correlation between multiple vehicle features in the vehicle feature space and vehicle idle emissions, and determining predetermined correlation features, wherein the predetermined correlation features are vehicle features with correlation greater than a predetermined correlation threshold. Specifically, for each vehicle feature in the constructed vehicle feature space, the Pearson correlation coefficient algorithm and the linear regression analysis method are used to quantitatively calculate the correlation degree with the vehicle idle emissions one by one, and by collecting a large amount of vehicle sample data, the Pearson correlation coefficient between each vehicle feature and the idle emissions is calculated to measure the strength of the linear correlation, and the linear regression model is used to analyze the influence and trend of the vehicle feature on the idle emissions, and a predetermined correlation threshold is set, such as the Pearson correlation coefficient is greater than 0.7 or the significance level in the linear regression model is less than 0.05. Only when the correlation degree between a certain vehicle feature and the vehicle idle emissions exceeds this threshold, it is identified as a predetermined correlation feature that has a significant impact on the idle emissions.

[0021] Step S130, query and obtain multiple initial vehicle feature sets, and screen the multiple initial vehicle feature sets based on the predetermined associated features to obtain the multiple vehicle feature sets. Specifically, multiple initial sets containing various vehicle features are obtained by querying the vehicle database and the monitoring system, and the initial vehicle feature sets are finely screened according to the previously determined predetermined associated features with significant association, such as engine displacement, vehicle body weight, etc., to remove data that does not contain the predetermined associated features or is weakly associated with the predetermined associated features, thereby obtaining multiple accurate vehicle feature sets for subsequent in-depth analysis and processing.

[0022] In one possible implementation, the vehicle monitoring log of the target area is called, and multiple vehicle models and multiple vehicle feature sets are queried to obtain. Based on the multiple vehicle feature sets, the multiple vehicle models are clustered to generate multiple vehicle thresholds, and vehicle idling carbon emissions are analyzed for the multiple vehicle thresholds respectively to determine multiple unit idling carbon emissions, and a vehicle threshold-unit idling carbon emissions mapping table is constructed. Step S100 further includes step S140, randomly selecting K feature sets from the multiple vehicle feature sets and setting them as K clustering centers, calculating the Euclidean distances between other vehicle feature sets and the K clustering centers respectively, and assigning other vehicle feature sets to the clustering center with the shortest Euclidean distance to obtain K cluster clusters. Specifically, K feature sets are randomly selected from numerous vehicle feature sets by random number generation, and the K feature sets are set as initial clustering centers. For other unselected vehicle feature sets, the Euclidean distance calculation is used to calculate the Euclidean distance between each unselected feature set and the K clustering centers. The smaller the distance, the more similar the two feature sets are. The unselected feature sets are classified into the category corresponding to the clustering center with the shortest distance to them, forming K preliminary clusters.

[0023] Step S150, respectively perform mean operations on the K clusters, update the K cluster centers based on the mean operation results, and determine K updated cluster centers. Specifically, for the obtained K clusters, respectively calculate the arithmetic mean of the feature values ​​corresponding to all feature sets in each cluster, and after calculating the means of all feature dimensions, use the new feature set composed of the means as the new cluster center, thereby determining K updated cluster centers.

[0024] Step S160, performing iterative clustering based on the K updated cluster centers until a predetermined clustering constraint is satisfied, outputting K current clusters, and mapping and aggregating the multiple vehicle models based on the K current clusters to obtain the multiple vehicle thresholds. Specifically, taking the newly determined K updated cluster centers as the starting point, repeat the above steps of calculating the Euclidean distance, assigning feature sets and updating cluster centers, and continuously iterate. After each iteration, check whether the predetermined clustering constraints are met. The predetermined clustering constraints can be that the cluster centers no longer change, that is, the difference between the newly calculated cluster centers and the cluster centers of the previous round in each feature dimension is less than a minimum value, or the maximum number of iterations set in advance is reached. When these constraints are met, stop the iteration and output the current K cluster clusters. According to the K current cluster clusters, map and aggregate multiple vehicle models according to the cluster clusters they belong to to form multiple vehicle thresholds. For example, if the feature set corresponding to vehicle model A belongs to cluster cluster 1, and the feature set corresponding to vehicle model B belongs to cluster cluster 2, then A and B are respectively aggregated into the corresponding vehicle thresholds.

[0025] In a possible implementation, the vehicle monitoring log of the target area is called, and multiple vehicle models and multiple vehicle feature sets are queried and obtained. Based on the multiple vehicle feature sets, the multiple vehicle models are clustered to generate multiple vehicle thresholds, and vehicle idle carbon emissions are analyzed for the multiple vehicle thresholds respectively to determine multiple unit idle carbon emissions, and a vehicle threshold-unit idle carbon emissions mapping table is constructed. Step S100 further includes step S170, randomly selecting a first vehicle threshold from the multiple vehicle thresholds, and obtaining a first vehicle model of the first vehicle threshold, wherein the first vehicle model is any vehicle model in the first vehicle threshold. Specifically, from among the numerous vehicle thresholds, a vehicle threshold is randomly selected by random number generation or random sampling, and it is defined as the first vehicle threshold, and one of the vehicle models included in the first vehicle threshold is randomly selected and set as the first vehicle model.

[0026] Step S180, taking the first vehicle model as a constraint, retrieving and obtaining a sample unit idling carbon emission set based on automobile big data, and performing mean calculation to obtain a first sample emission mean. Specifically, taking the selected first vehicle model as a condition and restriction, searching and screening are performed in the huge automobile big data, obtaining data of all sample unit idling carbon emissions related to the vehicle model, forming a sample unit idling carbon emission set, and calculating the arithmetic mean of all data in the set, thereby obtaining the first sample emission mean.

[0027] Step S190, based on the first sample emission mean, the sample unit idle carbon emission set is screened to obtain a standard unit idle carbon emission set, and the first vehicle unit idle carbon emission is obtained by mean calculation, wherein the standard unit idle carbon emission is the sample unit idle carbon emission whose deviation value from the first sample emission mean is less than a predetermined deviation threshold. Specifically, the obtained first sample emission mean is used as a benchmark, and the obtained sample unit idle carbon emission set is screened again, and only data whose deviation value from the first sample emission mean is less than a predetermined deviation threshold set in advance is retained, and the data constitutes a standard unit idle carbon emission set, and the arithmetic mean of the data in the set is calculated again, and the result obtained is the first vehicle unit idle carbon emission.

[0028] Step S1100, sequentially obtain multiple first vehicle models and multiple first vehicle unit idle carbon emissions, calculate the average to obtain the first unit idle carbon emissions, and add them to the multiple unit idle carbon emissions. Specifically, according to the above steps, repeat the operations in sequence to obtain multiple different first vehicle models and their corresponding first vehicle unit idle carbon emissions, summarize all the data of the first vehicle unit idle carbon emissions, calculate their arithmetic mean again, and the final result obtained is the first unit idle carbon emissions, and the first unit idle carbon emissions are added to the set of multiple unit idle carbon emissions.

[0029] Step S200, collects real-time vehicle information and real-time environmental information of multiple roads in the target area through a multi-source monitoring array, inputs the current time node, the real-time vehicle information and the real-time environmental information into a road flow predictor, performs traffic flow prediction within a predetermined future period, and outputs multiple predicted traffic flows. Specifically, multi-source monitoring arrays are rationally deployed along multiple roads in the target area. The monitoring equipment includes high-definition cameras installed above or on the roadside to capture images of vehicles, thereby obtaining information such as the number, model, and license plate of the vehicles; millimeter-wave radars are installed on both sides of the road or on the gantry to accurately measure the speed and position of the vehicle by transmitting and receiving millimeter waves; environmental sensors are distributed around the road and can detect environmental parameters such as temperature, humidity, wind speed, and rainfall in real time. The multi-source monitoring equipment will collect real-time vehicle information (such as the number of vehicles, speed, model, traffic direction, license plate, etc.) and real-time environmental information (such as weather conditions, temperature, humidity, wind speed, road construction conditions, accident conditions, etc.), as well as the accurate current time node, and transmit them to the data processing center via wired or wireless means. At the data processing center, all received data will be integrated and pre-processed. The data is input into a pre-trained road traffic predictor. The predictor is based on deep learning algorithms, such as BP neural networks, and can fully learn and understand the time series characteristics and complex nonlinear relationships in historical data. The predictor comprehensively considers multi-dimensional data such as the current time node, real-time vehicle information, and real-time environmental information, and predicts the traffic flow in a predetermined future period (for example, the next 1 hour, the next 2 hours, the next day, etc.). During the prediction process, the model will perform intelligent inference and calculation based on the traffic flow change trends under similar time nodes, vehicles and environmental conditions in the historical data. The predictor outputs multiple detailed predicted traffic flow results, including traffic flow forecasts for different roads and different time periods. The prediction results can be presented in the form of data tables, charts, etc., providing scientific, accurate and practical data basis for traffic management departments to make decisions on traffic planning, signal light control, road diversion, etc.

[0030] In a possible implementation, real-time vehicle information and real-time environmental information of multiple roads in the target area are collected through a multi-source monitoring array, the current time node, the real-time vehicle information and the real-time environmental information are input into a road flow predictor, a vehicle flow prediction within a predetermined future period is performed, and multiple predicted vehicle flows are output. Step S200 further includes step S210, screening the real-time vehicle information based on the multiple vehicle thresholds, determining multiple real-time vehicle flows, and randomly selecting a first real-time vehicle flow of the first vehicle threshold. Specifically, the acquired real-time vehicle information is filtered and classified using the multiple vehicle thresholds that have been determined as screening conditions, and the real-time vehicle flows belonging to different vehicle thresholds are accurately determined. After the classification is completed, the first vehicle threshold is randomly selected from the numerous vehicle thresholds, and one is arbitrarily selected from the corresponding real-time vehicle flows, which is defined as the first real-time vehicle flow.

[0031] Step S220, input the current time node, the first real-time vehicle flow and the real-time environmental information into the first traffic prediction branch, and output the first predicted flow, wherein the first traffic prediction branch is constructed based on the BP neural network. Specifically, the three sets of data, namely the current specific time node, the first real-time vehicle flow just selected and the real-time environmental information, are input together into the first traffic prediction branch, which is constructed based on the BP neural network, receives the input data, and outputs a prediction result, namely the first predicted flow, through the internal complex neuron connection and calculation.

[0032] Step S230, input the current time node, the first real-time vehicle flow and the real-time environmental information into the second flow prediction branch, and output the second predicted flow, wherein the second flow prediction branch is constructed based on the Bayesian network. Specifically, the three sets of data, namely the current time node, the first real-time vehicle flow and the real-time environmental information, are also input into the second flow prediction branch again. Unlike the first flow prediction branch, the second flow prediction branch is constructed based on the Bayesian network, and outputs another prediction result, namely the second predicted flow, according to the input data, the Bayesian theorem and probability reasoning.

[0033] Step S240, fuse the first predicted traffic flow and the second predicted traffic flow according to a predetermined weight ratio, output the first predicted traffic flow, and add it to the multiple predicted traffic flows, wherein the predetermined weight ratio is configured based on the prediction accuracy of the first traffic prediction branch and the second traffic prediction branch. Specifically, according to a pre-set weight ratio, a fusion calculation is performed on the first predicted traffic flow output by the first traffic prediction branch and the second predicted traffic flow output by the second traffic prediction branch, and the predetermined weight ratio is determined based on the accuracy performance of the first traffic prediction branch and the second traffic prediction branch in historical predictions. After the fusion calculation is completed, the final first predicted traffic flow is obtained and added to the set of multiple predicted traffic flows for subsequent analysis and application.

[0034] In a possible implementation, the current time node, the first real-time vehicle flow, and the real-time environmental information are input into the second traffic prediction branch, and the second predicted traffic is output, wherein the second traffic prediction branch is constructed based on the Bayesian network, and step S230 further includes step S231, using the first vehicle threshold and the predetermined future period as constraints, retrieving the vehicle monitoring log, and obtaining a sample traffic data set, wherein the sample traffic data includes a sample time node, sample real-time vehicle flow, sample real-time environmental information, and sample predicted vehicle flow. Specifically, the two conditions of the first vehicle threshold and the predetermined future period are clarified, and a search is performed in the database of the vehicle monitoring log to extract relevant data that meets these two constraints, thereby obtaining a sample traffic data set, which contains detailed information, such as a specific sample time node, the sample real-time vehicle flow, the sample real-time environmental information at that time, and the corresponding sample predicted vehicle flow.

[0035] Step S232, taking the time node, real-time traffic flow and real-time environmental information as input nodes, taking the predicted traffic flow as output nodes, and constructing a Bayesian network graph structure based on the expert knowledge base. Specifically, the three elements of the time node, real-time traffic flow and real-time environmental information in the sample traffic data set are set as input nodes, and the predicted traffic flow is set as the output node. Based on the knowledge base formed by the rich knowledge and experience of experts in the field of traffic flow, a Bayesian network graph structure is constructed, and the network structure can reflect the potential relationship and probability distribution between input and output.

[0036] Step S233, the Bayesian network graph structure is trained with parameters optimized by the sample traffic data set to obtain the second traffic prediction branch that meets the expected conditions. Specifically, the constructed Bayesian network graph structure is repeatedly trained and optimized using the acquired sample traffic data set. During the training process, the parameters in the network are continuously adjusted so that the network can better learn and understand the patterns and rules in the data. The training is continued until the performance of the network meets the expected conditions, thereby obtaining the second traffic prediction branch that can accurately perform traffic prediction.

[0037] Step S300, based on the road network topology of the target area, multiple signal lights and multiple signal control parameters are determined, and multiple regional signal control schemes are generated according to the multiple signal lights and multiple signal control parameters according to a predetermined interval step. Specifically, based on the topology information, the specific positions of the multiple signal lights set in the area are determined, and multiple signal control parameters related to the signal lights, such as green light duration, red light duration, yellow light duration, phase setting, etc., are clarified. According to the predetermined interval step, for example, every 1 second, multiple regional signal control schemes are generated according to the position of the signal light and the signal control parameters. Assuming that the initial green light duration of a certain signal light is 30 seconds, it is adjusted with a step of 1 second. The generated schemes include a series of different combinations of green light durations of 31 seconds, 32 seconds, 29 seconds, etc. Such step adjustment and combination are performed for each signal light, and then the coordination relationship between the multiple signal lights is comprehensively considered, so as to form multiple complete regional signal control schemes. By generating multiple schemes according to the predetermined interval step, the control of the signal light can be finely designed and optimized to adapt to different traffic flow and road conditions.

[0038] Step S400, within the regional traffic simulation space, perform vehicle idle simulation based on the multiple predicted traffic flows and the multiple regional signal control schemes, determine multiple simulated idle durations, calculate the overall idle carbon emissions based on the vehicle threshold-unit idle carbon emission mapping table and the multiple simulated idle durations, and obtain multiple total carbon emissions. Specifically, a regional traffic simulation space is created to simulate the actual traffic operation situation, and the multiple predicted traffic flows and multiple regional signal control schemes obtained previously are input into this simulation space. During the simulation process, according to the traffic flow and signal control schemes, the driving and stopping states of vehicles on the road are simulated, especially the idling conditions of the vehicles. By simulating each combination of traffic flow and signal control schemes, multiple simulated idling times are determined, that is, the length of time the vehicle is in the idling state in each case. According to the previously constructed vehicle threshold-unit idling carbon emission mapping table, the unit idling carbon emission value corresponding to the vehicle threshold to which the current vehicle belongs is searched, the unit idling carbon emission value found is multiplied by the corresponding simulated idling time, and then the calculation results of all vehicles are accumulated to calculate the overall idling carbon emission, and finally multiple total carbon emission results are obtained. For example, for a certain combination of traffic flow and signal control schemes, the unit idling carbon emission of the vehicle threshold to which vehicle A belongs is simulated to be X grams per hour, and the simulated idling time of vehicle A is Y hours, then the idling carbon emission of vehicle A is X*Y grams. Such calculations are performed for all vehicles and accumulated to obtain the total carbon emissions under this combination scheme. Such calculations are performed for different combinations of multiple predicted traffic flows and multiple regional signal control schemes to obtain multiple total carbon emissions.

[0039] In one possible implementation, within a regional traffic simulation space, vehicle idle simulations are performed based on the multiple predicted traffic flows and the multiple regional signal control schemes, multiple simulated idle durations are determined, and overall idle carbon emissions are calculated based on the vehicle threshold-unit idle carbon emission mapping table and the multiple simulated idle durations to obtain multiple total carbon emissions. Step S400 further includes step S410, which builds a regional traffic simulation space based on the digital twin and according to the road network topology, and renders the real-time environmental information and the multiple predicted traffic flows into the regional traffic simulation space. Specifically, digital twin technology is used. Digital twin technology is a comprehensive technology that combines physical entities, sensor data, virtual models and data analysis. Based on the detailed road network topology obtained, including specific parameters such as road length, width, number of lanes, and intersection settings, a regional traffic simulation space is built using professional modeling software and algorithms. The architecture and parameters of the space are highly consistent with the actual road network, and can accurately reflect the geometry and connection relationships of the roads. The real-time environmental information collected, such as precise temperature, humidity, wind speed, rainfall and other data, as well as multiple predicted traffic flow data obtained through advanced prediction algorithms, are accurately rendered into the regional traffic simulation space using high-performance graphics processing technology and data transmission technology, ensuring that the environmental conditions and traffic flow distribution in the simulation space are highly consistent with the actual situation, providing a real and reliable foundation for subsequent simulations.

[0040] Step S420, randomly select a first regional signal control scheme, use the regional traffic simulation space to perform N vehicle idle simulations on the first regional signal control scheme, select the mode of the N simulated idle durations as the first simulated idle duration, and add it to the multiple simulated idle durations, where N is an integer greater than 50. Specifically, from the numerous generated regional signal control schemes, a scheme is randomly selected through random number generation or random sampling, and marked as the first regional signal control scheme. The regional traffic simulation space that has been constructed and accurately renders the real-time environment and predicted traffic flow is fully utilized to perform N times (N is an integer greater than 50, for example, it can be set to 100 times) of high-precision vehicle idling simulation on the first regional signal control scheme. During each simulation, precise timing equipment and algorithms are used to accurately record the idling time of each vehicle. After the simulation is completed, a detailed statistical analysis is performed on the N idle time data obtained from the N simulations to find the idle time with the highest frequency, that is, the mode, and determine it as the first simulated idle time. The first simulated idle time is added to the set of multiple simulated idle times that have been collected, providing rich data support for further analysis of traffic conditions and optimization of signal control schemes.

[0041] Step S500, setting the regional signal control scheme corresponding to the minimum value of the multiple total carbon emissions as the optimal signal control scheme, and in the predetermined future period, controlling the multiple traffic lights in the target area according to the optimal signal control scheme. Specifically, the multiple total carbon emission values ​​calculated previously are compared and screened, and each total carbon emission value is checked one by one to determine the minimum value, and the regional signal control scheme corresponding to the minimum value is found. Since the scheme generates the least carbon emissions, it is set as the optimal signal control scheme. When the predetermined future period is reached, according to the specific provisions and parameters in the optimal signal control scheme, for example, for each traffic light in the target area, the control parameters such as the green light duration, red light duration, phase switching time set in the optimal scheme are precisely set and adjusted to ensure that during the entire predetermined future period, the multiple traffic lights in the target area are strictly controlled in accordance with the optimal signal control scheme to achieve efficient traffic operation and minimize carbon emissions. For example, assuming that the optimal signal control scheme stipulates that the green light duration of the traffic lights at a certain intersection between 8 and 9 in the morning is 40 seconds and the red light duration is 80 seconds, then during this time period, the traffic lights at the intersection will work according to this time setting.

[0042] The embodiment of the present application uses the method of calling the vehicle monitoring log of the target area to obtain the vehicle model and feature set, clustering to generate vehicle thresholds, and analyzing carbon emissions to construct a mapping table. Information collected through multi-source monitoring is input into the predictor to obtain the predicted traffic flow. The regional signal control scheme is generated based on the road network topology and parameters. In the simulation space, the idling time is simulated based on the predicted traffic flow and the scheme, the total carbon emissions are calculated, and the scheme with the minimum total carbon emissions is set as the optimal. The traffic lights are controlled accordingly, achieving the technical effect of reducing vehicle idling, improving traffic management efficiency, reducing regional vehicle idling carbon emissions, and promoting energy conservation, emission reduction, and traffic environment improvement by realizing accurate, flexible and timely regulation of traffic lights.

[0043] In the above, refer to Figure 1 The digital data processing method for dual carbon and energy conservation and emission reduction according to an embodiment of the present invention is described in detail. Figure 2 Describe the digital data processing middle platform for dual carbon and energy conservation and emission reduction according to an embodiment of the present invention.

[0044] The digital data processing platform for dual carbon and energy conservation and emission reduction according to the embodiment of the present invention is used to solve the technical problem that the existing traffic light control method cannot be accurately, flexibly and timely adjusted according to the changes in traffic flow, resulting in poor traffic management efficiency and serious idling of road vehicles, resulting in high carbon emissions from regional vehicle idling. By realizing accurate, flexible and timely regulation of traffic lights, the technical effect of reducing vehicle idling, improving traffic management efficiency, reducing regional vehicle idling carbon emissions, and promoting energy conservation and emission reduction and traffic environment improvement is achieved. The digital data processing platform for dual carbon and energy conservation and emission reduction includes: an idle carbon emission analysis module 10, a vehicle flow prediction module 20, a control scheme generation module 30, a total carbon emission calculation module 40, and a traffic light control module 50.

[0045] The idle carbon emission analysis module 10 is used to call the vehicle monitoring log of the target area, query and obtain multiple vehicle models and multiple vehicle feature sets, cluster the multiple vehicle models based on the multiple vehicle feature sets, generate multiple vehicle thresholds, perform vehicle idle carbon emission analysis on the multiple vehicle thresholds respectively, determine multiple unit idle carbon emissions, and construct a vehicle threshold-unit idle carbon emission mapping table;

[0046] The vehicle flow prediction module 20 is used to collect real-time vehicle information and real-time environmental information of multiple roads in the target area through a multi-source monitoring array, input the current time node, the real-time vehicle information and the real-time environmental information into a road flow predictor, perform vehicle flow prediction within a predetermined future period, and output multiple predicted vehicle flows;

[0047] The control scheme generating module 30 is used to determine a plurality of signal lights and a plurality of signal control parameters based on the road network topology of the target area, and generate a plurality of regional signal control schemes according to the plurality of signal lights and the plurality of signal control parameters at a predetermined interval step;

[0048] The total carbon emission calculation module 40 is used to perform vehicle idling simulations in the regional traffic simulation space based on the multiple predicted vehicle flows and the multiple regional signal control schemes, determine multiple simulated idling durations, and perform overall idling carbon emission calculations according to the vehicle threshold-unit idling carbon emission mapping table and the multiple simulated idling durations to obtain multiple total carbon emissions;

[0049] The traffic light control module 50 is used to set the regional signal control scheme corresponding to the minimum value of the multiple total carbon emissions as the optimal signal control scheme, and control the multiple traffic lights in the target area according to the optimal signal control scheme within the predetermined future period.

[0050] Next, the specific configuration of the idle carbon emission analysis module 10 will be described in detail. As described above, the vehicle monitoring log of the target area is called, and multiple vehicle models and multiple vehicle feature sets are queried and obtained. Based on the multiple vehicle feature sets, the multiple vehicle models are clustered to generate multiple vehicle thresholds, and vehicle idle carbon emissions are analyzed for the multiple vehicle thresholds respectively to determine multiple unit idle carbon emissions, and a vehicle threshold-unit idle carbon emissions mapping table is constructed. The idle carbon emission analysis module 10 further includes: a feature space construction unit, the feature space construction unit is used to construct a vehicle feature space, wherein the vehicle feature space at least includes vehicle type, body size, body weight, engine displacement, fuel efficiency and vehicle service life; a predetermined correlation feature determination unit, the predetermined correlation feature determination unit is used to sequentially perform correlation analysis on multiple vehicle features in the vehicle feature space and vehicle idle emissions to determine a predetermined correlation feature, wherein the predetermined correlation feature is a vehicle feature with a correlation greater than a predetermined correlation threshold; a vehicle feature set acquisition unit, the vehicle feature set acquisition unit is used to query and obtain multiple initial vehicle feature sets, and the multiple initial vehicle feature sets are screened based on the predetermined correlation feature to obtain the multiple vehicle feature sets.

[0051] Among them, the idle carbon emission analysis module 10 further includes: a cluster acquisition unit, which is used to randomly select K feature sets from the multiple vehicle feature sets and set them as K cluster centers, calculate the Euclidean distances between other vehicle feature sets and the K cluster centers respectively, and assign other vehicle feature sets to the cluster center with the shortest Euclidean distance to obtain K cluster clusters; a mean operation unit, which is used to perform mean operations on the K cluster clusters respectively, update the K cluster centers based on the mean operation results, and determine K updated cluster centers; an iterative clustering unit, which is used to perform iterative clustering based on the K updated cluster centers until the predetermined clustering constraints are met, output K current cluster clusters, and map and aggregate the multiple vehicle models based on the K current cluster clusters to obtain the multiple vehicle thresholds.

[0052] Among them, the idle carbon emission analysis module 10 further includes: a vehicle model acquisition unit, the vehicle model acquisition unit is used to randomly select a first vehicle threshold from the multiple vehicle thresholds and obtain a first vehicle model of the first vehicle threshold, wherein the first vehicle model is any vehicle model in the first vehicle threshold; an emission mean calculation unit, the emission mean calculation unit is used to retrieve a sample unit idle carbon emission set based on automobile big data with the first vehicle model as a constraint, and perform mean calculation to obtain a first sample emission mean; an idle carbon emission calculation unit, the idle carbon emission calculation unit is used to screen the sample unit idle carbon emission set based on the first sample emission mean, obtain a standard unit idle carbon emission set, and obtain a first vehicle unit idle carbon emission by mean calculation, wherein the standard unit idle carbon emission is a sample unit idle carbon emission whose deviation value from the first sample emission mean is less than a predetermined deviation threshold; an idle carbon emission mean calculation unit, the idle carbon emission mean calculation unit is used to sequentially obtain multiple first vehicle models and multiple first vehicle unit idle carbon emissions, obtain a first unit idle carbon emission by mean calculation, and add it to the multiple unit idle carbon emissions.

[0053] The specific configuration of the vehicle flow prediction module 20 will be described in detail below. As described above, the real-time vehicle information and real-time environmental information of multiple roads in the target area are collected through a multi-source monitoring array, the current time node, the real-time vehicle information and the real-time environmental information are input into the road flow predictor, the vehicle flow prediction within a predetermined future period is performed, and multiple predicted vehicle flows are output. The vehicle flow prediction module 20 further includes: a real-time vehicle flow determination unit, the real-time vehicle flow determination unit is used to screen the real-time vehicle information based on the multiple vehicle thresholds, determine multiple real-time vehicle flows, and randomly select the first real-time vehicle flow of the first vehicle threshold; a first predicted flow output unit, the first predicted flow output unit is used to input the current time node, the first real-time vehicle flow and the real-time environmental information into the road flow predictor, and the vehicle flow prediction within a predetermined future period is performed, and multiple predicted vehicle flows are output. A first traffic prediction branch outputs a first predicted traffic, wherein the first traffic prediction branch is constructed based on a BP neural network; a second predicted traffic output unit, wherein the second predicted traffic output unit is used to input the current time node, the first real-time vehicle traffic and real-time environmental information into the second traffic prediction branch, and output the second predicted traffic, wherein the second traffic prediction branch is constructed based on a Bayesian network; a fusion unit, wherein the fusion unit is used to fuse the first predicted traffic and the second predicted traffic according to a predetermined weight ratio, output the first predicted vehicle traffic, and add it to the multiple predicted vehicle traffic, wherein the predetermined weight ratio is configured based on the prediction accuracy of the first traffic prediction branch and the second traffic prediction branch.

[0054] Among them, the second predicted traffic output unit further includes: a traffic data set acquisition subunit, the traffic data set acquisition subunit is used to retrieve the vehicle monitoring log with the first vehicle threshold and the predetermined future period as constraints, and obtain a sample traffic data set, wherein the sample traffic data includes sample time nodes, sample real-time vehicle flow, sample real-time environmental information and sample predicted vehicle flow; a Bayesian network graph structure construction subunit, the Bayesian network graph structure construction subunit is used to use the time node, real-time vehicle flow and real-time environmental information as input nodes, and the predicted vehicle flow as output nodes, and construct a Bayesian network graph structure based on an expert knowledge base; a parameter optimization training subunit, the parameter optimization training subunit is used to perform parameter optimization training on the Bayesian network graph structure through the sample traffic data set to obtain the second traffic prediction branch that meets the expected conditions.

[0055] The specific configuration of the total carbon emission calculation module 40 will be described in detail below. As described above, in the regional traffic simulation space, vehicle idle simulation is performed based on the multiple predicted vehicle flows and the multiple regional signal control schemes, multiple simulated idle durations are determined, and the overall idle carbon emission calculation is performed according to the vehicle threshold-unit idle carbon emission mapping table and the multiple simulated idle durations to obtain multiple total carbon emissions. The total carbon emission calculation module 40 further includes: a simulation space construction unit, the simulation space construction unit is used to build a regional traffic simulation space based on the road network topology based on the digital twin, and render the real-time environmental information and the multiple predicted vehicle flows to the regional traffic simulation space; an idle simulation unit, the idle simulation unit is used to randomly select a first regional signal control scheme, use the regional traffic simulation space, perform N vehicle idle simulations on the first regional signal control scheme, select the mode of the N simulated idle durations as the first simulated idle duration, and add it to the multiple simulated idle durations, where N is an integer greater than 50.

[0056] The digital data processing middle platform for dual carbon and energy conservation and emission reduction provided in the embodiments of the present invention can execute the digital data processing method for dual carbon and energy conservation and emission reduction provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0057] Although the present application makes various references to certain modules in the middle platform according to the embodiments of the present application, any number of different modules may be used and run on the user terminal and / or server, and the various units and modules included are only divided according to functional logic, but are not limited to the above division, as long as the corresponding functions can be implemented; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0058] The above specific implementation manner does not constitute a limitation to the protection scope of the present application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present application should be included in the protection scope of the present application. In some cases, the actions or steps recorded in the present application can be performed in an order different from that in the embodiment and can still achieve the desired results. In addition, the process depicted in the accompanying drawings does not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

Claims

1. Digital data processing methods for dual carbon and energy conservation and emission reduction, It is characterized in that include: Calling the vehicle monitoring log of the target area, querying and obtaining multiple vehicle models and multiple vehicle feature sets, clustering the multiple vehicle models based on the multiple vehicle feature sets, generating multiple vehicle thresholds, performing vehicle idling carbon emission analysis on the multiple vehicle thresholds respectively, determining multiple unit idling carbon emissions, and constructing a vehicle threshold-unit idling carbon emission mapping table; Collecting real-time vehicle information and real-time environmental information of multiple roads in the target area through a multi-source monitoring array, inputting the current time node, the real-time vehicle information and the real-time environmental information into a road flow predictor, performing a traffic flow prediction within a predetermined future period, and outputting multiple predicted traffic flows; Determine a plurality of signal lights and a plurality of signal control parameters based on a road network topology of a target area, and generate a plurality of regional signal control schemes according to the plurality of signal lights and the plurality of signal control parameters at a predetermined interval step; In the regional traffic simulation space, based on the multiple predicted vehicle flows and the multiple regional signal control schemes, vehicle idle simulations are respectively performed to determine multiple simulated idle durations, and overall idle carbon emissions are calculated according to the vehicle threshold-unit idle carbon emission mapping table and the multiple simulated idle durations to obtain multiple total carbon emissions; The regional signal control scheme corresponding to the minimum value of the multiple total carbon emissions is set as the optimal signal control scheme, and within the predetermined future period, the multiple traffic lights in the target area are controlled according to the optimal signal control scheme.

2. According to the digital data processing method for dual carbon and energy conservation and emission reduction according to claim 1, It is characterized in that Get multiple vehicle feature sets, including: Constructing a vehicle feature space, wherein the vehicle feature space at least includes vehicle type, body size, body weight, engine displacement, fuel efficiency, and vehicle age; sequentially analyzing the correlation between a plurality of vehicle features in the vehicle feature space and vehicle idle emissions to determine a predetermined correlation feature, wherein the predetermined correlation feature is a vehicle feature having a correlation greater than a predetermined correlation threshold; A plurality of initial vehicle feature sets are queried and obtained, and the plurality of initial vehicle feature sets are screened based on the predetermined associated features to obtain the plurality of vehicle feature sets.

3. According to the digital data processing method for dual carbon and energy conservation and emission reduction according to claim 1, It is characterized in that Generate multiple vehicle thresholds, including: Randomly selecting K feature sets from the multiple vehicle feature sets as K cluster centers, calculating the Euclidean distances between other vehicle feature sets and the K cluster centers, and assigning other vehicle feature sets to the cluster center with the shortest Euclidean distance to obtain K cluster clusters; Performing mean operations on the K clusters respectively, updating the K cluster centers based on the mean operation results, and determining K updated cluster centers; Iterative clustering is performed based on the K updated cluster centers until a predetermined clustering constraint is satisfied, K current cluster clusters are output, and the multiple vehicle models are mapped and aggregated based on the K current cluster clusters to obtain the multiple vehicle thresholds.

4. According to the digital data processing method for dual carbon and energy conservation and emission reduction according to claim 1, It is characterized in that Determine multiple unit idling carbon emissions, including: Randomly selecting a first vehicle threshold from the multiple vehicle thresholds, and obtaining a first vehicle model of the first vehicle threshold, wherein the first vehicle model is any vehicle model in the first vehicle threshold; Taking the first vehicle model as a constraint, obtaining a sample unit idling carbon emission set based on automobile big data retrieval, and performing mean calculation to obtain a first sample emission mean; The sample unit idle carbon emission set is screened based on the first sample emission mean to obtain a standard unit idle carbon emission set, and the first vehicle unit idle carbon emission is obtained by average calculation, wherein the standard unit idle carbon emission is the sample unit idle carbon emission whose deviation from the first sample emission mean is less than a predetermined deviation threshold; A plurality of first vehicle models and a plurality of first vehicle unit idling carbon emissions are obtained in sequence, and a first unit idling carbon emission is obtained by averaging and added to the plurality of unit idling carbon emissions.

5. The digital data processing method for dual carbon and energy conservation and emission reduction according to claim 1, It is characterized in that Output multiple predicted traffic flows, including: Filtering the real-time vehicle information based on the multiple vehicle thresholds, determining multiple real-time vehicle flows, and randomly selecting a first real-time vehicle flow of a first vehicle threshold; Input the current time node, the first real-time vehicle flow and the real-time environment information into a first flow prediction branch, and output a first predicted flow, wherein the first flow prediction branch is constructed based on a BP neural network; Inputting the current time node, the first real-time vehicle flow and the real-time environmental information into a second flow prediction branch, and outputting a second predicted flow, wherein the second flow prediction branch is constructed based on a Bayesian network; The first predicted traffic flow and the second predicted traffic flow are merged according to a predetermined weight ratio, and the first predicted traffic flow is output and added to the multiple predicted traffic flows, wherein the predetermined weight ratio is configured based on the prediction accuracy of the first traffic prediction branch and the second traffic prediction branch.

6. The digital data processing method for dual carbon and energy conservation and emission reduction according to claim 5, It is characterized in that Construct the second traffic prediction branch, including: Taking the first vehicle threshold and the predetermined future period as constraints, searching the vehicle monitoring log to obtain a sample traffic data set, wherein the sample traffic data includes a sample time node, a sample real-time traffic flow, a sample real-time environmental information, and a sample predicted traffic flow; Taking time nodes, real-time traffic flow and real-time environmental information as input nodes, and predicted traffic flow as output nodes, a Bayesian network graph structure is constructed based on the expert knowledge base; The Bayesian network graph structure is trained with parameter optimization using the sample traffic data set to obtain the second traffic prediction branch that meets expected conditions.

7. The digital data processing method for dual carbon and energy conservation and emission reduction according to claim 1, It is characterized in that Determine multiple simulated idle times, including: Based on the digital twin, a regional traffic simulation space is constructed according to the road network topology, and the real-time environmental information and the multiple predicted vehicle flows are rendered into the regional traffic simulation space; A first regional signal control scheme is randomly selected, and N vehicle idle simulations are performed on the first regional signal control scheme using the regional traffic simulation space. The mode of the N simulated idle durations is selected as the first simulated idle duration, and is added to the multiple simulated idle durations, wherein N is an integer greater than 50.

8. Digital data processing platform for dual carbon and energy conservation and emission reduction, It is characterized in that The middle platform is used to implement the digital data processing method for dual carbon and energy conservation and emission reduction according to any one of claims 1 to 7, and the middle platform includes: An idle carbon emission analysis module, the idle carbon emission analysis module is used to call the vehicle monitoring log of the target area, query and obtain multiple vehicle models and multiple vehicle feature sets, cluster the multiple vehicle models based on the multiple vehicle feature sets, generate multiple vehicle thresholds, perform vehicle idle carbon emission analysis on the multiple vehicle thresholds respectively, determine multiple unit idle carbon emissions, and construct a vehicle threshold-unit idle carbon emission mapping table; A vehicle flow prediction module, which is used to collect real-time vehicle information and real-time environmental information of multiple roads in the target area through a multi-source monitoring array, input the current time node, the real-time vehicle information and the real-time environmental information into a road flow predictor, perform vehicle flow prediction within a predetermined future period, and output multiple predicted vehicle flows; A control scheme generating module, the control scheme generating module is used to determine a plurality of signal lights and a plurality of signal control parameters based on a road network topology of a target area, and generate a plurality of regional signal control schemes according to the plurality of signal lights and the plurality of signal control parameters at a predetermined interval step; A total carbon emission calculation module, the total carbon emission calculation module is used to perform vehicle idle simulations in a regional traffic simulation space based on the multiple predicted vehicle flows and the multiple regional signal control schemes, determine multiple simulated idle durations, and perform overall idle carbon emission calculations according to the vehicle threshold-unit idle carbon emission mapping table and the multiple simulated idle durations to obtain multiple total carbon emissions; A traffic light control module, the traffic light control module is used to set the regional signal control scheme corresponding to the minimum value of the multiple total carbon emissions as the optimal signal control scheme, and within the predetermined future period, control the multiple traffic lights in the target area according to the optimal signal control scheme.

Images